Interactions between proteins and ions are essential for various biological functions like structural stability, metabolism, and signal transport. Given that more than half of all proteins bind to ions, it becomes crucial to identify ion-binding sites. Accurate identification of protein-ion binding sites helps us to understand proteins’ biological functions and plays a significant role in drug discovery. While several computational approaches have been proposed, this remains a challenging problem due to the small size and high versatility of metals and acid radicals. In this study, we propose IonPred, a sequence-based approach that employs ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) to predict ion binding sites using only raw protein sequences. We successfully fine-tuned our pretrained model to predict the binding sites for nine metal ions (Zn2+, Cu2+, Fe2+, Fe3+, Ca2+, Mg2+, Mn2+, Na+, and K+) and four acid radical ion ligands (CO32−, SO42−, PO43−, NO2−). IonPred surpassed six current state-of-the-art tools by over 44.65% and 28.46% respectively in F1 score and MCC when compared on an independent test dataset. Our method is more computationally efficient than existing tools producing prediction results for a hundred sequences for a specific ion in under ten minutes.

Individual investors often struggle to predict stock prices due to the limitations imposed by the computational capacities of personal laptop Graphics Processing Units (GPUs) when running intensive deep learning models. This study proposes solving these GPU constraints by integrating deep learning models with technical analysis methods. This integration significantly reduces analysis time and equips individual investors with the ability to identify stocks that may yield potential gains or losses in an efficient manner. Thus, a comprehensive buy and sell algorithm, compatible with average laptop GPU performance, is introduced in the study. This algorithm offers a lightweight analysis method that emphasizes factors identified by technical analysis methods, thereby providing a more accessible and efficient approach for individual investors. To evaluate the efficacy of this approach, we analyzed the performance of eight deep learning models: LSTM (4 layers), CNN, BiLSTM (4 layers), CNN Attention, BiGRU CNN BiLSTM Attention, BiLSTM Attention CNN, CNN BiLSTM Attention, and CNN Attention BiLSTM. These models were used to predict stock prices for Samsung Electronics and Celltrion Healthcare. The CNN Attention BiLSTM model displayed superior performance among these models, with the lowest validation mean absolute error value. In addition, an experiment was conducted using WandB Sweep to determine the optimal hyperparameters for four individual hybrid models. These optimal parameters were then implemented in each model to validate their back-testing rate of return. The CNN Attention BiLSTM hybrid model emerged as the highest-performing model, achieving an approximate rate of return of 5 percent. Overall, this study offers valuable insights into the performance of various deep learning and hybrid models in predicting stock prices. These findings can assist individual investors in selecting appropriate models that align with their investment strategies, thereby increasing their likelihood of success in the stock market.

Tripping is the largest cause of falls and low swing foot ground clearance during the mid-swing phase, particularly at the critical gait event known as Minimum Foot Clearance (MFC) is the major risk factor for tripping-related falls. Intervention strategies to increase MFC height can be effective if applied in real-time based on feed-forward prediction. The current study investigated the capability of machine learning models to classify the MFC into various categories using toe-off kinematics data. Specifically, three MFC sub-categories (less than 1.5cm, between 1.5-2.0cm and higher than 2.0cm) were predicted applying machine learning approaches. A total of 18,490 swing phase gait cycles’ data were extracted from six healthy young adults, each walking for 5-minutes at a constant speed of 4km/h on a motorised treadmill. Both K-Nearest Neighbour (KNN) and Random-Forest were utilised for prediction based on the data from toe-off for five consecutive frames (0.025s duration). Foot kinematics data were obtained from inertial measurement unit attached to the mid-foot, recording tri-axial linear accelerations and angular velocities of the local coordinate. KNN and Random-Forest achieved 84% and 86% accuracy, respectively, in classifying MFC into the three sub-categories with run time of 0.39 seconds and 13.98 seconds respectively. The KNN-based model was found to be more effective if incorporated into an active exoskeleton as the intelligent system to control MFC based on the preceding gait event, toe-off due to its quicker computation time. The machine learning based prediction model shows promise for the prediction of critical MFC data indicating higher tripping risk.

Arrhythmia is a cardiac condition characterized by an irregular heart rhythm that hinders the proper circulation of blood, posing a severe risk to individuals’ lives. Globally, arrhythmias are recognized as a significant health concern, accounting for nearly 12 percent of all deaths. As a result, there has been a growing focus on utilizing artificial intelligence for the detection and classification of abnormal heartbeats. In recent years, self-operated heartbeat detection research has gained popularity due to its cost-effectiveness and potential for expediting therapy for individuals at risk of arrhythmias. However, building an efficient automatic heartbeat monitoring approach for arrhythmia identification and classification comes with several significant challenges. These challenges include addressing issues related to data quality, determining the range for heart rate segmentation, managing data imbalance difficulties, handling intra- and inter-patient variations, distinguishing supraventricular irregular heartbeats from regular heartbeats, and ensuring model interpretability. In this study, we propose the Reseek-Arrhythmia model, which leverages deep learning techniques to automatically detect and classify heart arrhythmia diseases. The model combines different convolutional blocks and identity blocks, along with essential components such as convolution layers, batch normalization layers, and activation layers. To train and evaluate the model, we utilized the MIT-BIH and PTB datasets. Remarkably, the proposed model achieves outstanding performance with an accuracy of 99.35% and 93.50% and an acceptable loss of 0.688 and 0.2564, respectively.

PM-Gati-Shakti Initiative, integration of ministries, including railways, ports, waterways, logistic infrastructure, mass transport, airports, and roads. Aimed at enhancing connectivity and bolstering the competitiveness of Indian businesses, the initiative focuses on six pivotal pillars known as "Connectivity for Productivity": comprehensiveness, prioritization, optimization, synchronization, analytical, and dynamic. In this study, we explore the application of these pillars to address the problem of "Maximum Demand Forecasting in Delhi." Electricity forecasting plays a very significant role in the power grid as it is required to maintain a balance between supply and load demand at all times, to provide a quality electricity supply, for Financial planning, generation reserve, and many more. Forecasting helps not only in Production Planning but also in Scheduling like Import / Export which is very often in India and mostly required by the rural areas and North Eastern Regions of India. As Electrical Forecasting includes many factors which cannot be detected by the models out there, We use Classical Forecasting Techniques to extract the seasonal patterns from the daily data of Maximum Demand for the Union Territory Delhi. This research contributes to the power supply industry by helping to reduce the occurrence of disasters such as blackouts, power cuts, and increased tariffs imposed by regulatory commissions. The forecasting techniques can also help in reducing OD and UD of Power for different regions. We use the Data provided by a department from the Ministry of Power and use different forecast models including Seasonal forecasts for daily data.

In this study, our primary objective was to analyze the tradeoff between accuracy and complexity in machine learning models, with a specific focus on the impact of reducing complexity and entropy on the production of landslide susceptibility maps. We aimed to investigate how simplifying the model and reducing entropy can affect the capture of complex patterns in the susceptibility maps. To achieve this, we conducted a comprehensive evaluation of various machine-learning algorithms for classification tasks. We compared the performance of these algorithms in terms of accuracy and complexity, considering both "before" and "after" scenarios of dimensionality reduction using Principal Component Analysis (PCA). Our findings revealed that reducing complexity and lowering entropy can lead to an increase in model accuracy. However, we also observed that this reduction in complexity comes at the cost of losing important complex patterns in the produced landslide susceptibility maps. By simplifying the model and reducing entropy, certain intricate relationships and uncertain patterns may be overlooked, resulting in a loss of information and potentially compromising the accuracy of the susceptibility maps. The analysis encompassed a diverse range of machine learning algorithms, including Random Forest (RF), Extra Trees (EXT), XGboost, LightGBM, Catboost, Naive Bayes (NB), K-Nearest Neighbors (KNN), Gradient Boosting Machine (GBM), and Decision Trees (DT). Each algorithm was evaluated for its strengths and limitations, considering the tradeoff between accuracy and complexity. Before dimensionality reduction, the algorithms demonstrated promising results, with RF exhibiting excellent AUC/ROC scores and average accuracy. However, computational costs were noted as a potential drawback for RF, especially when dealing with large datasets. EXT showcased robust performance and good accuracy, while XGboost demonstrated its ability to handle complex relationships within large datasets, albeit requiring careful hyperparameter tuning. The efficiency and scalability of LightGBM made it a suitable choice for large datasets, although it displayed sensitivity to class imbalance. Catboost excelled in handling categorical features, but longer training times were observed for larger datasets. NB showcased simplicity and computational efficiency but assumed independence among features. KNN, known for its capability to capture local patterns and spatial relationships, was found to be sensitive to the choice of distance metric. GBM, while capturing complex relationships effectively, was prone to overfitting without proper regularization. DT, with its interpretability and ease of understanding, faced limitations in terms of overfitting and limited generalization. After dimensionality reduction, certain algorithms exhibited improvements in their AUC/ROC scores and average accuracy, including RF, EXT, XGboost, and LightGBM. However, for a few algorithms, such as NB and DT, a decrease in performance was observed. This study provides valuable insights into the performance characteristics, strengths, and limitations of various machine learning algorithms in classification tasks. Researchers and practitioners can utilize these findings to make informed decisions when selecting algorithms for their specific datasets and requirements. We also aim to identify the potential factors contributing to the high accuracy rates obtained from these ensembled algorithms and explore possible shortcomings of non-ensembled algorithms that may result in lower accuracy rates. By conducting a comprehensive analysis of these algorithms, we seek to provide valuable insights into the benefits and limitations of ensembled approaches for landslide susceptibility mapping. Our study sheds light on the challenges faced when balancing accuracy and complexity in machine learning models for landslide susceptibility mapping. It emphasizes the importance of carefully considering the level of complexity and entropy reduction in relation to the specific patterns and uncertainties present in the data. By providing insights into this tradeoff, our research aims to assist researchers and practitioners in making informed decisions regarding model complexity and entropy reduction, ultimately improving the quality and interpretability of landslide susceptibility maps.

Brain-computer interfaces (BCI) from electroencephalography (EEG) provide a practical approach to support human-technology interaction. In particular, motor imagery (MI) is a widely-used BCI paradigm that guides the mental trial of motor tasks without physical movement. Here, we present a deep learning methodology, named Kernel-based Regularized EEGNet (KREEGNet), leveled on Centered Kernel Alignment and Gaussian Functional Connectivity, explicitly designed for EEG-based MI classification. The approach proactively tackles the challenge of intra-subject variability brought on by noisy EEG records and the lack of spatial interpretability within end-to-end frameworks applied for MI classification. KREEGNet is a refinement of the widely accepted EEGNet architecture, featuring an additional kernel-based layer for regularized Gaussian functional connectivity estimation based on CKA. The superiority of KREEGNet is evidenced by our experimental results from binary and multi-class MI classification databases, outperforming the baseline EEGNet and other state-of-the-art methods. Further exploration of our model’s interpretability is conducted at individual and group levels, utilizing classification performance measures and pruned functional connectivities. Our approach is a suitable alternative for interpretable end-to-end EEG-BCI based on deep learning.

Advances towards smart ecosystems showcases Internet of Things (IoT) as a transversal strategy to improve energy efficiency in buildings, to enhance their comfort and environmental conditions, and to grow knowledge about building behavior, its relationships with the users and the interconnections among themselves and with the environmental and ecological context. EU estimates that 75% of the building stock is inefficient and aged with +40 years old. Although many buildings have some kind of system for regulating their indoor temperature, only a small subset provides integrated Heating, Ventilation, and Air Conditioning (HVAC) systems; within that subset, only a low percentage includes smart sensors, and only a minimum of that percentage integrates those sensors into IoT ecosystems. This work proposes several contributions. On the one hand, to understand the built environment as a set of interconnected systems that constitute a complex framework where IoT ecosystems are key enabling technologies to improve energy efficiency and Indoor Air Quality (IAQ) by filling the gap between theoretical simulations and real measurements. On the other hand, to understand IoT ecosystems as cost-effective solutions where: acquire data through connected sensors, analyze information in real-time, and build knowledge to make data-driven decisions. Furthermore, data set is public for third-party use to contribute scientific community to their research studies. Thus, this paper also contributes with a detailed functional scheme of IoT ecosystem deployed in 3 buildings of University of Zaragoza (Spain) with +200 geolocated wireless sensors with +100 representative spaces. The obtained results, through real installations with IoT as learning factory, show several learned lessons (about building complexity; energy consumption, costs and savings; and IAQ and health improvement) and contribute, as a proof-of-concept, with a proposal of prediction of building performance based on both correlations (between CO2 and occupancy) and neural networks (applied to CO2 and temperature). In summary, in a real context of economic restrictions, complexity, higher energy costs, social vulnerability and climate change, IoT-based strategies, as proposed in this work, highlight as an open, modular and interoperable approach to move towards smart communities (buildings, cities, regions, etc.) by improving energy efficiency and environmental quality (indoor and outdoor) with low cost, quick implementation, and low impact on users within great challenges for growth, interconnection, climate change and sustainability.

Building Information Modelling (BIM) has gained significant relevance in civil engineering, particularly in the infrastructure sector. It offers the potential to increase efficiencies, optimize processes, and enhance sustainability throughout infrastructure projects’ life cycles. BIM consolidates information about asset components into a single model, enabling real-time updates, cost reduction, and improved consistency. Digital twins serve as valuable extensions of BIM in infrastructure, playing a crucial role during operation. By capturing real-time data from sensors and IoT devices, digital twins enabls continuous monitoring, proactive maintenance, efficient energy management, and informed decision-making for optimized operational efficiency. Advancements in 3D point cloud technologies, such as 3D laser scanning, have expanded BIM’s application in operation and maintenance. These technologies rapidly capture accurate and detailed three-dimensional information, prompting the exploration of automated alternatives to manual point cloud modeling. This paper demonstrates the application of supervised machine learning, specifically support vector machines, for analyzing and segmenting 3D point clouds, a crucial step in 3D modeling. Various approaches for semantic segmentation are introduced, investigated, and evaluated using diverse data sets. The results highlight the effectiveness of supervised machine learning techniques in achieving accurate segmentation of 3D point clouds.

Indoor localization (IL) is a significant topic of study with several practical applications. The area of IL has evolved greatly in recent years due to the introduction of numerous technologies such as WiFi, Bluetooth, cameras, and other sensors. Despite the growing interest in this field, there are numerous challenges and drawbacks that must be addressed to develop more accurate and sustainable systems for IL and its real-life applications. This review study gives an in-depth look into IL, covering the most promising artificial intelligence-based and hybrid strategies that have shown excellent potential in overcoming some of the limitations of classic methods. In addition, the paper investigates the significance of high-quality datasets and evaluation metrics in the design and assessment of IL algorithms. Furthermore, this overview study emphasizes the crucial role that machine learning techniques, such as deep learning and transfer learning, play in the advancement of IL. A focus on the importance of IL and the various technologies, methods, and techniques that are being used to improve it. Finally, The survey highlights the need for continued research and development to create more accurate and scalable techniques that can be applied across a range of industries, such as evacuation-egress routes, hazard-crime detection, smart occupancy-driven energy reduction and asset tracking and management.

The paper proposes a rock classification method using the vibration signal of the rotary drilling process. This proposed method classifies four rocks with a reliability of 100 %, from the vibration signal record of a lasting 1/4 second. For the design of a suitable classification method, several attributes of the vibration signal were calculated for two different signal recording lengths. Cluster dendrogram, ANOVA test, and boxplot were used to determine useful attributes and proper signal length. The classification rule was found using a decision tree, machine learning tool. The publication gradually describes the process of creating the classification method and the results of the reliability verification of the proposed classification method. Rock disintegration by rotary drilling was carried out under standardized experimental conditions. The disintegration rocks were andesite, granite, limestone, and concrete.

The phenomenon of seat occupancy in university libraries is a prevalent issue. However, existing solutions, such as software-based seat reservations and sensors-based occupancy detection, have proven to be inadequate in effectively addressing this problem. In this study, we propose a novel approach: a serial dual-channel object detection model based on Faster RCNN. Furthermore, we develop a user-friendly web interface and mobile APP to create a computer vision-based platform for library seat occupancy detection. To construct our dataset, we combine real-world data collection with UE5 virtual reality. The results of our tests also demonstrate that the utilization of personalized virtual dataset significantly enhances the performance of the convolutional neural network (CNN) in dedicated scenarios. The serial dual-channel detection model comprises three essential steps. Firstly, we employ Faster RCNN algorithm to determine whether a seat is occupied by an individual. Subsequently, we utilize an object classification algorithm based on transfer learning, to classify and identify images of unoccupied seats. This eliminates the need for manual judgment regarding whether a person is suspected of occupying a seat. Lastly, the web interface and APP provide seat information to librarians and students respectively, enabling comprehensive services. By leveraging deep learning methodologies, this research effectively addresses the issue of seat occupancy in library systems. It significantly enhances the accuracy of seat occupancy recognition, reduces the computational resources required for training CNNs, and greatly improves the efficiency of library seat management.

The purpose of this work is to compare two fracture prediction models with real-world data. The pure Artificial Neural Network (ANN) model emphasizes regression analysis, while the hybrid model (SVM-ANN) focuses on the combination of regression and classification analysis or Support Vector Machine. The results were subsequently tested against logging data by combining the Machine Learning approach with advanced logging tools. In this context, we used electrical image logs and the dipole acoustic tool which together allowed the distinction of 404 open fractures and 231 closed fractures and, consequently the estimation of fracture porosity. The results are then fed into two machine-learning algorithms. Pure Artificial Neural Networks and hybrid models are used to establish comprehensive results, which are subsequently tested to check the accuracy of the models. The outputs obtained from the two methods demonstrate that the hybridized model has a lower Root Mean Square Error (RMSE) than pure ANN. The results of our approach strongly suggest that incorporating hybridized machine learning algorithms in fracture porosity estimations can contribute to the development of more trustworthy static reservoir models in simulation programs. Finally, the combination of Machine Learning (ML) and well-log analysis do permit reliable estimation of fracture porosity in the Ahnet field in Algeria, where, in many places, advanced logging data is absent and costly.

In recent years, intelligent identification and prediction of ore deposits based on deep learning algorithm and image processing technology has gradually become one of the research frontiers in the field of geological and metallogenic prediction. However, this method also has many problems that need to be solved. For example, (1) very few trainable image samples containing mineral point labels; (2) The geological image features are small and irregular, and the image similarity is high; (3) It is difficult to calculate the influence of different geological prospecting factors on ore mineralization. Based on this, this paper constructs a deep learning network model Multiscale Feature Attention Framework (MFAF) based on geo-image data. The results show that MFCA-Net module in MFAF model can solve the problem of scarce mine label images to a certain extent. In addition, the channel attention mechanism SE-Net module can quantify the difference of influence of different source factors on mineralization. The prediction map is obtained by applying the MFAF model in the study of deposit identification and prediction in the research area of the southern section of Qin-hang metallogenic Belt. In the forecast map, many regions have high metallogenic potential. Through observation, it is found that the above predicted area covers 100% of the known ore deposits at present, which has a good prediction effect. Later, we can find out the specific reasons through field verification. The multi-scale feature fusion and attention mechanism MFA Framework in this paper can provide a new way of thinking for geologists in mineral exploration. The research of this paper also provides resource guarantee and technical support for the sustainable exploitation of mineral resources and the sustainable growth of society and economy.

With the exponential growth of machine learning and development of Artificial Neural Network (ANNs) in recent years, there is great opportunity to leverage this approach and accelarate bio-logical discoveries through applications on the analysis of bioinformatics data. Various types of datasets including for example protein or gene interaction networks, molecular structures and cellular signalling pathways, have already been used for machine learning by training ANNs for inference and pattern classification. However, unlike regular data structures that are commonly used in the computer science and engineering fields, bioinformatics datasets present challenges that require unique algorithmic approaches. The recent development of the geometric and deep learning approach within the machine learning field, is very promising towards accelerating analysis complex bioinformatics datasets. The principles of ANNs and their importance for bio-informatics machine learning is demonstrated herein, through presentation of the undelying mathematical and statistical foundations from group theory, symmetry, linear algebra. Further-more, the structure and functions of ANN algorithms that form the core principles of artificial intelligence are explained, in relation to the bioinformatics data domain. Overall, the manuscript provides guidance for researchers to understand the principles required for practicing machine learning and artificial intelligence, with the special considerations towards bioinformatics applications.

Artificial Intelligence (AI) models are expected to have a great impact in the manufacturing industry, optimizing time and resource cost by enabling applications such as predictive maintenance (PM) of production machines. A necessary condition for this is the availability of high quality data collected as close as possible to the process in question. With the advent of 5G equipped multi sensor platforms (MSPs), high sampling rate data can be collected and transmitted for processing in real time. This poses a data security challenge, since this data may give valuable insight into confidential business information of companies. Federated learning (FL) enables the training of AI models with data from multiple sources without it leaving the shop floor, by utilizing distributed computing resources available on premise. This paper introduces an architecture of FL based on data collected from 5G MSPs for enabling PM in industrial environments and discusses its potential benefits and challenges.

Topic discovery is finding the main idea of large amounts of textual data. It indicates the recurring topics in the documents, allowing an overview of the texts. Current topic discovery models receive the texts, with or without pre-processing of Natural Language Processing. The processing consists of stopwords removal, text cleaning and normalization (lowercase conversion). A topic discovery model that receives texts with or without processing generates general topics since the input data is many uncategorized texts. The general topics do not offer a detailed overview of the input texts, and manual text categorization is a time-consuming and tedious task. Accordingly, it is necessary to integrate an automatic text classification task in the topic discovery process to obtain specific topics with their top words that contain relevant relationships based on belonging to a class. Text classification performs a word analysis that makes up a document to decide what class or category is being identified; then, integrating the text classification before a topic discovery process will provide latent topics depicted by top words with a high coherence in each topic based on the previously obtained classes. Therefore, this paper exposes a approach that integrates text classification into topic discovery from large amounts of English textual data, such as 20-Newsgroup and Reuters corpora. The text classification is accomplished with a Convolutional Neural Network(CNN) incorporating three embedding models based on semantic relationships. The topic discovery over categorized texts is realized with Latent Dirichlet Analysis(LDA), Probabilistic Latent Semantic Analysis(PLSA), and Latent Semantic Analysis(LSA) algorithms. An evaluation process was performed based on the normalized topic coherence metric. The 20-Newsgroup corpus was classified, and twenty topics with ten top words were discovered for each class, obtaining 0.1723 normalized topic coherence when applying LDA, 0.1622 with LSA, and 0.1716 with PLSA. The Reuters corpus was also classified, obtaining 0.1441 normalized topic coherence when applying the LDA algorithm to obtain 20 topics for each class.

Recent advancements in Artificial Intelligence (AI), Deep Learning (DL), and computer vision have revolutionized various industrial processes through image classification and object detection. State-of-the-art Optical Character Recognition (OCR) and Object Detection (OD) technologies, such as YOLO and PaddleOCR, have emerged as powerful solutions for addressing challenges in recognizing textual and non-textual information on printed stickers. However, a well-established framework integrating these cutting-edge technologies for industrial applications still needs to be discovered. In this paper, we propose an innovative framework that combines advanced OCR and OD techniques to automate visual inspection processes in an industrial context. Our primary contribution is a comprehensive framework adept at detecting and recognizing textual and non-textual information on printed stickers within a company, harnessing the latest AI tools and technologies for sticker information recognition. Our experiments reveal an overall macro accuracy of 0.88 for the sticker OCR across three distinct patterns. Furthermore, the proposed system goes beyond traditional Printed Character Recognition (PCR) by extracting supplementary information, such as barcodes and QR codes present in the image, significantly streamlining industrial workflows and minimizing manual labor demands.

The appropriate maintenance of highway roads is critical for the safe operation of road networks and conserves maintenance costs. Multiple methods have been developed to investigate the surface of roads for various types of cracks and potholes, among other damage. Like road surface damage, the condition of expansion joints in concrete pavement is important to avoid unexpected hazardous situations. Thus, in this study, a new system is proposed for autonomous expansion joint monitoring using a vision-based system. The system consists of the following three key parts: (1) a camera-mounted vehicle, (2) indication marks on the expansion joints, and (3) a deep learning-based automatic evaluation algorithm. With paired marks indicating the expansion joints in a concrete pavement, they can be automatically detected. An inspection vehicle is equipped with an action camera that acquires images of the expansion joints in the road. You Only Look Once (YOLO) automatically detects the expansion joints with indication marks, which has a performance accuracy of 95%. The width of the detected expansion joint is calculated using an image processing algorithm. Based on the calculated width, the expansion joint is classified into the following two types: normal and dangerous. The obtained results demonstrate that the proposed system is very efficient in terms of speed and accuracy.

The administration of regional neuraxial analgesia for pain relief during labor is widely recognized as a safe and effective method involving medication delivery into the epidural or subarachnoid space in the lower back. This study proposes an innovative semantic image segmentation methodology emphasizing enhanced interpretability using convolutional Random Fourier Features and layer-wise weighted class-activation maps tailored explicitly for foot segmentation in regional analgesia monitoring. Namely, our contribution is twofold: i) a novel Random Fourier Features layer is introduced to deal with image data to enhance three well-known architectures (FCN, UNet, and ResUNet); ii) three novel quantitive measures are presented to evaluate the interpretability of a given deep learning model devoted to segmentation tasks. Our approach is rigorously evaluated on a demanding dataset of foot thermal images from pregnant women who received epidural anesthesia. Its small size and considerable variability characterize the dataset. Our validation results demonstrate that the proposed methodology not only achieves competitive foot segmentation performance but also significantly enhances the explainability of the process, rendering it well-suited for applications such as epidural insertion during labor.

Dataspaces are decentralized and open ecosystems that guarantee trustworthy and secure sharing of data among their participants. In recent years, dataspaces have gained popularity due to their design for managing and sharing heterogeneous data from various sources and domains; and their capability to incrementally solve data integration issues. Leveraging dataspace and advanced technologies plays a vital role in solving many real-world applications effectively and efficiently in real-time. Drone technology is one type of technology that can be deployed to gather data from different resources in harsh or smart environments. Beyond fifth-generation (B5G) communication networks significantly contribute to drones’ development and widespread use by providing low latency and high throughput. Therefore, data sharing among drones in B5G networks offer significant potential to enhance commercial and civilian applications. However, several security issues for collaboration and data sharing, such as data privacy leakage, because of sensitive data and the lack of trustworthy centralized monitoring. Furthermore, sharing data is one of the essential requirements for drone collaboration to achieve their tasks effectively and efficiently in real-time. This conceptual framework presents a novel dataspace in the sky, focusing on securing drone data sharing in B5G for Industry 4.0 toward Industry 5.0. We present how Federated Learning (FL) assists drones in collaboration effectively and efficiently, sharing models instead of raw data. However, because of the fragility of the central curator, the reliability of contribution recording, and the poor quality of shared local models, there are still significant security and privacy issues for drone-assisted smart environments in B5G. Therefore, we present the conceptual framework for leveraging blockchain and FL to secure and manage data sharing of collaborative drones’ dataspace in space in a decentralized fashion. The decentralisation of dataspaces would significantly expand the drive and market for the development of citizen-friendly mobility services.

The COVID-19 pandemic has struck educational experience systems around the globe. This paper investigates and evaluates the student participants’ perceptions who joined the international exchange seminar on global citizenship and peace held at a University in Hiroshima, Japan. Approximately seventy students and faculty members from nine to ten different universities from around the globe joined this summer program in August 2021 (online) and 2022 (face-to-face). This study is a mixed-method study. The first part consists of a quantitative analysis of BEVI data obtained from the students in the seminar before COVID-19 and after. The research concludes that there are no changes in the way students learn. The second part consists of qualitative data. This data shows the perceptions of students of online teaching versus hybrid teaching. It compares the differences in participants’ perceptions reported in students’ feedback on the programs during and post-COVID-19. Our results confirm prominent differences exist in the students’ perceptions of their learning experience during the pre-pandemic and post-pandemic periods. The findings of this study suggest that universities need to strive and define a meaning and purpose of international seminars, which enables students to experience a high level of intercultural social interaction face-to-face.

The COVID-19 pandemic has posed a significant global threat, leading to several initiatives for its control and management. One such initiative involves wastewater-based epidemiology, which has gained attention for its potential to provide early warning of virus outbreaks and real-time information on its spread. In this study, water samples from two wastewater treatment plants (WWTPs) located at the south east of Spain (Region of Murcia) namely Murcia, and Cartagena, were analyzed by RT-qPCR, Phylogenetic Analysis, and Machine Learning Approach. The aim was to determine whether SARS-CoV-2 detection in the WWTPs of these two cities could serve as a proxy for the virus's spread in the population. The results confirmed that the levels of SARS-CoV-2 in these wastewater samples changed concerning the number of SARS-CoV-2 cases detected in the population and variant occurrences were in line with clinical reported data. Additionally, the phylogenetic analysis showed that samples obtained in close sampling times exhibited a higher similarity than those obtained more distantly in time. A second analysis using a machine learning approach based on the mutations found in the SARS-CoV-2 spike protein was also conducted. Hierarchical Clustering (HC) was used as an efficient unsupervised approach for data analysis. Results indicated that samples obtained in October 2022 in Murcia and Cartagena were significantly different, which corresponded well with the different virus variants circulating in the two locations. The proposed methods in this study are adequate for comparing the Accumulated Natural Vector (ANV) of the SARS-CoV-2 sequences as a preliminary evaluation of potential changes in the variants that are circulating in a given population at a specific time point.

The research proposes a self-directed paradigm with self-design using the existing technology with LMS modules, discussions, and self-tests. The research establishes its criteria for assurance of teaching and learning known as 7x2C for the compliance of content, and appearance along with other criteria for the analysis. The above technology of web and LMS is tested for a business course that is technology-oriented in creating an experiential learning system for Covid-19 awareness. Similarly, among other ideas, an environment for educating learners about diabetes and obesity has been designed. The project is known as Sunchoke with its theme of Grow, Eat, and Heal. The educators can use their technology and apply self-directed pedagogy to transform this approach to their customized ways by using their content and rubrics.

The current neural networks for tomato leaf disease recognition have problems such as large model parameters, long training time, and low model accuracy. To solve these problems, a lightweight convolutional neural network LBFNet is proposed in this paper.First, a lightweight convolutional neural network LBFNet is established as the base model. Secondly, a three-channel attention mechanism module is introduced to learn the disease features in tomato leaf disease images and reduce the interference of redundant features. Finally, a cascade module is introduced to increase the depth of the model, solve the gradient descent problem, and reduce the loss caused by increasing the depth of the model. The quantized pruning technique is also used to further compress the model parameters and optimize the model performance. The results show that the LBFNet model achieves 99.06% accuracy on the LBFtomato dataset, with a training time of 996s and a single classification accuracy of over 94%. Further training using the saved weight file after quantized pruning makes the model accuracy reach 97.66%. Compared with the base model, the model accuracy was improved by 28%, and the model parameters were reduced by 96.7% compared with the traditional Resnet50. It was found that LBFNet can quickly and accurately identify tomato leaf diseases in complex environments, providing effective assistance to agricultural producers.

Global models have been developed to tackle the challenge of forecasting sets of series that are related or share similarities, but not for heterogeneous datasets. Various methods of partitioning by relatedness have been introduced to enhance the similarities of the set, resulting in improved forecasting accuracy but often at the cost of a reduced sample size, which could be harmful. To shed light on how the relatedness between series impacts the effectiveness of global models in real-world demand forecasting problems we perform an extensive empirical study using the M5 competition dataset. We examined cross-learning scenarios driven by the product hierarchy commonly employed in retail planning, which allow global models to capture interdependencies across products and regions more effectively. Our findings show that global models outperform state-of-the-art local benchmarks by a considerable margin, indicating that they are not inherently more limited than local models and can handle unrelated time series data effectively. The accuracy of data partitioning approaches increases, as the size of the data pools and the models' complexity decrease. However, there is a trade-off between data availability and data relatedness. Smaller data pools lead to increased similarity among time series, making it easier to capture cross-product and cross-region dependencies, but this comes at the cost of a reduced sample, which may not be beneficial. Finally, it's worth noting that the successful implementation of global models for heterogeneous datasets can significantly impact forecasting practice.

The deep energy method (DEM), a type of physics-informed neural network, is evolving as an alternative to finite element analysis. This method employs the principle of minimum potential energy to predict deformations under static loading conditions. However, the model’s accuracy is contingent upon choosing the appropriate architecture for the model, which can be challenging due to the high interactions between hyperparameters, large search space, difficulty in identifying objective functions, and non-convex relationships with the objective functions. To improve DEM’s accuracy, we first introduce random Fourier feature (RFF) mapping. RFF mapping helps with the training of the model by reducing bias towards high frequencies. The effects of six hyperparameters are then studied under compression, tension, and bending loads in planar linear elasticity. Based on this study, a systematic automated hyperparameter optimization approach is proposed. Due to the high interaction between hyperparameters and the non-convex nature of the optimization problem, Bayesian optimization algorithms are used. The models trained using optimized hyperparameters and having Fourier feature mapping can accurately predict deflections compared to finite element analysis. Additionally, the deflections obtained for tension and compression load cases are more sensitive to variations in hyperparameters than bending.

Election outcomes have been predicted in the past with the help of various state-of-the-art language models. Sentiment analysis helps in establishing the opinions of the public about a particular subject, a popular experiment known as opinion mining. Twitter has grown in popularity and proven to be a key tool in mining people’s sentiments concerning election and other trending subjects of interest. The outcome of the just concluded Presidential election in Nigeria shifts the focus on Lagos State governorship election. In this study, we propose a Bidirectional Encoder Representations from Transformers (BERT) model for the sentiment analysis of governorship election in Lagos State Nigeria using Twitter data. A total of 800,000 personal and public tweets were scraped from twitter concerning the three prominent contesting candidates using carefully selected search queries. The tweets were preprocessed to avoid noise and inconsistencies. The preprocessed tweets were passed into the pretrained and finetuned BERT model. The result was analyzed to establish the sentiments of the public about the candidates. The social networks of the candidates were also analyzed. The parameter-tuning yield different results with different learning rates (LR). Results showed that the learning rate at 1e-7 gave the best performance and that the smaller the learning rate, the higher the accuracy but the larger the epoch size, the higher the accuracy.

Nowadays, there is extensive production and use of plastic materials for different industrial activities. These plastics, either from their primary production sources or through degradation processes of the plastics themselves, can contaminate the ecosystem with micro and nanoplastics. Once in the aquatic environment, these microplastics can be the basis for the adsorption of chemical pollutants, favoring that these chemical pollutants disperse more quickly in the environment and can affect living beings. Due to the lack of information on adsorption, three machine learning models (random forest, support vector machine, and artificial neural network) to predict different microplastic/water partition coefficients (log Kd) were developed using two different approximations (based on the number of input variables). The best-selected machine learning models present, in general, correlation coefficients upper than 0.92 in the query phase, which indicate that these type of models could be used for a rapid estimation of the absorption of organic contaminants on microplastics.

Digital Elevation Model (DEM) is a representation of elevation data that represent terrain with or without overlaying objects of the Earth. It is the ideal and most widely used method for determining topography. DEMs are generated from various techniques such as traditional Surveying, Photogrammetry, InSAR, LiDAR, Clinometry and radargrammetry. It has been observed that mostly LiDAR-generated DEMs provide the best accuracy. The unavailability of LiDAR data in most of the region restricts global researchers from high-resolution and accurate DEMs. The recent launch of ICESat-2 with a 13m beam footprint and 0.7m pulse interval, promises elevations at high orbital precision. Its accuracy is of the order of few centimeters in complex topography, because of this ICESat-2 proves to be a good source to generate high-accuracy DEMs. ICESat-2 provides discrete photon data with elevations of points on the Earth’s surface. Traditional interpolation techniques tend to over-smooth the estimated space and still are unable to justify the complicated continuity in the topographical data. Machine learning algorithms are widely being used to extract patterns and spatial extent in geographic data. To estimate a DEM from ICESat-2 LiDAR point data, machine learning regression algorithms are implemented in this study. The present study has been performed for a plain region of Ghaziabad, Uttar Pradesh, India. Studies have shown that Cartosat-1 DEM V3 R1 product provides an accuracy of the order of 2m in predominantly plain regions, hence taken for this region. Current work focuses on comparing various regression-based machine-learning techniques to interpolate DEM from ICESat-2 data The RMSE of the interpolated DEM resulted from the Gradient Boosting Regressor, Random Forest Regressor, Decision Tree Regressor, and Multi-Layer Perceptron Regressor was 7.13m, 7.01m, 7.15m, and 3.76m, respectively when evaluated against the TANDEM-X DEM of the same region. The MLP Regressor is found to perform the best among the four algorithms tested.

Emotions are indicators of affective states and play a significant role in human daily life, behavior, and interactions. Giving emotional intelligence to the machines could, for instance, facilitate early detection and prediction of (mental) diseases and symptoms. Electroencephalography (EEG) -based emotion recognition is being widely applied because it measures electrical correlates directly from the brain rather than the indirect measurement of other physiological responses initiated by the brain. The recent development of non-invasive and portable EEG sensors makes it possible to use them in real-time applications. Therefore, this paper presents a real-time emotion classification pipeline, which trains different binary classifiers for the dimensions of Valence and Arousal from an incoming EEG data stream. After achieving a 23.9% (Arousal) and 25.8% (Valence) higher f1-score on the state-of-art AMIGOS dataset, this pipeline was applied to the dataset achieved by an emotion elicitation experimental framework developed within the scope of this thesis. Following two different protocols, 15 participants were recorded using two different consumer-grade EEG devices while watching 16 short emotional videos in a controlled environment. For an immediate label setting, the mean f1-score of 87% and 82% were achieved for Arousal and Valence, respectively. In a live scenario, while continuously being updated on the incoming data stream with delayed labels, the pipeline proved to be fast enough to achieve predictions in real time. However, the significant discrepancy from the readily available labels on the classification scores leads to future work to include more data with frequent delayed labels in the live settings.

Physiologically Based Pharmacokinetic Models (PBPK) are mechanistical tools generally employed in the pharmaceutical industry and environmental health risk assessment. These models are recognised by regulatory authorities for predicting organ concentration-time profile, pharmacokinetic and daily intake dose of xenobiotics. Extension of PBPK models to capture sensitive populations like pediatric, geriatric, pregnant females, fetus etc. and diseased population like renal impairment, liver cirrhosis etc. is a must. However, the current modelling practice and existing models are not mature enough to confidently predict the risk in these populations. A multidisciplinary collaboration between clinicians, experimental and modeler scientist is vital to improve the physiology, and calculation of biochemical parameters for integrating the knowledge and refining existing PBPK models. Specific PBPK covering compartments like cerebrospinal fluid, and hippocampus are required to gain mechanistic understanding about xenobiotic disposition in these sub-parts. The PBPK model assists in building quantitative adverse outcome pathways (qAOPs) for several endpoints like developmental neurotoxicity (DNT), hepatotoxicity and cardiotoxicity. Machine learning algorithms can predict physicochemical parameters required to develop in-silico models where experimental data is unavailable. Integrating machine learning with PBPK carries the potential to revolutionize the field of drug discovery and development and environmental risk. Overall, this review tried to summarize the recent developments in the in-silico models, building qAOPs, use of machine learning for improving existing models along with a regulatory perspective. This review can act as a guide for toxicologists who wish to build their careers in kinetic modeling.

Talker variability has been reported to facilitate generalization and retention of speech learning, but is also shown to place demands on cognitive resources. Our recent study provided evidence that phonetically-irrelevant acoustic variability in single-talker (ST) speech is sufficient to induce equivalent amounts of learning to the use of multiple-talker (MT) training. This study is a follow-up contrasting MT versus ST training with varying degrees of temporal exaggeration to examine how cognitive measures of individual learners may influence the role of input variability in immediate learning and long-term retention. Native Chinese-speaking adults were trained on the English /i/-/ɪ/ contrast. We assessed the trainees’ working memory and selective attention before training. Trained participants showed retention of more native-like cue weighting in both perception and production regardless of talker variability condition. The ST training group showed long-term benefit in word identification, whereas the MT training group did not retain the improvement. The results demonstrate the role of phonetically-irrelevant variability in robust speech learning and modulatory functions of nonlinguistic working memory and selective attention, highlighting the necessity to consider the interaction between input characteristics, task difficulty, and individual differences in cognitive abilities in assessing learning outcomes.

Renal clear cell carcinoma (ccRCC) comprises over 75% of all renal tumors and arises in the epithelial cells of the proximal convoluted tubule. Molecularly ccRCC is characterized by copy number alterations (CNAs) such as the loss of chromosome 3p and VHL inactivation. Additional driver mutations (SETD2, PBRM1, BAP1, and others) promote genomic instability and tumor cell metastasis through the dysregulation of various metabolic and immune-response pathways. Many researchers identified mutation, gene expression, and proteomic signatures for early diagnosis and prognostics for ccRCC. Despite a tremendous influx of data regarding DNA alterations, gene expression, and protein expression, the incorporation of these analyses for diagnosis and prognosis of RCC into the clinical application has not been implemented yet. In this review, we focused on the molecular changes associated with ccRCC development, along with gene expression and protein signatures, to emphasize the utilization of these molecular profiles in clinical practice. These findings, in the context of machine learning and precision medicine, may help to overcome some of the barriers encountered for implementing molecular profiles of tumors into the diagnosis and treatment of ccRCC.

Introduction: Social media platforms such as Facebook, LinkedIn, Twitter, among others have been used as a tool for staging protests, opinion polls, campaign strategy, medium of agitation and a place of interest expression especially during elections. Past studies have established people’s opinion elections using social media posts. The advent of state-of-the-art algorithms for unstructured text processing implies tremendous progress in natural language processing and understanding. Aim: In this work, a Natural Language framework is designed to understand Nigeria 2023 presidential election based on public opinion using Twitter dataset. Methods: Raw datasets concerning discourse around Nigeria 2023 elections from Twitter of 2,059,113 18 dimensions were collected. Sentiment analysis was performed on the preprocessed dataset using three different machine learning models namely: Long Short-Term Memory (LSTM) Recurrent Neural Network, Bidirectional Encoder Representations from Transformers (BERT) and Linear Support Vector Classifier (LSVC) models. Personal tweet analysis of the three candidates provided insight on their campaign strategies and personalities while public tweet analysis established the public’s opinion about them. The performance of the models was also compared using accuracy, recall, false positive rate, precision and F-measure. Results: LSTM model gave an accuracy, precision, recall, AUC and f-measure of 88%, 82.7%, 87.2% , 87.6% and 82.9% respectively; the BERT model gave an accuracy, precision, recall, AUC and f-measure of 94%, 88.5%, 92.5%, 94.7% and 91.7% respectively while the LSVC model gave an accuracy, precision, recall, AUC and f-measure of 73%, 81.4%, 76.4%, 81.2% and 79.2% respectively. Conclusion: The experimental results show that sentiment analysis and other Natural Language Processing tasks can aid in the understanding of the social media space. Results also revealed the leverage of each aspirant towards winning the election. We conclude that sentiment analysis can form a general basis for generating insights for election and modeling election outcomes.

Automated spectrum analysis serves as a troubleshooting tool that helps to diagnose faults in wireless networks like difficult signal propagation conditions and coexisting wireless networks. It provides a higher monitoring coverage while requiring less expertise compared to manual spectrum analysis. In this paper, we introduce a data set that can be used to train and evaluate deep learning models, capable of detecting frames from different wireless standards as well as interference between single frames. Since manually labelling a high variety of frames in different environments is too challenging, an artificial data generation pipeline has been developed. The data set consists of 20 000 augmented signal segments, each containing a random number of different Wi-Fi and Bluetooth frames, their spectral image representations and labels that describe the position and type of frame within the spectrogram. The data set contains results of intermediate processing steps that enables the research or teaching community to create new data sets for specific requirements or to provide new interesting examination examples.

Detailed flow distributions in vascular systems are the key to identifying hemodynamic risk factors for the development and progression of vascular diseases. Although computational fluid dynamics (CFD) has been widely used in bioengineering research on hemodynamics predictions, not only are high-fidelity CFD simulations time-consuming and computing-expensive, but also not friendly to clinical applications due to the difficulty of comprehensive numerical calculations. Machine learning (ML) algorithums to estimate the flow field in vascular systems based on the angiographic images of the blood flow using existed diagnostic tools are emerging as a new pathway to facilitate the mapping of hemodynamics. In present work, the dye injection in a water flow was simulated as an analogy of the contrast perfusion in blood flow using CFD. In the simulation, the light passes through the flow field and generates projective images, as an analogy of X-ray imaging. The simulations provide both the ground truth velocity field and the projective images of the flow with dye patterns. A rough velocity field was estimated using the optical flow method (OFM) based on projective images. ML algorithums are then trained using the ground truth CFD data and the OFM velocity estimation as the input. Finally, the interpretable (logistic regression) and deep (neural networks, convolutional neural networks, long short term memory) machine learning models are validated by using parallel in vitro experiments on the same flow setup. The validation results showed that the employed ML model significantly reduced the error rate from 53.5% to 2.5% in average for the v-velocity estimation.

The use of digital twins for the development of Autonomous Maritime Surface Vessels (AMSVs) has enormous potential to resolve the increasing need for water-based navigation and safety at the seas. Aiming at the problem of lack of broad and integrated digital twin implementations with live data along with the absence of a digital twin-driven framework for AMSV design and development, an application framework for the development of a fully autonomous vessel using an integrated digital twin in a 3D simulation environment has been presented. Our framework has four layers to ensure that the simulation and the real-world boat as well as the environment are as close as possible. Åboat, an experimental research platform for maritime automation and autonomous surface ship applications, equipped with two trolling electric motors, cameras, LiDARs, IMU and GPS has been used as the case study to provide a proof of concept. Åboat and its sensors, alongwith the environment have been replicated in a 3D simulation environment. Using the proposed application framework, we develop obstacle detection and path planning systems based on machine learning which leverage live data from a 3D simulation environment to mirror the complex dynamics of the real world.

Snow is a vital environmental parameter and dynamically responsive to climate change, particularly in mountainous regions. Snow cover can be monitored at variable spatial scales using Earth Observation (EO) data. Long-lasting remote sensing missions enable the generation of multi-decadal time series and thus the detection of long-term trends. However, there have been few attempts to use these to model future snow cover dynamics. In this study, we therefore explore the potential of such time series to forecast the Snow Line Elevation (SLE) in the European Alps. We generate monthly SLE time series from the entire Landsat archive (1985-2021) in 43 Alpine catchments. Positive long-term SLE change rates are detected, with the highest rates (5-8 m/y) in the Western and Central Alps. We utilize this SLE dataset to implement and evaluate seven uni-variate time series modeling and forecasting approaches. The best results were achieved by Random Forests, with a Nash-Sutcliffe efficiency (NSE) of 0.79 and a Mean Absolut Error (MAE) of 258 m, Telescope (0.76, 268 m), and seasonal ARIMA (0.75, 270 m). Since the model performance varies strongly with the input data, we developed a Combined forecast based on the best performing methods in each catchment. This approach was then used to forecast the SLE for the years 2022-2029. In the majority of the catchments the shift of the forecast median SLE level retained the sign of the long-term trend. In cases where a deviating SLE dynamic is forecast a discussion based on the unique properties of the catchment and past SLE dynamics is required. In the future, we expect major improvements in our SLE forecasting efforts by including external predictor variables in a multi-variate modeling approach.

Growth models of uneven-aged forests on the diameter class level can support silvicultural decision making. Machine learning brings added value to the modeling of dynamics at the stand or individual tree level based on data from permanent plots. The objective of this study is to explore the potential of machine learning for modeling growth dynamics in uneven-aged forests at the diameter class level based on inventory data from practice. Two main modeling approaches are conducted and compared: i) fine-tuned linear models differentiated per diameter class, ii) an artificial neural network (multilayer perceptron) trained on all diameter classes. The models are trained on the inventory data of the Canton of Neuchâtel (Switzerland), which are area-wide data without individual tree-level growth monitoring. Both approaches produce convincing results for predicting future diameter distributions. The linear models perform better at the individual diameter class level with test R2 typically between 50 and 70% for predicting increments in the numbers of stems at the diameter class level. From a methodological perspective, the multilayer perceptron implementation is much simpler than the fine-tuning of linear models. The linear models developed in this study achieve sufficient performance for practical decision support.

Deep convolutional neural networks (CNNs) have been widely used in various medical imaging tasks. However, due to the intrinsic locality of convolution operation, CNNs generally cannot model long-range dependencies well, which are important for accurately identifying breast cancer from unregistered multi-view mammograms. This motivates us to leverage the architecture of Vision Transformers to capture long-range relationships of multiple mammograms from the same patient. For this purpose, we employ local Transformer blocks to separately learn patch relationships within a specific view (CC/MLO) of one side (right/left) of mammogram. The outputs from different views and sides are concatenated and fed into global Transformer blocks, to jointly learn patch relationships between two different views of the left and right breasts. To evaluate the proposed model, we retrospectively assembled a dataset involving 949 sets of CC and MLO view mammograms, which include 470 malignant cases and 479 normal or benign cases. We trained and evaluated the model using a five-fold cross-validation method. Without any arduous preprocessing steps (e.g., optimal window cropping, chest wall or pectoral muscle removal, two-view image registration, etc.), our two-view Transformer-based model achieves lesion classification accuracy of 77.0% and area under ROC curve (AUC = 0.814), outperforming state-of-the-art multi-view CNNs by 3.1% and 3%, respectively. Meanwhile, the new two-view model improves mammographic case classification accuracies of two single-view models by 7.4% (CC) and 4.5% (MLO), respectively. The promising results unveil the great potential of using Transformers to develop high-performing computer-aided diagnosis (CADx) schemes of mammography.

Melanoma is considered to be the most aggressive form of skin cancer. Due to the similar shape of malignant and benign cancerous lesions, doctors spend considerably more time when diagnosing these findings. At present, the evaluation of malignancy is performed primarily by invasive histological examination of the suspicious lesion. Developing an accurate classifier for early and efficient detection can minimize and monitor the harmful effects of skin cancer and increase patient survival rates. This paper proposes a multi-class classification task using the CoAtNet architecture, a hybrid model that combines the depthwise convolution matrix operation of traditional convolutional neural networks with the strengths of Transformer models and self-attention mechanics to achieve better generalization and capacity. The proposed multi-class classifier achieves an overall precision of 0.901, recall 0.895, and AP 0.923, indicating high performance compared to other state-of-the-art networks.

Japan Aerospace Exploration Agency (JAXA) is going to launch Advanced Land Observing Satellite 3 (ALOS-3) after 2022. ALOS-3 satellite is capable of observing global land areas with wide swath (4000 km along-track direction and 70 km cross-track direction) at high spatial resolution (panchromatic: 0.8m, multispectral: 3.2m). Maintenance and updating of land cover and vegetation information at national level is one of the major goals of the ALOS-3 mission. This paper presents the potential of simulated ALOS-3 images for the classification and mapping of land cover and vegetation types at Genus-Physiognomy-Ecosystem (GPE) level. We acquired and simulated WorldView-3 images according to the configuration of the ALOS-3 satellite sensor and the simulated ALOS-3 images were utilized for the classification and mapping of land cover and vegetation types in three sites (Hakkoda, Zao, and Shiranuka) in northern Japan. This research dealt with 17 land cover and vegetation types in Hakkoda site, 25 land cover and vegetation types in Zao site, and 12 land cover and vegetation types in Shiranuka site. Ground truth data were newly collected in three sites, and we employed eXtreme Gradient Boosting (XGBoost) classifier with the implementation of 10-fold cross-validation method for assessing the potential of ALOS-3S images. The classification accuracies obtained in Hakkoda, Zao, and Shiranuka sites in terms of f1-score were 0.810, 0.729, and 0.805 respectively. The fine scale (3.2m) land cover and vegetation maps produced in the study sites showed clear and detailed view of the distribution of plant communities. Regardless of the limited number of the temporal images, ALOS-3S images showed high potential (at least 0.729 F1-score) for the land cover and vegetation classification in all three sites. The availability of more cloud free temporal scenes is expected for improved classification and mapping in the future.

This article discusses the use of a hand held electronic nose to obtain information on the presence of some aromatic defects in natural cork stoppers, such as haloanisoles, alkylmethoxypyrazines and ketones. The proposed prototype has been developed as an instrumentation system with up to eight commercial gas sensors. Machine learning algorithms such as k-nearest neighbors and artificial neural networks has been used. The use of this system tries to improve the current aromatic defect detection process in the cork stopper industry, which is done by gas chromatography or human test panels.

In the field of computer vision, large-scale image classification tasks are both important and highly challenging. With the ongoing advances in deep learning and optical character recognition (OCR) technologies, neural networks designed to perform large-scale classification play an essential role in facilitating OCR systems. In this study, we developed an automatic OCR system designed to identify up to 13,070 large-scale printed Chinese characters by using deep learning neural networks and fine-tuning techniques. The proposed framework comprises four components, including training dataset synthesis and background simulation, image preprocessing and data augmentation, the process of training the model, and transfer learning. The training data synthesis procedure is composed of a character font generation step and a background simulation process. Three background models are proposed to simulate the factors of the background noise and anti-counterfeiting patterns on ID cards. To expand the diversity of the synthesized training dataset, rotation and zooming data augmentation are applied. A massive dataset comprising more than 19.6 million images was thus created to accommodate the variations in the input images and improve the learning capacity of the CNN model. Subsequently, we modified the GoogLeNet neural architecture by replacing the FC layer with a global average pooling layer to avoid overfitting caused by a massive amount of training data. Consequently, the number of model parameters was reduced. Finally, we employed the transfer learning technique to further refine the CNN model using a small number of real data samples. Experimental results show that the overall recognition performance of the proposed approach is significantly better than that of prior methods and thus demonstrate the effectiveness of proposed framework, which exhibited a recognition accuracy as high as 99.39% on the constructed real ID card dataset.

This work aims to develop an autonomous system for the unmanned aerial vehicle (UAV) to land on a moving platform such as the automobile or marine vessels, providing a promising solution for a long-endurance flight operation, a large mission coverage range, and a convenient recharging ground station. Different from most state-of-the-art UAV landing frameworks which rely on UAV’s onboard computers and sensors, the proposed system fully depends on the computation unit situated on the ground vehicle/marine vessel to serve as a landing guidance system. Such novel configuration can therefore lighten the burden of the UAV and computation power on the ground vehicle/marine vessel could be enhanced. In particular, we exploit a sensor fusion-based algorithm for the guidance system to perform UAV localization, whilst a control method based upon trajectory optimization is integrated. Indoor and outdoor experiments are conducted and the result shows that a precise autonomous landing on a 43 X 43 cm platform could be performed.

In an industrial environment, the quality assurance of weld seams requires extensive efforts. The most commonly used methods for that are expensive and time-consuming destructive tests, since quality assurance procedures are difficult to integrate into production processes. Beyond that, available test methods allow only the assessment of a very limited set of characteristics. They are either suitable for determining selected geometric features or for locating and evaluating internal seam defects. The presented work describes an evaluation methodology based on microfocus X-ray computed tomography scans (µCT scans) which enable the 3D characterization of weld seams, including internal defects such as cracks and pores. A 3D representation of the weld contour, i.e., the complete geometry of the joint area in the component with all quality-relevant geometric criteria, is an unprecedented novelty. Both the dimensions of the weld seam and internal defects can be revealed, quantified with a resolution down to a few micrometers and precisely assigned to the welded component. On the basis of the methodology developed within the framework of this study, the results of the scans performed on the alloy AA 2219 can be transferred to other aluminum alloys. In this way, the data evaluation framework can be used to obtain extensive reference data for the calibration and validation of inline process monitoring systems employing Deep Learning-based data processing.

As a relatively high percentage of adenoma polyps are missed, a computer-aided diagnosis (CAD) tool based on deep learning can aid the endoscopist in diagnosing colorectal polyps or colorectal cancer in order to decrease polyps missing rate and prevent colorectal cancer mortality. Convolutional Neural Network (CNN) is a deep learning method and has achieved better results in detecting and segmenting specific objects in images in the last decade than conventional models such as regression, support vector machines or artificial neural networks. In recent years, based on the studies in medical imaging criteria, CNN models have acquired promising results in detecting masses and lesions in various body organs, including colorectal polyps. In this review, the structure and architecture of CNN models and how colonoscopy images are processed as input and converted to the output are explained in detail. In most primary studies conducted in the colorectal polyp detection and classification field, the CNN model has been regarded as a black box since the calculations performed at different layers in the model training process have not been clarified precisely. Furthermore, I discuss the differences between the CNN and conventional models, inspect how to train the CNN model for diagnosing colorectal polyps or cancer, and evaluate model performance after the training process.

We describe a novel system for online prediction of lead seizures from long-term intracranial electroencephalogram (iEEG) recordings for canines with naturally occurring epilepsy. This study adopts new specification of lead seizures, reflecting strong clustering of seizures in observed data. This clustering results in fewer lead seizures (~7 lead seizures per dog), and hence new challenges for online seizure prediction, that are addressed in the proposed system. In particular, machine learning part of the system is implemented using the Group Learning method suitable for modeling sparse and noisy seizure data. In addition, several modifications for the proposed system are introduced to cope with non-stationarity of noisy iEEG signal. They include: (1) periodic re-training of SVM classifier using most recent training data; (2) removing samples with noisy labels from training data; (3) introducing new adaptive post-processing technique for combining many predictions made for 20-second windows into a single prediction for 4 hr segment. Application of the proposed system requires only 2 lead seizures for training the initial model, and results in high prediction performance for all four dogs (with mean 0.84 sensitivity, 0.27 time-in-warning, and 0.78 false-positive rate per day). Proposed system achieves accurate prediction of lead seizures during long-term test periods, 3–16 lead seizures during 169–364 days test period, whereas earlier studies did not differentiate between lead vs. non-lead seizures and used much shorter test periods (~few days long).

Macula fovea detection is a crucial prerequisite towards screening and diagnosing macular diseases. Without early detection and proper treatment, any abnormality involving the macula may lead to blindness. However, with the ophthalmologist shortage and time-consuming artificial evaluation, neither accuracy nor effectiveness of the diagnose process could be guaranteed. In this project, we proposed a deep learning approach on ultra-widefield fundus (UWF) images for macula fovea detection. This study collected 2300 ultra-widefield fundus images from Shenzhen Aier Eye Hospital in China. Methods based on U-shape network (Unet) and Fully Convolutional Networks (FCN) are implemented on 1800 (before amplifying process) training fundus images, 400 (before amplifying process) validation images and 100 test images. Three professional ophthalmologists were invited to mark the fovea. A method from the anatomy perspective is investigated. This approach is derived from the spatial relationship between macula fovea and optic disc center in UWF. A set of parameters of this method is set based on the experience of ophthalmologists and verified to be effective. Results are measured by calculating the Euclidean distance between proposed approaches and the accurate grounded standard, which is detected by Ultra-widefield swept-source optical coherence tomograph (UWF-OCT) approach. Through a comparation of proposed methods, we conclude that, deep learning approach of Unet outperformed other methods on macula fovea detection tasks, by which outcomes obtained are comparable to grounded standard method.

Aim: To determine whether an AI model and single sensor measuring acceleration and ECG could model cognitive and physical fatigue for a self-paced trail run. Methods: A field-based protocol of continuous fatigue repeated hourly induced physical (~45 minutes) and cognitive (~10 minutes) fatigue on one healthy participant. Physical load was a 3.8 km, 200 m vertical gain, trail run with acceleration and electrocardiogram (ECG) data collected using a single sensor. Cognitive load was a Multi Attribute Test Battery (MATB) and separate assessment battery including the Finger Tap Test (FTT), Stroop, Trail Making A and B, Spatial Memory, Paced Visual Serial Addition Test (PVSAT), and a vertical jump. A fatigue prediction model was implemented using a Convolutional Neural Network (CNN). Results: When the fatigue test battery results were compared for sensitivity to the protocol load, FTT right hand (R2 0.71) and Jump Height (R2 0.78) were the most sensitive while the other tests were less sensitive (R2 values Stroop 0.49, Trail Making A 0.29, Trail Making B 0.05, PVSAT 0.03, spatial memory 0.003). Best prediction results were achieved with a rolling average of 200 predictions (102.4 s), during set activity types, mean absolute error for ‘walk up’ (MAE200 12.5%) and range of absolute error for ‘run down‘ (RAE200 16.7%). Conclusion: We were able to measure cognitive and physical fatigue using a single wearable sensor during a practical field protocol including contextual factors in conjunction with a neural network model. This research has practical application to fatigue research in the field.

We are calling for a paradigm shift in engineering education. In times of the Fourth Industrial Revolution (“4IR”), a myriad of potential changes is affecting all industrial sectors leading to increased ambiguity that makes it impossible to predict what lies ahead of us. Thus, incremental culture change in education is not an option any more. The vast majority of engineering education and training systems, having remained mostly static and underinvested in for decades, are largely inadequate for the new 4IR labor markets. Some positive developments in changing the direction of the engineering education sector can be observed. Novel approaches of engineering education already deliver distinctive, student centered curricular experiences within an integrated and unified educational approach. We must educate engineering students for a future whose main characteristics are volatility, uncertainty, complexity and ambiguity. Talent and skills gaps across all industries are poised to grow in the years to come. The authors promote an engineering curriculum that combine timeless didactic tradition, such as Socratic inquiry, project-based learning and first-principles thinking with novel elements (e.g. student centered active and e-learning by focusing on the case study and apprenticeship pedagogical methods) as well as a refocused engineering skillset and knowledge. These capabilities reinforce engineering students’ perceptions of the world and the subsequent decisions they make. This 4IR engineering curriculum will prepare engineering students to become curious engineers and excellent communicators better navigating increasingly complex multistakeholder ecosystems.

Functional Connectivity analysis using Electroencephalography signals is common. The EEG signals are converted to networks by transforming the signals into a correlation matrix and analyzing the resulting networks. Here, four learning models, namely, Logistic Regression, Random Forest, Support Vector Machine, and Recurrent Neural Networks, are implemented on the correlation matrix data to classify them either on their psychometric assessment or the effect of therapy; The EEG data is trail-based/event-related. The classifications based on RNN provided higher accuracy( 74-88%) than the other three models( 50-78%). Instead of using individual graph features, a correlation matrix provides an initial test of the data. When compared with the time-resolved correlation matrix, it offered a 4-5% higher accuracy. The time-resolved correlation matrix is better suited for dynamic studies here; it provides lower accuracy when compared to the correlation matrix, a static feature.

Artificial intelligence (AI) is a versatile term that is a conclusive remedy to solve the problem using past rational data after deep contemplation using these terms i-e basic statistics, carving data, familiarity with common AI algorithms. Seafood especially tiger prawn export as a busi-ness will provide enormous foreign exchange to any country if the farmers overcome the corre-lated vulnerabilities in prawn farming. This research is elucidating lacking in Tiger prawn (TP) farming like curbing of Oxygen, pH, water temperature, and nutrients, etc. Moreover, hatchery statistics in terms of juveniles will depict this study's clear picture of curbed aquaculture. For normative decisions, the Analytical Hierarchical Process (AHP) is used. The problem which has been faced by local prawn farmers that there is a stagnant TP growth in ponds, the reason is the predominant sensitivity factor in TP. For this reason, they need indemnification of thirteen fac-tors with natural resources to get the plausible results to get calmness in their lives. This study will solely focus on the TP growth model, and the monitoring effect will be established by the Artificial Intelligence algorithm. This study will employ the AHP, 0-1 scaling method, data cura-tion techniques, and ecological statistics. The life of Tiger Prawn (TP) depends upon these factors mainly, a) Physical and b) Chemical parameters. Physical parameters contain environment (E) provided to TP like season (S) and temperature (T) etc. whereas the quality of Ammonia NH3 (N) from fish waste, Oxygen level (O), and water quality hard & soft (W) lies in chemicals do-main. This research will Elucidate the factors which cause conceptual muddles in the aquamarine life of TP, for this reason, Statistical tools will assess the current result, forecast the gap. AHP will analyze the domain inputs, circumspect ramification which will depict visceral factors, later results depict which pond suits the TP. In curtail, these factors will be curbed to improve the growth of TP in a control conditioned environment.

Annotating training data is a time consuming and labor intensive process in deep learning, especially for images with many objects present. In this paper, we propose a method to allow deep networks to be trained on data with reduced numbers of annotations (per image) in heatmap regression tasks (e.g. object detection and counting), by applying an asymmetric loss function. In a real scenario, this reduction of annotations can be imposed by the researchers (e.g. ask the annotators to label only 50% of what they see in each image), or can potentially counteract unintentionally missing labels from the annotators. To demonstrate the effectiveness of our method, we conduct experiments in two domains, crowd counting and wheat spikelet detection, using different deep network architecture. We drop various percentages of instance annotations per image in training. Results show that an asymmetric loss function is effective across different models and datasets, even in very extreme cases with limited annotations provided (e.g. 90% of the original annotations reduced). Whilst tuning of the key parameters are required, we find that setting conservative parameter values can help more realistic situations, where only small amounts of data have been missed by annotators.

Abstract: Polylactic acid (PLA) is brittle in nature with extensive deformation property. For improvement of the end-use quality, it is of significant importance to enhance the producibility of fused deposition modeling (FDM)-printed objects in PLA. The purpose of this investigation is to boost toughness and to reduce the production cost of the FDM-printed tensile test samples with the desired part thickness. To attain the research purpose number of experiments are designed and analyzed by the Response Surface Method (RSM). The statistical analysis is performed to deal with this concern considering layer thickness, infill percentage, and extruder temperature as controlled factors. The tensile test specimens are printed based on the designed experiments, and the tensile strength tests are conducted by SANTAM 150 universal testing machine based on ASTM D638. The honeycomb internal fill pattern is applied for the production of light-weight and high-strength specimens. The area under Force- Extension curve up to fracture is acquired as the toughness of the printed specimens. This study also developed a modeling process using ANN and ANN-GA techniques for developing an accurate estimation for toughness, part thickness, and production cost as dependant variables. Results were evaluated by correlation coefficient and RMSE values. According to the modeling results, ANN-GA as a hybrid ML technique could successfully improve the accuracy of modeling about 7.5, 11.5 and 4.5 % for toughness, part thickness, and production cost, respectively, in comparison with those for the single ANN method. In the other side, the optimization results confirm that the optimized specimen is cost-effective and able to comparatively undergo deformation, which develops the usability of printed PLA objects. The research is accomplished under the constraints of PLA compatibility with existing fused deposition modeling setup without changing the functional hardware/software of the machine. Although the mechanical properties and dimensional accuracy of PLA have already been studied, there is little literature on the toughness of the printed PLA with honeycomb internal fill pattern.

The primary distribution systems are comprised of power lines delivering power to utility feeders from substations. The inspection and maintenance of damaged and broken power system insulators are of paramount importance for continuous power supply and public safety. hence, to identify any faults and defects in advance a periodic inspection of power line insulators and other components be ensured beforehand. To automate the process and reduce operational cost and risk Unmanned Aerial Vehicles (UAVs) are being extensively utilized. As they present a safer and efficient way to examine the power system insulators and their components without closing the power distribution system ensuring continuous supply to the end-users. To achieve these objectives in this work a novel dataset is designed by capturing real images using UAVs and manually generated images collected to overcome the data insufficiency problem. Deep Laplacian pyramids based super-resolution network is implemented to reconstruct high-resolution training images. To improve the visibility of low light images a low light image enhancement technique is used for the robust exposure correction of the training images. Using computer vision-based object detection techniques to identify faults and classify them according to classes they belong. A different fine-tuning strategy is implemented for fine-tuning the object detection model to increase detection accuracy for the specific faulty insulators. To improve the faults detection several flight path strategies are proposed for efficient inspection. Such strategies overcome the shuttering effect of insulators along with providing a less complex, time, and energy-efficient approach for capturing video stream of the power system components. Performance of different object detection models is presented for selecting the suitable one for fine-tuning on the specific faulty insulator dataset. Our proposed approach gives a less complex and more efficient flight strategy along with better results. For defect detection, our proposed method achieved an F1-score of 0.81 and 0.77 on two different datasets. Our approach is based on real aerial inspection of in-service porcelain insulators by extensive evaluation of several video sequences showing robust faults recognition and diagnostic capabilities. Our approach is demonstrated on data acquired by a drone in Swat Pakistan.

Background: White matter hyperintensities (WMH), of presumed vascular origin, are visible and quantifiable neuroradiological markers of brain parenchymal change. These changes may range from damage secondary to inflammation and other neurological conditions, through to healthy ageing. Fully automatic WMH quantification methods are promising, but still, traditional semi-automatic methods seem to be preferred in clinical research. We systematically reviewed the literature for fully automatic methods developed in the last five years, to assess what are considered state-of-the-art techniques, as well as trends in the analysis of WMH of presumed vascular origin. Method: We registered the systematic review protocol with the International Prospective Register of Systematic Reviews (PROSPERO), registration number - CRD42019132200. We conducted the search for fully automatic methods developed from 2015 to July 2020 on Medline, Science direct, IEE Explore, and Web of Science. We assessed risk of bias and applicability of the studies using QUADAS 2. Results: The search yielded 2327 papers after removing 104 duplicates. After screening titles, abstracts and full text, 37 were selected for detailed analysis. Of these, 16 proposed a supervised segmentation method, 10 proposed an unsupervised segmentation method, and 11 proposed a deep learning segmentation method. Average DSC values ranged from 0.538 to 0.91, being the highest value obtained from an unsupervised segmentation method. Only four studies validated their method in longitudinal samples, and eight performed an additional validation using clinical parameters. Only 8/37 studies made available their method in public repositories. Conclusions: We found no evidence that favours deep learning methods over the more established k-NN, linear regression and unsupervised methods in this task. Data and code availability, bias in study design and ground truth generation influence the wider validation and applicability of these methods in clinical research.

Tailed phages are the most abundant and diverse group of viruses on the planet. Yet, the smallest tailed phages display relatively complex capsids and large genomes compared to other viruses. The lack of tailed phages forming the common icosahedral capsid architectures T = 1 and T = 3 is puzzling. Here, we extracted geometrical features from high-resolution tailed phage capsid reconstructions and built a statistical model based on physical principles to predict the capsid diameter and genome length of the missing small tailed phage capsids. We applied the model to 3,348 isolated tailed phage genomes and 1,496 gut metagenome-assembled tailed phage genomes. Four isolated tailed phages were predicted to form T = 3 icosahedral capsids, and twenty-one metagenome-assembled tailed phages were predicted to form T < 3 capsids. The smallest capsid predicted was a T = 4/3 ≈ 1.33 architecture. No tailed phages were predicted to form the smallest icosahedral architecture, T = 1. We discuss the feasibility of the missing T = 1 tailed phage capsids and the implications of isolating and characterizing small tailed phages for viral evolution and phage therapy.

Purpose The gradual increase in geriatric issues and global imbalance of the ratio between patients and healthcare professionals has created a demand for intelligent systems with the least error-prone diagnosis results to be used by less medically trained persons and save clinical time. This paper aims at investigating the development of an image-based colourimetric analysis. The purpose of recognising such tests is to support wider users to begin a colourimetric test to be used at homecare settings, telepathology, etc. Design/methodology/approach The concept of an automatic colourimetric assay detection is delivered by utilising two cases. Training Deep Learning (DL) models on thousands of images of these tests using transfer learning, this paper i) classifies the type of the assay, and ii) classifies the colourimetric results. Findings This paper demonstrated that the assay type can be recognised using DL techniques with 100% accuracy within a fraction of a second. Some of the advantages of the pre-trained model over the calibration-based approach are robustness, readiness and suitability to deploy for similar applications within a shorter period of time. Originality/value To the best of our knowledge, this is the first attempt to provide Colourimetric Assay Type Classification (CATC) using DL. Humans are capable to learn thousands of visual classifications in their life. Object recognition may be a trivial task for humans, due to photometric and geometric variabilities along with the high degree of intra-class variabilities it can be a challenging task for machines. However, transforming visual knowledge into machines, as proposed, can support non-experts to better manage their health and reduce some of the burdens on experts.

The small satellite market continues to grow year after year. A compound annual growth rate of 17% is estimated during the period between 2020 and 2025. Low-cost satellites can send a vast amount of images to be post-processed at the ground to improve the quality and extract detailed information. In this domain lies the resolution enhancement task, where a low-resolution image is converted to a higher resolution automatically. Deep learning approaches to Super-Resolution (SR) reached the state-of-the-art in multiple benchmarks; however, most of them were studied in a single-frame fashion. With satellite imagery, multi-frame images can be obtained at different conditions giving the possibility to add more information per image and improve the final analysis. In this context, we developed and applied to the PROBA-V dataset of multi-frame satellite images a model that recently topped the European Space Agency’s Multi-frame Super Resolution (MFSR) competition. The model is based on proven methods that worked on 2D images tweaked to work on 3D: the Wide Activation Super Resolution (WDSR) family. We show that with a simple 3D CNN residual architecture with WDSR blocks and a frame permutation technique as data augmentation better scores can be achieved than with more complex models. Moreover, the model requires few hardware resources, both for training and evaluation, so it can be applied directly from a personal laptop.

The COVID-19 pandemic situation has created even more difficulties in the quick identification and screening of the COVID-19 patients for the medical specialists. Therefore, a significant study is necessary for detecting COVID-19 cases using an automated diagnosis method, which can aid in controlling the spreading of the virus. In this paper, the study suggests a Deep Convolutional Neural Network-based multi-classification approach (COV-MCNet) using eight different pre-trained architectures such as VGG16, VGG19, ResNet50V2, DenseNet201, InceptionV3, MobileNet, InceptionResNetV2, Xception which are trained and tested on the X-ray images of COVID-19, Normal, Viral Pneumonia, and Bacterial Pneumonia. The results from 3-class (Normal vs. COVID-19 vs. Viral Pneumonia) showed that only the ResNet50V2 model provides the highest classification performance (accuracy: 95.83%, precision: 96.12%, recall: 96.11%, F1-score: 96.11%, specificity: 97.84%) compared to rest of the models. The results from 4-class (Normal vs. COVID-19 vs. Viral Pneumonia vs. Bacterial Pneumonia) demonstrated that the pre-trained model DenseNet201 provides the highest classification performance (accuracy: 92.54%, precision: 93.05%, recall: 92.81%, F1-score: 92.83%, specificity: 97.47%). Notably, the ResNet50V2 (3-class) and DenseNet201 (4-class) models in the proposed COV-MCNet framework showed higher accuracy compared to the rest six models. This indicates that the designed system can produce promising results to detect the COVID-19 cases on the availability of more data. The proposed multi-classification network (COV-MCNet) significantly speeds up the existing radiology-based method, which will be helpful to the medical community and clinical specialists for early diagnosis of the COVID-19 cases during this pandemic.

Learning disorders (LD) are diagnosed in children whose academic skills of reading, writing or mathematics are impaired and lagged according to their age, schooling and intelligence. Children with LD experience substantial working memory (WM) deficits, even more pronounced if more than one of the academic skills is affected. We compared the task-related EEG power spectral density of children with LD (n= 23), with a control group of children with good academic achievement (n= 22), during the performance of a WM task. sLoreta was used to estimate the current distribution at the sources, and 18 brain regions of interests (ROIs) were chosen with an extended version of the eigenvector centrality mapping technique. In this way, we lessen some drawbacks of the traditional EEG at the sensor space by an analysis at the brain sources level over data-driven selected ROIs. Results: The LD group showed fewer correct responses at the WM task, an overall slower EEG with more theta activity in all ROIs, less upper-alpha power at posterior areas, and less high-frequency beta activity in frontal areas. We explain these EEG patterns in LD children as indices of an inefficient neural resource management related with a delay in the neural development.

During the period January 2014 – October 2018, four strong earthquakes occurred in the Ionian Sea, Greece. A rich aftershock sequence followed each event of them. More analytically, according to the manual solutions of National Observatory of Athens, the first event (K1), occurred on 26 January 2014 in Kefallinia Island with magnitude M_L = 5.8, which was followed by another in the same region (K2) on 3 February 2014 with magnitude M_L = 5.7. The third event occurred on 17 November 2015, M_L = 6.0 in Lefkas Island (L1) and the last on 25 October 2018, M_L = 6.6 in Zande Island (Z1). The first three of these earthquakes caused moderate structural damages mainly in houses and produced particular unrest to the local population. This work presents first the calculation of the source parameters of the strong events as well as for all earthquakes with magnitude M_L > 4.0, using the methodology of the Moment tensor inversion and secondary data from permanent GPS stations were analyzed to confirm the findings from seismological data and to investigate the displacement due to the earthquakes.

Google play store allow the user to download a mobile application (app) and user get inspired by the rating and reviews of the mobile app. A recent study analyzes that user preferences, user opinion for improvement, user sentiment about particular feature and detail with descriptions of experiences are very useful for an application developer. However, many application reviews are very large and difficult to process manually. Star rating is given of the whole application and the developer cannot analyze the single feature. In this research, we have scrapped 282,231 user reviews through different data scraping techniques. We have applied the text classification on these user reviews. We have applied different algorithms and find the precision, accuracy, F1 score and recall. In evaluated results, we have to also find the best algorithm.

A tunable quantum cascade laser (QCL) spectrometer was used to develop methods for detecting and quantifying high explosives (HE) in soil based on multivariate analysis (MVA) and artificial intelligence (AI). For quantification, mixes of 2,4-dinitrotoluene (2,4-DNT) with concentrations from 0% to 20% w/w were investigated using three types of soils: bentonite, synthetic soil, and natural soil. A Partial least squares regression model was generated for predicting 2,4-DNT concentrations. To increase its selectivity, the model was trained and evaluated using additional analytes as interferences, including other HEs such as PETN, RDX, and TNT and non-explosives such as benzoic acid and ibuprofen. For detection, mixes of different explosives in soils were used to implement two AI strategies. In the first strategy, the spectra of the samples were compared with those of soils recorded in a database to identify the most similar soils based on QCL spectroscopy. Next, a Classical Least Squares preprocessing (Pre-CLS) was applied to soils spectra selected from the database. The parameter obtained based on the sum of the weights of Pre-CLS was then used to generate a simple binary discrimination model for distinguishing between contaminated and uncontaminated soils, achieving an accuracy of 0.877. In the second AI strategy, the same parameter was added to a principal component matrix obtained from spectral data of samples and used to generate multi-classification models based on different machine learning algorithms. A Random Forest model worked best with 0.997 accuracy and allowing to distinguish between soils contaminated with DNT, TNT, or RDX and uncontaminated soils.

This work can be considered as a first step of designing a future competitive data-driven approach for remaining useful life prediction of aircraft engines. The proposed approach is an ensemble of serially connected extreme learning machines. The results of prediction of the first networks are scaled and fed to the next networks as an additive features to the original inputs. This feature mapping allows increasing the correlation of training inputs with their targets by holding new prior knowledge about the probable behavior of the target function. The proposed approach is evaluated under remaining useful estimation using a set of “time-varying” data retrieved from the public dataset C-MAPSS (Commercial Modular Aero Propulsion System Simulation) provided by NASA. The prediction performances are compared to basic extreme learning machine and proved the effectiveness of the proposed methodology.

Reliable estimates of poplar plantations area are not available at the French national scale due to the unsuitability and low update rate of existing forest databases for this short-rotation species. While supervised classification methods have been shown to be highly accurate in mapping forest cover from remotely sensed images, their performance depends to a great extent on the labelled samples used to build the models. In addition to their high acquisition cost, such samples are often scarce and not fully representative of the variability in class distributions. Consequently, when classification models are applied to large areas with high intra-class variance, they generally yield poor accuracies. In this paper, we propose the use of active learning (AL) to efficiently adapt a classifier trained on a source image to spatially distinct target images with minimal labelling effort and without sacrificing classification performance. The adaptation consists in actively adding to the initial local model, new relevant training samples from other areas, in a cascade that iteratively improves the generalisation capabilities of the classifier, leading to a global model tailored to different areas. This active selection relies on uncertainty sampling to directly focus on the most informative pixels for which the algorithm is the least certain of their class labels. Experiments conducted on Sentinel-2 time series showed that when the same number of training samples was used, active learning outperformed passive learning (random sampling) by up to 5% of overall accuracy and up to 12% of class F-score. In addition, and depending on the class considered, the random sampling required up to 50% more samples to achieve the same performance of an active learning-based model. Moreover, the results demonstrate the suitability of the derived global model to accurately map poplar plantations among other tree species with overall accuracy values up to 14% higher than those obtained with local models. The proposed approach paves the way for national-scale mapping in an operational context.

This article presents an automated vision-based algorithm for the die-scale inspection of wafer images captured using scanning acoustic tomography (SAT). This algorithm can find defective and abnormal die-scale patterns, and produce a wafer map to visualize the distribution of defects and anomalies on the wafer. The main procedures include standard template extraction, die detection through template matching, pattern candidate prediction through clustering, and pattern classification through deep learning. To conduct the template matching, we first introduce a two-step method to obtain a standard template from the original SAT image. Subsequently, a majority of the die patterns are detected through template matching. Thereafter, the columns and rows arranged from the detected dies are predicted using a clustering method; thus, an initial wafer map is produced. This map is composed of detected die patterns and predicted pattern candidates. In the final phase of the proposed algorithm, we implement a deep learning-based model to determine defective and abnormal patterns in the wafer map. The experimental results verified the effectiveness and efficiency of our proposed algorithm. In conclusion, the proposed method performs well in identifying defective and abnormal die patterns, and produces a wafer map that presents important information for solving wafer fabrication issues.

Prediction of crop yield is essential for food security policymaking, planning, and trade. The objective of the current study is to propose novel crop yield prediction models based on hybrid machine learning methods. In this study, the performance of artificial neural networks-imperialist competitive algorithm (ANN-ICA) and artificial neural networks-gray wolf optimizer (ANN-GWO) models for the crop yield prediction is evaluated. According to the results, ANNGWO, with R of 0.48, RMSE of 3.19, and MEA of 26.65, proved a better performance in the crop yield prediction compared to the ANN-ICA model. The results can be used by either practitioners, researchers or policymakers for food security.

Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include the detection of individual trees, tree species classification, bio-mass estimation, etc. Deep Neural Networks (DNN) have shown superior results when comparing with conventional machine learning methods such as Multi-Layer Perceptron (MLP) in cases of huge input data. The objective of this research was to investigate 3D convolutional neural networks (3D-CNN) to classify three major tree species in a boreal forest: pine, spruce, and birch. The proposed 3D-CNN models were employed to classify tree species in a test site in Finland. The classifiers were trained with a dataset of 3039 manually labelled trees. Then the accuracies were assessed by employing independent datasets of 803 records. To find the most efficient set of feature combination, we compare the performances of 3D-CNN models trained with hyperspectral (HS) channels, RGB channels, and canopy height model (CHM), separately and combined. It is demonstrated that the proposed 3D-CNN model with RGB and HS layers produces the highest classification accuracy. The producer accuracy of the best 3D-CNN classifier on the test dataset were 99.6%, 94.8%, and 97.4% for pines, spruces, and birches, respectively. The best 3D-CNN classifier produced ~5% better classification accuracy than the MLP with all layers. Our results suggest that the proposed method provides excellent classification results with acceptable performance metrics for HS datasets. Our results show that pine class was detectable in most layers. Spruce was most detectable in RGB data, while birch was most detectable in the HS layers. Furthermore, the RGB datasets provide acceptable results for many low-accuracy applications.

NMR spectral datasets, especially in systems with limited samples, can be difficult to interpret if they contain multiple chemical components (phases, polymorphs, molecules, crystals, glasses, etc…) and the possibility of overlapping resonances. In this paper, we benchmark several blind source separation techniques for analysis of NMR spectral datasets containing negative intensity. For benchmarking purposes, we generated a large synthetic datasbase of quadrupolar solid-state NMR-like spectra that model spin-lattice T1 relaxation or nutation tip/flip angle experiments. Our benchmarking approach focused exclusively on the ability of blind source separation techniques to reproduce the spectra of the underlying pure components. In general, we find that FastICA (Fast Independent Component Analysis), SIMPLISMA (SIMPLe-to-use-Interactive Self-modeling Mixture Analysis), and NNMF (Non-Negative Matrix Factorization) are top-performing techniques. We demonstrate that dataset normalization approaches prior to blind source separation do not considerably improve outcomes. Within the range of noise levels studied, we did not find drastic changes to the ranking of techniques. The accuracy of FastICA and SIMPLISMA degrades quickly if excess (unreal) pure components are predicted. Our results indicate poor performance of SVD (Singular Value Decomposition) methods, and we propose alternative techniques for matrix initialization. The benchmarked techniques are also applied to real solid state NMR datasets. In general, the recommendations from the synthetic datasets agree with the recommendations and results from the real data analysis. The discussion provides some additional recommendations for spectroscopists applying blind source separation to NMR datasets, and for future benchmark studies. Applications of blind source separation to NMR datasets containing negative intensity may be especially useful for understanding complex and disordered systems with limited samples and mixtures of chemical components.

Machine Learning (ML) approaches have been fruitfully applied to several classification problems of neurophysiological activity. Considering the relevance of emotion in human cognition and behaviour, ML found an important application field in emotion identification based on neurophysiological activity. Nonetheless, the literature results present a high variability depending on the neuronal activity measurement, the signal features and the classifier type. The present work aims to provide new methodological insight on ML applied to emotion identification based on electrophysiological brain activity. For this reason, we recorded EEG activity while emotional stimuli, high and low arousal (auditory and visual) were provided to a group of healthy participants. Our target signal to classify was the pre-stimulus onset brain activity. Classification performance of three different classifiers (LDA, SVM and kNN) was compared using both spectral and temporal features. Furthermore, we also contrasted the classifiers performance with static and dynamic (time evolving) features. The results show a clear increased in classification accuracy with temporal dynamic features. In particular, the SVM classifiers with temporal features showed the best accuracy (63.8 %) in classifying high vs. low arousal auditory stimuli.

A large amount of data is produced every day by stakeholders of the Air Traffic Management (ATM) system, in particular airline operators, airports, and air navigation service provider (ANSP). Most data is kept private for many reasons, including commercial and security concerns. More than data, shared information is precious, as it leverages intelligent decision-making support tools designed to smooth daily operations. We present a framework to detect, identify and characterise anomalies in past aircraft trajectory data. It is based on an open source of ADS-B based aircraft trajectories, and extracted information can benefit a wide range of stakeholders: Air Traffic Control (ATC) training centres could play more realistic simulations; ANSP may improve capacity indicators; academics improve safety models and risk estimations; and commercial stakeholders, like airlines and airports, may use such information to improve short-term predictions and optimise their operations. The technique is based on autoencoding artificial neural networks applied on flows of trajectories, which provide a useful reading grid associating cluster analysis with quantified level of abnormality. In particular, we find that the highest anomaly scores correspond to poor weather conditions, whereas anomalies with a lower score relate to ATC tactical actions.

The loss of integrity and adverse effect on mechanical properties can be concluded as attributing miro/macro-mechanics damage in structures, especially in composite structures. Damage as a progressive degradation of material continuity in engineering predictions for any aspects of initiation and propagation requires to be identified by a trustworthy mechanism to guarantee the safety of structures. Besides the materials design, structural integrity and health are usually prone to be monitored clearly. One of the most powerful methods for the detection of damage is machine learning (ML). This paper presents the state of the art of ML methods and their applications in structural damage and prediction. Popular ML methods are identified and the performance and future trends are discussed.

With the advancement in AR technology, more education-based applications are being developed using Augmented Reality, which has revolutionized the learning experience. However, in order to determine the application’s impact on student’s motivation, performance and their communication with the lecturer, various studies are conducted. These studies use one of the three research methodologies for data analysis and evaluation. In this systematic review, we have analyzed various research methodologies for system evaluation of the AR learning applications and recorded the student response toward the system. Also, we checked which methodology is preferred by researchers and why. A total number of 25 studies were analyzed which were published during the year of 2015 and 2019. The results indicate that most popular research technique is mixed methodology as it combines both qualitative and quantitative techniques. The purpose of this review is to offer new insights to researchers and provide them with advice about evaluation of AR applications and which tool or technique is more effective.

Deep behavioral covariates (DBCs) introduced in this perspective form a new class of covariates that have the potential to enhance the performance of predictive models and improve analytics in clinical decision support applications. DBCs can measure how engaged a patient tends to be and how he or she tends to respond to events, and they may be highly predictive of the patient’s outcomes for a planned treatment. DBCs may potentially serve as a standard to measure patient engagement and activation and may form highly efficient mechanisms for improving patient outcomes.

We analyze damage propagation modeling of turbo-engines in a data-driven approach. We investigate subspace tracking assuming a low dimensional manifold structure and a static behavior during the healthy state of the machines. Our damage propagation model is based on the deviation of the data from the static behavior and uses the notion of health index as a measure of the condition. Hence, we incorporate condition-based maintenance and estimate the remaining useful life based on the current and previous health indexes. This paper proposes an algorithm that adapts well to the dynamics of the data and underlying system, and reduces the computational complexity by utilizing the low dimensional manifold structure of the data. A significant performance improvement is demonstrated over existing methods by using the proposed algorithm on CMAPSS Turbo-engine datasets.

We introduce a total energy and environmental evaluation method in the manufacturing industry. The method gives us a series of descriptive indexes to assess the overall environmental effect level on materials, energy, wastes and products in the life cycle process. Meanwhile, the method uses partial indexes, environmental effect factors, and correction offsets into the quantitative model to analyze the learning process and rebound effect on the energy and environment at each procedure. In this work, we choose S-shaped learning curves to describe how to decrease energy consumption and improve the technical learning by doing for recent 30 years. Also, we draw the different rebound effect curves of the total energy-environmental evaluation with technical learning method, which use the annual industrial production growth rate to show that it's significant to estimate its effect on technology changes. The ideas about the interaction of energy and production environment from material flows to energy consumption, direct us to build an example to estimate quantitatively the results with different condition factors, and realize the process improvement and develop new products.

Optical networks are prone to power jamming attacks intending service disruption. This paper presents a Machine Learning (ML) framework for detection and prevention of jamming attacks in optical networks. We evaluate various ML classifiers for detecting out-of-band jamming attacks with varying intensities. Numerical results show that artificial neural network is the fastest ($10^6$ detection per second) for inference and most accurate ($\approx 100 \%$) in detecting power jamming attacks as well as identifying the optical channels attacked. We also discuss and study a novel prevention mechanism when the system is under active jamming attacks. For this scenario, we propose a novel resource reallocation scheme that utilizes the statistical information of attack detection accuracy to lower the probability of successful jamming of lightpaths while minimizing lightpaths' reallocations. Simulation results show that the likelihood of jamming a lightpath reduces with increasing detection accuracy, and localization reduces the number of reallocations required.

The basal ganglia (BG) are a central component of the brain, crucial to the initiation, execution and learning of adaptive actions. The BG are the major site of the action of dopamine. An important aspect of the BG architecture is the existence of two paths, direct and indirect, having different projection targets and dopamine receptor expression. To understand the BG, dopamine, and related disorders, it is imperative to understand the two paths. The standard account used in neuroscience research for decades posits that the role of the direct path is to support movements, while that of the indirect path is to suppress unselected or completed movements. This account is contradicted by converging evidence. Here, we explain why the arguments supporting the standard account are flawed, and present a new account, in which the role of the indirect path is completely opposite: to support automated execution. During acute events, the direct path allows coarse responses. These are refined by competition, and the resulting focused response is executed and learned by the indirect path, assisted by cholinergic interneurons and the subthalamic nucleus (STN). The new account allows a novel understanding of the symptoms of Parkinson's disease, in particular tremor and rigidity, and of its treatment by STN deep brain stimulation.

Timely detection of surface damages on wind turbine blades is imperative for minimising downtime and avoiding possible catastrophic structural failures. With recent advances in drone technology, a large number of high-resolution images of wind turbines are routinely acquired and subsequently analysed by experts to identify imminent damages. Automated analysis of these inspection images with the help of machine learning algorithms can reduce the inspection cost, thereby reducing the overall maintenance cost arising from the manual labour involved. In this work, we develop a deep learning based automated damage suggestion system for subsequent analysis of drone inspection images. Experimental results demonstrate that the proposed approach could achieve almost human level precision in terms of suggested damage location and types on wind turbine blades. We further demonstrate that for relatively small training sets advanced data augmentation during deep learning training can better generalise the trained model providing a significant gain in precision.

Detailed built-up area information is valuable for mapping complex urban environments. Although a large number of classification algorithms about built-up areas have been developed, they are rarely tested from the perspective of feature engineering and feature learning. Therefore we launched a unique investigation to provide a full test of the OLI imagery for 15-m resolution built-up area classification in 2015, in Beijing, China. Training a classifier requires many sample points, and we propose a method based on the ESA's 38-meter global built-up area data of 2014, Open Street Map and MOD13Q1-NDVI to achieve rapid and automatic generation of a large number of sample points. Our aim is to examine the influence of a single pixel and image patch under traditional feature engineering and modern feature learning strategies. In feature engineering, we consider spectra, shape and texture as the input features, and SVM, random forest (RF) and AdaBoost as the classification algorithms. In feature learning, the convolution neural network (CNN) is used as the classification algorithm. In total, 26 built-up land cover maps were produced. Experimental results show that: (1) the approaches based on feature learning are generally better than those based on feature engineering in terms of classification accuracy, and the performance of ensemble classifiers e.g., RF, is comparable to that of CNN. Two dimensional CNN and the 7 neighborhood RF have the highest classification accuracy of nearly 91%. (2) Overall, the classification effect and accuracy based on image patches are better than those based on single pixels. The features that can highlight the information of the target category (for example, PanTex and EMBI) can help improve classification accuracy.

This study proposes a mobile positioning method which adopts recurrent neural network algorithms to analyze the received signal strength indications from heterogeneous networks (e.g., cellular networks and Wi-Fi networks) for estimating the locations of mobile statioThis study proposes a mobile positioning method which adopts recurrent neural network algorithms to analyze the received signal strength indications from heterogeneous networks (e.g., cellular networks and Wi-Fi networks) for estimating the locations of mobile stations. The recurrent neural networks with multiple consecutive timestamps can be applied to extract the features of time series data for the improvement of location estimation. In practical experimental environments, there are 4,525 records, 59 different base stations, and 582 different Wi-Fi access points detected in Fuzhou University in China. The lower location errors can be obtained by the recurrent neural networks with multiple consecutive timestamps (e.g., 2 timestamps and 3 timestamps); the experimental results can be observed that the average error of location estimation was 9.19 meters by the proposed mobile positioning method with 2 timestamps.

In recent years, weeds is responsible for most of the agricultural yield losses. To deal with this threat, farmers resort to spraying pesticides throughout the field. Such method not only requires huge quantities of herbicides but impact environment and humans health. One way to reduce the cost and environmental impact is to allocate the right doses of herbicide at the right place and at the right time (Precision Agriculture). Nowadays, Unmanned Aerial Vehicle (UAV) is becoming an interesting acquisition system for weeds localization and management due to its ability to obtain the images of the entire agricultural field with a very high spatial resolution and at low cost. Despite the important advances in UAV acquisition systems, automatic weeds detection remains a challenging problem because of its strong similarity with the crops. Recently Deep Learning approach has shown impressive results in different complex classification problem. However, this approach needs a certain amount of training data but, creating large agricultural datasets with pixel-level annotations by expert is an extremely time consuming task. In this paper, we propose a novel fully automatic learning method using Convolutional Neuronal Networks (CNNs) with unsupervised training dataset collection for weeds detection from UAV images. The proposed method consists in three main phases. First we automatically detect the crop lines and using them to identify the interline weeds. In the second phase, interline weeds are used to constitute the training dataset. Finally, we performed CNNs on this dataset to build a model able to detect the crop and weeds in the images. The results obtained are comparable to the traditional supervised training data labeling. The accuracy gaps are 1.5% in the spinach field and 6% in the bean field.

Due to the limitations on the capabilities of current robots regarding task learning and performance, imitation is an efficient social learning approach that endows a robot with the ability to transmit and reproduce human postures, actions, behaviors, etc., as a human does. Stable whole-body imitation and task-oriented teleoperation via imitation are challenging issues. In this paper, a novel comprehensive and unrestricted real-time whole-body imitation system for humanoid robots is designed and developed. To map human motions to a robot, an analytical method called geometrical analysis based on link vectors and virtual joints (GA-LVVJ) is proposed. In addition, a real-time locomotion method is employed to realize a natural mode of operation. To achieve safe mode switching, a filter strategy is proposed. Then, two quantitative vector-set-based methods of similarity evaluation focusing on the whole body and local links, called the Whole-Body-Focused (WBF) method and the Local-Link-Focused (LLF) method, respectively, are proposed and compared. Two experiments conducted to verify the effectiveness of the proposed methods and system are reported. Specifically, the first experiment validates the good stability and similarity features of our system, and the second experiment verifies the effectiveness with which complicated tasks can be executed. At last, an imitation learning mechanism in which the joint angles of demonstrators are mapped by GA-LVVJ is presented and developed to extend the proposed system.

A timely inventory of agricultural areas and crop types is an essential requirement for ensuring global food security. Satellite remote sensing has proven to be an increasingly more reliable tool to identify crop types. With the Copernicus program and its Sentinel satellites, a growing source of satellite remote sensing data is publicly available at no charge. Here we use joint Sentinel-1 radar and Sentinel-2 optical imagery to create a crop map for Belgium. To ensure homogenous radar and optical input across the country, Sentinel-1 12-day backscatter composites were created after incidence angle normalization, and Sentinel-2 NDVI images were smoothed to yield dekadal cloud-free composites. An optimized random forest classifier predicted the 8 crop types with a maximum accuracy of 82% and a kappa coefficient of 0.77. We found that a combination of radar and optical imagery always outperformed a classification based on single-sensor inputs, and that classification performance increased throughout the season until July, when differences between crop types are largest. Furthermore we showed that the concept of classification confidence derived from the random forest classifier provided insight in the reliability of the predicted class for each pixel, clearly showing that parcel borders have a lower classification confidence. We concluded that the synergistic use of radar and optical data for crop classification led to richer information increasing classification accuracies compared to optical-only classification. Further work should focus on object-level classification and crop monitoring to exploit the rich potential of combined radar and optical observations.

The emerging use of visualization techniques in pathology and microbiol- ogy has been accelerated by machine learning (ML) approaches towards image preprocessing, classification, and feature extraction in an increasingly complex series of datasets. Modern Convolutional Neural Network (CNN) architectures have developed into an umbrella of vast image reinforcement and recognition methods, including a combined classification-localization of single/multi-object featured images. As a subtype neural network, CNN cre- ates a rapid order of complexity by initially detecting borderlines, edges, and colours in images for dataset construction, eventually capable in mapping intricate objects and conformities. This paper investigates the disparities between Tensorflow object detection APIs, exclusively, Single Shot Detector (SSD) Mobilenet V1 and the Faster RCNN Inception V2 model, to sample computational drawbacks in accuracy-precision vs. real time visualization capabilities. The situation of rapid ML medical image analysis is theoretically framed in regions with limited access to pathology and disease prevention departments (e.g. 3rd world and impoverished countries). Dark field mi- croscopy datasets of an initial 62 XML-JPG annotated training files were processed under Malaria and Syphilis classes. Model trainings were halted as soon as loss values were regularized and converged.

Deep learning has recently attracted much attention due to its excellent performance in processing audio, image, and video data. However, few studies are devoted to the field of automatic modulation classification (AMC). It is one of the most well-known research topics in communication signal recognition, which remains challenging for traditional methods due to the complex disturbance from other sources. This paper proposes a heterogeneous deep model fusion (HDMF) method to solve the problem in a unified framework. The contributions include: 1) The convolutional neural network (CNN) and long short-term memory (LSTM) are combined by two different ways without prior knowledge involved; 2) A large database, including eleven types of single-carrier modulation signals with various noises as well as a fading channel, is collected with various signal-to-noise ratios (SNRs) based on a real geographical environment; and 3) Experimental results demonstrate that HDMF is super capable of copping with the AMC problem, and achieves much better performance when compared with the independent network. The source code and the database will be publically available.

Sensitivity to weather conditions, and specially to clouds, is a severe limiting factor to the use of optical remote sensing for Earth monitoring applications. A possible alternative, is to resort to weather-insensitive synthetic aperture radar (SAR) images. However, in many real-world applications, critical decisions are made based on some informative spectral features, such as water, vegetation or soil indices, which cannot be extracted from SAR images. In the absence of optical sources, these data must be estimated. The current practice is to perform linear interpolation between data available at temporally close time instants. In this work, we propose to estimate missing spectral features through data fusion and deep-learning. Several sources of information are taken into account - optical sequences, SAR sequences, DEM - so as to exploit both temporal and cross-sensor dependencies. Based on these data, and a tiny cloud-free fraction of the target image, a compact convolutional neural network (CNN) is trained to perform the desired estimation. To validate the proposed approach, we focus on the estimation of the normalized difference vegetation index (NDVI), using coupled Sentinel-1 and Sentinel-2 time-series acquired over an agricultural region of Burkina Faso from May to November 2016. Several fusion schemes are considered, causal and non-causal, single-sensor or joint-sensor, corresponding to different operating conditions. Experimental results are very promising, showing a significant gain over baselines methods according to all performance indicators.

In this paper, we present the design of a wearable photoplethysmography (PPG) system, R-band for acquiring the PPG signals. PPG signals are influenced by the respiration or breathing process and hence can be used for estimation of respiration rate. R-Band detects the PPG signal that is routed to a Bluetooth low energy device such as a nearbyplaced smartphone via microprocessor. Further, we developed an algorithm based on Extreme Learning Machine (ELM) regression for the estimation of respiration rate. We proposed spectral kurtosis features that are fused with the state-ofthe-art respiratory-induced amplitude, intensity and frequency variations-based features for the estimation of respiration rate (in units of breaths per minute). In contrast to the neural network (NN), ELM does not require tuning of hidden layer parameter and thus drastically reduces the computational cost as compared to NN trained by the standard backpropagation algorithm. We evaluated the proposed algorithm on Capnobase data available in the public domain.

Highly flexible manufacturing systems require continuous run-time (self-) optimization of processes with respect to various parameters, e.g. efficiency, availability, energy consumption etc. A promising approach for achieving (self-) optimization in manufacturing systems is the usage of the context sensitivity approach. Thereby the Cyber-Physical Systems play an important role as sources of information to achieve context sensitivity. In this paper it is demonstrated how context sensitivity can be used to realize a holistic solution for (self-) optimization of discrete flexible manufacturing systems, by making use of Cyber-Physical System integrated in manufacturing systems/processes. A generic approach for context sensitivity, based on self-learning algorithms, is proposed aiming at a various manufacturing systems. The new solution is propos encompassing run-time context extractor and optimizer. Based on the self-learning module both context extraction and optimizer are continuously learning and improving their performance. The solution is following Service Oriented Architecture principles. The generic solution is developed and then applied to two very different manufacturing processes. This paper proposes a holistic solution to achieve context sensitivity for Flexible Manufacturing Systems, whereby the knowledge created by applying the context sensitivity approach can be used for (self-) optimization of manufacturing processes.

Human microbiome data from genomic sequencing technologies is fast accumulating, giving us insights into bacterial taxa that contribute to health and disease. Predictive modeling of such microbiota count data for classification of human infection from parasitic worms such as helminths can help in detection and management across global populations. Real-world datasets of microbiome experiments are typically sparse containing hundreds of measurements for bacterial species, of which only a few are detected in the bio-specimens that are analyzed. This feature of microbiome data produces the challenge of needing more observations for accurate predictive modeling and has been dealt with previously using different methods of feature reduction. To our knowledge, integrative methods such as transfer learning has not been explored in the microbiome domain yet, as a way to deal with data sparsity by incorporating knowledge of different but related datasets. One way of incorporating this knowledge is by using a meaningful mapping among features of these datasets. In this paper, we claim that this mapping would exist among members of each individual cluster grouped based on phylogenetic dependency among taxa and their association to the phenotype. We validate our claim by showing that models incorporating associations in such a grouped feature space result in no performance deterioration for the given classification task. In this paper, we test our hypothesis using classification models that detect helminth infection in microbiota of human fecal samples obtained from Indonesia and Liberia countries. In our experiments, we first learn binary classifiers for helminth infection detection by using Naive Bayes, Support Vector Machines, Multilayer Perceptrons, and Random Forest methods. In the next step, we add taxonomic modeling using the SMART-scan module to group the data, and learn classifiers using the same four methods, to test the validity of the achieved groupings. We observed a 6% to 23% and 7% to 26% performance improvement based on the Area Under ROC Curve (AUC) and Balanced Accuracy(Bacc) measures, respectively, over 10 runs of 10-fold cross-validation. These results show that using phylogenetic dependency for grouping our microbiota data actually results in a noticeable improvement in classification performance for helminth infection detection. These promising results from this feasibility study demonstrate that methods such as SMART-scan can be utilized in the future for knowledge transfer from different but related microbiome datasets by phylogenetically-related functional mapping, to enable novel integrative biomarker discovery.

Stroke constitutes a significant public health concern due to its impact on mortality and morbidity. This study investigates the utility of machine learning algorithms in predicting stroke and identifying key risk factors using data from the Suita study, comprising 7,389 participants and 53 variables. Initially, unsupervised K-prototype clustering categorized participants into risk clusters, while five supervised models including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosted Machine (Light-GBM) were employed to predict stroke outcomes. Stroke incidence disparities among identified risk clusters using the unsupervised K-prototype clustering method are substantial, according to the findings. Supervised learning, particularly RF was a preferable option because of the higher levels of performance metrics. The Shapley Additive Explanations (SHAP) method identified age, systolic blood pressure, hypertension, estimated glomerular filtration rate, metabolic syndrome, and blood glucose level as key predictors of stroke, aligning with findings from the unsupervised clustering approach in high-risk groups. Additionally, previously unidentified risk factors such as elbow joint thickness, fructosamine, hemoglobin, and calcium level demonstrate potential for stroke prediction. In conclusion, machine learning facilitated accurate stroke risk predictions and highlighted potential biomarkers, offering a data-driven framework for risk assessment and biomarker discovery.

Keywords: Electrical power systems, Support vector machines, Random Forest, Machine learning, Wavelet transform, Transmission lines fault, Electrical power quality, Short circuit, Classification of faults, Localization of faults, Decision trees, Ensemble learning, K-nearest neighbors.

Smart Living, an increasingly prominent concept, entails incorporating sophisticated technologies in homes and urban environments to elevate the quality of life for citizens. A critical success factor for Smart Living services and applications, from energy management to healthcare and transportation, is the efficacy of human action recognition (HAR). HAR, rooted in computer vision, seeks to identify human actions and activities using visual data and various sensor modalities. This paper extensively reviews the literature on HAR in Smart Living services and applications, amalgamating key contributions and challenges while providing insights into future research directions. The review delves into the essential aspects of Smart Living, the state of the art in HAR, and the potential societal implications of this technology. Moreover, the paper meticulously examines the primary application sectors in Smart Living that stand to gain from HAR, such as smart homes, smart healthcare, and smart cities. By underscoring the significance of the four dimensions of Context Awareness, Data Availability, Personalization, and Privacy in HAR, this paper serves as a valuable resource for researchers and practitioners striving to advance Smart Living services and applications.

Smart living, a concept that has gained increasing attention in recent years, revolves around integrating advanced technologies in homes and cities to enhance the quality of life for citizens. Sensing and human action recognition are crucial aspects of this concept. Smart living applications span various domains, such as energy consumption, healthcare, transportation, and education, which greatly benefit from effective human action recognition. This field, originating from computer vision, seeks to recognize human actions and activities using not only visual data but also many other sensor modalities. This paper comprehensively reviews the literature on human action recognition in smart living environments, synthesizing the main contributions, challenges, and future research directions. This review selects five key domains: Sensing Technology, Multimodality, Real-time Processing, Interoperability, and Resource-Constrained Processing, as they encompass the critical aspects required for successfully deploying human action recognition in smart living. These domains highlight the essential role that sensing and human action recognition play in successfully developing and implementing smart living solutions. This paper serves as a valuable resource for researchers and practitioners seeking to explore further and advance the field of human action recognition in smart living.

Cities are complex systems requiring urban design models that balance order and disorder. Collective creativity initiatives engage citizens in these processes, empowering bottom-up approaches that prioritize people and social well-being within urban development. This paper investigates an 'Urban Laboratory' as a case study, examining the potential of collective creativity to address urban complexity. The successful and ongoing project 'El Campo de Cebada' in Madrid, Spain, demonstrates how a community transformed a vacant lot into a vibrant social hub. The phases of this study include case selection, data collection, data analysis, and presentation of the results. This study identifies key enabling factors, including agents, management, social dynamics, infrastructure, and actions. These insights offer a methodological framework for designing future collaborative, resilient, and inclusive urban spaces, addressing the complex needs of communities within our cities.

We introduce the Transformation Flower Approach (TFA), a Theory of Change that attends to multiple value creation and institutional change as a dual design challenge. We highlight how the TFA integrates social scientific theories and models relevant for transformative change (in particular focusing on pathways, leverage points, governance, power, and values) and demonstrate its practical value by an application to the ongoing transformation of the Dutch food system. By providing a holistic, transdisciplinary and practically relevant approach that aims to support new social contract formation, the TFA goes beyond other transformative change approaches. Based on the notion of pathways, it offers a toolbox that aids in working towards desired futures, involving both incumbents and challengers in an effort to harness untapped yet proximal potentials in a forward-looking way. By embracing an innovation approach, it not only promises to circumvent resistance to change, but also serves as a step-by-step approach to identify options for multiple value creation and effective cooperation. We demonstrate the analytical and practical value of the TFA by discussing action perspectives at various levels and scales in the context of the Dutch food system transition, including (1) area-oriented approaches, (2) acceleration agendas for specific transformation pathways, and (3) actor-specific transformation flowers. In developing these, we emphasize the importance of interdependencies between leverage points. Our approach helps to identify opportunities to link transformative options (the what), actors (the who) and levers (the how) in dynamic interaction to embark on transformative pathways.

Amidst the escalating demands for efficient Intelligent Transportation Systems (ITS) management, the significance of accurate Origin-Destination (OD) data prediction has emerged as a paramount concern, given its indispensable role in the ITS domain. This paper introduces a groundbreaking integrated model, creatively fusing the unique strengths of Graph Convolutional Network (GCN), Residual Neural Network (ResNet), and Long Short-Term Memory Network (LSTM) into a single architecture, which we name GraphResLSTM, to exploit road segment average speed data for OD prediction. Compared with conventional road segment traffic volume data, average speed data is more readily available, significantly reducing the data accessibility barrier for OD prediction. We underscore the critical role of selection of key road segments and employs a combination of Entropy Weight Method and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to identify 41 representative road segments from the experimental road network. In the experimental phase, we simulate 86400000 seconds of traffic conditions, generating a total of 1440000 data records. Utilizing these simulated data, we design and conduct comparative experiments between models as well as data types. The results demonstrate that both the GraphResLSTM model and road segment average speed data outperform other models and data types notably in OD prediction tasks.