Accurately mapping individual tree species in densely forested environments is crucial to forest inventory. When considering only RGB images, this is a challenging task for many automatic photogrammetry processes. The main reason for that is the spectral similarity between species in RGB scenes, which can be a hindrance for most automatic methods. State-of-the-art deep learning methods could be capable of identifying tree species with an attractive cost, accuracy, and computational load in RGB images. This paper presents a deep learning-based approach to detect an important multi-use species of palm trees (Mauritia flexuosa; i.e., Buriti) on aerial RGB imagery. In South-America, this palm tree is essential for many indigenous and local communities because of its characteristics. The species is also a valuable indicator of water resources, which comes as a benefit for mapping its location. The method is based on a Convolutional Neural Network (CNN) to identify and geolocate singular tree species in a high-complexity forest environment, and considers the likelihood of every pixel in the image to be recognized as a possible tree by implementing a confidence map feature extraction. This study compares the performance of the proposed method against state-of-the-art object detection networks. For this, images from a dataset composed of 1,394 airborne scenes, where 5,334 palm-trees were manually labeled, were used. The results returned a mean absolute error (MAE) of 0.75 trees and an F1-measure of 86.9%. These results are better than both Faster R-CNN and RetinaNet considering equal experiment conditions. The proposed network provided fast solutions to detect the palm trees, with a delivered image detection of 0.073 seconds and a standard deviation of 0.002 using the GPU. In conclusion, the method presented is efficient to deal with a high-density forest scenario and can accurately map the location of single species like the M flexuosa palm tree and may be useful for future frameworks.

Deep neural networks are hegemonic approaches to many machine learning areas, including natural language processing (NLP). Thanks to the availability of large corpora collections and the capability of deep architectures to shape internal language mechanisms in self-supervised learning processes (also known as "pre-training"), versatile and performing models are released continuously for every new network design. But these networks, somehow, learn a probability distribution of words and relations across the training collection used, inheriting the potential flaws, inconsistencies and biases contained in such a collection. As pre-trained models have found to be very useful approaches to transfer learning, dealing with bias has become a relevant issue in this new scenario. We introduce bias in a formal way and explore how it has been treated in several networks, in terms of detection and correction. Also, available resources are identified and a strategy to deal with bias in deep NLP is proposed.

As a consequence of the global sanitary crisis in early 2020, universities had to tackle with a sudden shift in their teaching-learning strategies so that the preset competences could be fulfilled. This study presents the learning outcomes of the tasks implemented, student experiences and feedback, as well as some reflections from the instructors with a holistic perspective of the courses due to the measures and adaptations adopted. Six courses taught at Civil Engineering degrees of three universities, two from Spain and one from Peru, are analyzed. The teaching and evaluation strategies are described and some reflections are made by comparing the student’s performance with the previous course. Although the shift to online learning had to be made from day to day, with no time for preparation, the experience has proved that online learning can be beneficial in some aspects and have probably come to stay, although some others are difficult to replace with respect to face-to-face learning, especially students’ engagement and motivation.

The COVID-19 pandemic in Indonesia makes a significant impact both physically and psychologically. One month after the President of the Republic of Indonesia announced about the COVID-19 patient cases, the Indonesian Child Protection Commission data during April 2020, depicted that 76.7% of children were not happy to participate in distance learning because 81.8% were only given assignments by the teacher and 73.2% felt they had a heavy task and had a short period of time to complete. This reaction is an indicator of the children’s anxiety about distance learning. The anxiety that occurs in these students is assumed to depend on their social support and emotional maturity. When students get optimal family support and are able to control their emotions in the face of a pandemic, they can reduce anxiety in facing online learning. The subjects of this study were 202 junior high and high school students. The results showed that social support and emotional maturity simultaneously affect anxiety in online learning (Freg = 45.066, p = 0.00 <0.01). These results can be used as a basis for providing psycho-education to increase family support and emotional maturity to reduce anxiety in online learning.

In the field of machine learning, cluster analysis has always been a very important technology for determining useful or implicit characteristics in the data. However, the current mainstream cluster analysis algorithms require comprehensive analysis of the overall data to obtain the best parameters in the algorithm. As a result, handling large-scale datasets would be difficult. This research proposes a distributed related clustering mechanism for Unsupervised Learning, which assumes that if adjacent data are similar, a group can be formed by relating to more data points. Therefore, when processing data, large-scale datasets can be distributed to multiple computers, and the correlation of any two datasets in each computer can be calculated simultaneously. Later, results are processed through aggregation and filtering before assembled into groups. This method would greatly reduce the pre-processing and execution time of the dataset; in practical application, it only needs to focus on how the relevance of the data is designed. In addition, the experimental results show the accuracy, applicability, and ease of use of this method.

Rainfall retrieval using geostationary satellites provides critical means to the monitoring of extreme rainfall events. Using the relatively new Himawari 8 meteorological satellite with three times more channels than its predecessors, the deep learning framework of “convolutional autoencoder” (CAE) was applied to the extraction of cloud and precipitation features. The CAE method was incorporated into the Convolution Neural Network version of the PERSIANN precipitation retrieval that uses GOES satellites. By applying the CAE technique with the addition of Residual Blocks and other modifications of deep learning architecture, the presented derivation of PERSIANN operated at the Central Weather Bureau of Taiwan (referred to as PERSIANN-CWB) expands four extra convolution layers to fully use Himawari 8’s infrared and water vapor channels, while preventing degradation of accuracy caused by the deeper network. The development of PERSIANN-CWB was trained over Taiwan for its diverse weather systems and localized rainfall features, and the evaluation reveals an overall improvement from its CNN counterpart and superior performance over all other rainfall retrievals analyzed. Limitation of this model was found in the derivation of typhoon rainfall, an area requiring further research.

Transition from primary to secondary school is more successful when students’ learning is consistent. Students are also more likely to enjoy the school, engage with learning, and have a high academic achievement in the secondary school when they feel motivated. This is a critical aspect especially in cases when global pandemics situations allow only the online schooling opportunity. Students that are away from school lack the traditional sources of motivation and self-regulated learning skills, thus research is needed to identify other important factors that can be developed in remote settings. The aim of this study was to find out how students perceive their experience with the transition from primary to secondary school and how such a transition influences students’ self-regulated learning (SRL) and motivation. Self-reported data were collected during the COVID-19 breakout from a total of N=80, 6th and 7th grade students aged 12-14 years old. Results showed that students had a successful transition, especially when they are supported by their parents and teachers. Next, Bivariate Pearson Correlation analysis indicated that students’ perceptions about their experience with the transition from primary to secondary school and their self-regulated learning and motivation are significantly correlated. No gender differences were found among all main study variables.

In recent years, research has focused on generating mechanisms to assess the levels of subjects' cognitive workload when performing various activities that demand high concentration levels, such as driving a vehicle. These mechanisms have implemented several tools to analyze cognitive workload where the electroencephalographic (EEG) signals are the most used due to its high precision. However, one of the main challenges in the EEG signals implementing is finding the appropriate information to identify cognitive states. Here we show a new feature selection model for pattern recognition using information from EEG signals based on machine learning techniques called GALoRIS. GALoRIS combines Genetic Algorithms and Logistic Regression to create a new fitness function that identifies and selects the critical EEG features that contribute to recognizing high and low cognitive workload and structures a new dataset capable of optimizing the model's predictive process. We found that GALoRIS identifies data related to high and low cognitive workload of subjects while driving a vehicle using information extracted from multiple EEG signals, reducing the original dataset by more than 50%, maximizing the model's predictive capacity-achieving a precision rate greater than 90%.

Nutrient management of lowbush blueberry (Vaccinium angustifolium Ait.) depends on several yield-limiting features. Machine learning models can process such yield-impacting variables to predict berry yield. We investigated the effects of local variables on yields and nutrient management of lowbush blueberry. We collected 1504 observations from N-P-K fertilizer trials conducted in Quebec, Canada. Meteorological indices at various phenological stages showed the greatest impact on yield. High mean temperature at flower bud opening and after fruit maturation, and total precipitation at flowering showed positive effects. Low mean temperature and low total precipitation before bud opening, at flowering, and by fruit maturity, as well as number of freezing days (< -5ºC) before flower bud opening, showed negative effects. Soil fertility variables, leaf nutrient compositions and N-P-K fertilization showed smaller effects. Gaussian processes predicted berry yields from historical weather data, soil analysis, fertilizer dosage, and leaf nutrients with a root-mean-square-error of 1447 kg ha-1 on the testing data set. An in-house Markov chain algorithm optimized yields modelled with Gaussian processes from leaf nutrient composition, soil test value, and fertilizer dosage conditioned to specified historical weather features. We propose to use conditioned machine learning models to manage nutrients of lowbush blueberry at local scale.

At the start of 2020 the rapid onset of the coronavirus pandemic forced higher education institutions across the world to pivot from face to face to remote teaching. For teaching methods that involve the transmission and dissemination of verbal/visual information between academic staff and students, video technologies provided immediate methods to respond to the restricted access to campus. Practical activities, that usually involve interaction with equipment, presented a greater challenge to adapt for remote delivery. With restrictions on higher education being partially lifted, many institutions worldwide intend to offer blended learning, prioritizing in-person activities that are troublesome to deliver online, such as practicals. Social distancing measures are reducing capacity and placing increased pressure on space, creating a need to optimise limited time students have in the lab and strategies to determine which activities can best utilize this limited resource. Time is constrained, leaving little opportunity to make radical changes to learning and teaching structures. In this publication, The department of Mulicdipalnary Engineering Education (MEE) at the University of Sheffield, utilise their experiences in practical teaching to provide simple, implementable ideas for blended practicals which maximize students’ learning and experiences within the envelope of available resources.

The microbiome, by virtue of its interactions with the host, is implicated in various host functions including its influence on inflammation, nutrition, and homeostasis. Although driven by a complex combination of intrinsic and extrinsic factors, many chronic diseases such as diabetes, cancer, Inflammatory Bowel Disease among others are characterized by a disruption of microbial communities in at least one biological niche/organ system. Various molecular mechanisms between microbial and host components such as proteins, RNAs, metabolites etc have recently been elucidated, thus filling many gaps in our understanding of how the microbiome modulates host processes. Concurrently, high throughput technologies have enabled the profiling of heterogeneous datasets capturing community level changes in the microbiome as well as the host responses. However, due to pragmatic limitations with respect to parallel sampling and analytical procedures, big gaps still exist in terms of how the microbiome mechanistically influences host functions at a systems and community level. In the past decade, various computational biology and machine learning methodologies and approaches have been developed with an aim to fill these existing gaps. Due to the agnostic nature of the tools, they have been applied in various disease contexts to analyze and infer the interactions between the microbiome and host molecular components, and in the case of a few selected tools, on downstream host processes. Generally, most of the tools are enabled by frameworks to statistically or mechanistically integrate different types of -omic and meta -omic datasets followed by functional/biological interpretation. In this review, we provide an overview of the landscape of computational approaches for investigating mechanistic microbiome-host interactions and their potential benefit for basic and clinical research. These could include but are not limited to the development of activity and mechanism based biomarkers, uncovering mechanisms for therapeutic interventions and generating integrated signatures to stratify patients.

Generic object detection is one of the most important and flourishing branches of computer vision and has real-life applications in our day to day life. With the exponential development of deep learning-based techniques for object detection, the performance has enhanced considerably over the last 2 decades. However, due to the data-hungry nature of deep models, they don't perform well on tasks which have very limited labeled dataset available. To handle this problem, we proposed a transfer learning-based deep learning approach for detecting multiple pigs in the indoor farm setting. The approach is based on YOLO-v2 and the initial parameters are used as the optimal starting values for train-ing the network. Compared to the original YOLO-v2, we transformed the detector to detect only one class of objects i.e. pigs and the back-ground. For training the network, the farm-specific data is annotated with the bounding boxes enclosing pigs in the top view. Experiments are performed on a different configuration of the pen in the farm and convincing results have been achieved while using a few hundred annotated frames for fine-tuning the network.

Many universities and colleges worldwide suspended classroom teaching due to the novel coronavirus pandemic and switched to online teaching. The current cross-sectional study was carried out to analyze the impact of lockdown due to coronavirus disease 2019 (COVID-19) pandemic on the academic performance of veterinary medical students and researchers. Veterinary medical students and researchers were invited to answer an online google form questionnaire. A total of 1398 participants were from 92 different countries answered the questionnaire with response rate of 94.52%. The data showed that COVID-19 pandemic lockdown affected the academic performance of most participants (96.7%) with varying degrees. The mean evaluation scores for the online education in general was 5.06 ± 2.43 while that for the practical parts was 3.62± 2.56. Although online education provides an opportunity for self-study. The main challenge online education faces in veterinary medical science is how to give practical lessons. Since most of the subjects are practical; therefore, it is not easy to learn it online. Students think that it is difficult to fulfill the veterinary competencies only with online education system. Online education can be improved by making it more interactive, showing medical procedures in real situations, giving concise information, and providing 3D virtual tools to mimic the real situation.

The paper concludes the first research on mouth-based Emotion Recognition (ER), adopting a Transfer Learning (TL) approach. Transfer Learning results paramount for mouth-based emotion ER, because a few data sets are available, and most of them include emotional expressions simulated by actors, instead of adopting a real-world categorization. Using TL we can use fewer training data than training a whole network from scratch, thus more efficiently fine-tuning the network with emotional data and improving the convolutional neural network accuracy in the desired domain. The proposed approach aims at improving the Emotion Recognition dynamically, taking into account not only new scenarios but also modified situations with respect to the initial training phase, because the image of the mouth can be available even when the whole face is visible only in an unfavourable perspective. Typical applications include automated supervision of bedridden critical patients in an healthcare management environment, or portable applications supporting disabled users having difficulties in seeing or recognizing facial emotions. This work takes advantage from previous preliminary works on mouth-based emotion recognition using CNN deep-learning, and has the further benefit of testing and comparing a set of networks on large data sets for face-based emotion recognition well known in literature. The final result is not directly comparable with works on full-face ER, but valorizes the significance of mouth in emotion recognition, obtaining consistent performances on the visual emotion recognition domain.

Multidisciplinary Engineering Education (MEE) at the University of Sheffield is dedicated to delivering, at scale, practical teaching to students in the Faculty of Engineering. The COVID-19 pandemic initiated the sudden suspension of face to face teaching required MEE to translate over 600 in-lab practicals to a remote delivery format. With little opportunity to coordinate, academic staff independently adopted a variety of tactics to ensure practical learning outcomes were maintained. Following the reactive response, a proactive reflection was conducted and six categories of tactics for remote practicals have been established. These categories are Provide digital artefacts; Simulated practicals; Synchronous remote participation; Asynchronous participation by proxy; Perform procedure in alternative environment; Remote staff support. The advantages and drawbacks of each of these categories is discussed and it is suggested which tactics are appropriate for particular learning outcomes or operational and environmental outcomes of equivalent in-lab practicals. Further work to comprehensively align outcomes to tactics is proposed and lasting benefit from the analysis can be realized by adopting a principle of Remote Enhanced Practicals.

The vastness of chemical-space constrains traditional drug-discovery methods to the organic laws that are guiding the chemistry involved in filtering through candidates. Leveraging computing with machine-learning to intelligently generate compounds that meet a wide range of objectives can bring significant gains in time and effort needed to filter through a broad range of candidates. This paper details how the use of Generative-Adversarial-Networks, novel machine learning techniques to format the training dataset and the use of quantum computing offer new ways to expedite drug-discovery.

In this paper, we focus on developing a novel method to extract sea ice cover (i.e., discrimination/classification of sea ice and open water) using Sentinel-1 (S1) cross-polarization (vertical-horizontal, VH or horizontal-vertical, HV) data in extra wide (EW) swath mode based on the machine learning algorithm support vector machine (SVM). The classification basis includes the S1 radar backscatter coefficients and texture features that are calculated from S1 data using the gray level co-occurrence matrix (GLCM). Different from previous methods where appropriate samples are manually selected to train the SVM to classify sea ice and open water, we proposed a method of unsupervised generation of the training samples based on two GLCM texture features, i.e. entropy and homogeneity, that have contrasting characteristics on sea ice and open water. We eliminate the most uncertainty of selecting training samples in machine learning and achieve automatic classification of sea ice and open water by using S1 EW data. The comparison shows good agreement between the SAR-derived sea ice cover using the proposed method and a visual inspection, of which the accuracy reaches approximately 90% - 95% based on a few cases. Besides this, compared with the analyzed sea ice cover data Ice Mapping System (IMS) based on 728 S1 EW images, the accuracy of extracted sea ice cover by using S1 data is more than 80%.

Wideband signal detection is an important problem in wireless communication. With the rapid development of deep learning (DL) technology, some DL-based methods are applied to wireless technology, and the effect is obvious. In this paper, we propose a novel neural network for multi-type signal detection that can locate signals and recognize signal types in wideband spectrogram. Our network utilizes the key point estimation to locate the rough centerline of signal region and identify class. Then, several regressions are carried out to achieve properties, such as local offset and border offsets of bounding box, which is further synthesized for a more fine location. Experimental results demonstrate that our method performs more accurate than other DL-based object detection methods previously employed for the same detection task. Specifically, our method runs obviously faster than existing methods, and abandons the anchor generation, which makes it more favorable for real-time applications.

Restricted Boltzmann machines (RBMs) are the building blocks of some deep learning networks. However, despite their importance, it is our perception that some very important derivations about the RBM are missing in the literature, and a beginner may feel RBM very hard to understand. We provide here these missing derivations. We cover the classic Bernoulli-Bernoulli RBM and the Gaussian-Bernoulli RBM, but leave out the ``continuous'' RBM as it is believed not as mature as the former two. This tutorial can be used as a companion or complement to the famous RBM paper ``Training restricted Boltzmann machines: An introduction'' by Fisher and Igel.

While visual assessment is the standard technique for burn evaluation, computer-aided diagnosis is increasingly sought due to high number of incidences globally. Patients are increasingly facing challenges which are not limited to shortage of experienced clinicians, lack of accessibility to healthcare facilities, and high diagnostic cost. Certain number of studies were proposed in discriminating burn and healthy skin using machine learning leaving a huge and important gap unaddressed; whether burns and related skin injuries can be effectively discriminated using machine learning techniques. Therefore, we specifically use pre-trained deep learning models due to deficient dataset to train a new model from scratch. Experiments were extensively conducted using three state-of-the-art pre-trained deep learning models that includes ResNet50, ResNet101 and ResNet152 for image patterns extraction via two transfer learning strategies: fine-tuning approach where dense and classification layers were modified and trained with features extracted by base layers, and in the second approach support vector machine (SVM) was used to replace top-layers of the pre-trained models, trained using off-the-shelf features from the base layers. Our proposed approach records near perfect classification accuracy of approximately 99.9%.

In recent years, a range of problems under the broad umbrella of computer vision based analysis of ancient coins have been attracting an increasing amount of attention. Notwithstanding this research effort, the results achieved by the state of the art in published literature remain poor and far from sufficiently well performing for any practical purpose. In the present paper we present a series of contributions which we believe will benefit the interested community. We explain that the approach of visual matching of coins, universally adopted in existing published papers on the topic, is not of practical interest because the number of ancient coin types exceeds by far the number of those types which have been imaged, be it in digital form (e.g., online) or otherwise (traditional film, in print, etc.). Rather, we argue that the focus should be on understanding the semantic content of coins. Hence, we describe a novel approach—to first extract semantic concepts from real-world multimodal input and associate them with their corresponding coin images, and then to train a convolutional neural network to learn the appearance of these concepts. On a real-world data set, we demonstrate highly promising results, correctly identifying a range of visual elements on unseen coins with up to 84% accuracy.

Federated learning is a decentralized topology of deep learning, that trains a shared model through data distributed among each client (like mobile phones, wearable devices), in order to ensure data privacy by avoiding raw data exposed in data center (server). After each client computes a new model parameter by stochastic gradient decrease (SGD) based on their own local data, all locally-computed parameters will be aggregated in the server to generate an updated global model. Almost all current studies directly average different client computed parameters by default, but no one gives an explanation why averaging parameters is a good approach. In this paper, we treat each client computed parameter as a random vector because of the stochastic properties of SGD, and estimate mutual information between two client computed parameters at different training phases using two methods in two learning tasks. The results confirm the correlation between different clients and show an increasing trend of mutual information with training iteration. However, when we further compute the distance between client computed parameters, we find that parameters are getting more correlated while not getting closer. This phenomenon suggests that averaging parameters may not be the optimum way of aggregating trained parameters.

Physical-law based models are widely utilized in the aerospace industry. One such use is to provide flight dynamics models for use in flight simulators. For human-in-the-loop use, such simulators must run in real-time. Due to the complex physics of rotorcraft flight, to meet this real-time requirement, simplifications to the underlying physics sometimes have to be applied to the model, leading to model response errors in the predictions compared to the real vehicle. This study investigated whether a machine-learning technique could be employed to provide rotorcraft dynamic response predictions, with the ultimate aim of this model taking over when the physics-based model's accuracy degrades. In the current work, a machine-learning technique was employed to train a model to predict the dynamic response of a rotorcraft. Machine learning was facilitated using a Gaussian Process (GP) non-linear autoregressive model, which predicted the on-axis pitch rate, roll rate, yaw rate and heave responses of a Bo105 rotorcraft. A variational sparse GP model was then developed to reduce the computational cost of implementing the approach on large data sets. It was found that both of the GP models were able to provide accurate on-axis response predictions, particularly when the input contained all four control inceptors and one lagged on-axis response term. The predictions made showed improvement compared to a corresponding physics-based model. The reduction of training data to one-third (rotational axes) or one-half (heave axis) resulted in only minor degradation of the GP model predictions.

Condition monitoring of bearings is an open issue. The use of the stator current to monitor induction motors has been validated as a very advantageous and practical way to detect several types of faults. Nevertheless, for bearing faults the use of vibrations or sound generally offers better results in the accuracy of the detection although with some disadvantages related to the sensors used for monitoring. To improve the performance of bearing monitoring, it is proposed to take advantage of more information available in the current spectra, beyond the usually employed, incorporating the amplitude of a significant number of sidebands around the first eleven harmonics, growing exponentially the number of fault signatures. This is especially interesting for inverter-fed motors. But, in turn, this leads to the problem of overfitting when applying a classifier to perform the fault diagnosis. To overcome this problem, and still exploit all the useful information available in the spectra, it is proposed to use shrinkage methods, which have been lately proposed in machine learning to solve the overfitting issue when the problem has much more variables than examples to classify. A case study with a motor is shown to prove the validity of the proposal

The perspective suggests an unorthodox interpretation of cancer dynamics in terms of strange attractors and fluid turbulence. The relevance of strange attractors in tumor growth-invasion dynamics and chemical pattern formation are reviewed. Chemical turbulence, fractals and chaos are discussed as the principal characteristics of tumor ecosystems and their complex cybernetics. To conclude, cancers are presented as complex systems exhibiting chaotic gene expression dynamics.

Spike shape and morphometric characteristics are among the key characteristics of cultivated cereals associated with their productivity. Identification of the genes controlling these traits requires morphometric data at harvesting and analysis of numerous plants, which could be automatically done using technologies of digital image analysis. A method for wheat spike morphometry utilizing 2D image analysis is proposed. Digital images are acquired in two variants: a spike on a table (one projection) or fixed with a clip (four projections). The method identifies spike and awns in the image and estimates their quantitative characteristics (area in image, length, width, circularity, etc.). Section model, quadrilaterals, and radial model are proposed for describing spike shape. Parameters of these models are used to predict spike shape type (spelt, normal, or compact) by machine learning. The mean error in spike density prediction for the images in one projection is 4.61 (~18%) versus 3.33 (~13%) for the parameters obtained using four projections.

Equality and incomparability multi-label ranking have not been introduced to learning before. This paper proposes new native ranker neural network to address the problem of multi-label ranking including incomparable preference orders using a new activation and error functions and new architecture. Preference Neural Network PNN solves the multi-label ranking problem, where labels may have indifference preference orders or subgroups which are equally ranked. PNN is a nondeep, multiple-value neuron, single middle layer and one or more output layers network. PNN uses a novel positive smooth staircase (PSS) or smooth staircase (SS) activation function and represents preference orders and Spearman ranking correlation as objective functions. It is introduced in two types, Type A is traditional NN architecture and Type B uses expanding architecture by introducing new type of hidden neuron has multiple activation function in middle layer and duplicated output layers to reinforce the ranking by increasing the number of weights. PNN accepts single data instance as inputs and output neurons represent the number of labels and output value represents the preference value. PNN is evaluated using a new preference mining data set that contains repeated label values which have not experimented on before. SS and PS speed-up the learning and PNN outperforms five previously proposed methods for strict label ranking in terms of accurate results with high computational efficiency.

This paper presents a study and implementation of a convolutional neural network to identify and recognize humpback whale specimens from the unique patterns of their tails. Starting from a dataset composed of images of whale tails, all the phases of the process of creation and training of a neural network are detailed – from the analysis and pre-processing of images to the elaboration of predictions, using TensorFlow and Keras frameworks. Other possible alternatives are also explained when it comes to tackling this problem and the complications that have arisen during the process of developing this paper.

Cognitive neuroscience is the study of how the human brain functions on tasks like decision making, language, perception and reasoning. Deep learning is a class of machine learning algorithms that use neural networks. They are designed to model the responses of neurons in the human brain. Learning can be supervised or unsupervised. Ngram token models are used extensively in language prediction. Ngrams are probabilistic models that are used in predicting the next word or token. They are a statistical model of word sequences or tokens and are called Language Models or Lms. Ngrams are essential in creating language prediction models. We are exploring a broader sandbox ecosystems enabling for AI. Specifically, around Deep learning applications on unstructured content form on the web.

We propose a probabilistic graphical model for discriminative substrate characterization, to support geological and biological habitat mapping in aquatic environments. The model, called a fully connected conditional random field (CRF), is demonstrated using multispectral and monospectral acoustic backscatter from heterogeneous seafloors in Patricia Bay, British Columbia, and Bedford Basin, Nova Scotia. Unlike previously proposed discriminative machine learning algorithms, the CRF model considers both the relative backscatter magnitudes of different substrates and their relative proximities. The model therefore combines the statistical flexibility of a machine learning algorithm with an inherently spatial treatment of the substrate. The CRF model predicts substrates such that nearby locations with similar backscattering characteristics are likely to be in the same substrate class. The degree of proximity and allowable backscatter similarity are controlled by parameters that are learned from the data. CRF model results were evaluated against a popular generative model known as a Gaussian Mixture model that doesn't include spatial dependencies, only covariance between substrate backscattering response over different frequencies. Both models are used in conjunction with sparse bed observations/samples in a supervised classification. A detailed accuracy assessment, including a leave-one-out cross-validation analysis, was performed using both models. Using multispectral backscatter, the GMM model trained on 50% of the bed observations resulted in a 75% and 89% average accuracies in Patricia Bay and Bedford Basin, respectively. The same metrics for the CRF model were 78% and 95%. Further, the CRF model resulted in a 91% mean cross-validation accuracy across four substrate classes at Patricia Bay, and a 99.5% mean accuracy across three substrate classes at Bedford Basin, which suggest that the CRF model generalizes extremely well to new data. This analysis also showed that the CRF model was much less sensitive to the specific number and locations of bed observations than the generative model, owing to its ability to incorporate spatial autocorrelation in substrates. The CRF approach therefore may prove to be a powerful `spatially aware' alternative to other discriminative classifiers.

Allama Iqbal Open University (AIOU) is the largest distance learning institute of Pakistan and providing education to 1.4 million students. This is fairly a large setup across the country where students are geographically distributed. Currently the system works on a manual approach which is not efficient. Allocation of tutors and study centers to students plays a key role in distance learning for a better learning environment. Assigning tutors and study centers to distance learning students is a challenging task when there is huge geographical spread. The utilization of geospatial technologies in open and distance learning can fix allocation problems. This research analyzes the real data of twin cities Islamabad and Rawalpindi. The results show that the geospatial technologies can be used for efficient and proper resource utilization and allocation, which in turn can save the time and money. The overall idea fits into improved distance learning framework and related analytics.

Biofilms are congregations of bacteria on a surface, and they grow into obstacles for the functionalities of any device or machinery involves anything biological. Biofilms are developed through a biochemical system known as ‘Quorum Sensing’ that accounts for the chemical signaling that direct either biofilm formation or inhibition. Computational models that relate chemical and structural features of compounds to their performance properties have been used to aide in the discovery of active small molecules for many decades. These quantitative structure-activity relationship (QSAR) models are also important for predicting the activity of molecules that can have a range of effectiveness in biological systems. This study uses QSAR methodologies combined with and different machine learning algorithms to predict and assess the performance of several different compounds acting in Quorum Sensing. Through computational probing of the quorum sensing molecular interaction, new design rules can be elucidated for countering biofilms.

Recently, methods to detect DoS and spoofing attacks that occur on in-vehicle networks using CAN Protocol are being studied through deep learning models such as CNN, RNN, and LSTM. These studies have produced significant results in the field of In-Vehicle Network attack detection using deep learning models. In addition, significant results are being achieved through research on applying time series-based deep learning models such as LSTM to detect DoS attacks and replay attacks occurring in in-drone networks by expanding them to drones using the UAVCAN protocol. In this paper, we conducted an experiment to detect in-drone network attacks through non-time series analysis using machine learning models and deep learning models, and through appropriate learning for each attack type, it can also be analyzed through non-time series analysis. The results showed that it was possible to detect attacks.

The global issues of overweight and sedentary lifestyles demand comprehensive responses from health systems, yet health education still needs to be more cohesive and less sporadic. This study focuses on primary school children as a specific target for instilling healthy habits, employing ac-tive learning strategies to address healthy diet and physical activity. Through Problem-Based Learning projects, the study engaged fourth-grade primary students in acquiring healthy habits. The study was carried out over four consecutive years at a school with two lines, allowing the employment of an opportunity sample and evaluating intervention and control groups by com-paring their corresponding scores. Control groups integrated a total of 54 students, while the in-tervention group included a total of 159 students. A pre-test and post-test questionnaire were used for data collection. Evaluation differential scores revealed statistically significant higher scores in the intervention groups: 3.62 points in control groups and 6,94 in intervention groups, particu-larly in attitudinal competences. These strategies not only facilitated the development of crucial skills such as information search, synthesis, representation, analysis, decision-making, teamwork, and intrapersonal awareness but also significantly broadened the knowledge acquired in aspects related to healthy habits. This approach proved effective in helping children comprehend the im-portance of healthy choices and encouraged integrating such habits into their daily lives.

The rapid growth in the number of interconnected devices on the Internet (referred to as the Internet of Things – IoT), along with the huge volume of data that are exchanged and processed, has created a new landscape in network design and operation. Due to the limited battery size and computational capabilities of IoT nodes, data processing usually takes place on external devices. Since latency minimization is a key concept in modern era networks, edge servers that are in close proximity to IoT nodes gather and process related data, while in some cases data offloading in the cloud might have to take place. The interconnection of a vast number of heterogeneous IoT devices with the edge servers and the cloud, where IoT, edge and cloud converge to form a computing continuum, is also known as IoT-edge-cloud (IEC) continuum. Several key challenges are associated with this new computing systems architectural approach, including: i) design of connection and programming protocols aimed at properly manipulating a huge number of heterogeneous devices over diverse infrastructures; ii) design of efficient task offloading algorithms aimed at optimizing services execution; iii) support for security and privacy enhancements during data transfer to deal with the existent and even unforeseen attacks and threats landscape; iv) scalability, flexibility and reliability guarantees to face the expected mobility for IoT systems, and; v) design of optimal resource allocation mechanisms to make the most out of the available resources. These challenges become even more significant towards the new era of sixth generation (6G) networks, which will be based on the integration of various cutting edge heterogeneous technologies. Therefore, the goal of this survey paper is to present all recent developments in the field of IEC continuum systems, with respect to the aforementioned deployment challenges. In the same context, potential limitations and future challenges are highlighted as well. Finally, indicative use cases are also presented, from an IEC continuum perspective.

Falls are extremely damaging to the elderly. The number of elderly who have experienced falls has increased over the years, several of the elderly stay alone or in in badly maintained elderly homes. This makes a low-cost fall detection system a necessity. There has been huge improvements in terms of IoT systems, ML algorithms. Varied data sets have been collected across the world for fall detection. These data sets have a very little in common among them, in terms of user demographics, sensors used, the ADL and Fall activities Hence in this paper we present a data set that has wide user demographics, we used various sensors – such as accelerometer, gyroscope, magnetometer and hear rate. We used wrist worn sensors to collect data. In this paper we present a detailed analysis of the data set we collected using common ML algorithms such as – Naïve Bayes (NB), K Nearest Neighbor (KNN), Logistic Regression (LR), Random Forest (RF) and Support Vector Machines (SVM). We analyzed the performance of these algorithms for variations in accuracy with respect to age, gender, height, weight and health issues and we have identified outliers by analyzing each incorrect prediction. This paper provides the complete details of the data collection methodology, The methods used for analysis and presents the results of analysis in complete detail.

Continuous greenhouse gas emissions are causing global warming and impacting the habitats of many animals. Researchers in the field of electric power are making efforts to mitigate this situation. Operating and maintaining the power grid in an economic, low-carbon, and stable is challenging. To address the issue, we propose a grid dispatching technique that combines prediction technology, reinforcement learning, and optimization technology. Prediction technology can forecast future power demand and solar power generation, while reinforcement learning and optimization technology can make charging and discharging decisions for energy storage devices based on current and future grid conditions. In the power system, the aggregation of distributed energy resources increases uncertainty, particularly due to the fluctuating generation of renewable energy. This requires the use of advanced predictive control techniques to ensure long-term economic and decarbonization goals. In this paper, we present a real-time dispatching framework that integrates deep learning-based prediction, reinforcement learning-based decision-making, and stochastic optimization techniques. The framework can rapidly adapt to target uncertainty caused by various factors in real-time data distribution and control processes. The proposed framework achieved global Champion in the NeurIPS Challenge 2022 competition and demonstrated its effectiveness in practical scenarios of intelligent building energy management.

Log collection and storage is a crucial process for enterprises around the globe. Log analysis helps identify potential security breaches and, in some cases, is required by law for compliance. However, enterprises often delegate these responsibilities to third-party Cloud Service Providers (CSPs), where the logs are collected and processed for anomaly detection and stored in a data warehouse for archiving. Prevalent schemes rely on plain (unencrypted) data for anomaly detection. More often, these logs can reveal sensitive information about an organization or the customers of that organization. Hence, it is best to keep it encrypted at all times. This paper presents "SigML++," an extension of work done in "SigML." We utilize Fully Homomorphic Encryption (FHE) with the Cheon-Kim-Kim-Song (CKKS) scheme for supervised log anomaly detection on encrypted data. We use an Artificial Neural Network (ANN) based probabilistic polynomial approximations using a Perceptron with linear activation. We probabilistically approximate the Sigmoid activation function (σ(x)) in the encrypted domain for the intervals [−10,10] and [−50,50]. Experiments show better approximations for Logistic Regression (LR) and Support Vector Machine (SVM) for low-order polynomials.

Abstract: As the policies and regulations currently in place concentrate on environmental protection and greenhouse gas reduction, we are steadily witnessing a shift in the transportation industry towards electromobility. There are, though, several issues that need to be addressed to encourage the adoption of EVs at a larger scale. To this end, we propose a solution capable of addressing multiple EV charging scheduling issues, such as congestion management, scheduling a charging station in advance, and allowing EV drivers to plan optimized long trips using their EVs. The smart charging scheduling system we propose considers a variety of factors such as battery charge level, trip distance, nearby charging stations, other appointments, and average speed. Given the scarcity of data sets required to train the Reinforcement Learning algorithms, the novelty of the recommended solution lies in the scenario simulator, which generates the labelled datasets needed to train the algorithm. Based on the generated scenarios, we created and trained a neural network that uses a history of previous situations to identify the optimal charging station and time interval for recharging. The results are promising and for future work we are planning to train the DQN model using real-world data.

The Internet of Things (IoT) is one of the most widely used technologies today, and it has a significant effect on our lives in a variety of ways, including social, commercial, and economic aspects. In terms of automation, productivity, and comfort for consumers across a wide range of application areas, from education to smart cities, the present and future IoT technologies hold great promise for improving the overall quality of human life. However, cyber-attacks and threats greatly affect smart applications in the environment of IoT. The traditional IoT security techniques are insufficient with the recent security challenges considering the advanced booming of different kinds of attacks and threats. Utilizing artificial intelligence (AI) expertise, especially machine and deep learning solutions, is the key to delivering a dynamically enhanced and up-to-date security system for the next-generation IoT system. Throughout this article, we present a comprehensive picture on IoT security intelligence, which is built on machine and deep learning technologies that extract insights from raw data to intelligently protect IoT devices against a variety of cyber-attacks. Finally, based on our study, we highlight the associated research issues and future directions within the scope of our study. Overall, this article aspires to serve as a reference point and guide, particularly from a technical standpoint, for cybersecurity experts and researchers working in the context of IoT.

Efficient textual data distributions (TDD) alignment and generation are open research problems in textual analytics and NLP. It is presently difficult to parsimoniously and methodologically confirm that two or more natural language datasets belong to similar distributions, and to identify the extent to which textual data possess alignment. This study focuses on addressing a segment of the broader problem described above by applying multiple supervised and unsupervised machine learning (ML) methods to explore the behavior of TDD by (i) topical alignment, and (ii) by sentiment alignment. Furthermore we use multiple text generation methods including fine-tuned GPT-2, to generate text by topic and by sentiment. Finally we develop a unique process driven variation of Kullback-Leibler divergence (KLD) application to TDD, named KL Textual Distributions Contrasts (KL-TDC) to identify the alignment of machine generated textual corpora with naturally occurring textual corpora. This study thus identifies a unique approach for generating and validating TDD by topic and sentiment, which can be used to help address sparse data problems and other research, practice and classroom situations in need of artificially generated topic or sentiment aligned textual data.

Foods are complex products consisting of various ingredients of diverse origins. Along the food supply chains, food products are prone to spoilage and safety issues, which could give rise to different health-related concerns and outcomes. Furthermore, the existing highly centralised food systems generate substantial greenhouse gas emissions and food waste. In order to strengthen the sustainable decentralised "farm-to-fork" food chains, a mindset shift supported by relevant education and policy initiatives is highly required. The ERASMUS+ KA220 project SafeFood4EU was conceived with a crucial mission- to develop an interdisciplinary and innovative toolbox of higher education and lifelong learning courses that reflect various aspects of sustainable agri-food systems. The thematic areas discussed within the SafeFood4EU project have covered food safety and supply chain management, sustainable food systems and design, food production and quality of raw materials, food authenticity and analysis, and digital and soft skills. The main objectives have been to develop a distinctive content package and make it available to the students via an e-learning management system. The project's results, aimed at creating a pool of young and capable experts, can significantly impact future food security, thereby increasing awareness about the future challenges regarding food systems transition, dietary shift and the next generation's food security.

This paper represents a groundbreaking paradigm shift in network optimization. Departing from traditional static methodologies, this innovative approach harnesses the power of Generative Artificial Intelligence (AI) and Large Language Models (LLMs) to optimize cloud networks dynamically. By integrating advanced AI algorithms, this framework continuously adapts and evolves, ensuring optimal real-time performance. This dynamic optimization enhances efficiency and resilience, allowing cloud networks to adjust seamlessly to changing demands and conditions. Through the fusion of cutting-edge technology and adaptive intelligence, this approach heralds a new era in network optimization, empowering organizations to achieve unprecedent-ed levels of agility and scalability in their cloud infrastructures.

Deep learning heavily relies on statistical correlations to drive artificial intelligence (AI) innovations, particularly in computer vision applications like autonomous driving and robotics. However, despite providing a solid foundation for deep learning, these statistical correlations can be vulnerable to unforeseen and uncontrolled factors. The lack of prior knowledge guidance can result in spurious correlations, introducing confounding factors and affecting the model's robustness. To address this challenge, recent research efforts have focused on integrating causal theory into deep learning methodologies. By modelling the inherent and unbiased causal structure, causal theory can potentially mitigate the impact of spurious correlations effectively. Hence, this paper explores the basics of causal methodologies in image classification.

Scoring targets in shooting sports is a crucial and time-consuming task that relies on manually counting bullet holes. This paper introduced an automatic score detection model using object detection techniques. The performance of seven models belonging to two different architectural setups was compared. Models like YOLOv8n, YOLOv8s, YOLOv8m, RetinaNet-50, and RetinaNet-101 are single-shot detectors, while Faster RCNN-50 and Faster RCNN-101 belong to the two-shot detectors category. The dataset was manually captured from the shooting range and expanded by generating more versatile data using Python code. Before the dataset was trained to develop models, it was resized (640x640) and augmented using Roboflow API. The trained models were then assessed on the test dataset, and their performance was compared using matrices like mAP50, mAP50-90, precision, and recall. The results showed that YOLOv8 models can detect multiple objects with good confidence scores. Among all, YOLOv8m performed the best with the highest mAP50 value of 96.7%, followed by the performance of YOLOv8s with the mAP50 value of 96.5%. It is suggested that if the system is to be implemented in a real-time environment, YOLOv8s is a better choice since it took significantly less inference time (2.3ms) than YOLOv8m (5.7ms) and yet generated the competitive mAP50.

Wearable devices have become ubiquitous, collecting rich temporal data that offers valuable insights into human activities, health monitoring, and behavior analysis. Leveraging this data, researchers have developed innovative approaches to classify and predict time-based patterns and events in human life. Time-based techniques allow the capture of intricate temporal dependencies, which is the nature of the data coming from wearable devices. This paper focuses on predicting well-being factors, such as stress, anxiety, positive and negative affect, on the Tesserae dataset collected from office workers. We examine the performance of different methodologies, including deep learning architectures, LSTM, ensemble techniques, Random Forest (RF) and XGBoost and compare their performances for time-based and non-time-based versions. In time-based versions, we investigate the effect of previous records of well-being factors on the upcoming ones. The overall results show that time-based LSTM performs the best among conventional (non-time-based) RF, XGBoost, and LSTM. The performance even increases when we consider a more extended previous period, in this case, 3 past-days rather than 1 past-day to predict the next day. Furthermore, we explore the corresponding biomarkers for each well-being factor using feature ranking. The obtained rankings are compatible with the psychological literature. In this work, we validated them based on device measurements rather than subjective survey responses.

Nowadays, the Internet of Things (IoT) concept plays a pivotal role in society and brings new capabilities to different industries. The number IoT solutions in areas such as transportation and healthcare is increasing and new services are under development. In the last decade, society has experienced a drastic increase in IoT connections. In fact, IoT connections will increase in the next few years across different areas. Conversely, despite these benefits, several challenges still need to be faced to enable efficient and secure operations (e.g., interoperability, security, standards, and server technologies). Furthermore, although efforts have been made to produce datasets composed of attacks against IoT devices, several possible attacks are not considered. Most existing efforts do not consider an extensive network topology with real IoT devices. The main goal of this research is to propose a novel and extensive IoT attack dataset to foster the development of security analytics applications in real IoT operations. To accomplish this, 33 attacks are executed in an IoT topology composed of 105 devices. These attacks are classified into seven categories, namely DDoS, DoS, Recon, Web-based, Brute Force, Spoofing, and Mirai. Finally, all attacks are executed by malicious IoT devices targeting other IoT devices.

Extraversion, a Big Five personality trait, has been identified as a significant factor in COVID-19 positive coping—yet, relevant research is conflicting. Studies have not situated the influence of extraversion within a geographical and historical context. Thus, a sound base is lacking for assessing when opposing results regarding extraversion and COVID-19 positive coping are likely to result. Furthermore, extraversion with respect to COVID-19 coping has not been considered concerning other-directed learning in contrast to self-directed learning. To establish a sufficiently sound base, an examination of the range of high-ranking Google Scholar results on extraversion and COVID-19 coping from different countries during the pandemic’s various waves—pre and post vaccine introduction—is undertaken. The same are then considered for insights into public opinion. Following, extraversion is compared with other-directed learning and differentiated from self-directed learning. An understanding is thus presented for assessing when extraversion will necessarily be an effective personality trait for COVID-19 positive coping and when it will not. Extraversion’s effect will be found inherently inconsistent for identifying COVID-19 positive coping as a result, because of its dependence on other-directed learning. The conclusion: COVID-19 positive coping stability is contingent on personal values that guide self-directed learning, rather than other-directed extraversion.

Postural deficits such as hyperlordosis (hollow back) or hyperkyphosis (hunchback) are relevant health issues. Diagnoses depend on the experience of the examiner and are therefore often subjective and prone to errors. Machine learning (ML) methods in combination with explainable ar-tificial intelligence (XAI) tools have proven useful for providing an objective, data-based orien-tation. However, only a few works have considered posture parameters, leaving the potential of more human-friendly XAI interpretations still untouched. Therefore, the present work proposes an objective, data-driven ML system for medical decision support that enables especially human-friendly interpretations using counterfactual explanations (CFs). Posture data for 1151 subjects were recorded by means of stereophotogrammetry. An expert-based classification of the subjects regarding the presence of hyperlordosis or hyperkyphosis was initially performed. Using a Gaussian progress classifier, the models were trained and interpreted using CFs. Label errors were flagged and re-evaluated using confident learning. Very good classification performances for both hyperlordosis and hyperkyphosis were found, whereby the re-evaluation and correction of the test labels led to a significant improvement (MPRAUC = 0.97). A statistical evaluation showed that the CFs seemed to be plausible in general. In the context of personalized medicine, the present study’s approach could be of importance for reducing diagnostic errors and thereby improving the individual adaptation of therapeutic measures. Likewise, it could be a basis for the development of apps for preventive posture assessment.

A machine learning method for classifying Lung UltraSound is here proposed to pro- vide a point of care tool for supporting a safe, fast and accurate diagnosis, that can also be useful during a pandemic like as SARS-CoV-2. Given the advantages (e.g. safety, rapidity, portability, cost-effectiveness) provided by the ultrasound technology over other methods (e.g. X-ray, computer tomography, magnetic resonance imaging), our method was validated on the largest LUS public dataset. Focusing on both accuracy and efficiency, our solution is based on an efficient adaptive ensembling of two EfficientNet-b0 models reaching 100% of accuracy, which, to our knowledge, outperforms the previous state-of-the-art. The complexity of this solution keeps the number of parameters in the same order as an EfficientNet-b0 by adopting specific design choices that are adaptive ensembling with a combination layer, ensembling performed on the deep features, minimal ensemble only two weak models. Moreover, a visual analysis of the saliency maps on sample images of all the classes of the dataset reveals where the focus is on an inaccurate weak model versus an accurate model.

Downward short-wave (SW) solar radiation is the only essential energy source powering the atmospheric dynamics, ocean dynamics, biochemical processes, etc. on our planet. Clouds are the main factor limiting the SW flux over the land and the Ocean. For the accurate meteorological measurements of the SW flux one needs expensive equipment - pyranometers. For some cases where one does not need golden-standard quality of measurements, we propose estimating incoming SW radiation flux using all-sky optical RGB imagery which is assumed to incapsulate the whole information about the SW flux. We used DASIO all-sky imagery dataset with corresponding SW downward radiation flux measurements registered by an accurate pyranometer. The dataset has been collected in various regions of the World Ocean during several marine campaigns from 2014 to 2022, and it will be updated. We demonstrate the capabilities of several machine learning models in this problem, which are multilinear regression, Random Forests, Gradient Boosting and convolutional neural networks (CNN). We also applied the inverse target frequency (ITF) re-weighting of the training subset and the approach of pre-classification in order to raise the SW flux approximation quality. We found that the CNN is capable of approximating downward SW solar radiation with higher accuracy compared to existing empiric parameterizations. We also found that the ITF reweighting of the training subset increases the approximation quality substantially. The estimates of the SW radiation flux using all-sky imagery may be of particular use in case of the need for the fast radiative budgets assessment of a site.

Advanced machine learning algorithms, have the potential to be successfully applied to many areas of system modelling. In the present study the capability of ten machine learning algorithms in predicting the structural damage of an 8-storey reinforced concrete frame building subjected to single and successive ground motions is examined. From this point of view, the initial damage state of the structural system, as well as 16 well known ground motion intensity measures are adopted as the features of the machine-learning algorithms that aim to predict the structural damage after each seismic event. The structural analyses are performed considering both real and artificial mainshock–aftershock sequences, while the structural damage is expressed in terms of two overall damage indices. The comparative study results in the most efficient damage index, as well as the most promising machine learning algorithm in predicting the structural response of a reinforced concrete building under single or multiple seismic events. Finally, the configured methodology deployed in a user-friendly web-application.

Leader-follower autonomy (LFA) systems have so far only focused on vehicles following other vehicles. Though there have been several decades of research into this topic, there has not yet been any work on human-vehicle leader-follower systems. We present a system in which an autonomous vehicle — our ACTor 1 platform — can follow a human leader who controls the vehicle through gestures. We successfully developed a modular pipeline that uses artificial intelligence/deep learning to recognize hand-and-body gestures from a user in view of the vehicle’s camera and translate those gestures into physical action by the vehicle. We demonstrate our work using our ACTor 1 platform, a modified Polaris Gem 2 electric vehicle. This work has numerous applications, such as material transport in industrial contexts.

The paper demonstrates the analysis of Corona Virus Disease based on a probabilistic model. It involves a technique for classification and prediction by recognizing typical and diagnostically most important CT images features relating to Corona Virus. The main contributions of the research include predicting the probability of recurrences in no recurrence (first time detection) cases at applying our proposed approach for feature extraction. The combination of the conventional statistical and machine learning tools is applied for feature extraction from CT images through four images filters in combination with proposed composite hybrid feature extraction (CHFS). The selected features were classified by the stack hybrid classification system(SHC). Experimental study with real data demonstrates the feasibility and potential of the proposed approach for the said cause.

Deep learning (DL) and machine learning (ML) methods have recently contributed to the advancement of models in the various aspects of prediction, planning, and uncertainty analysis of smart cities and urban development. This paper presents the state of the art of DL and ML methods used in this realm. Through a novel taxonomy, the advances in model development and new application domains in urban sustainability and smart cities are presented. Findings reveal that five DL and ML methods have been most applied to address the different aspects of smart cities. These are artificial neural networks; support vector machines; decision trees; ensembles, Bayesians, hybrids, and neuro-fuzzy; and deep learning. It is also disclosed that energy, health, and urban transport are the main domains of smart cities that DL and ML methods contributed in to address their problems.

Publicly-funded scientists have a responsibility to engage with the public on scientific information, but are lacking a standardized framework and assessment strategy to do it well. The PEPS (Public Engagement Practices for Scientists) Method is an outcomes-centered framework employing standardized pedagogical methods with quantifiable outcomes. This approach reveals that scientists often have unrealistic expectations for achieving affective learning outcomes (i.e. changing views from anti- to pro-vaccine) by solely cognitive learning strategies (i.e. supplying data). The PEPS Method can serve as a roadmap for standardized science communication assessments, complementing existing science communication training programs for the next generation of scientists.

“You should know the words by the company they keep!” has been one of the most famous slogans attributed to John Rubert Firth, 1957. This has ignited a whole school in linguistic research known as the British empiricist contextualism. Sixty years later, many un- or semi-supervised machine learning algorithms have been successfully designed and implemented aiming at extracting word meaning from within the context of a text corpus. These algorithms treat words, more or less, as vectors of real numbers representing frequencies of word occurrences within context and word meaning as positions of words in a high-dimensional vector space model. Word associations, in turn, are treated as calculated distances among them. With the rise of Deep Learning (DL) and other artificial neural networks based architectures, learning the positioning of words and extracting word associations as measured by their distances has further improved. In this paper, however, we revisited the main stream of algorithmic approaches and set the stage for a partly cross-disciplinary evaluation framework to judge about the nature of the extracted word associations by state-of-the-art machine learning algorithms. Our preliminary results are based on word associations extracted from the application of DL framework on a Google News text corpus, as well as on comparisons with human created word association lists such as word collocation dictionaries and psycholinguistic experiments. The results and conclusions provide some insights into the inherited limitations in interpreting the type of word associations and underpinning relations between words with inevitable consequences in other areas, such as extraction of knowledge graphs or image understanding.

Human-Computer Interaction, including technology-aided instruction, is beginning to focus on virtual reality (VR) technology due to its ability to support immersive learning, teaching through simulation, and gamification of learning. These systems can deliver high-level multisensory learning experiences that are important in the teaching of many subjects, especially those involving abstract concepts or requiring spatial skills, such as organic chemistry. Haptic experiences with VR, however, remain a challenge. In addition, development have focused on general entertainment/gaming; VR systems in chemistry implement simulations of the chemistry laboratory and other advanced systems whereas those that support safe, game-like, immersive and multisensory learning of organic chemistry with haptics at pre-university education levels are scarce. We developed the VR Multisensory Classroom (VRMC) as an immersive learning environment within a VR head-mounted display, where learners employ hand movements to build hydrocarbon molecules and experience haptic feedback through gloves with built-in sensors and hand-tracking with the Leap Motion system. We report here the evaluation of the first prototype by learners from diverse backgrounds who reported on the ability of the VRMC to support high engagement, motivation, interest and organic chemistry learning as well as diverse learning styles. The VRMC is a novel VR classroom that supports immersive learning in molecular organic chemistry with haptics for multisensory learning.

Deep Learning (DL) has made significant advances in computer vision with the advent of Vision Transformers (ViT). Unlike Convolutional Neural Networks (CNNs), ViTs use self-attention to extract both local and global features from image data, and then use residual connections to feed these features directly into a fully networked multilayer perceptron head. In hospitals, hematologists prepare peripheral blood smears (PBSs) and read them under a medical microscope to detect abnormalities in blood counts such as leukemia. However, this task is time-consuming and prone to human error. This study investigates the transfer learning process of Google ViT and ImageNet CNNs to automate the reading of PBSs. The study used two online PBS datasets, PBC and BCCD, and transferred them into balanced datasets to investigate the influence of data amount and noise immunity on both neural networks. The PBC results show that Google ViT is an excellent DL neural solution for data scarcity. The BCCD results show that Google ViT is superior to ImageNet CNNs in dealing with unclean, noisy image data because it is able to extract both global and local features and use residual connections, despite the additional time and computational overhead.

This paper explores the increasing use of big data in education to create personalized learning experiences tailored to individual student needs. The trend, driven by vast amounts of educational data, requires the development of new techniques to optimize learning outcomes while addressing the ethical implications of data collection and utilization. The paper emphasizes the necessity for robust policy frameworks to ensure transparency and trust, based on clear guidelines and parental consent. It also discusses how educational institutions are updating curricula to prepare learners for a rapidly evolving workforce, incorporating contemporary AI technologies that impact education systems. The dual influence of AI presents both opportunities and challenges, necessitating a balanced and thoughtful approach. The paper advocates for a holistic strategy in integrating AI in education, emphasizing the importance of collaboration between the AI industry and other sectors to develop comprehensive policy frameworks for the ethical and effective use of AI in education.

This paper presents a repository of image databases where the image features are augmented with embedded vector field (VF) features to enhance the machine learning (ML) and increase classification statistics. Six VFs are formulated and used for the purpose of embedding. Three of them generate real shaped singular points (SPs): springing, sinking and saddle. The other three VFs generate seven kinds of SPs which include the real shaped SPs and four complex shaped SPs: repealing and attracting (out and in) spirals; clockwise and counterclockwise orbits (center). Also, the paper describes the VF singularities, their shapes, and locations according to the image objects. Then, the present work defines the mappings between the SPs’ shapes if the VFs are separately embedded into the same image. Thus, the paper infers which VFs are most appropriate for embedding into a particular image database such that the augmented SPs shapes enhance the ML classification. Examples of images with different embedded VFs are shown, in the text, to support and validate the theoretical conclusions. The contributions of the paper are: a description of the SPs location in an image; the mappings between the SPs of the different VFs; the definition of an imprint of an image in a VF; the generation of databases’ imprints. The advantage of classifying an image database with embedded VFs is that the new database enhances ML and improves the classification statistics if compared to the classification of the original image database with the same ML classifier. Furthermore, images with embedded SPs create a useful augmentation to the original image databases.

The application of deep learning in autonomous vehicles has surged over the years with the advances in technologies. This research explores the integration of deep learning algorithms into autonomous vehicles (AVs), focusing on their role in perception, decision-making, localization, mapping, and navigation. It shows that deep learning, which as a part of machine learning, mimics the human brain's neural networks, enabling advancements in perception, decision-making, localization, mapping, and overall navigation. Techniques like convolutional neural networks are used for image detection and steering control, while deep learning is crucial for path planning, automated parking, and traffic maneuvering. Localization and mapping are essential for AVs' navigation, with deep learning-based object detection mechanisms like Faster R-CNN and YOLO proving effective in real-time obstacle detection. Apart from the roles, the study also revealed that integration of deep learning in AVs faces challenges such as dataset uncertainty, sensor challenges, and model training intricacies. However, these issues can be addressed through increased standardization of sensors, real-life testing for model training, and advancements in model compression technologies can optimize the performance of deep learning in AVs. The study concludes that deep learning plays a crucial role in enhancing the safety and reliability of AV navigation. This study contributes to the ongoing discourse on the optimal integration of deep learning in AVs, aiming to foster their safety, reliability, and societal acceptance.

The potential of generalized machine learning models developed for crop water estimation was examined in the current study. Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), and Random Forest (RF) are three ensembled machine learning models that were developed using all of the data from a single location from 1976 to 2017 and then immediately applied at eleven different locations without the need for any local calibration. For the test period of January 2018 to June 2020, the model's capacity to estimate the numerical values of crop water requirement (Pen-man-Monteith (PM) ETo values) was assessed. In comparison to the GBM and RF models, the XGBoost model outperformed them both marginally and significantly. The estimate's weighted standard error was smaller than 0.85 mm/day, and the model's effectiveness varied from 96% to 99% across various locations. The model's strong performance was indicated by the decreased noise-to-signal ratio. A real-time water management system at the regional level can be seamlessly linked with this type of model due to its accuracy in estimating crop water requirements and its capacity to generalize.

The accurate counting of passengers in public transport systems is crucial for optimizing operations, improving service quality, and planning infrastructure. It can also contribute to reducing the number of public transport lines where a high frequency of vehicles is not needed in certain periods during the year, but also by increasing the number of lines where the need is increased. This paper provides a comprehensive review of current methodologies and technologies used for passenger counting, with a focus on image processing and machine learning techniques and concepts. The paper explores various algorithms, including traditional computer vision methods and advanced deep learning approaches, highlighting their strengths and limitations. Additionally, the paper examines the integration of these technologies with other sensing modalities such as infrared sensors, Wi-Fi, and RFID. By analyzing recent advancements and case studies, this review aims to offer insights into the effectiveness, scalability, and practicality of different passenger counting solutions and offers a solution proposal. The paper also analyzed the current GDPR regulation that applies to the European Union and how it affects the use of systems like this. Future research directions and potential areas for technological innovation are also discussed to guide further developments in this field.

Hyperspectral images (HSI) contain abundant spectral information. Efficient extraction and utilization of this information for image classification remain prominent research topics. Previously, hyperspectral classification techniques primarily relied on statistical attributes and mathematical models of spectral data. Deep learning classification techniques have recently been extensively utilized for hyperspectral data classification, yielding promising outcomes. This study proposes a deep learning approach that uses polarization feature maps for classification. Initially, the polar coordinate transformation method is employed to convert the spectral information of all pixels in the image into spectral feature maps. Subsequently, the proposed Deep Context Feature Fusion Network (DCFF-NET) is utilized to classify these feature maps. The model is validated using three open-source hyperspectral datasets: Indian Pines, Pavia University, and Salinas. The experimental results indicated that DCFF-NET achieves excellent classification performance. Experimental results on three public HSI datasets demonstrate that the proposed method accurately recognizes different objects with an overall accuracy (OA) of 86.68%, 94.73%, and 95.14% based on the pixel method, and 98.15%, 99.86%, and 99.98% based on the pixel-patch method.

The focus was on developing machine learning models to predict the IC50 values of the compound OTX015 using gene expression levels of cancer cell lines. Through regression-based machine learning models, particularly the SVM model, trained on pre-laboratory data, consistent and generalizable performance with low error scores was achieved. These models underwent enhancement via hyperparameter optimization and were tested on validation data. The results indicate the utility of machine learning in drug discovery processes and personalized medicine, offering rapid and cost-effective predictions of IC50 values. However, for enhanced reliability, further model development, data gathering, and evaluation with diverse compounds are recommended. In conclusion, this research demonstrates the potential of machine learning approaches to optimize experimental processes, reduce costs, and contribute to personalized treatments in healthcare by accurately predicting compound responses.

With the continuous advancement of digital transformation, digital payments are playing an increasingly important role in the financial industry. This study aims to utilize machine learning models to predict and analyze digital payment behavior. Initially, the background and significance of digital payments in the financial sector are introduced. Subsequently, the current status and trends of traditional digital payment distribution are reviewed, alongside related work on digital payment behavior prediction. Methodologically, principles and applications of machine learning models such as logistic regression, decision trees, and random forests are elaborated, along with experimental design and data preprocessing methods. The experimental results and discussion section illustrates the performance of each model in digital payment prediction and explores their impact on credit decisions. This exploration equips financial institutions with more effective user behavior analysis and risk management tools, thereby fostering future development and application of digital payment technologies.

We developed a novel machine learning (ML) algorithm with the goal of producing transparent models (i.e. understandable-by-humans) while also flexibly accounting for nonlinearity and interactions. Our method is based on ranked sparsity, and allows for flexibility and user-control in varying the shade of the opacity of black-box machine learning methods. The main tenet of ranked sparsity is that an algorithm should be more skeptical of higher-order polynomials and interactions \textit{a~priori} compared to main effects, and hence the inclusion of these more complex terms should require a higher level of evidence. In this work, we put our new ranked sparsity algorithm (as implemented in the open-source R package, `sparseR`) to the test in a predictive model "bakeoff" (i.e. a benchmarking study of ML algorithms applied "out-of-the-box," that is, with no special tuning). Algorithms were trained on a diverse set of simulated and real-world data sets from the Penn Machine Learning Benchmarks database, addressing both regression and binary classification problems. We evaluate the extent to which our human-centered algorithm can attain predictive accuracy that rivals popular black-box approaches such as neural networks, random forests, and support vector machines, while also producing more interpretable models. Using out-of-bag error as a meta-outcome, we describe the properties of data sets in which human-centered approaches can perform as well as or better than black-box approaches. We find that interpretable approaches predicted optimally or within 5% of the optimal method in most real-world data sets. We provide a more in-depth comparison of the performances of random forests to interpretable methods for several case studies, including exemplars in which algorithms performed similarly, and several cases when interpretable methods underperformed. This work provides a strong rationale for including human-centered transparent algorithms such as ours in predictive modeling applications.

This paper introduces a novel framework for zero-shot learning (ZSL), i.e., to recognize new categories that are unseen during training, by distilling knowledge from foundation models. Specifically, we first employ ChatGPT and DALL-E to synthesize reference images of unseen categories from text prompts. Then, the test image is aligned with text and reference images using CLIP and DINO. Finally, the predicted logits are aggregated according to their confidence to produce the final prediction.Experiments are conducted on multiple datasets, including CIFAR-10, CIFAR-100, and TinyImageNet. The results demonstrate that our model can significantly improve classification accuracy compared to previous approaches, achieving AUROC scores above 96\% across all test datasets. Our code is available at https://github.com/1134112149/MICW-ZIC.

The following article analyses the relationship between the mental health index and the variables of the Environment, Social and Governance-ESG model in the Italian regions between 2004 and 2023. First of all, a static analysis is proposed aimed at identifying trends relating to mental health in the Italian regions with indication of the regional gaps. Subsequently, a clustering with k-Means algorithm is proposed. Below is a comparison of 11 machine learning algorithms for predicting the performance of the mental health index. Finally, the article offers some economic policy suggestions. The results are critically discussed in light of the scientific literature.

The growing interest in fair AI development is evident. The ''Leave No One Behind'' initiative urges us to address multiple and intersecting forms of inequality in accessing services, resources, and opportunities, emphasising the significance of fairness in AI. This is particularly relevant as an increasing number of AI tools are applied to decision-making processes, such as resource allocation and service scheme development, across various sectors such as health, energy, and housing. Therefore, exploring joint inequalities in these sectors is significant and valuable for thoroughly understanding overall inequality and unfairness. This research introduces an innovative approach to quantify cross-sectoral intersecting discrepancies among user-defined groups using latent class analysis. These discrepancies can be used to approximate inequality and provide valuable insights to fairness issues. We validate our approach using both proprietary and public datasets, including EVENS and Census 2021 (England \& Wales) datasets, to examine cross-sectoral intersecting discrepancies among different ethnic groups. We also verify the reliability of the quantified discrepancy by conducting a correlation analysis with a government public metric. Our findings reveal significant discrepancies between minority ethnic groups, highlighting the need for targeted interventions in real-world AI applications. Additionally, we demonstrate how the proposed approach can be used to provide insights into the fairness of machine learning.

Image recovery by dictionary learning is of potential interest for many possible applications. To learn a dictionary, one needs to solve a minimization problem where the solution should be sparse. The K-SVD formalism, which is a generalization of the K-means algorithm, is one of the most popular methods to achieve this aim. We explain the preprocessing that is needed to bring images into a manageable format for the optimization problem.The learning process then takes place in terms of solving for sparse representations of the image batches. The main contribution of this paper is to give an experimental analysis of the recovery for highly textured imagery. For our study, we employ a subset of the Brodatz database. We show that the recovery of sharp edges plays a considerable role. Additionally, we study the effects of varying the number dictionary elements for that purpose.

Recent advancements in cognitive neuroscience, particularly in Electroencephalogram (EEG) signal processing, image generation, and brain-computer interfaces (BCI), have opened up new avenues for research. This study introduces a novel framework, Bridging Artificial Intelligence and Neurological Signals (BRAINS), which leverages the power of AI to extract meaningful information from EEG signals and generate images. The BRAINS framework addresses the limitations of traditional EEG analysis techniques, which struggle with nonstationary signals, spectral estimation, and noise sensitivity. Instead, BRAINS employs Long Short-Term Memory (LSTM) networks and contrastive learning, which effectively handle time-series EEG data and recognize intrinsic connections and patterns. The study utilizes the MNIST dataset of handwritten digits as stimuli in EEG experiments, allowing for diverse yet controlled stimuli. The data collected is then processed through an LSTM-based network employing contrastive learning and extracting complex features from EEG data. These features are fed into an image generator model, producing images as close to the original stimuli as possible. This study demonstrates the potential of integrating AI and EEG technology, offering promising implications for the future of brain-computer interfaces.

The need for solvating and encapsulating hydro-sensitive molecules drives noticeable trends in the applications of cyclodextrins in pharmaceutical industry, food, polymer, materials, and agricultural science. Among them, β-cyclodextrin is one of the most used for the entrapment of phenolic acid compounds to mask the bitterness of wheat bran. In this regard, there is still a need for a good predictive model that assesses β-cyclodextrin bitterness masking capabilities for various phenolic compounds. This study uses a dataset of 20 phenolic acids docked to the β-cyclodextrin cavity to generate three different binding constants. The data from docking study were combined with topological, topographical and quantum-chemical features from the ligands in a machine learning-based structure-activity relationship study. Three different models for each binding constant were computed using a combination of Genetic Algorithm (GA) and Multiple Linear Regression (MLR) approaches. The developed ML/QSAR models showed a very good performance, with high predictive ability and correlation coefficients of 0.969 and 0.984, for training and test sets, respectively. The models revealed several factors responsible for a binding with cyclodextrin, showing positive contributions toward the binding affinity values, including such features as presence of six-membered rings in the molecule, branching, electronegativity values, and polar surface area.

Fluorescence microscopic images of cells contain a large number of morphological features that are used as an unbiased source of quantitative information about cell status, through which researchers can extract quantitative information about cells and study the biological phenomena of cells through statistical and analytical analysis. As an important research object of phenotypic analysis, images have a great influence on the research results. Saturation artifacts present in the image result in a loss of grayscale information that does not reveal the true value of fluorescence intensity. From the perspective of data post-processing, we propose a two-stage cell image recovery model based on generative adversarial network to solve the problem of phenotypic feature loss caused by saturation artifacts. The model is capable of restoring large areas of missing phenotypic features. In the experiment, we adopt the strategy of progressive restore to improve the robustness of the training effect, and add the contextual attention structure to enhance the stability of the restore effect. We hope to use deep learning methods to mitigate the effects of saturation artifacts to reveal how chemical, genetic, and environmental factors affect cell state, providing an effective tool for studying the field of biological variability and improving image quality in analysis.

Drowsiness is a main factor for various costly defects, even fatal accidents in areas such as construction, transportation, industry and medicine, due to the lack of monitoring vigilance in the mentioned areas. The implementation of a drowsiness detection system can greatly help to reduce the defects and accident rates by alerting individuals when they enter a drowsy state. This research proposes an Electroencephalography (EEG) based approach for detecting drowsiness. EEG signals are passed through a preprocessing chain composed of artifact removal and segmentation to ensure accurate detection followed by different feature extraction methods to extract the different features related to drowsiness. This work explores the use of various machine learning algorithms such as Support Vector Machine (SVM) the K Nearest Neighbor (KNN) the Naive Bayes (NB) the Decision Tree (DT) and the Multilayer Perceptron (MLP) to analyze EEG signals sourced from the DROZY database, carefully labeled into two distinct states of alertness (awake, and drowsy). Segmentation into 10-second intervals ensures precise detection, while a relevant feature selection layer enhances accuracy and generalizability. The proposed approach achieves high accuracy rates of 99.84% and 96.4% for intra (subject by subject) and inter (cross-subject) modes, respectively. SVM emerges as the most effective model for drowsiness detection in the intra mode, while MLP demonstrates superior accuracy in the inter mode. This research offers a promising avenue for implementing proactive drowsiness detection systems to enhance occupational safety across various industries.

Accurate forecasting of crop yields holds paramount importance in guiding decision-making processes related to breeding efforts. This study focused on the application of multi-sensor data fusion and machine learning algorithms based on unmanned aerial vehicles (UAVs) in wheat yield prediction. Five machine learning (ML) algorithms namely random forest (RF), partial least squares (PLS), ridge regression (RR), K-Nearest Neighbor (KNN) and eXtreme Gradient Boosting Decision Tree (XGboost) were utilized for multi-sensor data fusion, and three ensemble methods including the second-level ensemble methods (stacking and feature-weighted) and the third-level ensemble method (simple average) for wheat yield prediction. The 270 wheat hybrids were used as planting materials under full and limited irrigation treatments. A cost-effective multi-sensor UAV platform, equipped with red–green–blue (RGB), multispectral (MS), and thermal infrared (TIR) sensors, was utilized to gather remote sensing data. The results revealed that the XGboost algorithm exhibited outstanding performance in multi-sensor data fusion, with the RGB+MS+Texture+TIR combination demonstrating the highest fusion performance (R2=0.660, RMSE= 0.754). Compared with the single ML model, the employment of three ensemble methods significantly enhanced the prediction accuracy of wheat yield. Notably, the third-layer simple average ensemble method demonstrated superior performance (R2 = 0.733, RMSE= 0.668 t ha-1). It significantly outperformed both the second-layer ensemble methods of Stacking (R2= 0.668, RMSE= 0.673 t ha-1) and feature-weighted (R2= 0.667, RMSE= 0.674 t ha-1), thereby exhibiting superior predictive capabilities. This finding demonstrated that the third-layer ensemble method not only augments the predictive ability of the model but also fine-tuned the accuracy of wheat yield prediction through the employment of simple average ensemble learning. Consequently, it offers a novel perspective for crop yield prediction and breeding selection.

Cardiovascular disease (CVD) and obesity are prevalent public health concerns with grave implications for morbidity and mortality, necessitating tailored interventions. This research explores the utility of fuzzy c-means clustering paired with principal component analysis (PCA) in detecting at-risk groups and personalizing health strategies for these conditions. Fuzzy c-means clustering allows for the dynamic classification of individuals into groups based on unique risk factors and intervention outcomes, while PCA aids in distilling complex data sets to uncover underlying patterns. The conjoined use of these methods has shown promise in identifying diverse risk profiles and in forecasting intervention success rates. The study acknowledges limitations, including possible biases stemming from data set composition and analytical parameter selection. Future research aims to refine these tools for clinical application. The results support implementing fuzzy c-means clustering and PCA for delineating specific target populations for health interventions, emphasizing careful use of these analytical approaches. Subsequent studies should focus on correlating these techniques with concrete clinical results to enhance public health measures.

Deep learning methods paired with sidescan sonar (SSS) are commonly used in underwater search and rescue operations for drowning victims, wrecks, and airplanes. However, these techniques are primarily designed to detect mine-like objects and are rarely applied to identifying features in dynamic dredge pit environments, due to a lack of datasets. In this study, we present a Sandy Point Dredge Pit (SPDP) dataset, in which high-resolution SSS data were collected from the west flank of Mississippi bird foot delta of the Louisiana inner shelf. This dataset contains a total of 385 SSS images. We introduce an Effective Geomorphology Classification model (EGC). By ablation studies, we analyze the utility of transfer learning on different model architectures and the impact of data augmentations on model performance. This EGC model will make geomorphic features identification in dredge pit environments quick and efficient which requires extensive experience and professional knowledge. The combination of SSS images and EGC model is a cost-effective and valuable toolkit for hazards monitoring in marine dredge pit environment. The SPDP SSS images dataset, especially the feature of pit wall without rotational slump, is also valuable for other machine learning modelers.

The review aims to assess fifteen (15) academic literature sources, highlighting the application of machine learning algorithms in the maintenance operations of optical fiber networks. It exhibits the collection of data using PRISMA methodology—Preferred Reporting Item for Systems Review and Meta-Analyses. The application, results, and performance metrics are discussed based on the collected observations, computations, and statistics in the studies, which revealed records of high accuracy degrees ranging from 86% to 98% on average and quality ML models including Neural Networks (NNs), Support Vector Machines (SVMs), and LSTM, as well as deep learning models that disclosed effective results of determining challenges and problems within the optical fiber lines. The review mainly centralized on superior machine learning technologies that surpass traditional techniques in fault detection and localization for improved optical fiber networks’ operations while providing insights into the limitations and challenges encountered in real-world applications of these models, offering a comprehensive perspective on the optical fiber network’s domain.

Feature selection is predominantly used in machine learning tasks, such as classification and regression. It selects a subset of features (relevant attributes of data points) from a larger set that contributes as optimally as possible to the informativeness of the model. There are exponentially many subsets of a given set, and thus, the exhaustive search is only practical for problems with at most a few dozen features. In the past, there have been attempts to reduce the search space using dynamic programming. However, models that consider similarity in pairs of features besides the quality of individual features do not provide the required optimal substructure. As a result, algorithms, which we will call suboptimal dynamic programming algorithms, find a solution that may deviate significantly from the optimal one. In this paper, we propose a dynamic programming algorithm with an iterative upgrade where the order of feature processing is inverted in each iteration. Such an alternating approach allows for improving the optimization function by using the score from the previous iteration to estimate the contribution of unprocessed features. The iterative process is proven to converge and terminate when the solution does not change in three successive iterations or when the number of iterations reaches the threshold. Results in more than 90 % of tests align with those of the exhaustive search, being competitive and often superior to the reference greedy approach. The validation was done by comparing the scores of output feature subsets and examining the accuracy of different classifiers learned on these features. In the context of feature selection, the proposed algorithm can be characterized as a filter method. However, we expect that the idea of alternating suboptimal optimization will soon be generalized to tasks beyond feature selection.

In this report, we present a study demonstrating how machine learning methods can reveal the interaction of different risk factors of post-transplant leukemic relapse and obtain robust predictions even with a modest clinical dataset. Using a cohort of 63 pediatric patients with acute lymphocytic leukemia (ALL) and 46 patients with acute myeloid leukemia (AML) who underwent stem cell transplant at a single institution, we built predictive models of leukemic relapse with both pretransplant and posttransplant patient variables (specifically lineage-specific chimerism) using the random forest classifier. The random forest classifier revealed different important predictive factors between ALL and AML in our relapse models consistent with previous knowledge. Furthermore, it also distinguished donor CD34 chimerism as most impactful in relapse prediction compare to donor chimerism of other cellular lineages in our dataset for ALL but CD3 for AML. Our models greatly improved sensitivity and specificity at predicting relapses in cross validation compared to a reference model based on our own institutional incidence of relapse and inferential statistical principles. Local Interpretable Model-Agnostic Explanations, an interpretable machine learning tool, confirmed our Random Forest Classification result and provided an intuitive explanation of how our machine learning models made the relapse prediction for each individual patient.

Goal-conditioned reinforcement learning (RL) holds promise for addressing intricate control challenges by enabling agents to learn and execute desired skills through separate decision modules. However, the irregular occurrence of required skills poses a significant challenge to effective learning. In this paper, we demonstrate the detrimental effects of this imbalanced skill(sub-goal) distribution and propose a novel training approach, Classified Experience Replay (CER), designed to mitigate this challenge. We demonstrate that adapting our method to conventional RL methods significantly enhances the performance of the RL agent. Considering the challenges inherent in tasks such as driving, characterized by biased occurrences of required sub-goals, our study demonstrates the improvement in trained outcomes facilitated by the proposed method. In addition, we introduce a specialized framework tailored for self-driving tasks on highways, integrating Model Predictive Control (MPC) into our RL trajectory optimization training paradigm. Our approach, utilizing CER with the suggested framework, yields remarkable advancements in trajectory optimization for RL agents operating in highway environments.

In paired-associate vocabulary learning task, second language learners employ different cognitive strategies, associated with either elaborative or rote rehearsal, resulting in different recall performance. The current study investigated the role of intelligence, measured with Raven’s Advanced Progressive Matrices, in strategy effects on performance and eye movement parameters. The Keyword method, which is regarded as a more effective cognitive strategy in paired-associate task, was induced on a sample of 32 healthy participants with normal or corrected to normal vision. Effective cognitive strategy use, mentioned in a structured post-hoc report, was found to improve performance after strategy induction. Higher intelligence score was associated with higher recall performance in case the Keyword method was reported, but not in the cases when no rote rehearsal was reported. No effect of cognitive strategy use on eye movement measures after explicit cognitive strategy instruction was revealed, which is supposed to be connected with lack of self-sustained strategy use immediately after strategy instruction. The findings emphasize the role of intelligence in cognitive strategy instruction.

The human voice has the potential to serve as a valuable biomarker for the early detection, diagnosis, and monitoring of pediatric conditions. This scoping review synthesizes the current knowledge on the application of Artificial Intelligence (AI) in analyzing pediatric voice as a biomarker for health. The included studies featured voice recordings from pediatric populations aged 0-17 years, utilized feature extraction methods, and analyzed pathological biomarkers using AI models. Data from 62 studies were extracted, encompassing study and participant characteristics, recording sources, feature extraction methods, and AI models. The review showed a global representation of pediatric voice studies, with a focus on developmental, respiratory, speech, and language conditions. The most frequently studied conditions were Autism Spectrum Disorder, intellectual disabilities, asphyxia, and asthma. Mel-Frequency Cepstral Coefficients were the most utilized feature extraction method, while Support Vector Machines were the predominant AI model. The analysis of pediatric voice using AI demonstrates promise as a non-invasive, cost-effective biomarker for a broad spectrum of pediatric conditions. However, further research and development are crucial to enhance the accuracy and applicability of these tools in clinical settings.

Background: Time-series biosignal data, representative of a physiological process, is often applied to time-sensitive machine learning applications that benefit from acceleration. Medical and research applications that process biosignal data in real-time may utilize new hardware architecture by switching from CPU to GPU devices to take advantage of the data processing speedups. In order to utilize machine learning kernels that are typically employed by a CPU on a GPU, the machine learning kernel must be reimplemented using custom compilers that can take advantage of GPU architecture. Objectives: The primary objective is to evaluate the speed of CPU-based machine learning algorithms commonly employed in biosignal process- ing and compare the speedup improvements obtained through GPU acceleration. Methods: A systematic search was conducted across multiple databases to identify studies employing GPU acceleration in biosignal processing. Inclusion and exclusion criteria are defined for GPU accel- eration studies. In this literature review, 12 studies of GPU kernel development for traditionally CPU-based kernels are analyzed. Results: It is found that a positive speedup occurs when using GPU kernels over traditional CPU-based algorithms in all instances. The speedup of GPU over CPU performance ranges between 1.87 to 27018.27 times faster. Conclusions: This review will contribute to the understanding of the role of GPU kernel development in biosignal processing, providing insights into performance improvements obtained by current GPU kernel development. The results indicate that GPU kernel development is a plausible direction to obtain real-time biosignal-based systems.

The calculation of effective doses is crucial in many medical and radiation fields, in order to ensure safety and compliance with regulatory limits. Traditionally, Monte Carlo codes using detailed human body computational phantoms have been used for such calculations. Monte Carlo dose calculations can be time-consuming and require expertise in different processes when building the computational phantom and dose calculations. This study employs various machine learning (ML) algorithms to predict the organ doses and effective dose conversion coefficients (DCCs) for different anthropomorphic phantoms. A comprehensive data set comprising neutron energy bins, organ labels, masses, and densities is compiled from Monte Carlo studies, and is used to train and evaluate the supervised ML models. This study includes a broad range of phantoms, including those from the International Commission of Radiation Protection (ICRP-110, ICRP-116 phantom), the Visible-Human Project (VIP-man phantom), and the Medical Internal Radiation Dose Committee (MIRD-Phantom), with row data prepared using numerical data and organ categorical labeled data. Extreme gradient boosting (XGB), gradient boosting (GB), and the random forest-based Extra Trees regressor are employed to assess the performance of the ML models against published ICRP neutron DCC values using the mean square error, mean absolute error, and R² metrics. The results demonstrate that the ML predictions significantly vary in lower energy ranges and vary less in higher neutron energy ranges, while showing good agreement with ICRP values at mid-range energies. Moreover, the categorical data models align closely with the reference doses, suggesting the potential of ML in predicting effective doses for custom phantoms based on regional populations, such as the Saudi voxel-based model. This study paves the way for efficient dose prediction using ML, particularly in scenarios requiring rapid results without extensive computational resources or expertise. The findings also indicate potential improvements in data representation and the inclusion of larger data sets to refine model accuracy and prevent overfitting. Thus, ML methods can serve as valuable techniques for the continued development of personalized dosimetry.

This research paper presents our investigation of the evolving trends in the field of Learning Sciences (LS) from 2005 to 2021. LS is a multidisciplinary field that integrates various scientific disciplines to study and support learning in real-world contexts (Hoadley, 2018). Our paper aims to understand how LS practices, methods, and disciplines of interest have changed over time, considering factors like the COVID-19 pandemic and the call for more equity-based research. We collected data from the International Society of Learning Sciences (ISLS) repository, which serves as one major platform that showcases LS research. We analysed the proceedings of the ISLS annual meetings and conferences, focusing on variables such as title, abstract, issue date, publisher, and collection using web scraping tools and the RStudio software for data collection and analysis. Our findings indicate several trends in LS research. In terms of methods and practices, design-based research (DBR) and participatory methods were commonly used in LS studies. However, there was a decline in the adoption of DBR in 2021, possibly due to the limitations imposed by the COVID-19 pandemic. Project-based learning, embodied interaction, and game-based learning were the most frequently used techniques among LS researchers. When examining the population of interest and domain focus in LS research. Learners were the primary focus, with a significant increase in the number of studies focusing on students over the years. However, there was also a noticeable increase in studies focusing on teachers in more recent years. In terms of subject disciplines, science and mathematics were the primary areas of focus, but there has been increasing attention to the arts and technology in recent years. Concerning equity-based research in LS, the finding revealed a significant increase in this area from 2005 to 2021, with ICLS studies tending to focus more on equity compared to CSCL studies. These findings contribute to understanding the current status and future development of the learning sciences.

This article uses machine learning analysis of wearable sensor data to explore the topic of driver differentiation. The study focuses on using detailed analyzes of data collected from wearable sensors to identify patterns that differentiate skilled drivers from inexperienced ones. On a predetermined driving route, participants experienced a variety of driving conditions, including parking, navigating cities, driving on highways and driving through residential neighborhoods. The gathered data was analyzed using machine learning techniques, yielding a classification accuracy of 94% overall. The results highlight important differences in sensor data between inexperienced and experienced drivers, providing insight into possible uses for improving safety protocols, driver education, and personalized feedback systems. The article fosters improvements in traffic safety and driver education by offering insightful information on the link between driver behavior analysis and machine learning.

Some optimal control problems need metaheuristics in searching for the optimal solution, especially when the process has certain characteristics like the Photobioreactor for Algae Growth (distributed parameter, nonlinearities, etc.). Particle Swarm Optimization (PSO) algorithms within control structures are a realistic approach; their task is often to predict the optimal control values working with a process model (PM). Owing to numerous numerical integrations, there is a big computational effort that is reflected in a large controller execution time. The authors propose to replace the PSO predictor with a machine learning model that has “learned” the quasi-optimal behavior of the couple (PSO, PM); the training data is obtained through closed-loop simulations over the control horizon. The new controller should preserve the process’s quasi-optimal control. In identical conditions, the process evolutions must also be quasi-optimal. The multiple Linear Regression and the Regression Neural Networks were considered as predicting models. The paper first proposes algorithms for collecting and aggregating data sets for the learning process. Algorithms for constructing the machine learning models, implementing the controllers, and closed-loop simulations are also proposed. The simulations prove that the two machine learning predictors have learned the PSO predictor’s behavior such that the process evolves almost identically. The resulting controllers’ execution time drastically decreased while keeping their optimality.

Gender has been a rarely addressed aspect in digital game-based learning (DGBL). Likewise, mixed results have been presented regarding the effects according to gender and the conditions that generate these effects. The present work studies the effects of a drill-and-practice mathe-matical game on primary students. The study focused on an analysis by gender, measuring learning performance, and motivation in the practice activity. Also, two instructional mechanics were considered regarding the question answering, a multiple-try (MTF) and a single-try (STF) condition, to search for possible differences. A total of 81 students from 4 courses and 2 schools participated in the experiment. The study's main findings were that: (a) the girls outperformed boys in terms of students' learning gains, (b) girls presented lower levels of competence and autonomy than boys, (c) in the MTF, girls presented lower levels of autonomy but no differences in competence contrasted to boys, (d) in the STF, girls presented lower levels of competence but no differences in autonomy against boys, and (e) no differences existed in interest, effort and value among gender overall o per instructional condition. This study enhances the knowledge of gender differences under diverse instructional settings, in particular providing insights into possible differences by gender when varying the number of attempts provided to students.

High-power laser facilities necessitate predicting incremental damage to final optics to identify evolving damage trends. In this study, we propose a surface damage detection method utilizing image segmentation employing ResNet-18, and a damage area estimation network employing U-Net++. Paired sets of online and offline images of optics obtained from a large laser facility is used to train the network. The trends of varying damage could be identified by incorporating additional experimental parameters. A key advantage of the proposed method is that the network can be trained end-to-end on small samples, eliminating the need for manual labeling or feature extraction. The software developed based on these models can facilitate the daily inspection and maintenance of optics in large laser facilities.

The present study comprises the second part of our previous work that dealt mainly with the phytochemical and physicochemical characterization of green coffee, clove, cinnamon/clove and nutmeg ethanolic extracts of grape origin. In the present study, we focused on producing a discriminating model concerning green coffee, clove, cinnamon, cinnamon and clove, and nutmeg fine powders based on multivariate analysis of variance and supervised learning on data of volatile compounds analysis, carried out with solid phase dynamic extraction in combination with gas chromatography/mass spectrometry. Results showed that 7 volatile compounds namely ethylene, methanol, 3-methylpentane, ethyl acetate, 9-hexadecen-1-ol, toluene, and methyl acetate could differentiate the investigated samples resulting in a 100% classification rate using the cross-validation method of linear discriminant analysis. Results were further confirmed using partial least squares regression analysis. The study contributes to the typification of green coffee, cinnamon, clove, cinnamon and clove and nutmeg, based on selected volatile compounds, and provides further support to the literature by means of possible adulteration given the statistical models developed.

The Ebola virus disease (EVD) is an extremely contagious and fatal illness caused by the Ebola virus. Recently, Uganda witnessed an outbreak of EVD, which generated a lot of attention on various social media platforms. To ensure effective communication and implementation of targeted health interventions, it is crucial for stakeholders to comprehend the sentiments expressed in the posts and discussions on these online platforms. In this study, we used deep learning techniques to analyze the sentiments expressed in Ebola-related tweets during the outbreak. We explored the application of three deep learning techniques to classify the sentiments in 8,395 tweets as positive, neutral, or negative. The techniques examined included a 6-layer convolutional neural network (CNN), a 6-layer long-short-term memory model (LSTM), and an 8-layer Bidirectional Encoder Representations from Transformers (BERT) model. The study found that the BERT model outperformed both the CNN and LSTM-based models across all the evaluation metrics, achieving a remarkable classification accuracy of 95\%. These findings confirm the reported effectiveness of transformer-based architectures in tasks related to natural language processing, such as sentiment analysis.

The number of engineers who are transitioning into environmental sustainability careers is growing, though a gap still exists between supply and demand. This presents an opportunity for undergraduate engineering students to fulfill the demand as environmental sustainability professionals. This qualitative exploratory study investigated environmental sustainability learning experiences and future career interests in environmental sustainability. The social cognitive theory (SCCT) was utilized as a theoretical lens, exploring undergraduate students’ environmental sustainability interests, related learning experiences and their interest in pursuing a future career in environmental sustainability. Twenty-five undergraduate engineering students in various engineering disciplines were interviewed for this study. Data were analyzed to (1) identify students’ interest in pursuing a career in environmental sustainability, (2) determine if students’ interests have changed since they began their undergraduate studies, and (3) explore how learning experiences have impacted students’ future career choice. The findings posit that exposure to environmental sustainability learning experiences is impactful and plays an important role, impacting students' interests in pursuing careers in sustainability. Results reveal that elements such as personal beliefs and salary considerations inspire career choices. This research contributes to addressing the demand for additional working professionals who are prepared to tackle environmental sustainability issues, highlighting the role of learning experiences in shaping students' career interests.

Children are inherently curious about everything they encounter, making the early years a perfect time for STEAM (science, technology, engineering, arts, and math) investigations. An outdoor learning environment can influence STEAM concept formation of preschoolers with intentional design that offer STEAM learning affordances. Despite the rising interest in early STEAM education, there is still limited literature on how the outdoor environment may influence STEAM learning behaviors of preschoolers (3-5 years old). This scoping review intends to evaluate the existing knowledge regarding the physical factors that contribute to STEAM learning affordances in an outdoor environment for children aged 3 to 5. The review included studies from the last twenty years. This scoping review was conducted in accordance with the criteria outlined in the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR). For this scoping review, 843 citations were discovered across four databases (JSTOR, Scopus, EBSCOhost, and Web of Science), ProQuest, and Google Scholar, and 31 articles were considered eligible for inclusion. Through the synthesis of information from those 31 studies, a list of STEAM learning behaviors of children and STEAM activity-supportive settings were identified that may positively influence preschoolers' STEAM concept development.

The incessant evolution of online platforms has ushered in a multitude of shopping modalities. Within the food industry, however, assessing the delectability of meals can only be tentatively determined based on consumer feedback encompassing aspects such as taste, pricing, packaging, service quality, delivery timeliness, hygiene standards, and environmental considerations. Traditional text data mining techniques primarily focus on consumers' emotional traits, disregarding pertinent information pertaining to the online products themselves. In light of these aforementioned issues in current research methodologies, this paper introduces the Bert BiGRU Softmax model combined with multimodal features to enhance the efficacy of sentiment classification in data analysis. Comparative experiments conducted using existing data demonstrate that the accuracy rate of the model employed in this study reaches 90.9%. In comparison to single models or combinations of three models with the highest accuracy rate of 7.7%, the proposed model exhibits superior accuracy and proves highly applicable to online reviews.

Machine Learning is increasingly and ubiquitously being used in the medical domain. Evaluation metrics like accuracy, precision, and recall may indicate the performance of the models but not necessarily the reliability of their outcomes. This paper assesses the effectiveness of a number of machine learning algorithms applied to an important dataset in the medical domain, specifically, mental health, by employing explainability methodologies. Using multiple machine learning algorithms and model explainability techniques, the project provides insights into the model workings to help determine the reliability of the machine learning algorithm predictions. The results are not intuitive. It was found that the models were focusing significantly on less relevant features and at times, unsound ranking of the features to make the predictions. The paper therefore argues that it is important for research in applied machine learning to provide insights into explainability of the models in addition to other performance metrics like accuracy. This is particularly important for applications in critical domains such as healthcare. A future direction is to investigate methods to quantify the effectiveness of the machine learning models in terms of the insights from their explainability.

In the era of Artificial Intelligence (AI), comprehending and responding to non-verbal communication is increasingly vital. This research extends AI's reach in bridging communication gaps, notably benefiting American Sign Language (ASL) and Taiwan Sign Language (TSL) communities. It focuses on employing various AI models, especially the Hierarchical Vision Transformer with Shifted Windows (Swin), for recognizing diverse sign language datasets. The study assesses Swin architecture's adaptability to different sign languages, aiming to create a universal platform for Unvoiced communities. Utilizing deep learning and transformer technologies, hybrid application prototypes have been developed for ASL-to-English translations and vice versa, with plans to expand this to multiple sign languages. The Swin models, trained on varied dataset sizes, show considerable accuracy, indicating their flexibility and effectiveness. This research underscores major advancements in sign language recognition and underlines a commitment to inclusive communication in the digital era. Future work will focus on enhancing these models and broadening their scope to include more sign languages, integrating multimodality and Large Language Models (LLMs), thereby fostering global inclusivity.

Introduction and Purpose: Nurses are expected to be competent in practice based on the domain of standards and interpersonal soft skills (ISS). Nurses are faced with inadequate physical assessment 28%, formulating diagnoses 56%, plans 34%, implementation 31%, evaluation 37,5%, and communication skills 41%. Aims to develop an ISS learning model based on transformative learning theory and digitalization (TLTD) to improve nurses’ competencies. Method: Used Explanatory cross-sectional involved 190 practitioner nurses. Variables of individual characters (X1), facilities (X2), Social environment support/SES (X3), TLTD (X4), ISS (X5), and nursing competencies (Y) were measured. Data was collected using a checklist questionnaire, conducted on 6 June to 10 August 2022 at Dili, Baucau, and Maliana hospitals. Used descriptive and inferential analysis with SEM-PLS. Result: Five of the 11 hypotheses of statistical p-value < 0,05 and T-Test > 1,96, including X2>X4, X3>X5, X4>X5, and X5>y, to form ISS learning model. The characteristic of respondents were 81,8% young adults, 67,9% women, 57,8% undergraduates, judging the previous training 35% was unsuccessful, and 45,8% did not meet expectations. Learning facilities that are still lacking include policies 23,7%, curriculum 23,4%, guideline 22,7%, modules 27,9%, infrastructure 20,3%, social environment support 24,2% low, organizational support, 30,0% low peer support and 26,3% low family support. The average TLTD is 25,3% to 34,2%, ISS 22,1% to 30,5%, and nurse competence 25,3% to 30,5%.Suggestion: Result of the study become base to improve nurse’s competencies. Conclusion: Learning model was formed by facilities, SES, TLTD, ISS, and nurses’ competencies.