The evaluation of machine unlearning has become increasingly significant as machine learning systems face growing demands for privacy, security, and regulatory compliance. This paper focuses on categorizing and analyzing evaluation metrics for machine unlearning, essential for assessing the success of unlearning processes. We divide the metrics into three key dimensions: unlearning effectiveness, unlearning efficiency, and model utility. Unlearning effectiveness examines the degree to which data is removed from the model, utilizing methods such as data removal completeness, privacy leakage detection, and perturbation analysis to ensure thorough data erasure. Unlearning efficiency considers metrics like time to unlearn, computational cost, and scalability, which are crucial for maintaining system performance in real-time environments. Model utility metrics, including accuracy retention, robustness, and fairness, ensure that unlearning does not compromise the model’s predictive capabilities. Through this categorization, we present a comprehensive framework for evaluating machine unlearning, providing a foundation for developing unlearning techniques that balance privacy, performance, and regulatory needs across diverse industries, particularly finance.

Monte Carlo techniques have been extensively used for planning laser-based clinical procedures such as photobiomodulation. However, the effect of several biological tissue characteristics, including morphological structure and physiological parameters, has not been carefully addressed in many applications. Specifically, many questions remain concerning the effect of skin phototype and body mass index on the efficacy of photobiomodulation for extraoral therapies. To address these questions, a Monte Carlo simulation model was developed to analyze the effects of body mass index-dependent skin structure and Fitzpatrick skin type, specifically tailored for the morphological characteristics of cheek tissue. The model describes the settings of a typical oral photobiomodulation treatment protocol for pain relief, namely the use of 660 nm and 808 nm laser wavelengths and a therapeutic dose of 2.0 J/cm² on the masseter muscle. The simulations were used to train a machine learning predictive model aimed at accelerating the treatment planning stage and assessing the importance of patient-specific parameters. A multiple regression approach was adopted to predict muscle dose and treatment time for the effective delivered dose.

While the surface of the Earth plays a key role in weather forecasting through its interaction with the atmosphere, in ensemble numerical weather predictions the uncertainty on the surface is only represented with perturbations in the parameterisations representing the surface processes. Data representing the surface, such as the land cover, are not perturbed. As fully data-driven forecasts without parameterisations are growing in importance, sampling the uncertainty on the land cover data brings a new way of making ensemble forecasts. Our work describes a method of generating ensemble land cover maps for numerical weather prediction. The target land cover map has the ECOCLIMAP-SG labels, used in the SURFEX surface model, and therefore is expected to have all relevant labels for surface-atmosphere interactions. The method translates the ESA WorldCover map to ECOCLIMAP-SG labels and resolution using auto-encoders. The land cover ensemble members are obtained by sampling the land cover probabilities in the output of the neural network. This paper builds upon the work done in a companion paper describing the high-resolution version of ECOCLIMAP-SG, called ECOCLIMAP-SG+, used for the training and evaluation of the neural network. The output map presented here, called ECOCLIMAP-SG-ML, improves upon the ECOCLIMAP-SG map in terms of resolution (from 300~m to 60~m), overall accuracy (from 0.41 to 0.63) and the ability to produce ensemble members.

Explainable AI (XAI) has the potential to transform healthcare by making AI-driven medical decisions more transparent, trustworthy, and ethically compliant. Despite its promise, the healthcare sector faces several challenges, including balancing interpretability and accuracy, integrating XAI into clinical workflows, and ensuring adherence to rigorous regulatory standards. This paper provides a comprehensive review of XAI in healthcare, covering techniques, challenges, opportunities, and advancements, thereby enhancing the understanding and practical application of XAI in healthcare. The study also explores responsible AI in healthcare, discussing new perspectives and emerging trends and providing valuable insights for researchers and practitioners. The insights and recommendations presented aim to guide future research and policy-making, promoting the development of transparent, trustworthy, and effective AI-driven solutions.

Kolmogorov–Arnold Network (KAN) is an emerging interpretable neural network compared to fully black-box MLPs. Recently, emerging works focus on comprehensive and fair comparisons between KAN and MLP in various tasks. However, these works didn't focus on the strongest advantage of KAN: generating symbolic outputs. The ability of KAN to provide scientific insights or even discover new science is under-examined. In this work, we propose several novel metrics to measure how well a KAN performs on symbolic function fitting: R^2-Mean, weighted R^2-complexity loss, and ranking metrics. We also propose a metric to determine mathematical complexity of a target function and evaluate KAN with several functions of different mathematical complexity. Additionally, we also tried inputs with different ranges to find the effect of normalization.

(1) Background: The rapid evolution of the internet and technological infrastructure has led to a surge in data generation across various contexts, increasing the use of machine learning tools to extract valuable information. Clustering, particularly using the K-means algorithm, is a common technique. However, determining the optimal number of clusters in K-means is challenging, as traditional methods like the elbow method can be imprecise and subjective. This study proposes a more accurate and objective method to identify the optimal number of clusters. (2) Methods: The proposed method utilizes the numerical derivative of cluster inertias and the maximum value of the ratio between contiguous derivatives. Implemented in Python using sklearn, numpy, and matplotlib, the method was validated with synthetic datasets generated by artificial intelligence, where cluster numbers are clearly distinguishable. (3) Results: The method proved to be more precise and less subjective than the traditional elbow method, accurately identifying the optimal number of clusters in all tested synthetic datasets. Additionally, it demonstrated computational efficiency with minimal RAM usage and execution time, making it suitable for practical data analysis applications. (4) Conclusions: This new mathematical and computational method significantly improves the determination of the optimal number of clusters in K-means, offering a more accurate and objective alternative to traditional techniques. Future work will extend this method to hierarchical clustering and develop a cloud service for wider accessibility.

The increasing complexity and volume of job listings in the digital era necessitate advanced recommendation systems to match job seekers with suitable opportunities. This paper presents a hybrid job recommendation system that integrates Collaborative Filtering (CF) and Content-Based Filtering (CBF) to enhance recommendation accuracy and user satisfaction. The CF component leverages historical user interactions and similarities between users to suggest jobs, while the CBF component analyzes job descriptions and user profiles to provide personalized recommendations based on individual preferences and qualifications. By combining these two approaches, the proposed system mitigates the limitations of each method and offers a more comprehensive and effective solution. Experimental results on a real-world dataset demonstrate the system's improved performance in terms of precision, recall, and F1-score compared to traditional recommendation models. This study contributes to the field of job recommendation systems by providing a robust framework that effectively bridges the gap between user needs and job market opportunities.

The importance of XAI is undeniable in the current scenario and thus it's importance in considerable. Unfortunately, there are a couple of scenarios where the current XAI models fail. Additionally, attackers seek vulnerabilities in these models. This review paper is intended to cover some of the important scenarios where the existing XAI models may fail and some progresses made which shows their vulnerabilities and how to secure them.

Prostate cancer (PCa) ranks as the second most fatal and sixth most prevalent cancer among males globally. This study focuses on leveraging deep learning networks to detect the Gleason grading of prostate cancer from histopathology images stained with Hematoxylin and Eosin (H&E). Six pathologists annotated the images, resulting in six distinct labels for each input image. A common ground truth label was established through majority voting approach. Subsequently, the dataset was trained using architectures: UNeT, UNeT++, DeepLabV3, DeepLabV3+, and GAN based segmentation network. Notably, GAN based network demonstrated superior performance, achieving an F1-score of 0.872 and a Jaccard Index of 0.777, outperforming the other architectures considered in this study.

Robotic path planning and navigation algorithms enable autonomous mobile robots to navigate complex environments. These algorithms allow robots to be deployed in search and rescue missions, where they can locate victims in hazardous areas inaccessible to humans. Additionally, autonomous driving algorithms hold the potential to revolutionize transportation by enabling self-driving cars to navigate roads safely and efficiently. This paper focuses on developing an algorithm for autonomous navigation of the mobile robot (Tortoise bot) using robot operating system (ROS), based on publish-subscribe communication facilitating seamless interaction between various nodes. Tortoise Bot is a differential wheeled robot whose movement is based on two separately driven wheels placed on either side of the robot body. The Raspberry Pi acts as the controller. A 360-degree LiDAR and RGB-D camera are used for creating a 3D map of the environment. Various state-of-the art software tools, such as Gazebo, Ubuntu, MATLAB and RPI imager are used. Initially, a simulation based on simple obstacle avoidance is done using gazebo and MATLAB. Another simulation based on trajectory tracking is implemented using MATLAB to study the kinematic model. Online navigation and path planning are executed with the help of teleoperation and Dynamic Window Approach algorithm. A novel Wander algorithm is created that avoids obstacles on its path. Object recognition is also implemented during autonomous navigation using YOLO.

Causal language can be a powerful tool for media outlets to subtly influence public perception and reinforce specific narratives. Therefore, identifying these linguistic patterns can be helpful in assessing the level of bias present in media content. In this paper, we directly compare the prevalence of causal language in headlines pertaining to the coverage of the Israel-Palestine conflict and the Russia-Ukraine war. We specifically look at the BBC and AlJazeera headlines covering the assault on Gaza since October 7, 2023. We use UniCausal, a model for causal text mining, in order to automatically extract the cause and effect of each headline. Our findings reveal that BBC headlines tend to avoid directly attributing causality to Israel for the violence in Gaza, whereas Al Jazeera headlines explicitly identify Israel as the responsible party. This differential use of causal language suggests a potential bias in media reporting.

Computational animation of spatiotemporal models for 3-D shape and motion is considered as core of dynamic real-time vision. This is based on sets of features evaluated from multi-focal image streams. Subjects are defined as special objects capable of sensing environmental parameters and of initiating own actions in combination with stored knowledge. Object/subject recognition and scene understanding are achieved on different levels. Multiple objects are tracked individually for perceiving their actual state (‘here and now’). Fast saccadic jumps in gaze direction allow flexible concentration on objects or parts of actual interest. By analyzing motion of relevant objects/subjects over a larger time scale on the level of state variables and documenting them in the ‘scene tree representation’ (computer graphics), the situation with respect to decision making is assessed. Various behavioral capabilities of subjects are represented on an abstract level for characterizing their potential behaviors. These are generated by stereotypical feed-forward and feedback control applications on a separate level close to the actuator hardware with corresponding methods. This dual representation on one level for decision making and one on the implementation level allows for flexibility and easy adaptation or extension. Results are shown for road vehicle guidance based on three cameras on a gaze-controlled platform.

Soft robotic manipulators consisting of serially-stacked segments combine actuation and structure in an integrated design. This design can be miniaturised while providing suitable actuation for applications such as minimally invasive surgery and for inspections in confined environments. The control of these robots, however, remains challenging, due to the difficulty in accurately modelling the robots, in coping with their redundancies, and in solving their full inverse kinematics. In this work, we explore a hybrid approach to control serial soft robotic manipulators that combines machine learning (ML) to estimate the inverse kinematics with a closed-loop control to compensate the remaining errors. For the ML part, we compare various approaches, including both kernel-based learning and more general neural networks. We validate the selected ML model experimentally. For the closed-loop control part, we first explore Jacobian formulations using both synthetic models and numerical approximations from experimental data. We then implement integral control actions using both these Jacobians, and evaluate them experimentally. In an experimental validation, we demonstrate that the hybrid control approach achieves setpoint regulation in a robot with 6 inputs and 4 outputs.

In the field of visualization, understanding users’ analytical process is important to determine the effectiveness of a designed visualization application. To understand the users’ analytical process, numerous studies have been performed to capture and analyze user interactions. Although many studies have emphasized the importance of analyzing user interactions to understand users’ analytical reasoning processes, few have successfully linked these interactions to users’ reasoning processes. This paper introduces an approach that bridges this gap by correlating semantic user interactions with analysis decisions through an interactive wire transaction analysis system and a visual state transition matrix. With the designed analysis system, interactive analysis can be performed to evaluate financial fraud in wire transactions. It also allows the mapping of captured user interactions and analytical decisions back onto the visualization, revealing users’ distinct results. The visual state transition matrix further aids to help understanding users’ analytical flows, revealing their decision-making processes. Classification machine learning algorithms are applied to assess the effectiveness of our approach in understanding analysts’ strategies by connecting them to their decisions. From the study, we observed an average of 72% accuracy in clearly classifying the semantic user interactions. For classifying individual decisions, we observed an average of 70% classification accuracy. This emphasizes the importance of capturing semantic user interactions to understand users’ analytical processes. Overall, it is determined that the proposed approach not only enhances the understanding of analytical behaviors but also offers a robust approach for evaluating user interactions in visualization tools.

Recent advancements in artificial intelligence (AI) and deep learning have revolutionized the field of protein engineering, particularly in the area of de novo protein design. This review article explores the impact of AI-driven approaches on protein design, with a specific focus on the role of structure prediction neural networks, such as AlphaFold and RoseTTAFold. The article discusses the paradigm shift brought about by these networks, which have enabled the design of proteins with unique structures and functions that are not found in nature. The review covers various aspects of AI-driven protein design, including the use of protein language models to harness evolutionary information, the development of de novo protein design workflows utilizing deep learning, and the application of generative models like RFdiffusion and RoseTTAFold All-Atom. The article also highlights the successes and applications of AI-driven protein design across diverse domains, such as enzyme engineering, antibody design, and vaccine development. Additionally, the review identifies current challenges and future directions in the field, emphasizing the need to address limitations in modeling conformational dynamics and designing proteins for in vivo functionality. The article concludes by underscoring the potential of AI-driven protein design to transform various aspects of science and technology, while also acknowledging the importance of interdisciplinary collaboration and the development of robust pipelines for the validation and optimization of designed proteins. Overall, this comprehensive review serves as a valuable resource for researchers and practitioners interested in understanding the current state and future prospects of AI-driven protein design.

Artificial intelligence (AI) refers to computer algorithms that replicate the cognitive function of humans. Machine learning is widely applicable using structured and unstructured data, while deep learning is derived from the neural networks of the human brain that process and interpret information. During the last decades, AI has been introduced in several aspects of healthcare. In this review, we aim to present the current application of AI in the neonatal intensive care unit. AI-based models have been applied to neurocritical care, including automated seizure detection algorithms and electroencephalogram-based hypoxic-ischemic encephalopathy severity grading systems. Moreover, AI models evaluating magnetic resonance imaging contributed to the progress of the evaluation of the neonatal developing brain and the understanding of how prenatal events affect both structural and functional network topologies. Furthermore, AI algorithms have been applied to predict the development of bronchopulmonary dysplasia and assess the extubation readiness of preterm neonates. Automated models have been also used for the detection of retinopathy of prematurity and the need for treatment. Among others, AI algorithms have been utilized for the detection of sepsis, the need for patent ductus arteriosus treatmnet, the evaluation of jaundice, and the detection of gastrointestinal morbidities. Finally, AI prediction models have been constructed for the evaluation of the neurodevelopmental outcome and the overall mortality of neonates. Although the application of AI in neonatology is encouraging, further research in AI models is warranted in the future including retraining clinical trials, validating the outcomes, and addressing serious ethics issues.

(1) Background: Although diagnostic criteria for massive hemorrhage with organ dysfunction such as disseminated intravascular coagulation associated with delivery have been empirically established based on clinical findings, strict logic has yet to be used to establish numerical criteria. (2) Methods: A dataset of 107 deliveries with ≥2,000 g of blood loss, among 13,368 deliveries from nine national perinatal centers in Japan between 2020 and 2023 was obtained. Twenty-three patients had fibrinogen levels <170 mg/dl, which is the initiation of coagulation system failure per our previous reports. Three of these patients had hematuria. We used six machine learning methods to identify the borderline criteria dividing the fibrinogen/fibrin/fibrinogen degradation product (FDP) planes, using 15 coagulation fibrinolytic factors. (3) Results: The boundaries of hematuria development on a two-dimensional plane of fibrinogen and FDP were obtained. If the FDP–fibrinogen/3–60 (mg/dl) value is positive, this indicates hematuria; otherwise, the case is non-hematuria, as demonstrated by the support vector machine method that seemed the most appropriate. (4) Conclusions: The borderline criterion dividing the fibrinogen/FDP plane for patients with hematuria that could be considered organ dysfunction in massive hemorrhage during delivery was obtained using artificial intelligence, and this method seemed to be useful.

Recent advancements in neural language models, particularly attention-based architectures like the Transformer, have substantially surpassed traditional methods in various natural language processing tasks. These models adeptly generate nuanced token representations by considering contextual relations within a sequence. However, augmenting these models with explicit syntactic knowledge, such as part of speech tags, has been found to remarkably bolster their effectiveness, especially under constrained data scenarios. This study introduces the Linguistic Enhanced Transformer (LET), which integrates multiple syntactic features, showing a notable increase in translation accuracy, evidenced by an improvement of up to 1.99 BLEU points on subsets of the WMT '14 English-German dataset. Furthermore, this paper demonstrates that enriching BERT models with syntax-aware embeddings enhances their performance on several GLUE benchmark tasks.

We developed a novel machine learning algorithm to augment clinical diagnosis of prostate cancer utilizing first and second-order texture analysis metrics and novel application of machine learning radiomics analysis. We successfully discriminated between significant prostate cancers versus non-tumor regions and provided accurate prediction between Gleason score cohorts with statistical sensitivity of greater than 0.91 sensitivity across three separate cohorts. Tumor heterogeneity and prediction between GS cohorts were quantified using two feature selection approaches and two classifiers with tuned hyperparameters (including grid search and randomized search). There was a total of 71 patients analyzed in this study. Multiparametric MRI, incorporating T2WI and the ADC maps, were used to derive radiomics features. Recursive feature elimination (RFE), the least absolute shrinkage and selection operator (LASSO), and two classification approaches, including a support vector machine (SVM) (with grid search) and random forest (RF) (with randomized search), were utilized to differentiate between non-tumor regions versus significant cancer and prediction among Gleason score groups. In T2WI images, the RFE feature selection approach combined with RF and SVM classifiers outperformed LASSO with SVM and RF classifiers regarding performance. The detection precision of the radiomics framework depending on multiple imaging modalities was lower than the diagnostic accuracy of single imaging modality model with every machine learning approach assessed. The best performance was achieved by combining LASSO and SVM into a model that used both T2WI and ADC. This model had an area under the curve (AUC) of 0.91. Radiomic features computed from ADC and T2WI images were used to predict three groups of Gleason score using two kinds of feature selection methods (RFE and LASSO), RF and SVM classifier models with tuned hyperparameters. Using combined sequences (T2WI and ADC map images) and combined radiomics (1st and GLCM features), LASSO, with a feature selection method with RF, was able to predict G3 with the highest sensitivity at a level AUC of 0.92. To predict G3 for single sequence (T2WI images) using GLCM features, LASSO with SVM achieved the highest sensitivity with an AUC of 0.92.

Inflation is a crucial macroeconomic indicator which measures changes in the general level of prices of goods and services. In recent years, a series of successive events affected the inflation rates. To fight this increase in inflation, governments start to take different actions through their monetary and fiscal policies. In this research 10 independent parameters were used to see their effect on inflation rates. Some are traditional like GDP, Population, and exchange rate while others are some new technology related parameters like E-money payments transactions and number of Institutions offering payment services/instruments. The dependent parameter is the consumer price index (CPI). All parameters were taken in 8 years period (2013-2020). Supervised machine learning is used to run a robust regression model. The results show that technology advancement in payments is not a catalyst for price inflation if it is used properly and under regulations and control monetary policies. The results direct regulators to have a good understanding of the situation and take the right action in their policies of adopting fintech businesses.

The way in which a person walks, known as human gait, is a significant indicator of overall health and well-being. Abnormalities in gait can indicate the presence of metabolic disorders, such as diabetes or obesity. However, detecting these disorders can be challenging using traditional methods, which often involve subjective assessments or invasive procedures. In this study, a novel methodology known as Criticality Analysis (CA) was proposed for the detection and monitoring of human gait in people with metabolic disorders taking part in an intervention to increase activity and reduce weight. The CA approach utilised inertial measurement unit gait data, alongside clinical health measures. This allows for the control of nonlinear growth in the system, resulting in lower dimensional, nonlinear, free-scale, stable, controlled, and organised trajectories. These trajectories were then analysed using a Support Vector Machine (SVM) algorithm, which is well-suited for this task due to its ability to handle nonlinear and dynamic data. The combination of the CA approach and the SVM algorithm demonstrated high accuracy and non-invasiveness in detecting metabolic disorders, yielding an average accuracy within the range of 78.2% to 90%. Additionally, the classification technique accuracy, at a group level was observed to reduce during period of the intervention (e.g., from week 2 to week 3) alongside changes in fitness and health, which indicates the potential of using the approach to measure and monitor biological systems. As such, this novel methodology has the potential to be a valuable tool for healthcare professionals in detecting and monitoring metabolic disorders, as well as other unknown diseases associated with the human biological system.

The rise in Internet users has brought with it the impending threat of cybercrime as the Internet of Things (IoT) increases and the introduction of 5G technologies continues to transform our digital world. It is now essential to protect communication networks from illegal intrusions in order to guarantee data integrity and user privacy. In this situation, machine learning techniques used in data mining have proven to be effective tools for constructing intrusion detection systems (IDS) and improving their precision. We use the well-known AWID3 dataset, a comprehensive collection of wireless network traffic, to investigate the effectiveness of machine learning in enhancing network security. Our work primarily concentrates on the Krack and Kr00k attacks, which target the most recent and dangerous flaws in IEEE 802.11 protocols. Through diligent implementation, we were able to successfully identify these threats using an IDS model that is based on machine learning. Notably, the resilience of our method was demonstrated by our Ensemble classifier’s astounding 99% success rate in detecting the Krack attack. The effectiveness of our suggested remedy was further demonstrated by the high accuracy rate of 96.7% displayed by our Neural Network-based model in recognizing instances of the Kr00k attack. Our research shows the potential for considerably boosting network security in the face of new threats by leveraging the capabilities of machine learning and a diversified dataset. Our findings open the door for stronger, more proactive security measures to protect IEEE 802.11 networks’ integrity, resulting in a safer online environment for all users.

The performance of 5 forecasting models was investigated for predicting nursery mortality using the master table built for 3,242 groups of pigs (~ 13 million animals) and 42 variables, which concerned the pre-weaning phase of production and conditions at placement in growing sites. After training and testing each model’s performance through cross-validation, the model with the best overall prediction results was the Support Vector Machine model in terms of Root Mean Squared Error (RMSE=0.406), Mean Absolute Error (MAE=0.284), and Coefficient of Determination (R2=0.731). Subsequently, the forecasting performance of the SVM model was tested on a new dataset containing 72 new groups, simulating ongoing and near real-time forecasting analysis. Despite a decrease in R2 values on the new dataset (R2=0.554), the model demonstrated high accuracy (77.78%) for predicting groups with high (5>%) or low (5<%) nursery mortality. This study demonstrated the capability of forecasting models to predict the nursery mortality of commercial groups of pigs using pre-weaning information and stocking conditions variables collected post-placement in nursery sites.

This review paper provides a comprehensive overview of machine vision pose measurement algorithms. The paper focuses on the state-of-the-art algorithms and their applications. The paper is structured as follows: The introduction in Section 1 provides a brief overview of the field of machine vision pose measurement. Section 2 describes the commonly used algorithms for machine vision pose measurement. Section 3 discusses the factors that affect the accuracy and reliability of machine vision pose measurement algorithms. Section 4 presents the applications of machine vision pose measurement in various fields. The paper provides specific examples of how machine vision pose measurement is used in each of these fields. Finally, Section 5 summarizes the paper and provides future research directions. The paper highlights the need for more robust and accurate algorithms that can handle varying lighting conditions and occlusion. It also suggests that the integration of machine learning techniques may improve the performance of machine vision pose measurement algorithms. Overall, this review paper provides a comprehensive overview of machine vision pose measurement algorithms, their applications, and the factors that affect their accuracy and reliability. It provides a valuable resource for researchers and practitioners working in the field of computer vision.

Existing one-shot neural architecture search (NAS) methods have to conduct a search over a giant super-net, which leads to the huge computational cost. To reduce such cost, in this paper, we propose a method, called FTSO, to divide the whole architecture search into two sub-steps. Specifically, in the first step, we only search for the topology, and in the second step, we search for the operators. FTSO not only reduces NAS’s search time from days to 0.68 seconds, but also significantly improves the found architecture's accuracy. Our extensive experiments on ImageNet show that within 18 seconds, FTSO can achieve a 76.4% testing accuracy, 1.5% higher than the SOTA, PC-DARTS. In addition, FTSO can reach a 97.77% testing accuracy, 0.27% higher than the SOTA, with nearly 100% (99.8%) search time saved, when searching on CIFAR10.

This paper explores how Artificial Intelligence (AI) can help reduce the communication gap and streamline the distribution of resources. It uses an exploratory case study to examine the current state of the communication gap and the potential opportunities AI can bring to close it. The paper will discuss the current state of the communication gap, the current methods of resource distribution, and the potential opportunities AI can bring to reduce the communication gap. It will also explore the potential implications of AI on resource distribution and the communication gap. The paper will review the existing literature on the communication gap, resource distribution, and AI. It will then focus on the opportunities AI can bring to the communication gap. It will analyze the use of machine learning, natural language processing, and other AI-based technologies to reduce the communication gap. It will also examine the potential implications of AI on resource distribution, such as developing more efficient distribution channels, increasing transparency, and reducing costs. Finally, the paper will analyze the impact of AI on the communication gap and resource distribution. It will discuss the potential challenges and benefits of using AI, such as the need for data security, the potential for bias, and the limitations of AI technology. The paper will also explore the potential for AI to improve the distribution of resources and reduce the communication gap. Overall, this paper provides an exploratory case study on the opportunities of how AI can contribute to reducing the communication gap and streamlining the distribution of resources. It discusses the potential implications of AI on the communication gap and resource distribution, and it reviews the potential challenges and benefits of using AI. The paper provides an in-depth analysis of the potential opportunities of using AI to reduce the communication gap and streamline the distribution of resources.

This paper has the objective of implementing the radial rotor position control of a three-phase bearingless induction machine with split winding and optimized drive structure, using the ADRC technique. Because it is a multivariable, nonlinear, time-varying system with coupled variables, it is necessary to use advanced control strategies in order for the system to operate efficiently and with good dynamic performance. The ADRC controller considers the total disturbance composed of unmodeled dynamics, nonlinearities, uncertainties, and load variations, as a new system state, to be estimated in real-time through an extended state observer. In this mode, disturbances are compensated in real-time, eliminating regime errors and with good response to disturbances in general.

Coagulation is the most sensitive step in drinking water treatment. Underdosing may not yield the required water quality, whereas overdosing may result in higher costs and excess sludge. Traditionally, the coagulant dosage is set based on bath experiments performed manually. Therefore, this test does not allow real-time dosing control, and its accuracy is subject to operator experience. Alternatively, solutions based on machine-learning (ML) have been evaluated as a computer-aided alternative. Despite these advances, there is open debate on the most suitable ML method applied to the coagulation process, capable of the most highly accurate prediction. This study addresses this gap, where a comparative analysis between ML methods was performed. As a research hypothesis, a novel data-driven fuzzy inference system (FIS) should provide the best performance due to its ability to deal with uncertainties inherent to complex processes. Although ML methods have been widely investigated, only a few studies report hybrid neuro-fuzzy systems applied to coagulation. Thus, to the best of our knowledge, this is the first study thus far to address the accuracy of this novel data-driven FIS for such application. The novel FIS provided the smallest error (0.86), indicating a promising alternative tool for real-time and highly accurate coagulant dosing in drinking water treatment.

This work focused on the evaluation of some machine learning (ML) models and their application in e-health, using intermediate nodes within an Internet of Things (IoT) platform used for heartbeat anomaly detection. For the evaluation of ML models, a set of statistical validation metrics was selected. These metrics were applied in the training, testing and validation phases of the models. The results obtained can determine relevant factors for the selection of ML models, either based on the statistical and intrinsic efficiency of the ML models, or on their suitability to be implemented in intermediate nodes within an IoT platform. the more Lightweight models such as Simple Linear Regression, Logistic Regression, and K Nearest Neighbors, could easily operate in intermediate nodes, and they are models that require low processing and storage to work. In conclusion, the approach for intermediate nodes of Internet of Things platforms using cognitive networks decreases the processing cost in cloud computing and transfers it to the fog layer.

Impaired wound healing is a significant financial and medical burden. The synthesis and deposition of extracellular matrix (ECM) in a new wound is a dynamic process that is constantly changing and adapting to the biochemical and biomechanical signaling from the extracellular microenvironments of the wound. This drives either a regenerative or fibrotic and scar-forming healing outcome. Disruptions in ECM deposition, structure, and composition lead to impaired healing in diseased states, such as in diabetes. Valid measures of the principal determinants of successful ECM deposition include bacterial contamination, tissue perfusion, and mechanical injury and strain. These measures are used by wound-care providers to intervene upon the healing wound to steer healing toward a more functional phenotype with improved structural integrity and healing outcomes and to prevent adverse wound developments.In this review, we discuss bioengineering advances in non-invasive detection of biologic and physiologic factors of the healing wound, visualizing and modeling the ECM, and computational tools to efficiently evaluate the complex data acquired from the wounds to prognosticate healing outcomes and intervene effectively. We focus on bioelectronics and biologic interfaces of the sensors and actuators for real time biosensing and actuation. We also discuss high-resolution, advanced imaging techniques, which go beyond traditional confocal and fluorescence microscopy to visualize microscopic details of the composition of the matrix, linearity of collagen, and live tracking of components within the ECM. Computational modeling of the matrix, including partial differential equation datasets as well as machine learning models that can serve as powerful tools for physicians to guide their decision-making process are discussed.

The influence of the Madden - Julian Oscillation (MJO) on the intensity of the Tropical Cyclones in the North Indian Ocean is investigated through a machine learning algorithm using cyclone data from the Joint Typhoon Warning Centre and MJO from the Bureau of Meteorology, Australia during 1974–2019. The scatter index varies from 0.45 for depressions to 0.03 for the super cyclonic storms indicating that the MJO index is another parameter that should be investigated in cyclone studies.

Amyotrophic Lateral Sclerosis (ALS) is a prototypical neurodegenerative disease characterized by progressive degeneration of motor neurons to severely effect the functionality to control voluntary muscle movement. Most of the non additive genetic aberrations responsible for ALS make its molecular classification very challenging along with limited sample size, curse of dimensionality, class imbalance and noise in the data. Deep learning methods have been successful in many other related areas but have low minority class accuracy and suffer from the lack of explainailbilty when used directly with RNA expression features for ALS molecular classification. In this paper we propose a deep learning based molecular ALS classification and interpretation framework. Our framework is based on training a convolution neural network (CNN) on images obtained from converting RNA expression values into pixels based on DeepInsight similarity technique. Then we employed Shapley Additive Explanations (SHAP) to extract pixels with higher relevance to ALS classifications. These pixels were mapped back to the genes which made them up. This enabled us to classify ALS samples with high accuracy for a minority class along with identifying genes that might be playing an important role in ALS molecular classifications. Taken together with RNA expression images classified with CNN, our preliminary analysis of the genes identified by SHAP interpretation demonstrate the value of utilising Machine Learning to perform molecular classification of ALS and uncover disease-associated genes.

Documenting cultural heritage by using artificial intelligence (AI) is crucial for preserving the memory of the past and a key point for future knowledge. However, modern AI technologies make use of statistical learners that lead to self-empiricist logic, which, unlike human minds, use learned non-symbolic representations. Nevertheless, it seems that it is not the right way to progress in AI. If we want to rely on AI for these tasks, it is essential to understand what lies behind these models. Among the ways to discover AI there are the senses and the intellect. We could consider AI as an intelligence. Intelligence has an essence, but we do not know whether it can be considered “something” or “someone”. Important issues in the analysis of AI concern the structure of symbols -operations with which the intellectual solution is carried out- and the search for strategic reference points, aspiring to create models with human-like intelligence. For many years, humans, seeing language as innate, have carried out symbolic theories. Everything seems to have skipped with the advent of Machine Learning. In this paper, after a long analysis of history, the rule-based and the learning-based vision, we propose KERMIT as a unit of investigation for a possible meeting point between the different learning theories. Finally, we propose a new vision of knowledge in AI models based on a combination of rules, learning and human knowledge.

Using data-driven models to solve predictive maintenance problems has been prevalent for original equipment manufacturers (OEMs). However, such models fail to solve two tasks that OEMs are interested in: (1) Making the well-built failure prediction models working on existing scenarios (vehicles, working conditions) adaptive to target scenarios. (2) Finding out the failure causes, furthermore, determining whether a model generates failure predictions based on reasonable causes. This paper investigates a comprehensive architecture towards making the predictive maintenance system adaptive and interpretable by proposing (1) an ensemble model dealing with time-series data consisting of a long short-term memory (LSTM) neural network and Gaussian threshold to achieve failure prediction one week in advance and (2) an online transfer learning algorithm and a meta learning algorithm, which render existing models adaptive to new vehicles with limited data volumes. (3) Furthermore, the Local Interpretable Model-agnostic Explanations (LIME) interpretation tool and super-feature methods are applied to interpret individual and general failure causes. Vehicle data from Isuzu Motors, Ltd., are adopted to validate our method, which include time-series data and histogram data. The proposed ensemble model yields predictions with 100% accuracy for our test data on engine stalling problem and is more rapidly adaptive to new vehicles with smaller error following application of either online transfer learning or the meta learning method. The interpretation methods help elucidate the global and individual failure causes, confirming the model credibility.

Concrete is a heterogeneous material with a disordered material morphology that strongly governs the behavior of the material. In this contribution, we present a computational tool called the Concrete Mesostructure Generator (CMG) for the generation of ultra-realistic virtual concrete morphologies for mesoscale and multiscale computational modeling and simulation of concrete. Given an aggregate size distribution, realistic generic concrete aggregates are generated by a sequential reduction of a cuboid to generate a polyhedron with multiple faces. Thereafter, concave depressions are introduced in the polyhedron using gaussian surfaces. The generated aggregates are assembled into the mesostructure using a hierarchic random sequential adsorption algorithm. The virtual mesostructures are first calibrated using laboratory measurements of aggregate distributions. The model is validated by comparing the elastic properties obtained from laboratory testing of concrete specimens with the elastic properties obtained using computational homogenisation of virtual concrete mesostructures. Finally, a 3D-convolutional neural network is trained to directly generate elastic properties from voxel data.

The mechanical engineering requires heat treatment after rough machining to reach the mechanical strength, but the heat treatment can induce workpiece deformation, so that the workpiece cannot be reworked. In this study, the plasma was integrated with a lathe, and the on line heat treatment was performed to achieve the mechanical strength and hardness, so as to reduce the machining process and handling. However, for on line heat treatment, it is important to study the machine and plasma parameters of the lathe and plasma, and the research method is used eventually to optimize the process, reduce the machining cost and machining error. The variable factors in surface on line real-time heat treatment are revolution, feed rate and current, the objective function is the hardness of mechanical properties. In the screening experiment, the interaction of factors was discussed using full factorial experiment. The Central Composite Design was combined with the Lack-of-Fit test for optimization experiment, the R2 coefficient was used to determine whether the regression model is appropriate. The optimum parameters were derived from the contour diagram and response surface diagram. The experimental results show that the significant factors include revolution, feed rate and current, the optimum parameters include revolution 168rpm, feed rate 0.068mm/rev and current 86A. The experimental results of optimum parameters show that the surface hardness is increased from 306HLD to 806HLD, the surface hardening effect is enhanced by 163%, so the on line real-time heat treatment equipment has a best hardening effect.

Neural networks present the characteristics that the results are strongly dependent on the training data, the weight initialisation, and the hyper-parameters chosen. The determination of the distribution of a statistical estimator, as the Mean Squared Error (MSE) or the accuracy, is fundamental to evaluate the performance of a neural network model (NNM). For many machine learning models, as linear regression, it is possible to analytically obtain information as variance or confidence intervals on the results. Neural networks present the difficulty of being not analytically tractable due to their complexity. Therefore, it is impossible to easily estimate distributions of statistical estimators. When estimating the global performance of an NNM by estimating the MSE in a regression problem, for example, it is important to know the variance of the MSE. Bootstrap is one of the most important resampling techniques to estimate averages and variances, between other properties, of statistical estimators. In this tutorial, the application of two resampling (including bootstrap) techniques to the evaluation of neural networks’ performance is explained from both a theoretical and practical point of view. Pseudo-code of the algorithms is provided to facilitate their implementation. Computational aspects, as the training time, are discussed since resampling techniques always require to run simulations many thousands of times and, therefore, are computationally intensive. A specific version of the bootstrap algorithm is presented that allows the estimation of the distribution of a statistical estimator when dealing with an NNM in a computationally effective way. Finally, algorithms are compared on synthetically generated data to demonstrate their performance.

We discuss the implementation of a suite of virtual diagnostics at the FACET-II facility currently under commissioning at SLAC National Accelerator Laboratory. The diagnostics will be used for prediction of the longitudinal phase space along the linac, spectral reconstruction of the bunch profile and non-destructive inference of transverse beam quality (emittance) using edge radiation at the injector dogleg and bunch compressor locations. These measurements will be folded in to adaptive feedbacks and ML-based reinforcement learning controls to improve the stability and optimize the performance of the machine for different experimental configurations. In this paper we describe each of these diagnostics with expected measurement results based on simulation data and discuss progress towards implementation in regular operations.

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.

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.

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%.

The world has been evolving with new technologies and advances day-by-day. With the advent of various learning technologies in every field, the research community is able to provide solution in every aspect of life with the applications of Artificial Intelligence, Machine Learning, Deep Learning, Computer Vision, etc. However, with such high achievements, it is found to lag behind the ability to provide explanation against its prediction. The current situation is such that these modern technologies are able to predict and decide upon various cases more accurately and speedily than a human, but failed to provide an answer when the question of why to trust its prediction is put forward. In order to attain a deeper understanding into this rising trend, we explore a very recent and talked-about novel contribution which provides rich insight on a prediction being made -- ``Explainability.'' The main premise of this survey is to provide an overview for researches explored in the domain and obtain an idea of the current scenario along with the advancements published to-date in this field. This survey is intended to provide a comprehensive background of the broad spectrum of Explainability.

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.

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.

Facing with errors of a product after machining was a big title in this field. That will affect to product’s quality with unpredictable situation when products is in use for some particular application such as in medical facilities. Improving the precision of machine tools by exploring temperature on multiple points and measuring differential locations of the spindle is going to be executed in this study. A temperature measurement tool and a software running on Windows platform have been developed and combining with Non-bar system in order to support analyzing the temperature rising with the changes of length of the spindle to find the compensation solution based on eccentricity and length distortion. In this study, the whole tests have done on UX300 five – axis CNC machine tools for this investigation and the errors after applying compensation function have reduced 70% at least, with respect to the errors after machining without using compensation function.

Several optimization models of irreversible reverse cycle machines have been developed based on different optimization criteria in the literature, most of them using linear heat transfer laws at the source and sink. This raises the issue how close to actual operation conditions they are, since the heat transfer law on the phase-change processes is dependent on ΔT3. This paper addresses this issue by proposing a general model for study and optimization of thermal machines with two heat reservoirs applied to a Carnot-like refrigerator, with non-linear heat transfer laws and internal and external irreversibility. The optimization was performed using First and Second Law of Thermodynamics and Lagrange multipliers method. Thus, several constraints were imposed to the system, also different objective functions were considered, allowing finding the optimum operating conditions, as well as the limited variation ranges of the system parameters. Results show that the nature of the heat transfer laws affects the optimum values of system parameters for obtaining maximum performances and also their magnitude. Sensitivity studies with respect to system several parameters are presented. The results contribute to the understanding of the system limits in operation under different constraints and allow choosing the most convenient variables in given circumstances.

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.

The economic development and infrastructure of a nation are closely interrelated. In addition, public trust in national infrastructure facilities is closely linked to the preservation of the advantages provided by these facilities to the public. Since the 1970s, Korea has achieved exponential economic growth over a short period of time and the number of infrastructure facilities has increased correspondingly. This compressed economic development has been underpinned by the national infrastructure, whose safety and usability have been excluded from the scope of the development. However, after around 30 years, structural deterioration coupled with general insensitivity to safety in today’s society has considerably reduced public trust in using the infrastructure. Realistically, policies that mainly focus on developing new technologies related to infrastructure construction have led to practical limitations that discourage the development of technologies for maintenance or inspection. Furthermore, current maintenance works face certain limitations caused by various reasons: insufficient budget, increasing number of infrastructure facilities requiring maintenance, shortage of manpower, and rapidly increasing number of aging infrastructure facilities. To overcome these limitations, a new approach is required that is different from general inspection methods under the existing rules and regulations. In this context, this study aimed to explore the efficiency of bridge inspection and maintenance by unmanned aerial vehicles (UAVs) that could observe inaccessible areas, could be conveniently and easily controlled, and could offer high economic benefits. To this end, various tests were performed on elevated bridges, and suitable UAV images were obtained. The obtained UAV images were inspected by using machine vision technology, thereby excluding subjective evaluations by humans. Methods for enhancing the objectivity of the inspection were also discussed. The test results showed that both the efficiency and objectivity of the proposed method were better than those of the existing bridge maintenance and inspection methods.

This paper introduces a new rotor design for the easy insertion and removal of the rotor windings. The shape of the rotor is optimized based on surrogate method in order to achieve the lowest power loss under the maximum power output. The performance of the new rotor is examined in 2-D finite element software and validated by experiments. This rotor shows good potentials for reducing the maintenance and repair costs of synchronous machines, making it suitable for manufacturers within the mass production markets such as gen-sets, steam turbines, wind power generators and hybrid electric vehicles.

The land use land cover (LULC) map is extensively employed for different purposes. The LULC maps provided by the Portuguese National Geographic Information System (SNIG) are not ideal for continuous assessment and regular scrutiny. Machine learning (ML) algorithms applied in remote sensing (RS) data has been proven effective in image classification, object detection, and semantic segmentation. Previous studies have shown that Random Forest (RF) and Support Vector Machine (SVM) consistently achieved high accuracy for land classification. In this study, the application of RF and SVM classifiers, and object-based (OBIA) and pixel-based (PBIA) approaches with Sentinel-2A imagery was evaluated using Google Earth Engine (GEE) platform for land cover classification of a burned area in the Serra da Estrela Natural Park (PNSE), Portugal. This aimed to detect the land cover change and closely observe the burned area and vegetation recovery after the 2022 wildfire. The combination of RF and OBIA achieved the highest accuracy in all evaluation metrics. At the same time, a comparison with the Normalized Difference Vegetation Index (NDVI) map and Conjunctural Land Occupation Map (COSc) of 2023 year indicated that the SVM and PBIA map resembled the maps better.

In an era marked by digitization and automation, extracting relevant information from business documents, like electricity invoices, remains a major challenge. To address this, we need to use machine-learning techniques to automate the process, reduce manual labor, and minimize errors. This work introduces a new method for extracting key values from this type of invoice, including customer personal data, bill breakdown, electricity consumption, or marketer data. We evaluate several machine learning techniques, such as Naive Bayes, Logistic Regression, Random Forests, or Support Vector Machines. Our approach uses a bag-of-words strategy and custom-designed features specifically tailored for electricity data. We tested the method on the IDSEM dataset, which includes 75.000 electricity invoices with eighty-six different fields. The method converts PDF invoices into text and processes each word separately using a context of eleven words. The results of our experiments indicate that Support Vector Machines and Random Forests perform exceptionally well in capturing numerous values with high precision. The study also explores the advantages of our custom features and evaluates the performance of the model on unseen documents. The precision obtained with Support Vector Machines is 91,86%, peaking at 98,47% for one document template. These results demonstrate the effectiveness of our method in accurately extracting key values from invoices.

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.

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.

Soybean with insignificant differences in appearance have large differences in their internal physical and chemical components, therefore follow-up storage, transportation and processing require targeted differential treatment. A fast and effective machine learning method based on hyperspectral data of soybean for pattern recognition of categories is designed as a non-destructive testing method in this paper. A hyperspectral-image dataset with 2299 soybean seeds in 4 categories is collected; Ten features is selected by extreme gradient boosting algorithm from 203 hyperspectral bands in range 400 to 1000 nm; A Gaussian radial basis kernel function support vector machine with optimization by the Tree-structured Parzen Estimator algorithm is built as TPE-RBF-SVM model for pattern recognition of soybean categories. The metrics of TPE-RBF-SVM are significantly improved compared with other machine learning algorithms. The accuracy is 0.9165 in the independent test dataset which is 9.786% higher for vanilla RBF-SVM model and 10.02% higher than the extreme gradient boosting model.

Gaining insight into tribological systems is crucial for optimizing efficiency and prolonging operational lifespans in technical systems. Experimental investigations are time-consuming and costly, especially for reciprocating seals in fluid power systems. Elastohydrodynamic lubrication (EHL) simulations offer an alternative but demand significant computational resources. Physics-informed neural networks (PINNs) provide a promising solution using physics-based approaches to solve partial differential equations. While PINNs have successfully modeled hydrodynamics with stationary cavitation, they have yet to address transient cavitation with dynamic geometry changes. This contribution applies a PINN framework to predict pressure build-up and transient cavitation in sealing contacts with dynamic geometry changes. The results demonstrate the potential of PINNs for modeling tribological systems and highlight their significance in enhancing computational efficiency.

To make wind power more competitive, it is necessary to reduce turbine downtime and reduce costs associated with wind turbine Operation and Maintenance (O&amp;M). Incorporating machine learning in developing condition-based predictive maintenance methodologies for wind turbines can enhance their efficiency and reliability. This paper presents a monitoring method that utilizes Base Density for the Support Vector Machine (BDSVM) and the evolutionary Fourier spectra of vibrations. This method allows smart monitoring of the function evolution of the turbine. A complex optimal function (FO) for 5-degree order has been developed that will be the boundary function of the BDSVM to timely determine the magnitude, frequency, and place of the failure occurring in wind turbine drive.

Smart farm is a technology that greatly helps improve the productivity and quality of crops and is being actively introduced into indoor environments such as green houses. However, it has not yet been distributed to field-grown crops. The main reason is that, unlike indoor environments, it is very difficult to collect sensor data for monitoring the growth environment of crops in open fields where weather conditions change significantly and power supply is difficult. Additionally, because various sensors are used, the data formats of the devices are different, making it difficult to process. This paper presents a field crop growth environment monitoring and big data analysis system. The proposed system first solves power supply and data communication problems using solar power generation and LPWA technology. Additionally, based on the oneM2M architecture, data from various sensors is transmitted to the server using standardized technology. The transmitted data is stored and managed on the server as big data, and can be used to predict the production and quality of field-grown crops and take appropriate measures. The proposed system is expected to create an environment optimized for the growth of field crops and help prevent and manage diseases.

When using computer-aided translation systems in a typical, professional translation workflow, there are several stages at which there is room for improvement. The SCATE (Smart Computer-Aided Translation Environment) project investigated several of these aspects, both from a human-computer interaction point of view, as well as from a purely technological side. This paper describes the SCATE research with respect to improved fuzzy matching, parallel treebanks, the integration of translation memories with machine translation, quality estimation, terminology extraction from comparable texts, the use of speech recognition in the translation process, and human computer interaction and interface design for the professional translation environment. For each of these topics, we describe the experiments we performed and the conclusions drawn, providing an overview of the highlights of the entire SCATE project.

The zoonotic disease known as monkeypox, which is related to smallpox, can be difficult to diagnose since it resembles other illnesses that might cause the same symptoms. In this study, we present an accurate technique for monkeypox detection based on convolutional neural networks (CNNs). Our method improves diagnosis reliability by having the CNN model incorporate a dataset of nine important symptoms. For creating CNN-based monkeypox detection system, the researchers used a collection of high-definition photos and nine symptoms. The model was constructed using TensorFlow's Keras API and Python 3.10, classifying lesions based on a probabilistic score. A likelihood greater than 50% on CNN indicated that the case was really monkeypox. If not, five or more symptoms suggested that monkeypox may be present with metrics including accuracy, precision, recall, and F1-score. The study developed a CNN model to predict monkeypox from lesion images and symptom analysis. The model, built with layers including convolutional, pooling, and fully connected, achieved high accuracy and low loss, with metrics like ROC AUC (0.84), precision (0.78), and recall (0.90). The model effectively differentiates between monkeypox and other conditions. Tables illustrate the model's predictions based on various symptom combinations, highlighting its capability to assess monkeypox risk with high confidence. The study developed a CNN model integrating patient symptoms and skin lesion images for accurate monkeypox diagnosis. With a balanced accuracy of 82%, F1-Score of 84%, and sensitivity and specificity of 80% and 85%, respectively, the model effectively distinguishes monkeypox from similar illnesses. It demonstrated resilience despite limited high-resolution images, emphasizing the potential of CNNs in medical diagnosis. The model's performance can be further improved by incorporating additional data and advanced techniques, enhancing early detection in future outbreaks.

The increasing need for autonomy for space exploration missions is becoming more and more relevant in the design of missions to small bodies. The long communication latencies and sensitivity of the system to unplanned environment perturbations pose autonomous methods as a key design block for this type of mission. In this work, a fully autonomous gnc methodology is introduced. This methodolody relies on published cnn-based techniques for surface recognition and pose estimation and on also existing mpc-based techniques for the design of a trajectory to perform a soft landing on an asteroid. Combining hda with relative navigation systems, a gsm is built on-the-fly as images are acquired. These gsms provide the gnc system with information about feasible landing spots and populate a longitude-latitude map with safe/hazardous labels that are later processed to find an optimal landing spot based on mission requirements and a distance-from-hazard metric. The methodology is exemplified using Bennu as the body of interest and a gsm is built for an arbitrary reconnaissance orbit.

Wildfires increasingly threaten ecosystems and infrastructure, making accurate burn severity mapping (BSM) essential for effective disaster response and environmental management. Machine learning (ML) models utilizing satellite-derived vegetation indices are crucial for assessing wildfire damage; however, incorporating many indices can lead to multicollinearity, reducing classification accuracy. While Principal component analysis (PCA) is commonly used to address this issue, its effectiveness relative to other feature extraction (FE) methods in BSM remains un-derexplored. This study aims to enhance ML classifier accuracy in BSM by evaluating various FE techniques that mitigate multicollinearity among vegetation indices. Using composite burn index (CBI) data from the 2014 Carlton Complex fire in the United States as a case study, we extracted 118 vegetation indices from seven Landsat-8 spectral bands. We applied and compared 13 different FE techniques—including linear and nonlinear methods such as PCA, t-distributed stochastic neighbor embedding (t-SNE), linear discriminant analysis (LDA), Isomap, uniform manifold approximation and projection (UMAP), factor analysis (FA), independent component analysis (ICA), multidimensional scaling (MDS), truncated singular value decomposition (TSVD), non-negative matrix factorization (NMF), locally linear embedding (LLE), spectral embedding (SE), and neighborhood components analysis (NCA). The performance of these techniques was benchmarked against six ML classifiers to determine their effectiveness in improving BSM accu-racy. Our results show that alternative FE techniques can outperform PCA, improving classifica-tion accuracy and computational efficiency. Techniques like LDA effectively captured nonlinear relationships critical for accurate BSM. The study contributes to the existing literature by providing a comprehensive comparison of FE methods, highlighting the potential benefits of underutilized techniques in BSM

The revolution of physiotherapy is achieved by the application of artificial intelligence (AI) in medical rehabilitation programs. While the integration of virtual reality (VR) and robotics has already marked significant strides in the industry, AI is taking patient rehabilitation to new heights. The integration of AI, VR and robotics in physiotherapy linked to a significant leap forward in patient rehabilitation. These technologies not only increase the effectiveness of the treatment, but also make it more accessible and attractive. In this article, we propose to study the use of AI in the management of medical rehabilitation programs, and we present a comprehensive survey of the latest empirical studies, highlighting AI-based technologies that facilitate the rehabilitation process, trying to demonstrate that the integration of AI in medical rehabilitation programs offers a transformative approach to patient care.

One of the most hotly debated topics in technology is the transparency between AI models and humans. As artificial intelligence (AI) continues to permeate various sectors, the demand for transparency in AI decision-making has become increasingly critical. This paper presents a comprehensive review of Explainable Artificial Intelligence (XAI), examining 57 key studies that focusing on various explanation approaches and their impact on the trust and accountability of end-users. Recognizing the obstacles resulting from the black-box nature of AI models, this work focuses on the need for the proper methods that can be used in the explanation process, enabling both people and AI models to work together. The findings highlight the importance of XAI in enhancing trust, particularly in complex environments such as healthcare and finance, and propose directions for future research to further develop reliable and interpretable AI solutions.

Employee turnover is a significant issue for financial institutions, impacting productivity, increasing recruitment costs, and disrupting critical operations. In this project, this study aimed to predict employee turnover using a dataset containing attributes such as employee satisfaction, performance, and tenure. By framing the task as a binary classification problem, this study employed CatBoost and XGBoost, two advanced regression-based algorithms, to develop predictive models. This paper's analysis demonstrated that CatBoost outperformed XGBoost across all evaluation metrics, including MAE, MSE, RMSE, and R², making it the more effective model for predicting turnover in the financial sector. The study highlights key factors contributing to employee attrition, such as job satisfaction, tenure, and promotion opportunities, offering actionable insights for retention strategies. Additionally, by predicting probabilities rather than binary outcomes, this study aims to make more detailed decisions about employee retention. This research provides valuable tools for financial institutions to mitigate the risk of turnover, retain critical talent, and ensure operational continuity.

The rapid development of advanced AI technologies poses serious existential threats and necessitates research on safe and responsible Human-AI alignment. We hypothesize that the evolution of AI may be viewed not as something accidental or artificial, but as a natural part of the evolution of intelligence in living species. This perspective suggests a different view of the Human-AI relationship, where AI is not seen as a threat or a mere enhancement of humans, but as a mean of revealing and establishing true human nature — achieving greater freedom and self-determination. While in previous evolutionary stages, more freedom was attained through inculturation, AI can serve as a tool in the next stage by providing a direct connection between individuals and culture, overcoming the limitations of traditional cultural acquisition processes and giving rise to post-human free beings. A specific step-by-step framework rooted in cognitive evolution theories is proposed, along with potential directions for empirical research.

Deep-learning-based convection schemes receive wide attention due to its impressive im-provement on precipitation distribution and tropical convections of earth system simulation. But they cannot represent the stochasticity of moist physics, which will degrade the simulation of large-scale circulations, climate mean, and variability. To solve this problem, a stochastic pa-rameterization scheme based on probabilistic diffusion model named DIFF-MP is developed. The cloud-resolving data from GRIST model is coarse-grained into resolved-scale variables and sub-grid contributions due to moist physics to form the training data. DIFF-MP’s performance is compared against generative adversarial network and variational autoencoder. Results show that DIFF-MP is consistently better than the other two models on prediction error, coverage ratio, and spread-skill correlation. The standard deviation, skewness, and kurtosis of subgrid contributions generated by DIFF-MP is also closer to the testing data than the others. Interpretability experiment shows that DIFF-MP’s parameterization of moist physics is physically reasonable.

This study explores the industrial property market in Hong Kong, a sector characterized by its unique features and atypical market behaviour. Particularly, this research employs machine learning techniques to predict property prices based on a set of features, including location, square footage, floor level, accessibility to mass transit railway station and the like. To ensure transparency and understanding, the Shapley value is employed to quantify the relative importance of each feature in predicting property prices. Our analysis reveals the existence of non–linear relationships among these features, as demonstrated by the wide distribution of SHAP values for most features, which are illustrated in a beeswarm plot that span both sides of the baseline. This finding indicates a complex interaction among such features as square footage, age, floor level, carpark, proximity to mass transit railway stations, location, and property prices. The results contribute valuable insights into the relationships between industrial property characteristics and their corresponding values, thereby equipping stakeholders with enhanced understanding of the market to support informed decision–making.

This study investigates the possibility of using machine learning models created in DeepLabCut and Create ML to automate aspects of behavioral coding and aid in behavioral analysis. Two models with different capabilities and complexities were constructed and compared to a manually observed control period. The accuracy of the models was assessed before being applied to 7 nights of footage of the nocturnal behavior of two African elephants (Loxodonta africana). The resulting data was used to draw conclusions regarding behavioral differences between the two elephants and between individually observed nights, thus proving that such models can aid researchers in be-havioral analysis. The models were capable of tracking simple behaviors with high accuracy, but had certain limitations regarding detection of complex behaviors, such as the stereotyped behavior sway, and displayed confusion when deciding between visually similar behaviors. Further expansion of such models may be desired to create a more capable aid with the possibility of automating behavioral coding.

Artificial Intelligence (AI) and Machine Learning (ML) are rapidly advancing. These technologies have significantly impacted the consumer goods market, including the smart footwear industry. AI and ML are extensively utilized in the design and production of smart and agile footwear. There are various methods for manufacturing smart footwear, which can be categorized based on their applications. These include medical and healthcare smart footwear, assistive footwear for individuals with impairments, footwear designed for navigation in unfamiliar areas, foot-wear for studying foot movements and gait analysis, safety footwear, anti-skid footwear, foot-wear for the elderly, army shoes, and energy-harvesting footwear, among others. These smart shoes enable real-time patient monitoring and provide appropriate suggestions for their care. Additionally, smart footwear can be classified based on the tools and techniques used in their production, as well as the sensors and Internet of Things (IoT) devices integrated into them. This paper reviews the various tools and techniques used in the creation of smart footwear for dif-ferent applications.

The continuous expansion of Large Language Models (LLMs) has significantly transformed the fields of artificial intelligence (AI) and natural language processing (NLP). This paper reviews the rapidly evolving domain of language models and introduces the concept of Extremely Large Language Models (XtremeLLMs), a new category defined for models exceeding one trillion parameters. These models are monumental in scale and engineered to enhance performance across a diverse range of language tasks. This study aims to establish a comprehensive framework that explores the significant opportunities and complex challenges presented by such extensive scaling and emphasises the implications for future advancements in the field.

Recurrent Neural Networks (RNNs) have significantly advanced the field of machine learning by enabling the effective processing of sequential data. This paper provides a comprehensive review of RNNs and their applications, highlighting advancements in architectures such as Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRUs), Bidirectional LSTM (BiLSTM), and stacked LSTM. The study examines the application of RNNs in different domains, including natural language processing (NLP), speech recognition, financial time series forecasting, bioinformatics, autonomous vehicles, and anomaly detection. Additionally, the study discusses recent innovations, such as the integration of attention mechanisms and the development of hybrid models that combine RNNs with convolutional neural networks (CNNs) and transformer architectures. This review aims to provide machine learning researchers and practitioners with a comprehensive overview of the current state and future directions of RNN research.

Anxiety in older individuals is understudied despite its prevalence. Investigating its occurrence can be challenging, yet understanding the factors influencing its recurrence is important for improved management. This study aimed to model the recurrence of anxiety symptomatology in an older population within a five-month timeframe. Data included baseline socio-demographic and general health information for older adults aged 60 years or older with at least mild depressive symptoms. A Bayesian network model explored the relationship between baseline data and recurrent anxiety symptomatology. Model evaluation employed the Area Under the Receiver Operating Characteristic Curve (AUC). The Bayesian model was also compared to three machine learning models. The model achieved an AUC of 0.821 on the test data, using a threshold of 0.367. This result surpassed both the Logistic Regression and XGBoost models, but slightly behind SGDClassifier. Key factors associated with recurrence of anxiety symptomatology were: “Not being able to stop or control worrying”; “Becoming easily annoyed or irritable”; “Trouble relaxing”; and “depressive symptomatology severity”. The model demonstrated generalisation abilities and outperformed some machine learning models while being less complex and more explainable. These findings indicate a prioritised sequence of predictors to identify individuals most likely to experience recurrent anxiety symptomatology.

Groundwater is becoming increasingly important in the Pacific Northwest of the USA due to declining snowpack volumes and shifts in precipitation type and timing, all connected with climate change. The Upper Williamson Basin of the Klamath Watershed is a groundwater dominated watershed with massive fluctuations in year-to-year streamflow volumes over the past four decades, including the complete absence of any live flow for several years. The precise relationship between groundwater and streamflow in the basin has been difficult to assess due to a limited number of monitoring wells and significant gaps in the water level time history. To address this challenge, we use a novel imputation technique that leverages Earth observations and machine learning to impute gaps in water level records. We use these more complete datasets to compute a groundwater storage change time series for the basin. We show that groundwater storage is highly correlated to streamflow and that groundwater storage is correlated to rainfall with a three- to four-year delay that appears variable depending on groundwater storage volumes. The tools and relationships we present make it possible for water managers to estimate when streamflows will return to the basin and be more informed to support better management.

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.

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.

This paper presents the formative assessment to implement mobile portable chest X-ray (PDX) machines for Tuberculosis (TB) contact tracing in Oyo and Osun States, Nigeria. This descriptive qualitative study was carried out in 8 Local Government Areas, and 24 FGDs and 33 KIIs were conducted using a 4-stage sampling technique to select participants. Validated transcribed notes were entered and analysed using Nvivo. The respondents' ages ranged from 17-85 years, with a mean age of 42.08±14.9 years, and 4.0% had a postgraduate degree. The majority of the government officials stated that deploying the PDX machine intervention at the community level is the best means as it offers a level of convenience to the community members in the sense that there will be limited disruption to their daily activities as well as zero concerns about the cost of transportation to the health facility. The portable X-ray machine intervention should be implemented at the community level for contact tracing to allow more TB contacts living with the index patient to be screened. However, the PDX machine can also be set up in a special location, and the TB contacts can be invited for the screening.

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.

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.

To address the problems of insufficient semantic fusion between text and questions and the lack of consideration of global semantic information encountered in machine reading comprehension models, we proposed a machine reading comprehension model called BERT_hybrid based on BERT and hybrid attention mechanism. In this model, BERT is utilized to separately map the text and questions into the feature space. Through the integration of Bi-LSTM, attention mechanism, and self-attention mechanism, the proposed model achieves comprehensive semantic fusion between text and questions. The probabilities distribution of answers is computed using Softmax. Experimental results on the public dataset DuReader demonstrate that the proposed model achieves improvements in BLEU-4 and ROUGE-L scores compared to existing models. Furthermore, to validate the effectiveness of the proposed model design, we analyze the factors influencing the model’s performance.

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.

Intrusion Detection Systems play a crucial role in a network. They can detect different network attacks and raise warnings on them. Machine learning-based IDSs are trained on datasets that, due to the context, are inherently large, since they can contain network traffic from different time periods and often include a large number of features. In this paper, we present two contributions: the study of the importance of feature selection when using an IDS dataset, while striking a balance between performance and the number of features; and the study of the feasibility of using a low-capacity device, the Nvidia Jetson Nano, to implement an IDS in a low-capacity network. The results, comparing the GA with other well-known techniques in feature selection and reduction, show that the GA has a higher F1-score of 76%, although the time to find the optimal set of features surpasses other methods; the reduction of the number of features reduces the processing time without a significant impact in f1-score. The Jetson Nano allows the classification of network traffic with an overhead of 10 times in comparison to a traditional server.

The blood counts of α thalassemia carriers (α-thal) are similar to those of β thalassemia carriers, except for Hgb A2 that is not elevated. The objective of this study was to determine whether mathematical formulas are effective for detecting suspected α-thal. The data were obtained from the database of the prevention program for detecting couples at risk for having a child with hemoglobinopathy. RBC indices were analyzed using mathematical formulas and the sensitivity and negative predictive value (NPV) calculated. Among 1334 blood counts suspected α-thal analyzed, only the Shine&Lal and the Support Vector Machine formulas revealed high sensitivity and NPV. Sensitivity was 85.54 and 99.33% and NPV 98.93 and 99.93%, respectively. Molecular defects were found in 291, 81 had normal α genes. Molecular analysis was not performed in 962. Based on these results, mathematical formulas incorporating one of these reliable formulas for detecting suspected α or β thalassemia carriers in the program of the automatic analyzers can flag these results and increase the awareness of the primary physicians about the carrier risk and send an alert with a recommendation for further testing.

One route to reducing CO2 emissions is to improve the energy efficiency of machines. For example, conventional combustion engines are being downsized (and down-speeded), are now running on lower viscosity engine lubricants (such as SAE 0W-20 or lower viscosity grades) and often also have stop-start systems fitted (to prevent engine idling when the vehicle is stopped). Some of these changes result in higher levels of mixed and boundary friction, and so accurate estimation of mixed/boundary friction losses is becoming of increased importance, both for estimating friction losses, and also for estimating wear volumes. Traditional approaches to estimating mixed/boundary friction, which employ real area of contact modelling such as the Greenwood-Tripp model [1] are widely used, but recent experimental data suggests that these approaches underestimate mixed/boundary friction losses [2-5]. A new model has been developed, based on experimental data, which estimates the proportion of mixed/boundary lubrication, X, as a function of the value (where is the ratio of the oil film thickness separating the surfaces to the combined root mean square surface roughness of the interface surfaces). The precise equation that describes the way in which X varies with takes the form of a “reverse S-curve”, which makes physical sense since S-curves arise naturally in growth processes, and in mixed/boundary lubrication, the real area of contact of rough surfaces grows as the load (and 1/) increases. Numerical estimates of mixed/boundary lubrication losses in internal combustion engines are presented here and compared with published data [2,6]. In addition, the improved method described here is used to estimate both the financial cost of mixed/boundary lubrication for today’s passenger car fleet, and the CO2 emissions associated with these friction losses.

The article presents the operation of the automatic pine sawn timber inspection system, which was developed at the Woodinspector company and offered commercially. The vision inspection system is used to detect various wood defects, including knots, blue stain, and mechanical damage caused by worms. Blue stain is a defect that is difficult to detect based on the color of the wood, because it can be easily confused with wood defects or dirt that do not impair its strength properties. In particular, the issues of detecting blue stain in wood, the use of artificial neural networks and improving the operation of the system in production conditions were discussed.

Heart failure is a leading cause of death among people worldwide. The cost of treatment can be prohibitive, and early prediction of heart failure would reduce treatment costs to patients and hospitals. Improved prediction of readmission would also be of great help hospital, allowing them to better manage their treatment programs and budgets. This systematic review aims to summarize recent studies of predictive analytics models that have been constructed to predict heart failure and readmission. Some of these models use a statistical approach and others a machine learning approach. Electronic patient health records, including demography, physical and clinical values, and laboratory findings are used to design and build predictive models. Predictive analytics with good performance have become essential for clinicians and specialists. Choosing a suitable machine learning algorithm and data preprocessing technique will improve predictive model performance, including data imputation and class imbalance.

Machine learning models facilitate the search for non-linear relationships when modeling hydrological processes, but they are equally effective for automation at the data preparation stage. The tasks whose automation was analyzed consisted in estimating changes in the roughness of a mountain streambed and the extent of floods from images. The Segment Anything Model (SAM) developed this year by Meta was used for this purpose. Images from many years from the Wielka Puszcza mountain stream located in the Polish Carpathians were used as the only input data. The model was not additionally trained for the described tasks. The model can be run in several modes, but the two most appropriate were used in this study. The first one is available in the form of a web application, while the second one is available in the form of a Jupyter notebook run in the Google Colab environment. Both methods do not require specialized knowledge and can be used by virtually any hydrologist. In the roughness estimation task, the average Intersection over Union (IoU) ranges from 0.55 for grass to 0.82 for shrubs/trees. Ultimately, it was possible to estimate the roughness coefficient of the mountain streambed between 0.027 and 0.059 based solely on image data. In the task of estimation of the flood extent, when selecting appropriate images, one can expect IoU at the level of at least 0.94, which seems to be an excellent result considering that SAM is a general-purpose segmentation model. It can therefore be concluded that SAM model can be a useful tool for a hydrologist.

Ransomware constitutes a distinctive category of pernicious software that sequesters a user's digital assets by encryption, holding them hostage until a sum is extorted from the victim. These incursions have escalated to become among the most prevalent and significant threats confronting both individuals and corporate entities. In combatting this virulent program, dynamic analysis has been established as the favored detection modality. Such analyses typically hinge on Windows API calls, the conduits through which programs requisition services from the operating system. Yet, the superfluous and unrelated Windows API calls interjected by adversaries into the execution stream of suspect binaries precipitate an excessively noisy behavioral sequence, which impairs the performance of counter-ransomware mechanisms. The research outlined herein introduces a novel non-signature-based detection paradigm that harnesses efficacious Windows API call sequences through supervised machine learning strategies. An innovative Enhanced Min Max (EmRmR) filter technique is proposed, aiming to purge noisy features and isolate the most indicative feature subset that encapsulates the ransomware's true behavior. The EmRmR method, diverging from the traditional Min Max approach, circumvents the superfluous calculations that are a hallmark of the conventional algorithms, thereby necessitating a reduced number of evaluations. Additionally, a refinement procedure has been integrated to contract the program's call trace volume by discarding those Windows API calls lacking a robust correlation with ransomware's pivotal behavior. Subsequent to rigorous experimental analyses and juxtaposition with extant behavior-based detection methodologies, the proposed strategy has demonstrated its efficacy in differentiating ransomware behavior, delivering high detection precision alongside a diminution in false-positive occurrences.

Autonomous Driving (AD) has become a prominent research area in the field of Artificial Intelligence (AI) and Machine Learning (ML) in recent years. This opens the door wider for self-driving cars to surpass conventional vehicles in the current market share. Despite its apparent simplicity, AD is composed of complex and heterogeneous systems, which are in need of a high level of coordination and alignment to ensure both full automation and safety. Therefore, numerous research studies have been conducted over the last few years to facilitate such coordination and accelerate the capacity of these types of vehicles to be self-managed in complex situations. The paper summarises these approaches that led to building what is known nowadays as the autonomous driving pipeline. Moreover, although skepticism exists regarding the practicality of AD as a viable alternative to traditional vehicles, extensive research suggests the multiple benefits of relying on them for mobility. While challenges remain in implementing AD in the real world, including regulation and technical issues, substantial progress in recent years indicates a growing acceptance of AD in the near future. This paper further explores the advantages and opportunities of the conducted such systems in facilitating the practicality of Autonomous Driving.

The precipitation, flocculation, and deposition of asphaltene cause severe formation damage within a reservoir and shorten a well’s productive life. Pressure depletion is one factor that contributes to asphaltene precipitation during production; therefore, the first step in managing asphaltene is to determine the onset pressure of the precipitation. While there are numerous equation of state models that can be used to predict the onset pressure, these models are complex and heavily reliant on tuning parameters. Using multivariate linear regression, this work attempts to develop a simple and accurate thermodynamic model for predicting the upper precipitation onset pressure under pressure depletion above the bubble point pressure (Pb) at various temperatures. A total of 94 experimental data points from 37 published crude oil data sets were compiled from the literature. To develop the model, 59 experimental data points were used as training data and 35 experimental data points as testing data. According to the results of the multicollinearity test, the bubble point pressure, temperature, resins, and saturate-to-aromatic ratio were chosen as predictors. The upper onset pressure data with comparable trends were clustered, and unsupervised recognition of three distinct cluster groups was performed. For each cluster identified, a multivariate linear regression model was developed. The model was chosen based on Mallow’s coefficient of determination (Cp), adjusted R² (statistical measure of fit), and S (standard error of the regression slope). The developed model was tested using a data set, and the results showed an adjusted R² of 96.25%, with a mean absolute error of 4.1%. The model was randomly applied to 15 data points to compare it to perturbed-chain statistical associated fluid theory (PC SAFT) and the Peng-Robinson equation of state models and to the multivariate regression models of Fahim (2007) and Ameli et al. (2016). The results showed that the mean absolute error for predicting the asphaltene precipitation onset pressure was 2.82% using Peng-Robinson, 2.36% using the PC SAFT equation of state, 23.96% using the Fahim model, 24.80% using the model reported by Ameli et al., and 2.39% using the newly developed multivariate regression model. The developed multivariate model appears to be as accurate as the PC SAFT equation of state modeling with tuning parameters. The primary advantage of multivariate regression is that, unlike the PC SAFT equation of state model, it does not require saturates, aromatics, resins, and asphaltenes (SARA)-based characterization methodologies or rigorous parameter tuning. It is simple to use, quick, and it produces results in a short period of time.

Cybersecurity plays a relevant role in the new digital age in aerospace industry. Predictive algorithms are necessary to interconnect complex systems within the cyberspace. In this context, where security protocols do not apply, challenges to maintain data privacy and security arise for the organizations. Thus, the need of cybersecurity is required. The four main categories to classify threats are interruption, fabrication, modification and interception. They all share a common thing, soften the three pillars which cybersecurity needs to guarantee. These pillars are confidentiality, availability and integrity of data (CIA). Data injection can contribute to this event by creation of false indicators which can lead to errors creation during the manufacturing engineering process. In this paper, the impact of data injection on existing dataset used on manufacturing process is shown. The design model synchronizes the following mechanisms developed within machine learning techniques which are, the risk matrix indicator to assess the probability of producing an error, the dendrogram to clusters the dataset in groups with similarities, the logistic regression to predict the potential outcomes and the confusion matrix to analyze the performance of the algorithm. The results presented in this study, which was carried out using a real dataset related to the electrical harnesses installed in a C295 military aircraft, estimate that injection of false data indicators increase the probability of errors creation in 24.22 % on the predicted outcomes required for the generation of the manufacturing process. Overall, implementing cybersecurity measures and advanced methodologies to detect and prevent cyberattacks are necessary.

The Dst index is the geomagnetic storm index used to measure the energy level of geomagnetic storms, and the prediction of this index is of great significance for the geomagnetic storm study and the solar activity. In contrast to traditional numerical modelling techniques, machine learning, which has emerged in decades ago based on rapidly developing computer hardware and software and artificial intelligence methods, has been unprecedentedly developed in geophysics, especially solar-terrestrial space physics. This study chooses two machine learning models, the LSTM (Long-Short Time Memory, LSTM) and EMD-LSTM model (Empirical Mode Decomposition, EMD), to model and predict the Dst index. By building the Dst index data series from 2018-2023, two models were built to fit and predict the data. Firstly, we evaluated the influences of the learning rate and the amount of training data on the prediction accuracy of the LSTM model, and finally, 10-3 was thought as the optimal learning rate; secondly, the two models were used to predict the Dst index in the solar active and quiet periods, respectively, and the RMSE (Root Mean Square Error) of the LSTM model in the active period is 7.34 nT, the CC (correlation coefficient) is 0.96, those of the quiet period are 2.64nT and 0.97; the RMSE and r of EMD-LSTM model are 8.87nT and 0.93 in active time and 3.29nT and 0.95 in the quiet time. Finally, the prediction accuracy of the LSTM model in short time period is slightly better than the EMD-LSTM model. However, there will be a problem of prediction lag, which the EMD-LSTM model can then solve, and can better predict the geomagnetic storm.

Snow parameters have traditionally been retrieved using discontinuous, multi-band sensors; however, continuous hyperspectral sensor are now being developed as an alternative. In this paper we investigate the performance of various sensor configurations using machine learning neural networks trained on a simulated dataset. Our results show improvements in accuracy of retrievals of snow grain size and impurity concentration for continuous hyperspectral channel configurations. Retrieval accuracy of snow albedo was found to be similar for all channel configurations.

Tracking temperature changes in certain geographic regions is a current task in modern research on Earth's climate changes. One of the global problems in solving this task is related to the large volume of measured data and the search for appropriate methods for effective determination of changes. The purpose of this research is to track climate temperature changes using a machine learning-based automated change detection method. The presented method includes training of a two-level structure of neural networks, with measured temperatures for a ten-year period of time for a certain geographical region. In the testing phase, the neural structure classifies measured temperatures for two three-year periods, before and after the ten-year time period, respectively, for the same geographic region. An algorithm was developed to visualize the studied regions by creating a map with their geographic coordinates. The classification results in the neural structure outputs are presented and analyzed as possible temperature changes. Suggestions for continuing and expanding the research in the future are discussed.

Low-resource languages often face the problem of insufficient data, which leads to poor quality in machine translation. One approach to address this issue is data augmentation. Data augmentation involves creating new data by transforming existing data through methods such as flipping, cropping, rotating, and adding noise. Traditionally, pseudo-parallel corpora are generated by randomly replacing words in low-resource language machine translation. However, this method can introduce ambiguity as the same word may have different meanings in different contexts. This study proposes a new approach for low-resource language machine translation, which involves generating pseudo-parallel corpora by replacing phrases. The performance of this approach is compared with other data augmentation methods, and it is observed that combining it with other data augmentation methods further improves performance. To enhance the robustness of the model, R-Drop regularization is also used. R-Drop is an effective method for improving the quality of machine translation. The proposed method was tested on Chinese-Kazakh (Latin script) translation tasks, resulting in performance improvements of 4.99 and 7.7 for Chinese-to-Kazakh and Kazakh-to-Chinese translations, respectively.

Recent advances in mathematical modelling and artificial intelligence have challenged the use of traditional regression analysis in biomedical research. This study examined artificial and cancer research data using binomial and multinomial logistic regression and compared its performance with other machine learning models such as random forests, support vector machines, Bayesian classifiers, k-nearest neighbours and repeated incremental clipping (RIPPER). The alternative models often outperformed regression in accurately classifying new cases. Logistic regression had a structural problem similar to early single-layer neural networks, which limited its ability to identify variables with high statistical significance for reliable class assignment. Therefore, regression is not always the best model for class prediction in biomedical datasets. The study emphasises the importance of validating selected models and suggests that a mixture of experts approach may be a more advanced and effective strategy for analysing biomedical datasets.

: Innovative solutions are now being researched to manage the ever-increasing amount of data required to optimize the performance of internal combustion engines. Machine Learning ap-proaches have shown to be a valuable tool for signal prediction due to their real-time and cost-effective deployment. Among them, the architecture consisting of Long Short-Term Memory (LSTM) and one-dimensional Convolutional Neural Networks (1DCNN) has emerged as a highly promising and effective option for replacing the role of physical sensors. The architecture com-bines the capacity of LSTM to detect patterns and relationships in smaller segments of the signal with the ability of 1DCNN to detect patterns and relationships in larger segments of the signal. The purpose of this work is to assess the feasibility of substituting a physical device dedicated to calculating the torque supplied by a spark-ignition engine. The suggested architecture was trained and tested using signals from the field during a test campaign conducted under transient operating conditions. The results reveal that LSTM+1DCNN is particularly well suited for signal prediction with considerable variability. It constantly outperforms other architectures used for comparison, with average error percentages of less than 2%, proving the architecture's ability to replace physical sensors.