Search

Android has been a significant target of malware applications due to the exponential growth of mobile devices. This may result in severe threats to Android users such as financial loss, information leakage etc. The security of smartphones has encouraged the researchers in applying machine learning techniques to enhance the Android malware detection rate as the traditional approaches are not effective in distinguishing unknown malware. In recent years, many malicious apps have been detected on Android devices using machine learning based approaches. The problem with these detection systems is that they give a high false positive and false negative rate. Therefore, it is imperative to develop methods for better identifying and classifying malware. The main contribution of this paper is to improve the classification accuracy by fusing the base classifiers. This paper proposes a fusion approach named as MalDetect that enables an effective combination of machine learning techniques to improve the identification rate of malware. The proposed approach is based on the base classifiers and a set of ranking algorithms defined on their predictive error rate. The purpose of this method is to improve the detection rate of Android malware. Two datasets i.e. Drebin and AndroMD are used to illustrate the effectiveness of the proposed approach. Experimental results show that the proposed approach performs better than the individual base classifiers and traditional ensemble learning techniques for identifying Android malware. Further, the proposed approach is compared with the renowned Stacking ensemble technique that uses a meta -classifier. From the experimental outcomes, it is found that the weighted F-measure obtained from the Stacking for Drebin and AndroMD datasets is 0.9811 and 0.9775 respectively whereas the weighted F-measure acquired from the proposed approach is 0.9857 and 0.9790 respectively. [ABSTRACT FROM AUTHOR]

Epilepsy is one of the most paramount neurological diseases, affecting about 1% of the world's population. Seizure detection and classification are difficult tasks and are ongoing challenges in biomedical signal processing to enhance medical diagnosis. This paper presents and highlights the unique frequency and amplitude information found within multiple seizure types, including their morphologies, to aid the development of future seizure classification algorithms. Whilst many published works in the literature have reported on seizure detection using electroencephalogram (EEG), there has yet to be an exhaustive review detailing multi-seizure type classification using EEG. Therefore, this paper also includes a detailed review of multi-seizure type classification performance based on the Temple University Hospital Seizure Corpus (TUSZ) dataset for focal and generalised classification, and multi-seizure type classification. Deep learning techniques have a higher overall average performance for focal and generalised classification compared to machine learning techniques, whereas hybrid deep learning approaches have the highest overall average performance for multi-seizure type classification. Finally, this paper also highlights the limitations of the TUSZ dataset and suggests some future work, including the curation of a standardised training and testing dataset from the TUSZ that would allow a proper comparison of classification methods and spur advancement in the field. [ABSTRACT FROM AUTHOR]

Every day, humans make hundreds of decisions, most of which are based on information we gather from our surroundings. The majority of this perception when it comes to driving is visual. Autonomous vehicles that are capable of recognizing items around them and making quick decisions in response to these impulses are self-driving cars. Self-driving cars are the main concern and an emerging subject for every automobile giant in the world. Death due to human failure in a road accident increases with every passing month and with technology assisting humans in every possible field, it is essential to prioritize road safety with it. In a thorough investigation of traffic safety, it was discovered that human error was the sole cause of 57% of accidents and a contributory factor in more than 90% of them. In comparison, only 2.4% of crashes were the result of a mechanical issue, and 4.7% were the result of environmental variables alone. Autonomous cars not only help reduce human errors while driving but also help in reducing driver's fatigue to a greater extent. This study examines the work of a number of scholars in order to provide a quick summary of how computer vision is being used in autonomous cars today. Previous research has shown the use of deep learning algorithms with the help of LiDAR sensors but they come with the problem of being relied on costly hardware. This paper focuses on the vertical and lateral movement of the car while using a more budget friendly yet effective option using just simple computer vision algorithms like Color space transformation, Canny edge detection and Hough line transformation to make the car detect lane lines and steering the car so that it remains bound to them. Simple computer vision requires less operational hardware which indicates that using cost effective boards like Raspberry Pi and Nvidia Jetson Nano can yield much more powerful results. The paper also highlights the reconstruction of a ready-made remote-controlled car that helps understanding autonomous cars even better. [ABSTRACT FROM AUTHOR]

In the 5G smart grid, battery liquid leakage negatively affects the safe storage and transportation of electricity. Image edge detection help locate the liquid leakage phenomenon. This paper proposes a digitalization-based algorithm that converts the image to the codeword and judges the edge by the code weight. Its main steps are image sampling, quantization, coding and judging. Compared with traditional Sobel and Canny operators, the algorithm dramatically enhances detection ability with machine learning. Moreover, this paper applies the algorithm to detect the leakage of infrared battery images in the 5G smart grid; The results show that it can accurately extract the liquid leakage location, improving fault diagnosis and early risk warning. [ABSTRACT FROM AUTHOR]

Financial time series prediction has many applications in economics, but producing profitable strategies certainly has a special place among them, a daunting challenge. Statistical and machine learning techniques are intensively researched in the search for a holy grail of stock markets forecasting. However, it is not clear to prospecting researchers how good those popular models are regarding useful predictions on a real scenario. This paper contributes to that discussion, providing decisive evidences contrary to the use of basic out-of-the-box models, specifically Artificial Neural Networks (ANN), Support Vector Machines (SVM), Random Forest (RF) and Naive-Bayes (NB). Results consider optimistic and unreal variables often found in literature, as well as a more close-to-real simulation of the models usage. Specifically, current day closing prices direction forecasting results are contrasted with those on next day forecasts. As expected, when forecasting the current day, accuracy is almost perfect. However, when used to forecast next day closing direction, with a strict data separation policy and without direction or snooping bias, ANN, SVM, RF and NB produce results essentially equal to random guessing. The main achieved result is the demonstration of how a machine learning approach would fare in a support decision system for forecasting short-term future market direction, regardless of the level of market development, considering more than 100 securities in a 10 years period. Consequences for algorithmic trading relate to discouraging usage of the considered models as implemented here. On a more abstract sense, this paper presents more evidence to the Efficient Market Hypothesis (EMH). [ABSTRACT FROM AUTHOR]

Automatic fault diagnosis in many systems is performed via the analysis of vibration data in the time or frequency domain. In the literature, many approaches for extracting featured from signals for fault diagnosis have been proposed. In this paper, we apply a variety of transform functions including Fourier, Wavelet, etc. to extract features from the vibration data, which includes the statistical features and some features automatically extracted via Convolutional Neural Networks (CNNs). For each of these feature extraction approaches, a learning algorithm is trained to diagnose the faults and their results are aggregated in an ensemble machine learning algorithm. The weights of the base learner algorithms are optimized via an evolutionary algorithm to achieve the best-weighted voting scheme. The architecture of CNNs has a significant effect on the performance of the algorithm, thus, in this paper, an evolutionary algorithm is proposed to find the best architecture for CNNs in fault diagnosis. The CNNs are trained via gradient descent algorithms which suffer from getting stuck in local optima. To manage this, we propose an evolutionary algorithm that benefits from the speed of gradient descent and the global search of evolutionary algorithms. The proposed algorithm is tested on a number of benchmark problems and the experimental results are presented. • An ensemble algorithm is proposed for fault diagnosis. • Different feature extractors are exploited. • An evolutionary training algorithm is proposed. [ABSTRACT FROM AUTHOR]

In this paper we investigate the role of self-learning agents in multi-agent models of financial markets. We develop an agent-based simulation model of a financial market and, in addition to the agents with fixed strategies used in previous research, we introduce an agent with a self-learning strategy. To model the behavior of such an agent, we use deep reinforcement learning algorithms, namely deep deterministic policy gradient (DDPG). Next, we conduct a comparative analysis of the results of the constructed model with outcomes of previously proposed models, as well as with the characteristics of real market. To conduct comparative analysis, we use stylized facts of asset returns that allow us to evaluate and compare the characteristics of the markets. Our results show that a model with a self-learning agent gives a better approximation of the real market than a model with classic agents. In particular, unlike the model with classical agents, the model with a self-learning agent turns out to be not so heavy-tailed. Thus, we demonstrate that for a complete understanding of market processes simulation models should take into account self-learning agents that have a significant presence at modern financial markets. Finally, we present the python package 1 1 https://github.com/Kiri28/Agent-Based%5fMarket%5fsimulator. , which was developed by us as part of the research implementation. This package allows to simulate the financial market, as well as create your own agents and evaluate their impact on the market. • The paper explores the role of self-learning agents in modern financial market models. • We use stylized facts based analysis to compare simulated markets with each other. • Using a comparative analysis, we show that our model better describes real markets. • The paper provides our Python package for simulating financial markets. [ABSTRACT FROM AUTHOR]

Applying machine learning (ML) methods to multi-factor authentication is becoming increasingly popular. However, there is no comprehensive methodology to evaluate biometric systems based on machine learning in the literature. This paper proposes a general methodology for evaluation the ML-based systems for impostor recognition/detection using biometric traits. This includes creation of learning and testing sets with appropriate size balance (proportion) between these sets, selecting the number of instances coming from different users, evaluation of the influence of the impostors number on their detection rate, and the impact of the number of records representing user's behavior. In addition, we propose how the real data (possibly affected by account takeover attempts) could be used to extend the enrollment data to support the impostor detection. The proposed approach was used for a systematic comparison of an extensive set of ML and statistical methods. For some of them, the false acceptance rate (FAR) close to zero and false rejection rate (FRR) smaller than 0.05 in a supervised experiment were accomplished, proving the merit of certain ML-based approaches. Moreover, using the method proposed in the paper, a classifier trained on experimental data achieved FAR below 0.05 on the real-world data collected at an actual financial web page. • General methodology for evaluating ML impostor recognition using biometric traits. • Evaluation of the influence of the impostors number on their detection rate. • Evaluation of the impact of the number of records representing user's behavior. • The proposed approach tested on ML methods reaching FAR and FRR smaller than 0.05. • Test-bed trained classifier achieved FAR < 0.05 on data from financial service. [ABSTRACT FROM AUTHOR]

Fake news refuting is an essential part of online social networks (OSNs) management. Identifying the potential voluntary fake news refuters who can spontaneously repost the fake news refutation messages on the OSNs, and intentionally exposing such messages to them can contribute a lot to fake news regulation. Therefore, to fully utilize available user features and enhance fake news refuter identification, the paper proposes a novel paradigm for refuter classification problem, which leverages the pre-trained techniques and mixture of expert system to unify the structured and unstructured data. Specifically, the unstructured text records are first understood by the pre-trained ERNIE2 model, and then feed into Chi-Merge grounded Convolutional Neural Networks, which are expert classifiers in our framework, along with the structured profile data for further transformation. Besides, features extracted from text data are used for determining weights for multiple expert classifiers. Experiments on near 60 k real-world Weibo user data prove that our framework outperforms the large-scale pre-trained deep learning methods and traditional machine learning classification models. This paper provides a novel perspective of fake news refutation from the refuter's side and sheds light on artificial intelligence-driven OSNs management. [ABSTRACT FROM AUTHOR]

• Machine learning approaches to resolve identity issues. • Implementing TensorFlow to investigate policing dataset. • Predictive models using ML techniques to identify fraudulent or genuine IDs. This paper focuses on applications of various machine learning techniques on an anonymized policing dataset used in EU SPIRIT Horizon 2020 project to identify fraudulent identities and help Law Enforcement Agencies (LEAs) in their investigation in finding potential criminals and identity resolution. Lack of qualitative data and appropriate methodology to carry out research on criminal fraudulent identities is a common reason for fewer research in this area. Additionally, it is a very sensitive data to work with and minor inaccuracy in prediction of result causes massive impact in the society as genuine people could be questioned whereas criminals could be sent free. Both of these issues are addressed in this paper by application of 39 million records from policing dataset and working towards higher accuracy while building the model. Various machine learning approaches are applied to train the dataset to make predictions and the research focus on being able to predict the 5 suspected fraudulent identities out of 39 million records in the policing dataset. One of the applied machine learning techniques include TensorFlow along with Keras model which has seldomly been applied by researchers in detection of criminal data. To compare the results and test accuracy of TensorFlow model, other machine learning techniques such as Support Vector Machine, Naïve Bayes and K-nearest Neighbours are also applied to have a comparative study on the obtained outcomes from each model. The goal of this research is to find fraudulent IDs amongst all the anonymized IDs in the criminal dataset using TensorFlow and three other machine learning models and select the most optimal model out of them. Since the model is comparing two names so string-matching techniques such as Levenshtein edit distance, Hamming Distance, Jaro-Winkler and Soundex were applied to select an effective approach first before building the model and analysing the results. TensorFlow model demonstrated highest accuracy with relatively least execution time and the only model to successfully predict all the 5 suspects from the policing dataset. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is a neurodegenerative disorder that produces both motor and non-motor complications, degrading the quality of life of PD patients. Over the past two decades, the use of wearable devices in combination with machine learning algorithms has provided promising methods for more objective and continuous monitoring of PD. Recent advances in artificial intelligence have provided new methods and algorithms for data analysis, such as deep learning (DL). The aim of this article is to provide a comprehensive review of current applications where DL algorithms are employed for the assessment of motor and non-motor manifestations (NMM) using data collected via wearable sensors. This paper provides the reader with a summary of the current applications of DL and wearable devices for the diagnosis, prognosis, and monitoring of PD, in the hope of improving the adoption, applicability, and impact of both technologies as support tools. Following PRISMA (Systematic Reviews and Meta-Analyses) guidelines, sixty-nine studies were selected and analyzed. For each study, information on sample size, sensor configuration, DL approaches, validation methods and results according to the specific symptom under study were extracted and summarized. Furthermore, quality assessment was conducted according to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) method. The majority of studies (74%) were published within the last three years, demonstrating the increasing focus on wearable technology and DL approaches for PD assessment. However, most papers focused on monitoring (59%) and computer-assisted diagnosis (37%), while few papers attempted to predict treatment response. Motor symptoms (86%) were treated much more frequently than NMM (14%). Inertial sensors were the most commonly used technology, followed by force sensors and microphones. Finally, convolutional neural networks (52%) were preferred to other DL approaches, while extracted features (38%) and raw data (37%) were similarly used as input for DL models. The results of this review highlight several challenges related to the use of wearable technology and DL methods in the assessment of PD, despite the advantages this technology could bring in the development and implementation of automated systems for PD assessment. • Deep learning and wearable technology are used in diagnosis and monitoring. • Growing interest in the use of deep learning and wearables in Parkinson's disease. • The adoption of deep learning in Parkinson's disease is currently under development. • Technical and methodological challenges difficult the technology adoption. [ABSTRACT FROM AUTHOR]

• We have developed a clustering algorithm for an unknown number of clusters by MOGA. • It works with continuous and categorical featured data sets. • It can work with data sets having missing values. • The final solution is selected by majority vote by all non-dominated solutions. • Context-sensitive and cluster-orient genetic operators are designed. Many clustering algorithms categorized as K -clustering algorithm require the user to predict the number of clusters (K) to do clustering. Due to lack of domain knowledge an accurate value of K is difficult to predict. The problem becomes critical when the dimensionality of data points is large; clusters differ widely in shape, size, and density; and when clusters are overlapping in nature. Determining the suitable K is an optimization problem. Automatic clustering algorithms can discover the optimal K. This paper presents an automatic clustering algorithm which is superior to K -clustering algorithm as it can discover an optimal value of K. Iterative hill-climbing algorithms like K -Means work on a single solution and converge to a local optimum solution. Here, Genetic Algorithms (GA s) find out near global optimum solutions, i.e. optimal K as well as the optimal cluster centroids. Single-objective clustering algorithms are adequate for efficiently grouping linearly separable clusters. For non-linearly separable clusters they are not so good. So for grouping non-linearly separable clusters, we apply Multi-Objective Genetic Algorithm (MOGA) by minimizing the intra-cluster distance and maximizing inter-cluster distance. Many existing MOGA based clustering algorithms are suitable for either numeric or categorical features. This paper pioneered employing MOGA for automatic clustering with mixed types of features. Statistical testing on experimental results on real-life benchmark data sets from the University of California at Irvine (UCI) machine learning repository proves the superiority of the proposed algorithm. [ABSTRACT FROM AUTHOR]

• The paper focuses on a pick-up routing problem with a three-dimensional (3D-PRP) loading constraint. • The paper combines genetic algorithm for pick-up routing with machine learning for three-dimensional loading problem. • K-means algorithm is developed for clustering phase. • The paper includes four expert systems. • Results of a real dataset are highly promising. This paper presents a combinatorial problem called a pick-up routing problem with a three-dimensional (3D-PRP) loading constraint, clustered backhauls at the operational level, and train loading at the tactical level for an intermodal transportation network. A two-phase approach, called clustering first, packing-routing second, is proposed for use during the first stage. The clustering of backhauls is carried out using the k-means algorithm. A hybrid approach is provided, which combines the packing of orders by first solving a 3D loading problem for each cluster using machine learning with a best-fit-first strategy, with routing using a genetic algorithm. During the second stage, the train-loading problem is solved using a mixed integer programming approach to minimise the total costs by incorporating various cost types, in which detention and demurrage costs are taken into account. All solution approaches are computationally evaluated on real-world data provided by an international logistics firm and new randomly generated instances. Comparisons are carried out using both exact solution methods and heuristic approaches, and the proposed approach was shown to be more effective for real-world problems. [ABSTRACT FROM AUTHOR]

• This paper proposes the Recursive General Regression Neural Network Oracle. • The algorithm was compared to several other classifiers. • It had the highest performance metrics such as accuracy and area under the curve. • The algorithm had also bested the literature in the performance metrics. This research introduces the Recursive General Regression Neural Network Oracle (R-GRNN Oracle) and is demonstrated on several binary classification datasets. The traditional GRNN Oracle classifier (Masters et al., 1998) combines the predictive powers of several machine learning classifiers by weighing the amount of error each classifier has on the final predictions. Each classifier is assigned a weight based on the percentage of errors it contributes to the final predictions as the classifiers evaluate the dataset. The proposed R-GRNN Oracle is an enhancement to the GRNN Oracle in which the proposed algorithm consists of an oracle within an oracle – where the inner oracle acts as a classifier with its own predictions and error contribution. By combining the inner oracle with other classifiers, the R-GRNN Oracle produces superior results. The classifiers considered in this study are: Support Vector Machine (SVM), Multilayer Perceptron (MLP), Probabilistic Neural Network (PNN), Gaussian Naïve Bayes (GNB), K-Nearest Neighbor (KNN), and Random Forest (RF). To demonstrate the effectiveness of the proposed approach, several datasets were used, with the primary one being the publicly available Spambase dataset. The predictions of SVM, MLP, KNN, and RF were used to create the first GRNN Oracle, which was then enhanced with the high performances of SVM and RF to create the second oracle, the R-GRNN Oracle. The combined recursive model was 93.24% accurate using 10-fold cross validation, higher than the 91.94% of the inner GRNN Oracle and the 91.29% achieved by RF, the highest performance by a stand-alone classifier. The R-GRNN Oracle was not only the most accurate, but it also had the highest AUC, sensitivity, specificity, precision, and F1-score (97.99%, 91.86%, 94.40%, 93.28%, and 92.57%, respectively). The research contribution of this paper is introducing the concept of recursion (a concept not fully explored in machine learning models and applications) and testing this structure's ability on further enhancing the performance of the traditional oracle. The recursive model has also been applied to several other datasets: The Human Resources, Bank Marketing, and Monoclonal Gammopathy of Undetermined Significance (MGUS) datasets. The results of these implementations are summarized in this paper. [ABSTRACT FROM AUTHOR]

Automatic modulation recognition (AMR) has garnered significant attention in both civilian and military domains, with applications ranging from spectrum sensing and cognitive radio (CR) to the deterrence of adversary communication. Index modulation (IM) represents an innovative digital modulation technique that exploits the indices of parameters of communication systems to transmit extra information bits. This paper aims to examine the performance of a convolutional neural network (CNN)-based AMR across various IM systems, including spatial modulation (SM), quadrature spatial modulation (QSM), and generalized spatial modulation (GSM) with eight digital modulation schemes. In this study, we leverage confusion matrices, receiver operating characteristic (ROC) curves, and F1 scores to illustrate the recognition model's outputs. • Modulation recognition models exploit deep learning algorithms effectively. • Index modulation is a novel technique for conveying additional information. • Three datasets are created for the recognition of eight digital modulation schemes. • Three modulation recognition scenarios analyze the system's performance. • Quadrature amplitude modulation types are more robust than phase shift keying types. [ABSTRACT FROM AUTHOR]

Amidst the robust development of the service economy and information technology, the information age has significantly transformed consumption concepts and service demands. The requirements for logistics services from customers have become increasingly stringent. Beyond price and speed, quality has steadily emerged as the most crucial factor. When evaluating express services, experts primarily choose indicators from an enterprise perspective, mainly overlooking customer perception. The purpose of this paper is to establish a key index system for assessing the quality of express services aimed at improving the service quality of express deliveries within the development mode of intelligent logistics. In terms of methodology, we proposed a quantitative and qualitative e-commerce logistics service evaluation system. Specifically, we developed a key index system for assessing the quality of express services based on the theory of the six senses and the selection from an index library at first. And then, we ascertained the weight of each index in the evaluation by analyzing the proportion of customer comments. We employed analysis methods of machine learning, text data processing, mathematical statistics, and big data technology to determine the evaluation index and evaluation model of express service. Finally, our primary findings from the empirical verification and analysis of a real express enterprise indicate that this evaluation model can effectively assess the quality of express services. Our model can evaluate the current service quality and predict the quality of future services. We have derived some interpretations and conclusions based on these analyses and findings. Firstly, the level of customer perception is of great importance in the evaluation of express service quality. Secondly, our model can provide valuable feedback for express enterprises to improve their services. Lastly, we proposed corresponding improvement strategies to enhance the service quality of express enterprises under the intelligent logistics development mode. • Customer perception, not just enterprise indicators, is critical for comprehensive express service quality evaluation. • A machine learning and big data driven model is developed to evaluate and predict express service quality. • The model is empirically shown to be effective and can aid service quality improvement for intelligent logistics. [ABSTRACT FROM AUTHOR]

The high dimensionality of data hinders the learning ability of machine learning algorithms. Feature selection techniques can be used to reduce dimensionality, which is an important step for processing high-dimensional data. Feature selection solves this problem by removing irrelevant and redundant information, which can improve learning models, reduce calculation time, and improve learning accuracy. In this paper, a novel filter in mixed-attribute datasets for feature selection is proposed. The independent attributes are mixed or heterogeneous in the sense that both numerical and categorical attribute types may appear together in the same dataset. Based on the preordonnances theory, we use a new concept to quantify the relevance and redundancy of features even if there are heterogeneous (mixed-type) data. The technique for order preference by similarity to the ideal solution is one of the well-known multicriteria decision-making methods; it is utilized as a weighting and informative feature selection filter. To assess the effectiveness of the proposed method, several experiments, both simulated and real, are performed, including a comparison to other well-known filter methods. The experimental results show that, in most cases, the method yielded competitive results in comparison to other methods. • Introducing new criterions for relevance and complementarity. • Dealing with mixed-attribute datasets without requiring a preprocessing step. • The multi-criteria decision method, namely TOPSIS, is used to score the explanatory features. • Investigate the performance of the proposed filter in high-dimensional data by using simulated and real data sets. [ABSTRACT FROM AUTHOR]

Over the years, the study on logic mining approach has increased exponentially. However, most logic mining models disregarded any efforts in expanding the search space which led to poor generalizability property of the retrieved induced logic. In light of this gap, this paper initiated the hybridization of logic mining approach with a multi-objective training algorithm namely Modified Niche Genetic Algorithm. The core impetus of this algorithm is to ensure optimal production of multiple superstrings via Wan Abdullah method resulting in multiple units associative memory feature of the Discrete Hopfield Neural Network. Therefore, the storage capacity of DHNN increases which directed towards larger search space of locating optimal induced logic. Additionally, several modifications were imposed to counter other issues such as, rigid logical rule, outdated quality of best logic, and high dependency on the supervised attributes selection method. Experimentation was done on 20 repository datasets from reputable machine learning repositories. Results showed that the proposed model outperformed all baseline methods in terms of accuracy = 0.8727, precision = 0.9845, specificity = 0.9988, and Matthew's correlation coefficient = 0.5815. [ABSTRACT FROM AUTHOR]

Financial fraud is a persistent problem in the finance industry that may have severe consequences for individuals, businesses, and economies. Graph Neural Networks (GNNs) are a class of deep learning models designed to operate on graph data structures that consist of nodes and edges connecting them. GNNs have emerged as a powerful tool for detecting fraudulent activities in complex financial systems because they can analyze the network structure of financial transactions, capturing patterns and anomalies that traditional rule-based and machine learning methods might miss. The objective of this systematic review is to provide a comprehensive overview of the current state-of-the-art technologies in using Graph Neural Networks (GNNs) for financial fraud detection, identify the gaps and limitations in the existing research, and suggest potential directions for future research. We searched five academic databases, including Web of Science, Scopus, IEEE Xplore, ACM, and science direct using specific keywords and search strings related to graph neural networks, financial areas, and anomaly detection to identify relevant publications, resulting in a total of 388 unique articles. We selected the relevant publications based on the inclusion, exclusion, and quality assessment criteria, and 33 articles were included in the review. In addition, forward snowballing was used to identify relevant papers that were not captured in the initial search. Data was extracted from the selected articles, then analyzed and summarized to identify current state, gaps, and trends in the literature. Our review presents a new taxonomy of GNNs applied in financial fraud detection and identifies potential research directions in this field. We find that GNNs applied to financial fraud detection have mostly been employed in a supervised or semi-supervised manner, with limited exploration of unsupervised approaches. In addition to financial areas, we explore the different types of graphs such as homogeneous, heterogenous, static, temporal, and dynamic graphs, and investigate the various learning mechanisms and anomaly types studied. We also note a lack of research on edge-level and graph-level anomaly detection commonly employed in financial domain. [ABSTRACT FROM AUTHOR]

Computer system failures can cause significant financial and reputational damage, making it critical to detect and prevent them before they occur. In this article, we propose a novel approach for predicting system failures based on log file analysis, called MABFailPred. Our approach leverages a Blockchain-based Multi-Agent architecture to analyze execution traces and detect early warning signals for system failure prediction during execution. Moreover, we introduce a new method for extracting log keys called HCLPars. The MABFailPred approach comprises four agents that work together to gather log keys, categorize data, develop a failure model, and make predictions. The use of blockchain ensures that agent and administrator predictions are synchronized, and agent collaboration is coordinated. We validate our approach by applying it to a real-world distributed system and accurately predicting problems before they occur. Our proposed approach represents a significant advancement in the field of system failure prediction, with the potential to enhance the reliability and security of computer systems. By employing a machine learning algorithm, our approach can predict anomalies in real-time and places a strong emphasis on the continuous monitoring of system behavior. The paper includes a validation of the approach using the Hadoop Distributed File System (HDFS) log dataset. According to our findings, the proposed approach achieves superior performance compared to other methods on the same dataset, with a precision of 0.998. This result establishes a new state-of-the-art performance level for the dataset. • Failure prediction based on system log files using Multi agent system and Blockchain. • Implement and evaluate MABFailPred based on supervised learning algorithms (rule-based classification, decision tree algorithm). • Implement and evaluate a Hierarchical Clustering Log Parsing method (HCLPars), for extracting log keys. [ABSTRACT FROM AUTHOR]

Heart rate variability serves as a valuable indicator and biomarker for stress detection and monitoring. Feature selection, which aims to identify relevant features from a large set of variables, is a crucial preprocessing step towards this. However, this task becomes challenging due to high dimensionality and the presence of irrelevant and redundant attributes. The Minimum Redundancy and Maximum Relevance (mRMR) feature selection method addresses this challenge by selecting relevant features while controlling redundancy. This paper presents extensions and evaluated versions of the mRMR feature selection methods for stress detection using Heart Rate Variability (HRV) measures. The proposed feature selection methods extend the traditional mRMR by replacing the Pearson correlation redundancy with non-linear feature redundancy measures capable of capturing more complex relationships between variables. An extensive empirical evaluation is conducted on the proposed mRMR extensions, comparing them with four other baseline feature selection methods using three publicly available datasets. The experimental results demonstrate the effectiveness of incorporating the non-linear feature redundancy measure into the feature selection process. [ABSTRACT FROM AUTHOR]

The increase in data variability and quantity makes it urgent for learning complex multivariate probability distributions. The state-of-the-art Tree Augmented Naive Bayes (TAN) classifier uses maximum weighted spanning tree (MWST) to graphically model data with excellent time and space complexity. In this paper, we theoretically prove the feasibility of scaling up one-dependence MWST to model high-dependence relationships, and then propose to apply a heuristic search strategy to improve the fitness of extended topology to data. The newly added edges to each attribute node may provide a local optimal solution. Then ensemble learning is introduced to improve the generalization performance and reduce the sensitivity to variation in training data. The experimental results on 32 benchmark datasets reveal that this highly scalable algorithm inherits the expressive power of TAN and achieves an excellent bias–variance tradeoff, and it also demonstrates competitive classification performance when compared to a range of high-dependence or ensemble learning algorithms. • We extend TAN to identify the high-dependence relationships. • Causal semantics are described in the form of DAG. • Ensemble learning helps improve the topology robustness. [ABSTRACT FROM AUTHOR]

The optimisation of a machine learning (ML) solution is a core research problem in the field of automated machine learning (AutoML). This process can require searching through complex configuration spaces of not only ML components and their hyperparameters but also ways of composing them together, i.e. forming ML pipelines. Optimisation efficiency and the model accuracy attainable for a fixed time budget suffer if this pipeline configuration space is excessively large. A key research question is whether it is both possible and practical to preemptively avoid costly evaluations of poorly performing ML pipelines by leveraging their historical performance for various ML tasks, i.e. meta-knowledge. This paper approaches the research question by first formulating the problem of configuration space reduction in the context of AutoML. Given a pool of available ML components, it then investigates whether previous experience can recommend the most promising subset to use as a configuration space when initiating a pipeline composition/optimisation process for a new ML problem, i.e. running AutoML on a new dataset. Specifically, we conduct experiments to explore (1) what size the reduced search space should be and (2) which strategy to use when recommending the most promising subset. The previous experience comes in the form of classifier/regressor accuracy rankings derived from either (1) a substantial but non-exhaustive number of pipeline evaluations made during historical AutoML runs, i.e. 'opportunistic' meta-knowledge, or (2) comprehensive cross-validated evaluations of classifiers/regressors with default hyperparameters, i.e. 'systematic' meta-knowledge. Overall, numerous experiments with the AutoWeka4MCPS package, including ones leveraging similarities between datasets via the relative landmarking method, suggest that (1) opportunistic/systematic meta-knowledge can improve ML outcomes, typically in line with how relevant that meta-knowledge is, and (2) configuration-space culling is optimal when it is neither too conservative nor too radical. However, the utility and impact of meta-knowledge depend critically on numerous facets of its generation and exploitation, warranting extensive analysis; these are often overlooked/underappreciated within AutoML and meta-learning literature. In particular, we observe strong sensitivity to the 'challenge' of a dataset, i.e. whether specificity in choosing a predictor leads to significantly better performance. Ultimately, identifying 'difficult' datasets, thus defined, is crucial to both generating informative meta-knowledge bases and understanding optimal search-space reduction strategies. • Exploring characteristics of ML problems and how these impact reduction strategies. • Assessing the advantages and disadvantages of constructing meta-knowledge. • Investigating the underlying mechanism of search space reduction strategies. [ABSTRACT FROM AUTHOR]

• RL minimizes robot travel in mobile fulfillment via order allocation & sequencing. • Evaluation shows RL's consistent travel distance reduction and computation time across scenarios. • Results show RL outperforms soft computing in large order fulfillment. Robotic Mobile Fulfillment Systems (RMFS) can benefit large e-commerce warehouse operations significantly. To fulfill the orders received, RMFS deploys mobile robots to carry shelves back and forth from the storage area to the picking station. Order allocation and sequencing for mobile robots is a complex yet critical task as it influences the distance traveled by mobile robots in fulfilling the orders, i.e., appropriately allocating and sequencing the orders. In this paper, a Simultaneous Allocation and Sequencing of Orders Reinforcement Learning (SASORL) algorithm is proposed to minimize the distance traveled by mobile robots. Unlike existing methods, the SASORL algorithm optimizes order allocation and sequencing concurrently, significantly reducing mobile robot travel distance. The proposed SASORL algorithm encompasses three sets, namely state, action, and reward/penalty. The state set comprises the orders fulfilled, whereas the action set contains the orders yet to be fulfilled. The distance traveled by the mobile robot as a result of the orders allocated and sequenced is taken as the penalty for the proposed SASORL algorithm. As the proposed SASORL algorithm simultaneously allocates and sequences the orders to the mobile robots, the action set depletes, the state set enlarges, and the penalty updates until the action set becomes null. Each episode restarts with the learned experience of the prior episodes, and after completing a few episodes, the SASORL algorithm is capable of generating an optimal order allocation and sequence that commits the minimum travel distance to the mobile robots. SASORL algorithm is superior to widely adopted soft computing techniques when orders are randomly distributed. This superiority is evidenced by a 26% reduction in the maximum distance traveled by all mobile robots, a 54% reduction in the standard deviation of the distance traveled by the mobile robots, and a marginal increase of 7% in the total distance traveled by all mobile robots. Moreover, the SASORL algorithm outperforms soft computing techniques by 44% in terms of computation time. [ABSTRACT FROM AUTHOR]

Accurate and timely diagnosis of Type 2 Diabetes is a highly challenging task due to its initial asymptomatic nature and complex risk factor composition. Recently, Machine Learning (ML) has been actively used to build improved Type 2 Diabetes classification systems. One important aspect of these systems has been feature selection. Filter feature selection techniques especially based on mutual information have been popularly employed in recent works. However, most of them have focused on selecting relevant features and eliminating redundant ones. A third relationship called feature interaction may exist if input features are highly correlated, as in the case of Type 2 Diabetes. Feature interaction signifies the additional information about the target provided by the interaction between a subset of input features, that may not be relevant to the target individually. Second, many of the existing ML models are black-box, making the model interpretability very difficult. This paper proposes an efficient ML framework for the classification of Prediabetes and Type 2 Diabetes by incorporating feature interactions. It presents a hybrid filter-wrapper technique called Feature Interaction-based Greedy Sequential Feature selection. Agglomerative Feature Clustering and Dendrogram visualization for the analysis of interactive features is performed. A model-agnostic explainability technique of SHapley Additive explanations (SHAP) is augmented to provide local and global explanations of model predictions. The performance of the proposed classification framework was found to be interpretable as well as efficient with an accuracy of 98.8669%, precision of 98.8660%, recall of 98.8665%, and F-score of 0.9886 for Diabetes. For Prediabetes, an accuracy of 90.1187%, precision of 94.6958%, recall of 90.1187%, and F-score of 0.9403 was obtained. [ABSTRACT FROM AUTHOR]

Nowadays, video surveillance systems are commonly found in most public and private spaces. These systems typically consist of a network of cameras that feed into a central node. However, the processing aspect is evolving towards distributed approaches, leveraging edge-computing. These distributed systems are capable of effectively addressing the detection of people or events at each individual node. Most of these systems, rely on the use of deep-learning and segmentation algorithms which enable them to achieve high performance, but usually with a significant computational cost, hindering real-time execution. This paper presents an approach for people detection and action recognition in the wild, optimized for running on the edge, and that is able to work in real-time, in an embedded platform. Human Action Recognition (HAR) is performed by using a Recurrent Neural Network (RNN), specifically a Long Short-Term Memory (LSTM). The input to the LSTM is an ad-hoc, lightweight feature vector obtained from the bounding box of each detected person in the video surveillance image. The resulting system is highly portable and easily scalable, providing a powerful tool for real-world video surveillance applications (in the wild and real-time action recognition). The proposal has been exhaustively evaluated and compared against other state-of-the-art (SOTA) proposals in five datasets, including four widely used (KTH, WEIZMAN, WVU, IXMAX) and a novel one (GBA) recorded in the wild, that includes several people performing different actions simultaneously. The obtained results validate the proposal, since it achieves SOTA accuracy within a much more complicated video surveillance real scenario, and using a lightweight embedded hardware. • Real-time action recognition based on LSTMs with an ultralight feature vector. • Experimental results on for widely used dataset and a novel dataset in-the-wild. • Comparison to other state-of-the-art methods. • Achieves accuracy close to state-of-the-art while reducing computational cost. • Proposal runs in real time in an embedded platform. [ABSTRACT FROM AUTHOR]

Over the past decades, online social networks such as Twitter and Facebook have become a significant part of people's daily lives, particularly amid the ongoing global calamity — the COVID-19 pandemic. This gives room for social bot attacks that are designed to automatically replicate the behavior of real accounts. Most of these bots are employed for nefarious purposes such as disseminating false information, artificially amplifying the popularity of a person or movement, or spreading spam. Many studies have been conducted in an attempt to discover new strategies for identifying social bot accounts. To deal with large-scale attacks from social bots, Machine Learning has emerged as a noticeable path of bot detection problem that can handle massive amounts of data. However, the heterogeneity between studies in terms of problem statements, proposed processes, datasets, and evaluation metrics makes it difficult to assess and compare the efficiency of proposed methods. In this paper, we propose a systematic view of supervised learning methodologies for tweet-based social bot detection, ranging from shallow learning to specific deep learning models. In addition, we introduce a framework that measures various performance aspects and summarizes the in-depth analysis of the results, which were obtained using two datasets comprising 26224 labeled Twitter accounts. The results of this framework, we believe, will be beneficial as a practical guideline for other bot detection research or applications that require the use of machine learning techniques. [ABSTRACT FROM AUTHOR]

Railway switches are critical components in the rail system. Operation and maintenance tasks are essential to ensure proper functioning and avoid any failure that can cause delays, reducing operational safety. Data from condition monitoring systems requires advanced analysis tools. This paper presents the analysis of power output data of railway switches. A novel approach is proposed based on statistical analysis techniques combined with Machine Learning techniques to classify power curves by analyzing different sections of the power curves. These curves are studied statistically to classify them into normal and non-normal curves. Then, a dataset is generated with normal and non-normal labelled curves. Shapelets and k-Nearest Neighbour classification algorithms are applied to these data with good results (accuracy, sensitivity and specificity above 88% in each case). As a further analysis, a second dataset with the sectioned curves is done to detect non-normal curves without analyzing the complete curve. For this case study, k-Nearest Neighbour algorithm is able to classify with higher accuracy on the last section of the curve. [ABSTRACT FROM AUTHOR]

Accurate traffic congestion estimation and prediction are critical building blocks for smart trip planning and rerouting decisions in transportation systems. Over the decades, there have been many studies focusing on traffic congestion estimation and prediction with different statistical approaches (e.g., Markov chain) and machine learning models (e.g., clustering, Bayesian networks, and artificial neural networks). However, there is a lack of a unified framework to address the mechanisms of different models and integrate the advantages of different methods through combinations. This paper introduces the FD-Markov-LSTM model, a hybrid interpretable approach that combines the fundamental diagram (FD), Markov chain, and long short-term memory (LSTM). The aim is to estimate and predict traffic states by integrating statistical data in both congested and uncongested scenarios. The FD-Markov-LSTM model leverages the FD to identify hierarchical traffic states and utilizes the Markov process to capture the probabilistic transitions between these states. We employ the LSTM model to further capture the residual time series produced by the Markov chain model (assuming a memoryless property) to enhance the estimation and prediction performance. The proposed model's accuracy in estimating and predicting traffic flow is evaluated using empirical data from three case studies conducted in Beijing and Los Angeles. The results highlight a significant improvement in accuracy compared to classical benchmark models such as the Markov model, ARIMA model, k-Nearest Neighbor model, Random Forest model, and LSTM. Specifically, the FD-Markov-LSTM model achieves reductions of over 39% in mean absolute error, 35% in root mean squared error, and 7.4% in mean absolute percentage error. These results clearly demonstrate that the FD-Markov-LSTM model outperforms the benchmark models, enabling more precise predictions of traffic flow. [ABSTRACT FROM AUTHOR]

The Internet has revolutionised the way information is retrieved, and the increase in the number of users has resulted in a surge in the volume and heterogeneity of available data. Recommender systems have become popular tools to help users retrieve relevant information quickly. Food Recommender Systems (FRS), in particular, have proven useful in overcoming the overload of information present in the food domain. However, the recommendation of food is a complex domain with specific characteristics causing many challenges. Additionally, very few systematic literature reviews have been conducted in the domain on FRS. This paper presents a systematic literature review that summarises the current state-of-the-art in FRS. Our systematic review examines the different methods and algorithms used for recommendation, the data and how it is processed, and evaluation methods. It also presents the advantages and disadvantages of FRS. To achieve this, a total of 67 high-quality studies were selected from a pool of 2,738 studies using strict quality criteria. The review reveals that the domain of food recommendation is very diverse, and most FRS are built using content-based filtering and ML approaches to provide non-personalised recommendations. The review provides valuable information to the research field, helping researchers in the domain to select a strategy to develop FRS. This review can help improve the efficiency of development, thus closing the gap between the development of FRS and other recommender systems. • Most recommender systems use content-based filtering and predict recommendations with various machine learning algorithms. • Graph-based systems that employ various machine learning algorithms for recommendation are prevalent recently. • Several studies ignore personal attributes of users when producing recommendations. • Most systems use one source for their data, which is most often Allrecipes. • Offline evaluation with accuracy-based metrics is widely-used for measuring the performance of the FRS. [ABSTRACT FROM AUTHOR]

Simulation-driven structural health monitoring (SHM) is crucial for enhancing the safety and reliability of structures. Its primary aim is to utilize numerical simulations to design efficient SHM systems, reducing costs while maintaining effectiveness. However, challenges arise due to disparities between simulations and physical measurements, stemming from uncertainties, noise, and simplifications. These challenges also extend to SHM methods using machine learning, particularly deep neural networks (DNNs). This paper bridges the gap between DNNs trained on simulated data and real-world experiments by investigating three transfer learning (TL) techniques: feature augmentation, direct fine-tuning, and boosting-based fine-tuning. The focus is on guided wave damage interaction coefficients (WDICs) as damage-sensitive features, modeled by DNNs for damage identification in thin plates, commonly found in aerospace structures like aircraft fuselages. This classification task compares measured and predicted WDICs in a common guided wave SHM configuration with one actuator and three sensors. Training and extensive testing datasets are generated using advanced finite element simulations and laser Doppler vibrometer experiments. The study demonstrates that TL techniques significantly enhance DNN prediction accuracy and improve damage identification performance for untrained scenarios compared to purely simulation-based DNNs. Among the TL approaches explored, feature augmentation with appropriate activation functions and boosting-based fine-tuning yield the most promising results. Using four out of twelve TL datasets, feature augmentation reduces the simulation-based mean absolute percentage error from 46.80% to 35.98% and increases coefficient of determination R 2 values from 0.02 to 0.72. With six TL datasets and a boosting-based fine tuning, the mean absolute percentage error decreases from 47.42% to 35.20%, maintaining similar R 2 values. While TL substantially enhances prediction accuracy, its impact on damage identification is slightly less pronounced, with improvements in relative classification accuracy by approximately 5% compared to simulation-based DNNs. These findings highlight the efficacy of TL techniques for damage identification in thin plates using WDICs and DNNs, emphasizing the influence of TL training and DNN model variations. Furthermore, they showcase the potential of TL methods to enhance DNN performance in future SHM applications, particularly emphasizing the promise of feature augmentation and boosting. • Novel simulation-driven structural health monitoring technique using guided waves. • Deep neural network modeling to predict wave damage interaction coefficients. • Bridging disparity between simulations and experiments through transfer learning. • Study of transfer learning techniques based on feature augmentation and fine tuning. • Demonstrated significant enhancement in simulation-based neural network performance. [ABSTRACT FROM AUTHOR]

Due to the operation of modern industrial equipment under high pressure, high speed and high load conditions, cracks inevitably appear on the surfaces of metal components. Crack detection on metal surfaces is increasingly becoming a focal point in the field of non-destructive testing. In order to locate and quantitatively analyze surface cracks on metallic materials as early as possible to reduce the cost in industrial production, this paper achieves rapid localization of surface cracks by establishing a line laser thermography scanning system. An unsupervised edge detection algorithm of principal component analysis combined with K-means (PK) is proposed to achieve accurate crack edge detection by combining with a point-pulse laser thermography system. The accuracy of the PK algorithm is confirmed by comparison with other edge detection algorithms. After that, accurate identification of crack depth is achieved by selecting temperature features through particle swarm optimization algorithm and optimizing hyper-parameters of support vector machine and k-nearest neighbor through Bayesian search method. The experiments show that the best recall and accuracy of PK for crack detection are 82.9% and 86.2%, respectively; Combining the particle swarm optimization algorithm with the BS method, the mean square error of SVR and KNN for crack depth recognition is 0.092 and 0.089, respectively. [ABSTRACT FROM AUTHOR]

Due to the increasing use of Machine Learning models in high stakes decision making settings, it has become increasingly important to have tools to understand how models arrive at decisions. Assuming an already trained Supervised Classification model, post-hoc explanations can be obtained via so-called counterfactual analysis: a counterfactual explanation of an instance indicates how this instance should be minimally modified so that the perturbed instance is classified in the desired class by the given Machine Learning classification model. Most of the Counterfactual Analysis literature focuses on the single-instance single-counterfactual setting, in which the analysis is done for one single instance to provide one single counterfactual explanation. Taking a stakeholder's perspective, in this paper we introduce the so-called collective counterfactual explanations. By means of novel Mathematical Optimization models, we provide a counterfactual explanation for each instance in a group of interest, so that the total cost of the perturbations is minimized under some linking constraints. Making the process of constructing counterfactuals collective instead of individual enables us to detect the features that are critical to the entire dataset to have the individuals classified in the desired class. Our methodology allows for some instances to be treated individually, as in the single-instance single-counterfactual case, performing the collective counterfactual analysis for a fraction of records of the group of interest. This way, outliers are identified and handled appropriately. Under some assumptions on the classifier and the space in which counterfactuals are sought, finding collective counterfactual explanations is reduced to solving a convex quadratic linearly constrained mixed integer optimization problem, which, for datasets of moderate size, can be solved to optimality using existing solvers. The performance of our approach is illustrated on real-world datasets, demonstrating its usefulness. • A new model for Explainable Artificial Intelligence is proposed. • Counterfactual Explanations for a full group of individuals are sought. • Sparsity both at individual and group level is achieved. [ABSTRACT FROM AUTHOR]

Optimal path planning is a fundamental problem in artificial intelligence (AI) and has wide applications in areas such as robotics, transportation, and logistics. In this paper, we propose a novel approach for ordering algorithms in pathfinding problems using the concept of shell layers. Our approach aims to improve the computational efficiency and distance cost of ordering algorithms. To evaluate the effectiveness of our approach, we compare it with five state-of-the-art techniques commonly used in the field of ordering algorithms on eight different scenarios with varying configurations. Our results show that our proposed approach outperformed the state-of-the-art techniques in terms of time-computational complexity and distance cost in most of the scenarios, demonstrating its potential as a new state-of-the-art technique for ordering algorithms. Specifically, our approach outperformed the nearest neighbor, A*, branch and bound, Christofides, and genetics ordering algorithms. However, we also identified two specific situations where our approach was outperformed by two state-of-the-art algorithms due to the specific distribution of the goal nodes. These findings highlight the importance of evaluating and comparing ordering algorithms in various scenarios. Our approach has significant implications for AI research and development, as it has the potential to improve the performance of pathfinding algorithms in various applications. We also discuss the limitations of our approach and potential areas for further research, such as investigating the effectiveness of our approach in different types of graphs and exploring the potential use of machine learning techniques to optimize the shell layer construction. The code for this study is available at https://github.com/abdullah1aloush1/MuGONA. • Equally-spaced nodes formed over workspace with obstacles, optimizing search process. • Efficient neighboring graph built for equally-spaced nodes, reducing complexity. • Path optimization for navigation by ordering goal nodes, reducing time and distance. • Path smoothing for navigation via interpolation to yield a trajectory on path nodes. [ABSTRACT FROM AUTHOR]

Due to the enormous amount of user-generated content being generated on the web, labeling such data is a time-consuming and expensive endeavor. As a result, we have limited annotated data and the vast majority of data are unlabeled. Analysis reveals that extracting (external) knowledge from unlabeled data and integrating it with knowledge extracted from labeled data is a beneficial task for text information processing, in particular text classification. In this paper, we present a hybrid approach for classifying sentiments that employs external knowledge, which is categorized as either general-purpose sentiment knowledge or domain-related knowledge. General-purpose sentiment knowledge is extracted from sentiment lexicons, whereas domain-related knowledge is extracted from unlabeled data from the same or related domains. Similar domains for a given domain are identified based on their similarity score in terms of overlapping features. The proposed approach utilizes both forms of external knowledge and combines them with logistic regression to train an improved classification model. The classification model uses the conventional gradient descent algorithm for optimization, and its convergence analysis indicates that it is convex and converges to the global optimum. The proposed approach is empirically evaluated and compared to three baselines and one state-of-the-art method using standard performance evaluation metrics on a multi-domain sentiment dataset. The experiment results are encouraging, demonstrating that the proposed approach considerably outperforms the baseline approaches and outperforms the state-of-the-art approach by up to 2% in terms of both f-score and accuracy. • A hybrid approach for document-level sentiment classification that makes use of external knowledge. • A domain-specific knowledge extraction approach from unlabeled text documents. • A detailed convergence analysis of the proposed optimization model used in the proposed approach. [ABSTRACT FROM AUTHOR]

To improve the classification accuracy of hand movements from sEMG signals, this paper puts forward a unified hand gesture classification framework which exploits the potentials of variational mode decomposition (VMD) and multi-class support vector machine (SVM). Acquiring the sEMG signals from 25 intact subjects for ten functional activities in real-time, we implement a non-recursive adaptive decomposition technique to sEMG signals and perform power spectral analysis to identify the dominant narrow-band intrinsic mode functions (IMFs) that contain prominent biomarkers. Subsequently, to compute the optimal feature vectors from a set of entropy measures, this work investigates the performance of two techniques namely minimum redundancy and maximum relevance (MRMR) technique and kernel principal component analysis (kPCA). After extracting the optimal set of entropy features, the proposed approach implements a multi-class SVM based on one-vs-one (OVO) strategy to classify the hand gestures. The performance of the multi-class SVM compared with those of the K-nearest neighbor (KNN) and naïve bayes (NB) classifiers highlight that multi-class SVM offers superior performance with an average classification accuracy of 99.98%. Moreover, for statistical analysis of the experimental results, this work performs Friedman test to analyze the significance of the SVM, KNN and NB classifier performances. Finally, the performance comparison of the proposed approach with those of the state-of-the-art techniques highlights the superiority of the proposed framework to improve the hand gesture classification accuracy. • VMD augmented multi-class SVM framework is presented for gesture recognition. • Optimal entropy measures from decomposed IMFs are extracted through kPCA technique. • A maximum classification accuracy of 99.98% is achieved using multi-class SVM. • Statistical analysis of ML classifier models is performed using Friedman test. [ABSTRACT FROM AUTHOR]

Stochastic optimization (SO) algorithms based on the Powerball function, namely powered stochastic optimization (PoweredSO) algorithms, have been confirmed, effectively, and demonstrated great potential in the context of large-scale optimization and machine learning tasks. Nevertheless, the issue of how to determine the learning rate for PoweredSO is a challenge and still unsolved problem. In this paper, we propose a class of adaptive PoweredSO approaches that are efficient, scalable and robust. It takes advantage of the hypergradient descent (HD) technique to automatically acquire an online learning rate for PoweredSO-like methods. In the first part, we study the behavior of the canonical PoweredSO algorithm, the Powerball stochastic gradient descent (pbSGD) method, with HD. The existing PoweredSO algorithms also suffer from the high variance because they take the similar algorithmic framework to SO algorithms, arising from sampling tactics. Therefore, the second portion develops an adaptive powered variance-reduced optimization method via utilizing both variance-reduced technique and HD. Moreover, we present the convergence analysis of the proposed algorithms and explore their iteration complexity on non-convex cases. Numerical experiments are conducted on machine learning tasks, verifying the superior performance over modern SO algorithms. • We propose a type of adaptive powered stochastic optimization algorithms. • The theoretical analysis of the resulting algorithms is established. • Experiments on machine learning tasks verify the efficacy of the algorithms. [ABSTRACT FROM AUTHOR]

At present, the serious challenge of human-robot collaboration is how to establish an interaction interface with multi-directional interactivity and robustness. This paper applies surface electromyography (sEMG) signals as the interface medium, and proposes a robust 3D arm strength estimation model based on hybrid deep learning networks (R3DNet) to build a stable interaction interface and achieve reliable human-robot collaboration performance in 3D operation scenarios. R3DNet adopts the modular design idea and includes a feature extraction module, a regression estimation module, and a robust enhancement module. In the feature extraction module, an autoencoder structure-based network and a new loss function are proposed to extract the fusion features of multi-channel sEMG signals. In the regression estimation module, an arm strength model based on transfer learning algorithms is proposed. This model considers the similarity of arm strength estimation in each direction and realizes the arm strength estimation from one to three dimensions through the fine-tune strategy. The robust enhancement module adopts a residual structure and aims to address the problem of poor model robustness due to non-ideal conditions such as electrode displacement, muscle fatigue, muscle time-varying characteristics and differences in muscle characteristics among subjects. Further, an improved adaptive admittance control method is proposed to help the robot to adjust collaborative behavior according to the changing arm strength of the human tutor. The results of comparison experiments and multi-point flexible assembly experiments verify the validity and engineering realizability of R3DNet for human-robot collaboration. [ABSTRACT FROM AUTHOR]

• AER system utilizes kinematic data for enhanced human–computer interaction. • Diverse algorithms achieve >99% success (small windows), >88% (larger). • Innovative analysis: joint neighborhood, window size, axis combination efficiency. • Practical CNN algorithms enable real-time emotion recognition. • Insights from transparent datasets lead to emotion recognition advancements. This study introduces an automatic emotion recognition system (AER) focusing on skeletal-based kinematic datasets for enhanced human–computer interaction. Departing from conventional approaches, it achieves real-time emotion recognition in real-life situations. The dataset covers seven emotions and undergoes assessment by eight diverse machine and deep learning algorithms. A thorough investigation is undertaken by varying window sizes and data states, including raw positions and feature-extracted data. The findings imply that incorporating advanced techniques like joint-related feature extraction and robust classifier models yields promising outcomes. Dataset augmentation via varying window sizes enriches insights into real-world scenarios. Evaluations exhibit classification accuracy surpassing 99% for small windows, 94% for medium, and exceeding 88% for larger windows, thereby confirming the robust nature of the approach. Furthermore, we highlight window size's impact on emotion detection and the benefits of combining coordinate axes for efficiency and accuracy. The analysis intricately examines the contributions of features at both the joint and axis levels, assisting in making well-informed selections. The study's contributions include carefully curated datasets, transparent code, and models, all of which ensure the possibility of replication. The paper establishes a benchmark that bridges theory and practicality, solidifying the proposed approach's effectiveness in balancing accuracy and efficiency. By pioneering advanced AER through kinematic data, it sets a new standard for efficacy while driving seamless human–computer interaction through rigorous analysis and strategic design. [ABSTRACT FROM AUTHOR]

This paper introduces new flexible loss functions for binary classification in Gradient-Boosted Decision Trees (GBDT) that combine Dice-based and cross-entropy-based losses and offer link functions from either a generalized extreme value (GEV) or exponentiated exponential logistic (EEL) distribution. Testing 27 different GBDT models using XGBoost on a Freddie Mac mortgage loan database showed that the choice of the loss function is useful. Specifically, when the class imbalance ratio (IR) is less than 99, using a skewed GEV distribution-based link function in XGBoost enhances discriminatory power and classification accuracy while retaining a simple model structure, which is particularly important in credit scoring applications. In cases where class imbalances are severe, typically between IRs of 99 and 200, we found that an advanced loss function, which is composed of a symmetric hybrid loss function and a link derived from a positively skewed EEL distribution, outperforms other XGBoost variants. Based on our findings, the accuracy improvements of these proposed extensions result in lower misclassification costs, which are especially evident when IR is below 99, which results in higher profitability for the business. Furthermore, the study highlights the transparency associated with GBDT, which is also an integral component of financial applications. Researchers and practitioners can use these insights to create more accurate and discriminative machine learning models, with possible extensions to other GBDT implementations and machine learning techniques that take into account loss functions. The source code for the proposed approach is publicly available at https://github.com/jm-ml/flexible-losses-for-binary-classification-with-GBDT. [ABSTRACT FROM AUTHOR]

In this paper, we propose a physics-informed neural network-based scheme to solve time-varying impulsive fractional differential equations without any labeled data. At first, the existence and uniqueness of the solution of the impulsive fractional system are proved theoretically using the Bourdin state transition matrix-based solution representation and the Banach fixed point theorem. The proposed method uses the physics-informed neural network, extreme learning machines, and the theory of functional connections. A neural network is employed as the free function to construct the constrained expression. Based on the constrained expression, the linear system is trained using the extreme learning machine algorithm, and the nonlinear system is trained using the iterative least squares method, as the only trainable parameters are the output weights. The convergence and error analysis for the algorithm is derived. The neural network training is graphically demonstrated for the nonlinear system using the loss obtained in each iteration. For the linear case, the results are validated with the original solution, while for the nonlinear case, it is verified with the original solution and other classical methods. The primary use of the theory of functional connections is it helps the solution satisfy the physical constraint. • Existence of solution of time-varying IFDE is proved by Banach theory and STM. • PINN-XTFC approach for time-varying IFDE is developed. • The convergence and error analysis are derived in detail. • Error for certain examples is compared with the classical PINN-based solution. [ABSTRACT FROM AUTHOR]

Deep machine learning models including Convolutional Neural Networks (CNN) have been successful in the detection of Mild Cognitive Impairment (MCI) using medical images, questionnaires, and videos. This paper proposes a novel Multi-branch Classifier-Video Vision Transformer (MC-ViViT) model to distinguish MCI from those with normal cognition by analyzing facial features. The data comes from the I-CONECT, a behavioral intervention trial aimed at improving cognitive function by providing frequent video chats. MC-ViViT extracts spatiotemporal features of videos in one branch and augments representations by the MC module. The I-CONECT dataset is challenging as the dataset is imbalanced containing Hard-Easy and Positive–Negative samples, which impedes the performance of MC-ViViT. We propose a loss function for Hard-Easy and Positive–Negative Samples (HP Loss) by combining Focal loss and AD-CORRE loss to address the imbalanced problem. Our experimental results on the I-CONECT dataset show the great potential of MC-ViViT in predicting MCI with a high accuracy of 90.63% accuracy on some of the interview videos. • We propose MC-ViViT to detect MCI from facial videos in the I-CONECT Study. • We design the MC module to enrich the extracted spatio-temporal features. • We develop HP loss to address the inter-and intra-class imbalanced data. [ABSTRACT FROM AUTHOR]

Multi-instance learning (MIL), as a special version of classification, focuses on labeled sets (bags) consisting of unlabeled instances and has drawn accumulative attention due to its significant importance in practical applications. However, most existing MIL methods just utilize partial information (bags or instances) of MIL data to construct the kernel function, resulting in deteriorated classification performance of MIL. In this paper, we propose a Double Similarities weighted Multi-Instance Learning (DSMIL) kernel framework, which utilizes the similarities of Bag-to-Bag (B2B) and Instance-to-Bag (I2B). In the proposed kernel framework, the similarities of B2B and I2B could be derived from the prototypes distance of inter-bag and similarity matrix of intra-bag, respectively, based on the affinity propagation (AP) clustering of the bag. Meanwhile, we give theoretical proof of the validity of the designed kernel function. Experimental results on benchmark and semi-synthetic datasets show that our proposed method obtains competitive classification performance and achieves robustness to parameters and noise. • A double similarities weighted MIL kernel is proposed and proved as a valid kernel. • The DSMIL integrates the similarities of B2B and I2B into the kernel function. • The DSMIL obtains competitive results on benchmark datasets and newsgroups dataset. [ABSTRACT FROM AUTHOR]

Learning convolutional networks on graphs have been a popular topic for machine learning on graph-structured data and achieved state-of-the-art results on various practical tasks. However, most existing works ignore the impact of per-class distribution, therefore their performance may be limited due to the diversity of various categories. In this paper, we propose a novel class-aware progressive self-training (CPS) algorithm for training graph convolutional networks (GCNs). Compared to other self-training algorithms for GCNs' learning, the proposed CPS algorithm leverages the class distribution to update the original graph structure in each self-training loop, including: (a) find these high-confident unlabeled nodes in the graph for each category to add pseudo labels, in order to enlarge the current set of labeled nodes; (b) delete these noisy edges between different classes for graph sparsification. Then, the optimized graph is used for next self-training loops in hopes of enhancing the classification performance. We evaluate the proposed CPS on several datasets commonly used for GCNs' learning, and the experimental results show that the proposed CPS algorithm outperforms other baselines. [ABSTRACT FROM AUTHOR]

Predicting the difficulty of playing a musical score is essential for structuring and exploring score collections. Despite its importance for music education, the automatic difficulty classification of piano scores is not yet solved, mainly due to the lack of annotated data and the subjectiveness of the annotations. This paper aims to advance the state-of-the-art in score difficulty classification with two major contributions. To address the lack of data, we present Can I Play It? (CIPI) dataset, a machine-readable piano score dataset with difficulty annotations obtained from the renowned classical music publisher Henle Verlag. The dataset is created by matching public domain scores with difficulty labels from Henle Verlag, then reviewed and corrected by an expert pianist. As a second contribution, we explore various input representations from score information to pre-trained ML models for piano fingering and expressiveness inspired by the musicology definition of performance. We show that combining the outputs of multiple classifiers performs better than the classifiers on their own, pointing to the fact that the representations capture different aspects of difficulty. In addition, we conduct numerous experiments that lay a foundation for score difficulty classification and create a basis for future research. Our best-performing model reports a 39.5% balanced accuracy and 1.1 median square error across the nine difficulty levels proposed in this study. Code, dataset, and models are made available for reproducibility. • Introducing CIPI, the most comprehensive piano difficulty dataset, with 652 pieces across 9 levels. • We design models using various music performance aspects, guided by musicology insights. • Using multi-view music performance model predictions boosts accuracy. • Choosing the right loss function is vital for ordinal regression tasks as difficulty prediction. • We carry out extensive experiments helpful for further research. [ABSTRACT FROM AUTHOR]

Optimizing drug dosages is essential for effective treatment. Clinical protocols may not suit all types of patients evenly, due to many drug trials not being designed to account for all comorbities or clinically relevant outcomes. Methodologies to optimize drug policies with observational data exist, but struggle due to limited data completeness in clinical settings. Computational methods can help overcome these challenges by leveraging field knowledge. This paper proposes an Individualized Doser (IDoser), a core dosing model that links drug dose to relevant covariates via a set of coefficients and includes a loss function to code needed assumptions and requirements. Coordinate descent is used to obtain a fitted model with minimal loss. The loss function also measures performance when validating the model with unseen data. We validated the proposed approach using the case of follicle-stimulating hormone (FSH) dosing for controlled ovarian stimulation (COS). When compared to clinical practice, IDoser achieved a net improvement of up to 31.97% in the validation cases. We present a simple but effective method to bridge the gap between current clinical dosing policies and gold policies based on the true underlying and often unknown dose–response functions. [Display omitted] • IDoser allows to incorporate domain knowledge in the dosing model. • The search for policy solutions is customizable depending on the dosing problem. • For FSH dosing, up to 31.97% improvement was observed against a clinical practice. • Its flexible capabilities indicate potential applicability for similar problems. [ABSTRACT FROM AUTHOR]

Automated Essay Scoring (AES) is a challenging topic in Natural Language Processing. Recently, deep learning models have achieved remarkable performance for the AES task. However, applying deep learning models to the AES system in practice is expensive when both data collection and model training are taken into consideration. This paper aims to tackle this problem by proposing the Crowdsourcing-based Automated Essay Scoring (CAES) framework. The proposed framework gradually collects data through crowdsourcing and incrementally trains the AES models. In particular, we propose the Incremental Learning with Dynamic Exemplar Herding (ILDEH) approach to simultaneously tackle catastrophic forgetting and concept drift. The proposed approach dynamically updates the exemplar set by the Dynamic Exemplar Herding algorithm to obtain the best approximation of the overall data distribution and selectively apply knowledge distillation on the model outputs by Linear Outlier Suppression loss to retain the learned knowledge. Moreover, we use a lightweight AES model for effective and efficient essay scoring. The experimental results show that our proposed ILDEH approach outperforms other strong baseline approaches for the AES task. Moreover, the CAES framework is able to steadily improve the AES performance in the crowdsourcing environment with only 10.6% training time of the conventional approach. Further analysis shows that one single CPU server can support daily updates of more than 300 AES models, which is sufficient for most practical AES systems. • We proposed the Crowdsourcing-based Automated Essay Scoring (CAES) framework. • We proposed an incremental learning approach to efficiently train AES models. • Our proposed approach outperforms strong baseline approaches. • The CAES framework requires only 10.6% of the conventional training time. • The CAES framework supports daily update of 300 AES models on a single CPU server. [ABSTRACT FROM AUTHOR]

Animation drama and movies are important entertainment sources for children and young people. However, many of these entertainment videos introduce ideas such as violence, fighting, abuse, and car accidents, which are not suitable for children and young people. In order to prevent children from viewing these videos, different countries' government bodies put restrictions on age on these videos. Violence detection is mostly done using manual inspection, which is time and resource consuming and cannot achieve a very good result. Therefore, artificial technologies such as deep learning and machine learning can detect violence in a video. Bleeding is one of the distinct characteristics of violent actions presented in such videos. This paper aims to propose a system that can detect a given video's blood in real-time. Researchers have proposed different image processing-based techniques to detect violence, but their proposed systems lack precision and real-time detection. To this end, a deep learning-based approach is proposed to detect violence in a given video and images. A Faster R-CNN model is modified due to the sophisticated characteristics of the violence in the cartoon and animation images to achieve the highest performance. The backbone of the proposed violence detection model is changed to a modified RegNet model to extract the features from the frame. The standard inner lateral connection is replaced with the modulated deformable convolutional (MDC) layer to extract deformable feature maps. A novel distributed attention module (DAM) is proposed on the feature pyramid network to improve the performance of the feature extraction. The multiscale Region of interest (ROI) Align is adapted to improve the detection performance of violence in a different scenario. Moreover, the classification approach is integrated with the detection model to classify the different levels of violence in a given frame. We have explored state-of-the-art object detection methods such as Faster R-CNN, Cascade R-CNN, yolov3-spp, SSD, FCOS, and yolov5 to detect violence in a particular frame of a video. We compared the different models' performances and found out that the modified Faster R-CNN is appropriate for real-time blood detection in a given video or image with high accuracy. This study makes a significant contribution to detecting violence in animation videos which will help different platforms and government bodies to regulate entertainment content. [ABSTRACT FROM AUTHOR]

• Exploring the effect of locally weighted learning with machine learning model. • Gain ratio are used to select the most important environmental factor. • LWL-RS-ADT appears as an accurate model in assessing landslide susceptibility. Assessing landslide susceptibility and predicting the possibility of landslide event is the foundation and prerequisite for emergency response and management of landslide disaster. The target of current paper is to propose five integration models based on integrating locally weighted learning (LWL) with a radial basis function classifier (RBF), Fisher's linear discriminant (FLDA), quadratic discriminant analysis (QDA), a Credal decision tree (CDT), an alternating decision tree (ADT) and random subspace (RS) and the performance of five integration models were compared for modeling landslide susceptibility. Yongxin County from China was employed as a study area, 364 landslide locations and fifteen environmental factors were applied. The results demonstrate that the proposed LWL-RS-ADT model is more reliable and stable than the other models. Among the fifteen environmental factors, NDVI, lithology, and altitude are the very significant factors in the six models. It is concluded that the proposed integration models provide an effective way to predict the susceptibility of landslides. [ABSTRACT FROM AUTHOR]

• Propose an improved random forest based on the improvement of decision trees. • Improve the evaluation mechanism for the classification effect of decision trees. • Propose a method for quantifying the diversity between decision trees. • Multiple tests verify the superiority of the proposed improved random forest. Random forest is one of the most widely used machine learning algorithms. Decision trees used to construct the random forest may have low classification accuracies or high correlations, which affects the comprehensive performance of the random forest. Aiming at these problems, the authors proposed an improved random forest based on the classification accuracy and correlation measurement of decision trees in this paper. Its main idea includes two parts, one is retaining the classification and regression trees (CARTs) with better classification effects, the other is reducing the correlations between the CARTs. Specifically, in the classification effect evaluation part, each CART was applied to make predictions on three reserved data sets, then the average classification accuracies were achieved, respectively. Thus, all the CARTs were sorted in descending order according to their achieved average classification accuracies. In the correlation measurement part, the improved dot product method was proposed to calculate the cosine similarity, i.e., the correlation, between CARTs in the feature space. By using the achieved average classification accuracy as reference, the grid search method was used to find the inner product threshold. On this basis, the CARTs with low average classification accuracy among CART pairs whose inner product values are higher than the inner product threshold were marked as deletable. The achieved average classification accuracies and correlations of CARTs were comprehensively considered, those with high correlation and weak classification effect were deleted, and those with better quality were retained to construct the random forest. Multiple experiments show that, the proposed improved random forest achieved higher average classification accuracy than the five random forests used for comparison, and the lead was stable. The G-means and out-of-bag data (OBD) score obtained by the proposed improved random forest were also higher than the five random forests, and the lead was more obvious. In addition, the test results of three non-parametric tests show that, there were significant diversities between the proposed improved random forest and the other five random forests. This effectively proves the superiority and practicability of the proposed improved random forest. [ABSTRACT FROM AUTHOR]