Search

This paper thoroughly explores the role of object detection in smart cities, specifically focusing on advancements in deep learning-based methods. Deep learning models gain popularity for their autonomous feature learning, surpassing traditional approaches. Despite progress, challenges remain, such as achieving high accuracy in urban scenes and meeting real-time requirements. The study aims to contribute by analyzing state-of-the-art deep learning algorithms, identifying accurate models for smart cities, and evaluating real-time performance using the Average Precision at Medium Intersection over Union (IoU) metric. The reported results showcase various algorithms' performance, with Dynamic Head (DyHead) emerging as the top scorer, excelling in accurately localizing and classifying objects. Its high precision and recall at medium IoU thresholds signify robustness. The paper suggests considering the mean Average Precision (mAP) metric for a comprehensive evaluation across IoU thresholds, if available. Despite this, DyHead stands out as the superior algorithm, particularly at medium IoU thresholds, making it suitable for precise object detection in smart city applications. The performance analysis using Average Precision at Medium IoU is reinforced by the Average Precision at Low IoU (APL), consistently depicting DyHead's superiority. These findings provide valuable insights for researchers and practitioners, guiding them toward employing DyHead for tasks prioritizing accurate object localization and classification in smart cities. Overall, the paper navigates through the complexities of object detection in urban environments, presenting DyHead as a leading solution with robust performance metrics. [ABSTRACT FROM AUTHOR]

In this paper, the authors propose a new machine learning paradigm, federated machine learning. This method produces accurate predictions without revealing private data. It requires less network traffic, reduces communication costs and enables private learning from device to device. Federated machine learning helps to build models and further the models are moved to the device. Applications are particularly prevalent in healthcare, finance, retail, etc., as regulations make it difficult to share sensitive information. Note that this method creates an opportunity to build models with huge amounts of data by combining multiple databases and devices. There are many algorithms available in this area of machine learning and new ones are constantly being created. Our paper presents a comparative analysis of algorithms: FedAdam, FedYogi and FedSparse. But we need to keep in mind that FedAvg is at the core of many federated machine learning algorithms. Data testing was conducted using the Flower and Kaggle platforms with the above algorithms. Federated machine learning technology is usable in smartphones and other devices where it can create accurate predictions without revealing raw personal data. In organizations, it can reduce network load and enable private learning between devices. Federated machine learning can help develop models for the Internet of Things that adapt to changes in the system while protecting user privacy. And it is also used to develop an AI model to meet the risk requirements of leaking client's personal data. The main aspects to consider are privacy and security of the data, the choice of the client to whom the algorithm itself will be directed to process the data, communication costs as well as its quality, and the platform for model aggregation. [ABSTRACT FROM AUTHOR]

This paper analyzes various machine learning algorithms to predict student failure in a specific educational dataset and a specific environment. The paper handles the prediction of student failure given the students' grades, course difficulty level, and GPA, differing from most of the provided studies in the literature, where focus is given to the surrounding environment. The main aim is to early detect students at risk of academic underperformance and implement specific interventions to enhance their academic outcomes. A diverse set of eleven Machine Learning (ML) algorithms was used to analyze the dataset. The data went through preprocessing, and features were engineered to effectively capture essential information that may impact students' academic performance. A meticulous process for model selection and evaluation was utilized to compare the algorithms' performance with regard to metrics such as accuracy, precision, recall, F-score, specificity, and balanced accuracy. Our results demonstrate significant variability in the performance of the different algorithms, with Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs) showing the highest overall performance, followed closely by Gradient Boosting Classifier (GBC), Neuro-Fuzzy, and Random Forest (RF). The other algorithms exhibit varying performance levels, with the Recurrent Neural Networks (RNNs) showing the weakest results in recall and F-score. Educational institutions can use the insight gained from this study to make data-driven decisions and design targeted interventions to help students at risk succeed academically. Furthermore, the methodology presented in this paper can be generalized and applied to other educational datasets for similar predictive purposes. [ABSTRACT FROM AUTHOR]

Big data analysis technologies and machine learning techniques are essential for examining and forecasting the state of network security as global concerns about cyber security grow. Models for monitoring network security have a number of challenges, including resource consumption, inaccuracies, low processing efficiency, and incompatibility with real-time and large-scale scenarios. This paper proposes a novel approach to Network Security Situation Awareness (NS-SA) using Big Data (BD) analytics and machine learning. The proposed approach addresses the limitations of existing NS-SA models by leveraging data purification and simplification techniques, and by employing an updated back propagation (BP) neural network to construct an NS BD analysis model. The paper provides a comprehensive explanation of the model's structure and outlines the relevant model techniques. Extensive testing has been conducted to ensure the model's accuracy and applicability in understanding NS scenarios. This study focuses on MATLAB and Python-based implementation of a neural network for network security using a big data approach. The results demonstrate the potential and value of the proposed model in accurately assessing and forecasting NS conditions. The proposed approach has several advantages over existing NS-SA models. It is more efficient in terms of resource usage, it is more accurate in its analysis of network data, It is more applicable in real-time and large-scale scenarios and it is more robust to noise and heterogeneity in network data. [ABSTRACT FROM AUTHOR]

The trend of the next generation of the internet has already been scrutinized by top analytics enterprises. According to Gartner investigations, it is predicted that, by 2024, 75% of the global population will have their personal data covered under privacy regulations. This alarming statistic necessitates the orchestration of several security components to address the enormous challenges posed by federated and distributed learning environments. Federated learning (FL) is a promising technique that allows multiple parties to collaboratively train a model without sharing their data. However, even though FL is seen as a privacy-preserving distributed machine learning method, recent works have demonstrated that FL is vulnerable to some privacy attacks. Homomorphic encryption (HE) and differential privacy (DP) are two promising techniques that can be used to address these privacy concerns. HE allows secure computations on encrypted data, while DP provides strong privacy guarantees by adding noise to the data. This paper first presents consistent attacks on privacy in federated learning and then provides an overview of HE and DP techniques for secure federated learning in next-generation internet applications. It discusses the strengths and weaknesses of these techniques in different settings as described in the literature, with a particular focus on the trade-off between privacy and convergence, as well as the computation overheads involved. The objective of this paper is to analyze the challenges associated with each technique and identify potential opportunities and solutions for designing a more robust, privacy-preserving federated learning framework. [ABSTRACT FROM AUTHOR]

Algorithms for machine learning have found extensive use in numerous fields and applications. One important aspect of effectively utilizing these algorithms is tuning the hyperparameters to match the specific task at hand. The selection and configuration of hyperparameters directly impact the performance of machine learning models. Achieving optimal hyperparameter settings often requires a deep understanding of the underlying models and the appropriate optimization techniques. While there are many automatic optimization techniques available, each with its own advantages and disadvantages, this article focuses on hyperparameter optimization for well-known machine learning models. It explores cutting-edge optimization methods such as metaheuristic algorithms, deep learning-based optimization, Bayesian optimization, and quantum optimization, and our paper focused mainly on metaheuristic and Bayesian optimization techniques and provides guidance on applying them to different machine learning algorithms. The article also presents real-world applications of hyperparameter optimization by conducting tests on spatial data collections for landslide susceptibility mapping. Based on the experiment's results, both Bayesian optimization and metaheuristic algorithms showed promising performance compared to baseline algorithms. For instance, the metaheuristic algorithm boosted the random forest model's overall accuracy by 5% and 3%, respectively, from baseline optimization methods GS and RS, and by 4% and 2% from baseline optimization methods GA and PSO. Additionally, for models like KNN and SVM, Bayesian methods with Gaussian processes had good results. When compared to the baseline algorithms RS and GS, the accuracy of the KNN model was enhanced by BO-TPE by 1% and 11%, respectively, and by BO-GP by 2% and 12%, respectively. For SVM, BO-TPE outperformed GS and RS by 6% in terms of performance, while BO-GP improved results by 5%. The paper thoroughly discusses the reasons behind the efficiency of these algorithms. By successfully identifying appropriate hyperparameter configurations, this research paper aims to assist researchers, spatial data analysts, and industrial users in developing machine learning models more effectively. The findings and insights provided in this paper can contribute to enhancing the performance and applicability of machine learning algorithms in various domains. [ABSTRACT FROM AUTHOR]

Pulmonary diseases are various pathological conditions that affect respiratory tissues and organs, making the exchange of gas challenging for animals inhaling and exhaling. It varies from gentle and self-limiting such as the common cold and catarrh, to life-threatening ones, such as viral pneumonia (VP), bacterial pneumonia (BP), and tuberculosis, as well as a severe acute respiratory syndrome, such as the coronavirus 2019 (COVID-19). The cost of diagnosis and treatment of pulmonary infections is on the high side, most especially in developing countries, and since radiography images (X-ray and computed tomography (CT) scan images) have proven beneficial in detecting various pulmonary infections, many machine learning (ML) models and image processing procedures have been utilized to identify these infections. The need for timely and accurate detection can be lifesaving, especially during a pandemic. This paper, therefore, suggested a deep convolutional neural network (DCNN) founded image detection model, optimized with image augmentation technique, to detect three (3) different pulmonary diseases (COVID-19, bacterial pneumonia, and viral pneumonia). The dataset containing four (4) different classes (healthy (10,325), COVID-19 (3,749), BP (883), and VP (1,478)) was utilized as training/testing data for the suggested model. The model's performance indicates high potential in detecting the three (3) classes of pulmonary diseases. The model recorded average detection accuracy of 94%, 95.4%, 99.4%, and 98.30%, and training/detection time of about 60/50 s. This result indicates the proficiency of the suggested approach when likened to the traditional texture descriptors technique of pulmonary disease recognition utilizing X-ray and CT scan images. This study introduces an innovative deep convolutional neural network model to enhance the detection of pulmonary diseases like COVID-19 and pneumonia using radiography. This model, notable for its accuracy and efficiency, promises significant advancements in medical diagnostics, particularly beneficial in developing countries due to its potential to surpass traditional diagnostic methods. [ABSTRACT FROM AUTHOR]

With the increasing number of connected devices in the Internet of Things (IoT) era, the number of intrusions is also increasing. An intrusion detection system (IDS) is a secondary intelligent system for monitoring, detecting and alerting against malicious activity. IDS is important in developing advanced security models. This study reviews the importance of various techniques, tools, andmethods used in IoT detection and/or prevention systems. Specifically, it focuses on machine learning (ML) and deep learning (DL) techniques for IDS. This paper proposes an accurate intrusion detection model to detect traditional and new attacks on the Internet of Vehicles. To speed up the detection of recent attacks, the proposed network architecture developed at the data processing layer is incorporated with a convolutional neural network (CNN), which performs better than a support vector machine (SVM). Processing data are enhanced using the synthetic minority oversampling technique to ensure learning accuracy. The nearest class mean classifier is applied during the testing phase to identify new attacks. Experimental results using the AWID dataset, which is one of the most common open intrusion detection datasets, revealed a higher detection accuracy (94%) compared to SVM and random forest methods. [ABSTRACT FROM AUTHOR]

In this growing world of the internet, most of our daily routine tasks are somehow connected to the internet, from smartphones to internet of things (IoT) devices to cloud networks. Internet users are growing rapidly, and the internet is accessible to everyone from anywhere. Data phishing is a cyber security attack that uses deception to trick internet users to get their content and information. In this attack, malicious users try to steal personal data such as login credentials, credit card details, health care information, etc., of the users on the internet. They exploit users' sensitive information using vulnerabilities. Information stealers are known as phishers. Phishers use different techniques for phishing. One of the most common methods is to direct the users to a false website to enter their login credentials and their details on these phishing sites. Phishing websites look like the original websites. Phishers use these details to get access to the user's accounts and hijack them for monetary purposes. Many internet users fall for this trap of phishing sites and share their personal and sensitive details. In this paper, we will analyze and implement machine learning (ML) techniques to detect phishing attacks. There are different methods to identify phishing attacks, one of them is by checking the uniform resource locator (URL) address using ML. ML is used to teach a machine to differentiate between phishing and original site URLs. There are many different techniques to overcome this attack. This research paper aims to provide accurate and true phishing detection with less time complexity. [ABSTRACT FROM AUTHOR]

Time-Series-Classification (TSC) is an important machine learning task for many branches of science. Symbolic representations of time series, especially Symbolic Fourier Approximation (SFA), have been proven very effective for this task, given their abilities to reduce noise. In this paper, we improve upon SCALE-BOSS using multiple symbolic representations of time series. More specifically, the proposed SCALE-BOSS-MR incorporates into the process a variety of window sizes combined with multiple dilation parameters applied to the original and to first-order differences' time series, with the latter modeling trend information. SCALE-BOSS-MR has been evaluated using the eight datasets with the largest training size of the UCR time series repository. The results indicate that SCALE-BOSS-MR can be instantiated to classifiers that are able to achieve state-of-the-art accuracy and can be tuned for scalability. [ABSTRACT FROM AUTHOR]

Privacy-utility tradeoff remains as one of the fundamental issues of differentially private machine learning. This paper introduces a geometrically inspired kernel-based approach to mitigate the accuracy-loss issue in classification. In this approach, a representation of the affine hull of given data points is learned in Reproducing Kernel Hilbert Spaces (RKHS). This leads to a novel distance measure that hides privacy-sensitive information about individual data points and improves the privacy-utility tradeoff via significantly reducing the risk of membership inference attacks. The effectiveness of the approach is demonstrated through experiments on MNIST dataset, Freiburg groceries dataset, and a real biomedical dataset. It is verified that the approach remains computationally practical. The application of the approach to federated learning is considered and it is observed that the accuracy-loss due to data being distributed is either marginal or not significantly high. [ABSTRACT FROM AUTHOR]

This paper proposes a matrix-based collaborative filtering (CF) employing personal values (MCFPV). Introduction of various factors such as diversity and long-tailedness in addition to accuracy is a recent trend in the study of recommender systems. We think recommending acceptable items while satisfying users' preference is important when considering other factors than accuracy. Also, interpretability is one of important characteristics recommender systems should have. To recommend acceptable items on the basis of an interpretable mechanism, this paper proposes a matrix-based recommendation method based on personal values-based modeling. Whereas existing CF based on matrix factorization methods are known to be more accurate than neighborhood-based CF, latent factors obtained by existing methods are difficult to interpret. On the other hand, user/item models of the propose method (MCFPV) is expected to be interpretable, because it represents the effect of each attribute items have on user's decision making. Regarding a model relationship matrix that connects user and item models, this paper proposes two approaches: manual setting and machine learning approaches. Experimental results using 5 datasets generated from actual review sites show that the proposed methods recommend much unpopular items than the state-of-the art matrix factorization-based methods while keeping precision and recall. [ABSTRACT FROM AUTHOR]

The Internet of things (IoT) is emerging as a prime area of research in the modern era. The significance of IoT in the daily life is increasing due to the increase in objects or things connected to the internet. In this paper, routing protocol for low power and lossy networks (RPL) is examined on the Contiki operating system. This paper used RPL attack framework to simulate three RPL attacks, namely hello-flood, decreased-rank and increased-version. These attacks are simulated in a separate and simultaneous manner. The focus remained on the detection of these attacks through artificial neural network (ANN)-based supervised machine learning approach. The accurate detection of the malicious nodes prevents the network from the severe effects of the attack. The accuracy of the proposed model is computed with hold-out approach and tenfold cross-validation technique. The hyperparameters have been optimized through parameter tuning. The model presented in this paper detected the aforesaid attacks simultaneously as well as individually with 100% accuracy. This work also investigated other performance measures like precision, recall, F1-score and Mathews correlation coefficient (MCC). [ABSTRACT FROM AUTHOR]

Featured Application: This work applies machine learning to enhance the prediction of deforestation related to oil palm. This research can be used for decision makers trying to foresee and manage deforestation caused by palm oil production. Providing information about deforestation prediction can help users to make appropriate decisions about where and when they can establish new plantations to ensure a sustainable oil palm production. Deforestation is recognized as an issue that has negative effects on the ecosystem. Predicting deforestation and defining the causes of deforestation is an important process that could help monitor and prevent deforestation. Deforestation prediction has been boosted by recent advances in geospatial technologies and applications, especially remote sensing technologies and machine learning techniques. This paper highlights the issue of predicting deforestation related to oil palm, which has not been focused on in existing research studies. The paper proposes an approach that aims to enhance the prediction of deforestation related to oil palm plantations and palm oil production. The proposed approach is based on a conceptual framework and an assessment of a set of criteria related to such deforestation. The criteria are assessed and validated based on a sensitivity analysis. The framework is based on machine learning and image processing techniques. It consists of three main steps, which are data preparation, model training, and validation. The framework is implemented in a case study in the Aceh province of Indonesia to show the feasibility of our proposed approach in predicting deforestation related to oil palm. The implementation of the proposed approach shows an acceptable accuracy for predicting deforestation. [ABSTRACT FROM AUTHOR]

Intelligent lower-limb prosthesis appears in the public view due to its attractive and potential functions, which can help amputees restore mobility and return to normal life. To realize the natural transition of locomotion modes, locomotion mode classification is the top priority. There are mainly five steady-state and periodic motions, including LW (level walking), SA (stair ascent), SD (stair descent), RA (ramp ascent), and RD (ramp descent), while ST (standing) can also be regarded as one locomotion mode (at the start or end of walking). This paper mainly proposes four novel features, including TPDS (thigh phase diagram shape), KAT (knee angle trajectory), CPO (center position offset) and GRFPV (ground reaction force peak value) and designs ST classifier and artificial neural network (ANN) classifier by using a user-dependent dataset to classify six locomotion modes. Gaussian distributions are applied in those features to simulate the uncertainty and change of human gaits. An angular velocity threshold and GRFPV feature are used in the ST classifier, and the artificial neural network (ANN) classifier explores the mapping relation between our features and the locomotion modes. The results show that the proposed method can reach a high accuracy of 99.16% ± 0.38%. The proposed method can provide accurate motion intent of amputees to the controller and greatly improve the safety performance of intelligent lower-limb prostheses. The simple structure of ANN applied in this paper makes adaptive online learning algorithms possible in the future. [ABSTRACT FROM AUTHOR]

Machine learning (ML) is frequently used to identify malicious traffic flows on a network. However, the requirement of complex preprocessing of network data to extract features or attributes of interest before applying the ML models restricts their use to offline analysis of previously captured network traffic to identify attacks that have already occurred. This paper applies machine learning analysis for network security with low preprocessing overhead. Raw network data are converted directly into bitmap files and processed through a Two-Dimensional Convolutional Neural Network (2D-CNN) model to identify malicious traffic. The model has high accuracy in detecting various malicious traffic flows, even zero-day attacks, based on testing with three open-source network traffic datasets. The overhead of preprocessing the network data before applying the 2D-CNN model is very low, making it suitable for on-the-fly network traffic analysis for malicious traffic flows. [ABSTRACT FROM AUTHOR]

Support vector machine (SVM) is a supervised machine learning algorithm for classification and regression problems. SVM performs better when combined with other classifiers or optimized with an optimization algorithm. The SVM parameters such as kernel and penalty have good performance on the classification accuracy. Recently, a lot of evolutionary optimization algorithms were used for optimizing the SVM. In this paper, an Improved Cat Swarm Optimization (ICSO) was proposed for optimizing the parameters of SVM with the aim of enhancing its performance. CSOs have the problem of a low convergence rate and are easily trapped in local optima. To address this problem, a new parameter was added to the velocity for the tracing mode and the Opposition-Based Learning (OBL) technique was used to modify the CSO algorithm (ICSO-SVM). A new parameter was introduced to guide the cats' positions to the local and global best positions in the velocity tracing mode of the CSO algorithm. The proposed algorithm was verified using 15 datasets from the University of California Irvine (UCI) data repository and also six different performance metrics were used. The experimental results clearly indicate that the proposed method performs better than the other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Background: Diabetes mellitus (DM) is a chronic condition that can lead to a variety of consequences. Diabetes is a condition that is caused by factors such as age, lack of exercise, sedentary lifestyle, family history of diabetes, high blood pressure, depression and stress, poor food, and so on. Diabetics are at a higher risk of developing diseases such as heart disease, nerve damage (diabetic neuropathy), eye problems (diabetic retinopathy), kidney disease (diabetic nephropathy), stroke, and so on. According to the International Diabetes Federation, 382 million people worldwide suffer from diabetes. By 2035, this number will have risen to 592 million. Every day, a large number of people become victims, and many are ignorant whether they have it or not. It primarily affects individuals between the ages of 25 and 74 years. If diabetes is left untreated and undiagnosed, it can lead to a slew of complications. The emergence of machine learning approaches, on the other hand, solves this crucial issue. Aims and Objectives: The aim was to study the DM and analyze how machine learning algorithms are used to identify the diabetes mellitus at an early stage, which is one of the most serious metabolic disorders in the world today. Methods and Materials: Data was obtained from databases such as Pubmed, IEEE xplore, and INSPEC,and from other secondary sources and primary sources in which methods based on machine learning approaches used in healthcare to predict diabetes at an early stage are reported. Results: After surveying various research papers, it was found that machine learning classification algorithms like Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Random Forest (RF) etc shows the best accuracy for predicting diabetes at an early stage. Conclusion: Early detection of diabetes is critical for effective therapy. Many people have no idea whether or not they have it. The full assessment of Machine learning approaches for early diabetes prediction and how to apply a variety of supervised and unsupervised machine learning algorithms to the dataset to achieve the best accuracy are addressed in this paper.. Furthermore, the work will be expanded and refined to create a more precise and general predictive model for diabetes risk prediction at an early stage. Different metrics can be used to assess performance and for accurate diabetic diagnosis. [ABSTRACT FROM AUTHOR]

Travel time reliability affects the behavior of passengers in private or public transportation and can be seen as an important factor in the context of freight transportation. The main cause of travel time oscillation, known as travel time reliability, is congestion. Congestion is classified into two categories: recurring and nonrecurring. Recurring congestion, which is the topic of this study, is formed when supply surpasses capacity. Peak periods are good examples of recurring congestion. In this paper, by utilizing different bagging regressor methods, the effect of speed flow reduction, compared to Free Flow Speed (FFS) in terms of congestion was studied on the Planning Time Index (PTI) on a section of Interstate 64 in the United States (US). Then, by analyzing PTI changes based on congestion variation, it was revealed that when speed reduction surpasses 10%, travel time leaves its reliability. Also, when the congestion is somewhere around 0.7 to 0.75, the unreliability becomes severe. These findings were directly extracted from scatter plots drawn by bagging and bootstrapping samples which were used to improve the accuracy of PTI prediction. [ABSTRACT FROM AUTHOR]

Featured Application: A new Weak Learn algorithm which classifies examples is proposed based on multiple thresholds. The weight assigning scheme of the Weak Learn algorithm is changed correspondingly for the AdaBoost algorithm in this paper. Theoretical identification is provided to show the superiority. Experimental studies are also presented to verify the effectiveness of the method. Adaptive boost (AdaBoost) is a prominent example of an ensemble learning algorithm that combines weak classifiers into strong classifiers through weighted majority voting rules. AdaBoost's weak classifier, with threshold classification, tries to find the best threshold in one of the data dimensions, dividing the data into two categories-1 and 1. However, in some cases, this Weak Learning algorithm is not accurate enough, showing poor generalization performance and a tendency to over-fit. To solve these challenges, we first propose a new Weak Learning algorithm that classifies examples based on multiple thresholds, rather than only one, to improve its accuracy. Second, in this paper, we make changes to the weight allocation scheme of the Weak Learning algorithm based on the AdaBoost algorithm to use potential values of other dimensions in the classification process, while the theoretical identification is provided to show its generality. Finally, comparative experiments between the two algorithms on 18 datasets on UCI show that our improved AdaBoost algorithm has a better generalization effect in the test set during the training iteration. [ABSTRACT FROM AUTHOR]

In this paper, we propose a method for combining forecasts generated by different models based on long short-term memory (LSTM) ensemble learning. While typical approaches for combining forecasts involve simple averaging or linear combinations of individual forecasts, machine learning techniques enable more sophisticated methods of combining forecasts through meta-learning, leading to improved forecasting accuracy. LSTM's recurrent architecture and internal states offer enhanced possibilities for combining forecasts by incorporating additional information from the recent past. We define various meta-learning variants for seasonal time series and evaluate the LSTM meta-learner on multiple forecasting problems, demonstrating its superior performance compared to simple averaging and linear regression. [ABSTRACT FROM AUTHOR]

Machine learning, a subfield of artificial intelligence, emphasizes the creation of algorithms capable of learning from data and generating predictions. However, in actuarial science, the interpretability of these models often presents challenges, raising concerns about their accuracy and reliability. Explainable artificial intelligence (XAI) has emerged to address these issues by facilitating the development of accurate and comprehensible models. This paper conducts a comparative analysis of various XAI approaches for tackling distinct data-driven insurance problems. The machine learning methods are evaluated based on their accuracy, employing the mean absolute error for regression problems and the accuracy metric for classification problems. Moreover, the interpretability of these methods is assessed through quantitative and qualitative measures of the explanations offered by each explainability technique. The findings reveal that the performance of different XAI methods varies depending on the particular insurance problem at hand. Our research underscores the significance of considering accuracy and interpretability when selecting a machine-learning approach for resolving data-driven insurance challenges. By developing accurate and comprehensible models, we can enhance the transparency and trustworthiness of the predictions generated by these models. [ABSTRACT FROM AUTHOR]

Cardiac arrest is a severe heart anomaly that results in billions of annual casualties. Smoking is a specific hazard factor for cardiovascular pathology, including coronary heart disease, but data on smoking and heart death not earlier reviewed. The Heart Rate Variability (HRV) parameters used to predict cardiac arrest in smokers using machine learning technique in this paper. Machine learning is a method of computing experience based on automatic learning and enhances performances to increase prognosis. This study intends to compare the performance of logistical regression, decision tree, and random forest model to predict cardiac arrest in smokers. In this paper, a machine learning technique implemented on the dataset received from the data science research group MITU Skillogies Pune, India. To know the patient has a chance of cardiac arrest or not, developed three predictive models as 19 input feature of HRV indices and two output classes. These model evaluated based on their accuracy, precision, sensitivity, specificity, F1 score, and Area under the curve (AUC). The model of logistic regression has achieved an accuracy of 88.50%, precision of 83.11%, the sensitivity of 91.79%, the specificity of 86.03%, F1 score of 0.87, and AUC of 0.88. The decision tree model has arrived with an accuracy of 92.59%, precision of 97.29%, the sensitivity of 90.11%, the specificity of 97.38%, F1 score of 0.93, and AUC of 0.94. The model of the random forest has achieved an accuracy of 93.61%, precision of 94.59%, the sensitivity of 92.11%, the specificity of 95.03%, F1 score of 0.93 and AUC of 0.95. The random forest model achieved the best accuracy classification, followed by the decision tree, and logistic regression shows the lowest classification accuracy. [ABSTRACT FROM AUTHOR]

This paper proposes a hybrid feature selection sequence complemented with filter and wrapper concepts to improve the accuracy of Machine Learning (ML) based supervised classifiers for classifying the survivability of breast cancer patients into classes, living and deceased using METABRIC and Surveillance, Epidemiology and End Results (SEER) datasets. The ML-based classifiers used in the analysis are: Multiple Logistic Regression, K-Nearest Neighbors, Decision Tree, Random Forest, Support Vector Machine and Multilayer Perceptron. The workflow of the proposed ML algorithm sequence comprises the following stages: data cleaning, data balancing, feature selection via a filter and wrapper sequence, cross validation-based training, testing and performance evaluation. The results obtained are compared in terms of the following classification metrics: Accuracy, Precision, F1 score, True Positive Rate, True Negative Rate, False Positive Rate, False Negative Rate, Area under the Receiver Operating Characteristics curve, Area under the Precision- Recall curve and Mathews Correlation Coefficient. The comparison shows that the proposed feature selection sequence produces better results from all supervised classifiers than all other feature selection sequences considered in the analysis. [ABSTRACT FROM AUTHOR]

Anxiety is a common mental health issue that affects a significant portion of the global population and can lead to severe physical and psychological consequences. The proposed system aims to provide an objective and reliable method for the early detection of anxiety levels by using patients' physical symptoms as input variables. This paper introduces an expert system utilizing a fuzzy inference system (FIS) to predict anxiety levels. The system is designed to address anxiety's complex and uncertain nature by utilizing a comprehensive set of input variables and fuzzy logic techniques. It is based on a set of rules that represent medical knowledge of anxiety disorders, making it a valuable tool for clinicians in diagnosing and treating these disorders. The system was tested on real datasets, demonstrating high accuracy in the prediction of anxiety levels. The FIS-based expert system offers a powerful approach to cope with imprecision and uncertainty and can potentially assist in addressing the lack of effective remedies for anxiety disorders. The research primarily focused on Asian countries, such as Pakistan, and the system achieved an accuracy of 87%, which is noteworthy. [ABSTRACT FROM AUTHOR]

Recently, Panama wilt disease that attacks banana leaves has caused enormous economic losses to farmers. Early detection of this disease and necessary preventive measures can avoid economic damage. This paper proposes an improved method to predict Panama wilt disease based on symptoms using an agro deep learning algorithm. The proposed deep learning model for detecting Panama wilts disease is essential because it can help accurately identify infected plants in a timely manner. It can be instrumental in large-scale agricultural operations where Panama wilts disease could spread quickly and cause significant crop loss. Additionally, deep learning models can be used to monitor the effectiveness of treatments and help farmers make informed decisions about how to manage the disease best. This method is designed to predict the severity of the disease and its consequences based on the arrangement of color and shape changes in banana leaves. The present proposed method is compared with its previous methods, and it achieved 91.56% accuracy, 91.61% precision, 88.56% recall and 81.56% F1-score. [ABSTRACT FROM AUTHOR]

Finance sector is the wealth backbone of any country, so risk assessment and fraud detection have great importance. Risk assessment is the process of identifying vulnerabilities to an organization by identifying risk involved in each and every new plans, policies or investments. This paper concentrates on risk level detection of loan application and insurance claim and suggests a predictive model for risk assessment and fraud detection using three efficient machine learning algorithms after applying under sampling technique on data and compares the accuracy difference of them, on imbalanced and resampled datasets with the leading machine learning algorithms Random Forest ad SVM (support vector machine). [ABSTRACT FROM AUTHOR]

Software is playing a growing role in many safety-critical applications, and software systems dependability is a major concern. Predicting faulty modules of software before the testing phase is one method for enhancing software reliability. The ability to predict and identify the faulty modules of software can lower software testing costs. Machine learning algorithms can be used to solve software fault prediction problem. Identifying the faulty modules of software with the maximum accuracy, precision, and performance are the main objectives of this study. A hybrid method combining the autoencoder and the K-means algorithm is utilized in this paper to develop a software fault predictor. The autoencoder algorithm, as a preprocessor, is used to select the effective attributes of the training dataset and consequently to reduce its size. Using an autoencoder with the K-means clustering method results in lower clustering error and time. Tests conducted on the standard NASA PROMIS data sets demonstrate that by removing the inefficient elements from the training data set, the proposed fault predictor has increased accuracy (96%) and precision (93%). The recall criteria provided by the proposed method is about 87%. Also, reducing the time necessary to create the software fault predictor is the other merit of this study. [ABSTRACT FROM AUTHOR]

Explainable artificial intelligence (XAI) is a group of techniques and evaluations that allows users to understand artificial intelligence knowledge and increase the reliability of the results produced using artificial intelligence. XAI can assist actuaries in achieving better estimations and decisions. This study reviews the current literature to summarize XAI in common actuarial problems. We proposed a research process based on understanding the type of AI used in actuarial practice in the financial industry and insurance pricing and then researched XAI implementation. This study systematically reviews the literature on the need for implementation options and the current use of explanatory artificial intelligence (XAI) techniques for actuarial problems. The study begins with a contextual introduction outlining the use of artificial intelligence techniques and their potential limitations, followed by the definition of the search equations used in the research process, the analysis of the results, and the identification of the main potential fields for exploitation in actuarial problems, as well as pointers for potential future work in this area. [ABSTRACT FROM AUTHOR]

This paper proposes a machine learning-based position prediction approach to determine the position of a light-emitting diode (LED) target using a new measuring system called the multi-aperture positioning system (MAPS). The measurement system is based on a photogrammetric approach using an aperture mask and a single camera sensor. To achieve high accuracy in position calculation, several complex algorithms with high computational complexity are used. The accuracy of the system is equal to or better than that of existing photogrammetric devices. We investigate whether a neural network (NN) can replace the algorithms currently used in the system software to increase the measurement frequency with similar accuracy. Simulated images are used to train the NN, while real images are used to measure performance. Previously, various algorithms were used to calculate the position of the target from the captured images. Our approach is to train an NN, using thousands of labeled images, to predict the position of the target from these images. We investigate whether systematic measurement errors can be avoided; not all factors affecting the measurement precision are yet known, can always be accurately determined, or change over time. When NNs are used, all information contained in the images is learned by the model, considering all influences present at the time of training. Results show that the trained NN can achieve similar performance to the previously used Gaussian algorithm in less time since no filters or other pre-processing of images are required. This factor directly affects the measurement frequency of the MAPS. The light spot center was detected with sub-pixel accuracy without systematic errors in contrast to some of the previously used algorithms. The simulation of the sensor images needs to be improved to investigate the full potential of the NN. [ABSTRACT FROM AUTHOR]

As the importance of email increases, the amount of malicious email is also increasing, so the need for malicious email filtering is growing. Since it is more economical to combine commodity hardware consisting of a medium server or PC with a virtual environment to use as a single server resource and filter malicious email using machine learning techniques, we used a Hadoop MapReduce framework and Naïve Bayes among machine learning methods for malicious email filtering. Naïve Bayes was selected because it is one of the top machine learning methods(Support Vector Machine (SVM), Naïve Bayes, K-Nearest Neighbor(KNN), and Decision Tree) in terms of execution time and accuracy. Malicious email was filtered with MapReduce programming using the Naïve Bayes technique, which is a supervised machine learning method, in a Hadoop framework with optimized performance and also with the Python program technique with the Naïve Bayes technique applied in a bare metal server environment with the Hadoop environment not applied. According to the results of a comparison of the accuracy and predictive error rates of the two methods, the Hadoop MapReduce Naïve Bayes method improved the accuracy of spam and ham email identification 1.11 times and the prediction error rate 14.13 times compared to the non-Hadoop Python Naïve Bayes method. [ABSTRACT FROM AUTHOR]

The recent rise of machine learning (ML) has been leveraged by practitioners and researchers to provide new solutions to an ever growing number of business problems. As with other ML applications, these solutions rely on model selection, which is typically achieved by evaluating certain metrics on models separately and selecting the model whose evaluations (i.e., accuracy-related loss and/or certain interpretability measures) are optimal. However, empirical evidence suggests that, in practice, multiple models often attain competitive results. Therefore, while models' overall performance could be similar, they could operate quite differently. This results in an implicit tradeoff in models' performance throughout the feature space which resolving requires new model selection tools. This paper explores methods for comparing predictive models in an interpretable manner to uncover the tradeoff and help resolve it. To this end, we propose various methods that synthesize ideas from supervised learning, unsupervised learning, dimensionality reduction, and visualization to demonstrate how they can be used to inform model developers about the model selection process. Using various datasets and a simple Python interface, we demonstrate how practitioners and researchers could benefit from applying these approaches to better understand the broader impact of their model selection choices. [ABSTRACT FROM AUTHOR]

The presence of COVID-19 infection and its threat to human life has led to the urgent need to contribute to combating it, so global initiatives have emerged to regulate and manage the virus, with the aim of eliminating it once and for all. Since the use of image processing has succeeded in solving many complicated problems in the medical field, it can now be employed to aid in the fight against COVID-19 and control it by extracting the relevant features collected from medical imaging datasets and categorizing using machine learning and deep learning approaches in order to diagnose and predict the COVID-19 disease. This study provides an overview of current findings on machine learning methods that have been applied to COVID-19 and aspects related to the types of algorithms, the medical dataset used, and the accuracy of researchers' results. This paper, review the latest proposed models for COVID-19 classification and diagnosis applied to CT scans and chest X-ray images to provide further insight into disease reduction. COVID-19 diagnosis is critical for identifying an infected person and preventing the virus from spreading. Because diffusion is rapid, an automated rapid diagnostic mechanism is required to deal with a huge population so image processing methods are the most suitable technology for this. These models' accuracy ranged from 80.6% to 100%, demonstrating that image-processing methods can be used to assess and diagnose COVID-19 clinically. [ABSTRACT FROM AUTHOR]

The perfect physical health and mental wellbeing is an important aspect of human kind. Healthcare sectors involving machine learning and deep learning is providing good healthcare services is helping people for safeguarding them from being exploited with extra and unnecessary expenditures on medical check-ups. This gives treatments and many health services on time when needed. In this paper, different performance metrics are applied on online bipolar dataset named "Theory of mind in remitted bipolar disorder dataset" from Kaggle to evaluate the diagnosis for bipolar disorder feature prediction and analysis. In this study the proposed accuracy is better as compared to previous traditional models. As a result, artificial neural networks reduce the time taken in training and classification of dataset in prediction as given in result by optimal combination of epoch and hyperperameters. [ABSTRACT FROM AUTHOR]

Nowadays, fake news is prevalent and too simple to propagate through social media, particularly during elections and pandemics like COVID-19. Several fake news stories have appeared on social media sites like LINE, Facebook, and Twitter after the COVID-19 epidemic throughout the world. Also, a lot of older individuals simply forward these communications without checking their veracity, which speeds up the dissemination of fake information. So, our goal is to identify fake news using machine learning. In this paper, we describe a supervised method that automatically gathers a sizable but noisy training dataset made up of a significant number of tweets. We will categorize tweets during collection into trustworthy and untrustworthy sources, then using the dataset to train a classifier. The categorization of fake and real tweets is the next classification objective for which we apply that classifier. We first demonstrate that real news is larger in size, shared on Twitter for a longer length of time, and shared by people with more followers than following. Second, we employed machine learning models like support vector machine (SVM), random forest (RF), and decision tree (DT), and we found out that the SVM is the best of all the models due to its best results and 99% accuracy. [ABSTRACT FROM AUTHOR]

Multimedia, machine learning and deep learning applications have a significant constraint on power consumption. A multiplier is a crucial component for many error-aware applications. An efficient approximate computing scheme is used for the error-tolerant applications due to higher accuracy in power cases. In the Booth, multiplier approximation is implemented for partial product generation and accumulations network. The significant stage of a multiplier is accumulation. In this paper, an efficient accumulation stage is suggested for the Radix-4 and 8-bit approximate Booth multiplier. The proposed accumulation multiplier has high speed, minimum area, negligible path delay and low power consumption. Compared to the Booth multiplier design with modified Booth encoding and conventional carry look-ahead adder for product generation with no other error, the proposed 8-bit multiplier design-I reduced power consumption, area and delay a maximum of 13.7%, 8.4% and 19.8%, respectively. Also, our proposed design is compared with the design of Booth multiplier with approximate Booth encoding and conventional carry look-ahead adder for product generation. The proposed 8-bit multiplier design-II reduced power consumption, area and delay by a maximum of 38.2%, 28.3% and 13.7%, respectively. [ABSTRACT FROM AUTHOR]

In this paper, we present a new Multiple learning to prediction algorithm model that used three different combinations of machine-learning methods to improve the accuracy of the α-β filter algorithm. The parameters of α and β were tuned in dynamic conditions instead of static conditions. The proposed system was designed to use the deep belief network (DBN), the deep extreme learning machine (DELM), and the SVM as three different learning algorithms. Then these learned parameters were trained by the machine-learning algorithms tuned to the α-β filter algorithm as a prediction module, and they gave the final predicted results. The MAE and RMSE were used to evaluate the performance of the proposed α-β filter with different learning algorithms. Each algorithm recorded different best-case accuracy results; for the DBN, we achieved 3.60 and 2.61; for the DELM, we obtained the best-case result of 3.90 and 2.81; and finally, for the SVM, 4.0 and 3.21 were attained in terms of the RMSE and MAE, respectively, as compared to 5.21 and 3.95. When assessed in comparison with the typical alpha–beta filter algorithm, the proposed system provided results with better accuracy. [ABSTRACT FROM AUTHOR]

Sprayed concrete lining is a commonly employed support measure in tunnel engineering, which plays an important role in construction safety. Compressive strength is a key performance indicator of sprayed concrete lining, and the traditional measuring method is time-consuming and laborious. This paper proposes various hybrid machine learning algorithms to accomplish the advanced prediction of compressive strength of sprayed concrete lining based on the mixture design. Two hundred and five sets of experimental data were collected from a water conveyance tunnel in north western China for model construction, and each set of data was made up of six basic input variables (i.e., water, cement, mineral powder, superplasticizer, coarse aggregate, and fine aggregate) and one output variable (i.e., compressive strength). In order to eliminate the correlation between input variables, a new composite indicator (i.e., the water-binder ratio) was introduced to achieve dimensionality reduction. After that, four hybrid models in total were built, namely BPNN-QPSO, SVR-QPSO, ELM-QPSO, and RF-QPSO, where the hyper-parameters of BPNN, SVR, ELM, and RF were auto-tuned by QPSO. Engineering application results indicated that RF-QPSO achieved the lowest mean absolute percentage error (MAPE) of 3.47% and root mean square error (RMSE) of 1.30 and the highest determination coefficient (R² ) of 0.93 in the four hybrid models. Moreover, RFQPSO had the shortest running time of 0.15 s, followed by SVR-QPSO (0.18 s), ELM-QPSO (1.19 s), and BPNN-QPSO (1.58 s). Compared with BPNN-QPSO, SVR-QPSO, and ELM-QPSO, RF-QPSO performed the most superior performance in terms of both prediction accuracy and running speed. Finally, the importance of input variables on the model performance was quantitatively evaluated, further enhancing the interpretability of RF-QPSO. [ABSTRACT FROM AUTHOR]

Background: Under-five mortality is a matter of serious concern for child health as well as the social development of any country. The paper aimed to find the accuracy of machine learning models in predicting under-five mortality and identify the most significant factors associated with under-five mortality. Method: The data was taken from the National Family Health Survey (NFHS-IV) of Uttar Pradesh. First, we used multivariate logistic regression due to its capability for predicting the important factors, then we used machine learning techniques such as decision tree, random forest, Naïve Bayes, K- nearest neighbor (KNN), logistic regression, support vector machine (SVM), neural network, and ridge classifier. Each model's accuracy was checked by a confusion matrix, accuracy, precision, recall, F1 score, Cohen's Kappa, and area under the receiver operating characteristics curve (AUROC). Information gain rank was used to find the important factors for under-five mortality. Data analysis was performed using, STATA-16.0, Python 3.3, and IBM SPSS Statistics for Windows, Version 27.0 software. Result: By applying the machine learning models, results showed that the neural network model was the best predictive model for under-five mortality when compared with other predictive models, with model accuracy of (95.29% to 95.96%), recall (71.51% to 81.03%), precision (36.64% to 51.83%), F1 score (50.46% to 62.68%), Cohen's Kappa value (0.48 to 0.60), AUROC range (93.51% to 96.22%) and precision-recall curve range (99.52% to 99.73%). The neural network was the most efficient model, but logistic regression also shows well for predicting under-five mortality with accuracy (94% to 95%)., AUROC range (93.4% to 94.8%), and precision-recall curve (99.5% to 99.6%). The number of living children, survival time, wealth index, child size at birth, birth in the last five years, the total number of children ever born, mother's education level, and birth order were identified as important factors influencing under-five mortality. Conclusion: The neural network model was a better predictive model compared to other machine learning models in predicting under-five mortality, but logistic regression analysis also shows good results. These models may be helpful for the analysis of high-dimensional data for health research. [ABSTRACT FROM AUTHOR]

This paper presents the machine learning (ML) method, a novel approach that could be a profitable idea to optimize fleet management and achieve a sufficient output to reduce operational costs, by diminishing trucks' queuing time and excavators' idle time, based on the best selection of the fleet. The performance of this method was studied at the Zenouz kaolin mine to optimize the type of loader and the number of trucks used to supply the processing plant's ore demands. Accordingly, five years' data, such as dates, weather conditions, number of trucks, routes, loader types, and daily hauled ore, were collected, adapted, and processed to train the following five practical algorithms: linear regression, decision tree, K-nearest neighbour, random forest, and gradient boosting algorithm. By comparing the results of the algorithms, the gradient boosting decision tree algorithm was determined to be the best fit and predicted test data values with 85% accuracy. Subsequently, 11,322 data were imported into the machine as various scenarios and daily hauled minerals as output results were predicted for each working zone individually. Finally, the data which had the minimum variation from the selected required scheduled value, and its related data concerning loader type and the number of demanded trucks, were indicated for each day of the working year. [ABSTRACT FROM AUTHOR]

In this paper, a new ensemble forecasting model for short-term load forecasting (STLF) is proposed based on extreme learning machine (ELM). Four important improvements are used to support the ELM for increased forecasting performance. First, a novel wavelet-based ensemble scheme is carried out to generate the individual ELM-based forecasters. Second, a hybrid learning algorithm blending ELM and the Levenberg–Marquardt method is proposed to improve the learning accuracy of neural networks. Third, a feature selection method based on the conditional mutual information is developed to select a compact set of input variables for the forecasting model. Fourth, to realize an accurate ensemble forecast, partial least squares regression is utilized as a combining approach to aggregate the individual forecasts. Numerical testing shows that proposed method can obtain better forecasting results in comparison with other standard and state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The paper demonstrates the dependability of assignment testing in the identification of an appropriate breed to monitor comprehensive genetic information from molecular markers to analyse the collection of real population data covering 22 horse breeds registered in the Czech Republic, including native breeds and genetic resources. If 17 microsatellites are used, the mean number of alleles per locus corresponds to 10.4. The count of alleles at the individual loci ranges between five (HTG07) and 17 (ASB17). The loci ASB02, ASB23, HMS03, HTG10, and VHL20 exhibit the highest gene diversity and observed heterozygosity (both above 80%), with the mean value of 0.77 and 0.73, respectively. The moderate total inbreeding coefficient (5.2%) is estimated across all the loci and breeds. The levels of apparent breed differentiation span from zero between the Czech Warmblood and Slovak Warmblood to 0.15 between the Shetland Pony and Standardbred. The phylogenetic breed relationships are revealed via the NeighbourNet dendrogram constructed from Reynolds' genetic distances, which clearly separate the Coldblood draught, Hot/Warmblood, and Pony horses. Our results reveal that the Bayesian approach (the Rannala and Mountain technique) provides the most intensive prediction power (83.6%) out of the GENECLASS tools and that the Bayes Net algorithm exhibits the best efficiency (78.4%) from the WEKA machine learning workbench options, considering the use of the five-fold cross validation technique. The algorithms could be trained on large real reference data sets, and thus there appears another viable perspective for machine learning in horse ancestry testing. In this context, it is also important to stress the fact that innovated computational tools will potentially lead towards structuring a novel web server to allow the identification of horse breeds. [ABSTRACT FROM AUTHOR]

Outlier detection is critical in many business applications, as it recognizes unusual behaviours to prevent losses and optimize revenue. For example, illegitimate online transactions can be detected based on its pattern with outlier detection. The performance of existing outlier detection methods is limited by the pattern/behaviour of the dataset; these methods may not perform well without prior knowledge of the dataset. This paper proposes a multi-level outlier detection algorithm (MCOD) that uses multi-level unsupervised learning to cluster the data and discover outliers. The proposed detection method is tested on datasets in different fields with different sizes and dimensions. Experimental analysis has shown that the proposed MCOD algorithm has the ability to improving the outlier detection rate, as compared to the traditional anomaly detection methods. Enterprises and organizations can adopt the proposed MCOD algorithm to ensure a sustainable and efficient detection of frauds/outliers to increase profitability (and/or) to enhance business outcomes. [ABSTRACT FROM AUTHOR]

A key aspect of life cycle management for pursuing sustainability is machine condition prognosis, which requires a condition monitoring system that estimates machine system deterioration to assist engineers in determining which maintenance actions to take. Conventional data-driven methods such as machine learning, have two issues. One is data dependency. The accuracy of a data-driven method depends on the data volume because a data-driven method builds a classification model on the basis of historical data as training data. However, it is difficult to acquire enough data on all deterioration modes, which requires a long time, because deterioration modes are diverse, and some of them rarely happen. The other issue is interpretability. When a condition monitoring system using a data-driven method sends the degree of deterioration (DoD) of the machine system to maintenance engineers, they have difficulty in understanding the results because the method is a black box. The objective of this paper is to address these two issues. We propose a model-based method that simulates machine system deterioration with a cyber physical system (CPS). Model-based methods address these issues in the following manner. First, the methods can simulate the progress of deterioration from an initial condition to failure to estimate the DoD. Second, the methods employ mathematical models that represent machine systems. Engineers create such mathematical models (which we call "physical models") by referring to various kinds of knowledge like design information and the result of failure mode and effects analysis. A physical model allows us to reason about a machine system to address interpretability. For dealing with machinery that has multiple operation modes, we introduce a state space to clarify the relationship among input, observable state variables, and DoD in a physical model. The CPS estimates DoD by comparing observed data with simulated data in the state space. In our case study, we evaluated our proposed method with a hydraulic pump of a mining machine. First we created a physical model with Modelica, which is a multi-domain modeling language. Then, the method constructed the state space by simulating deterioration with the physical model given all combinations of inputs and DoD. After that, we showed that the estimated DoD tended to increase until the hydraulic pump was replaced, using the observed data from an actual mining machine. As a result, the experimental results revealed that the proposed method succeeded in identifying the DoD with observed data of the hydraulic pump of a mining machine. [ABSTRACT FROM AUTHOR]

By utilizing kernel functions, support vector machines (SVMs) successfully solve the linearly inseparable problems. Subsequently, its applicable areas have been greatly extended. Using multiple kernels (MKs) to improve the SVM classification accuracy has been a hot topic in the SVM research society for several years. However, most MK learning (MKL) methods employ L1-norm constraint on the kernel combination weights, which forms a sparse yet nonsmooth solution for the kernel weights. Alternatively, the Lp-norm constraint on the kernel weights keeps all information in the base kernels. Nonetheless, the solution of Lp-norm constraint MKL is nonsparse and sensitive to the noise. Recently, some scholars presented an efficient sparse generalized MKL (L1- and L2-norms based GMKL) method, in which L1  L2 established an elastic constraint on the kernel weights. In this paper, we further extend the GMKL to a more generalized MKL method based on the p-norm, by joining L1- and Lp-norms. Consequently, the L1- and L2-norms based GMKL is a special case in our method when p=2. Experiments demonstrated that our L1- and Lp-norms based MKL offers a higher accuracy than the L1- and L2-norms based GMKL in the classification, while keeping the properties of the L1- and L2-norms based on GMKL. [ABSTRACT FROM AUTHOR]

Several organizations are implementing large-scale Internet of Things (IoT)-based ecosystems, such as Industrial IoT (IIoT). Such systems are vulnerable to new threats and intrusions because of the nature of their networks. It is necessary to secure such systems by developing feature selection integrated with robust machine learning models. In this paper, a two-phase IIoT traffic prediction model is built for detecting normal and anomalous IIoT behavior. The system is divided into two phases. In the first phase, multi-objective non-dominated sorting with whale optimization approach (MNSWOA) and ideal point method (IPM) is implemented for feature selection. The key quality attributes are retrieved for effective classification. In the second phase, the feature selection results are sent to the random forest (RF) classifier for traffic prediction. Experimental results on IIoT datasets, namely CTU-13, AWID and Gas–Water show that the proposed technique MNSWOA–IPM–RF obtains enhanced performance in terms of accuracy, true positive rate, true negative rate and area under the ROC curve. Also, comparisons indicate that the proposed MNSWOA–IPM–RF model has superior results than benchmark multi-objective optimization techniques. [ABSTRACT FROM AUTHOR]

This paper presents a novel, sequentially executed supervised machine learning‐based electric theft detection framework using a Jaya‐optimized combined Kernel and Tree Boosting (KTBoost) classifier. It utilizes the intelligence of the XGBoost algorithm to estimate the missing values in the acquired dataset during the data pre‐processing phase. An oversampling algorithm based on the Robust‐SMOTE technique is utilized to avoid the unbalanced data class distribution issue. Afterward, with the aid of few very significant statistical, temporal, and spectral features extracted from the acquired kWh dataset, the complex underlying data patterns are comprehended to enhance the accuracy and detection rate of the classifier. For effectively classifying the consumers into "Honest" and "Fraudster," the ensemble machine learning‐based classifier KTBoost, with Jaya algorithm optimized hyperparameters, is utilized. Finally, the developed model is re‐trained using a reduced set of highly important features to minimize the computational resources without compromising the performance of the developed model. The outcome of this study reveals that the proposed theft detection method achieves the highest accuracy (93.38%), precision (95%), and recall (93.18%) among all the studied methods, thus signifying its importance in the studied area of research. [ABSTRACT FROM AUTHOR]

With a sharp increase in the information volume, analyzing and retrieving this vast data volume is much more essential than ever. One of the main techniques that would be beneficial in this regard is called the Clustering method. Clustering aims to classify objects so that all objects within a cluster have similar features while other objects in different clusters are as distinct as possible. One of the most widely used clustering algorithms with the well and approved performance in different applications is the k-means algorithm. The main problem of the k-means algorithm is its performance which can be directly affected by the selection in the primary clusters. Lack of attention to this crucial issue has consequences such as creating empty clusters and decreasing the convergence time. Besides, the selection of appropriate initial seeds can reduce the cluster's inconsistency. In this paper, we present a new method to determine the initial seeds of the k-mean algorithm to improve the accuracy and decrease the number of iterations of the algorithm. For this purpose, a new method is proposed considering the average distance between objects to determine the initial seeds. Our method attempts to provide a proper tradeoff between the accuracy and speed of the clustering algorithm. The experimental results showed that our proposed approach outperforms the Chithra with 1.7% and 2.1% in terms of clustering accuracy for Wine and Abalone detection data, respectively. Furthermore, achieved results indicate that comparing with the Reverse Nearest Neighbor (RNN) search approach, the proposed method has a higher convergence speed. [ABSTRACT FROM AUTHOR]