Search

Condition monitoring and predictive maintenance applications receive ongoing scientific attention in production technology. Larger companies, especially machine and component manufacturers, already offer related products. Small and medium-sized enterprises (SMEs) in particular show interest in developing and offering solutions in this market themselves to gain economic advantages, to improve resource utilization of their machines or to be able to offer these advantages to their own customers. In the development process, however, they often encounter problems already in the digitization of the machines. The first hurdle is to obtain an analysis-capable data set. This is due to the fact that common and established general data mining development process models, such as CRISP-DM, do not focus on production technology, causing difficulties for engineers during deployment. A problem with existing process models is the limited practicality in the engineering domain due to restricted adaptability. In a previous paper, a guideline for engineers for data mining suitable digitization of production machines was developed in order to solve these problems. The related results were provided in the context of a project for condition monitoring of mixing machines. In this paper, the proposed method is applied to components of a 5-axis CNC milling machine in three different monitoring use cases. A complete workflow is presented, including effect analysis, sensor selection, formulation of predictive scenarios, data preparation, training of machine learning algorithms and vizualization. Data and documentation are provided alongside this publication. [ABSTRACT FROM AUTHOR]

Many research studies confirmed that the application of machine learning methods for predicting students at risk of academic failure can be beneficial for improving student performance in higher education institutions. Simultaneously, these studies emphasised the importance of the input data quality, its precise pre-processing and thoroughly selected features on final performance metrics of the applied classification algorithms. However, the stand-alone application of well-known classification algorithms still has performance limitations, which can be outperformed using ensembles of classifiers. Therefore, this paper aims to evaluate the overall contribution of the selected ensemble methods to the early prediction of students at risk of dropping out of learning courses. All phases of CRISP-DM methodology are described in this study to explain the complexity of the problem of the practical adoption of voting-based heterogeneous ensemble methods in the case of data obtained from the course of the university learning management system compared to traditional classification algorithms enhanced by ensemble learning with AdaBoost and XGBoost methods. As a result, the study confirmed that the features which characterise the students' performance and their interactions in the course can be considered the most significant for the identification of the students at risk of dropping out. Moreover, in the case of advanced ensemble algorithms, the overall accuracy, recall, precision, and f1 score were improved by 2-4%. The proposed method has demonstrated exceptional performance. Finally, the paper summarises the findings and their implications for effective prediction. [ABSTRACT FROM AUTHOR]

The competitive airline sector has grown at a breakneck pace in the last two decades. A useful source for collecting consumer feedback and performing various forms of analysis on it is proper data collection. This collection of data can be used for sentiment analysis. Sentiment analysis is a type of analysis that involves extracting sentiment to find attitudes and emotions associated with the text or data supplied. It's a classification approach in which machine learning techniques are used to identify positive and negative words or reviews in text-driven databases. Further to explain the reasons for negative comments, a word cloud and a bar graph are used. Sentiment analysis is used to analyze the Airline reviews dataset in this paper. To test the performance of sentiment analysis, many Machine Learning (ML) algorithms have been utilized, such as Naive Bayes, Support Vector Machine, and Decision Tree (DT), and each of these approaches has produced distinct results. The performance of Google's BERT algorithm has been evaluated to that of other machine learning algorithms in our research. Furthermore, this paper explores the Bert architecture, which has been pre-trained on two NLP tasks: Masked language modeling and Sentence prediction. The "Random Forest" is used as a baseline against which the results of the "BERT Model" are compared because its performance is the best among the machine learning models. In terms of performance criteria such as accuracy, precision, recall, and F1-score, it is discovered that BERT outperformed the other ML techniques. [ABSTRACT FROM AUTHOR]

Accuracy of a classifier is important for the success of any prediction model. The more accuracy a classifier possesses, the more robust the system is made on it. In this paper, a disease prediction model is developed in Python for the classification of diabetes in patients. In the research paper, study is performed to make a comparative analysis of the performance of machine learning classification algorithms. The classifier's performances are enhanced by of tuning the hyperparameters of classifiers and applied different dataset preprocessing methods. In this experimental analysis, four models have been created, and each model is based on a dataset, obtained by different preprocessing methods of PIMA dataset. For each model, K-Nearest Neighbors, Decision Tree, Random Forest, and Support vector machines classification algorithms, have been applied and classifier's hyperparameters are tuned to get better results from these models. A detail analysis has also performed to get the best prediction model, the best classifier and effective preprocessing methods for it. The prediction model use F1score as the main metric. The highest F1score and accuracy are 75.68 % and 88.61% respectively, which is achieved by Random Forest classifier for dataset model D3 obtained by removing the samples having missing or unknown values from PIMA dataset. [ABSTRACT FROM AUTHOR]

Predicting faults in software aims to detect defects before the testing phase, allowing for better resource allocation and high-quality software development, which is a requisite for any organization. Machine learning techniques aid in the resolution of such issues and a variety of predictive models are being developed to categorize the software into defective modules and the one which is non-defective ones. Though applying these advanced machine learning techniques results in better utilization of time and other resources, there is still poor prediction as reported in many studies. This is because of several challenges that block defective software data, including redundancy, correlation, feature irrelevance, missing samples, and an imbalanced distribution between the faulty and non-faulty classes. Ensemble Machine learning has been adopted by practitioners and researchers globally to deal with such problems, and it is proven to demonstrate some improvement in defect prediction performance. In this review paper, all ensemble-based machine learning techniques developed for software defect prediction from 2018 to 2021 have been critically analyzed. The nucleus of this paper is to get a deep insight into why the various hybrid models still suffer from poor performance on the available datasets. A detailed review with a focus on multiple perspectives viz. faulty and non-defective datasets, performance evaluation criteria, and machine learning techniques have revealed certain gaps that can be addressed by developing more robust hyperparameter optimization algorithms, feature engineering, developing stacking and averaging models. [ABSTRACT FROM AUTHOR]

The dynamism of our digital universe systems presents a key challenge for predictive analytics. Ensuring the model's ability to generalize beyond the training data is crucial for reliable predictions. Recent research has primarily focused on understanding and addressing the phenomenon of concept drift: the changes in the system that afect the model's accuracy. This paper aims to resolve this issue by introducing an online technique implemented using Light Gradient Boosting Machine (LGBM) classifier for concept drift detection and adaptation. Online LGBM is adjusted incrementally based on the most recent information, allowing it to adapt to changing patterns in the data stream. The proposed technique attempts to leverage incremental learning, ensemble learning, and the sliding window method to deal with concept drift. The experiments on Electricity, Spam and MixedAbrupt Drift datasets result in higher accuracy 86.77%, 97.67%, and 65.25% as compared to the ofine LGBM with lower accuracy 71.52%, 90.86%, and 50.01% respectively. The hyperparameters of LGBM are optimized using the Bayesian method. [ABSTRACT FROM AUTHOR]

Significant changes have been observed from 2019 in the COVID period as study styles shifted from traditional to hybrid learning. This paper predicted the applicability of the hybrid learning mode of education in the programming labs for the informatics faculty. It explored novel vital features that predicted the applicability of hybrid learning in the practical labs of the informatics domain. For this, the Classification and Regression Tree (CART) identified the relevance of hybrid education with an accuracy of 71.7%. The confusion matrix of the CART model has 67.3% correctness (sensitivity) for "Yes", and 76% correctness (specificity) for "No" during validation. The false negative rate (type II error) is 32.7%, and the false positive rate (type I error) is 24%. The AUC value of the CART model is 0.68. Some obstacles were identified, such as isolation from the natural study environment, reduced quality of interaction with other faculty, and turning o ff the mic or camera during labs. Also, it was found that the university initiated and provided support to create less stress and ease of communication. Adopting the Hyrbid learning mode is unsuitable for handling group tasks or projects in the laboratory. Also, the hybrid learning mode proved a vital mode of study in practical labs as online learning with a safe environment. [ABSTRACT FROM AUTHOR]

Vehicle detection and classification is one of the major challenges for automated traffic surveillance as well as for military defence systems to identify enemy vehicles. For efficient real-time surveillance, accurate detection and classification of many vehicle kinds, including cars, trucks, buses, and so forth are important. This paper focuses on different methods of machine learning used toidentify thevehicle and then then categorize each vehicle according to the classes. It also explores the critical insight of existing vehicle detection and classification approaches using various machine learning methods like YOLO, CNN, R-CNN, and AdaBoost. The majority of the research projects now in existence solely consider increasing image-based accuracy, which has poor real-time performance and uses more computational resources. [ABSTRACT FROM AUTHOR]

Traffic congestion has become a critical issue in metropolitan areas, inflicting significant hardships on individuals on a daily basis. This adverse situation poses multifaceted challenges, including increased air pollution, heightened fuel consumption, and compromised road safety. Deep learning algorithms, encompassing both Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) have showcased remarkable performance in areas such as computer vision, natural language processing, healthcare, finance, and autonomous systems. This research paper proposes a novel methodology to develop a vehicle detection model - VehiNet, which can subsequently be refined to create an automated traffic signal system. The study explores the effectiveness of various CNN, RNN, and deep learning algorithms and techniques in accomplishing this objective. The dataset picked for the study in addition to being compiled from internet resources, was also painstakingly assembled manually using a variety of methods to collect over 2000 photographs from various angles, lighting conditions, and locations within Bengaluru city. The main motive is to apply CNN, RNN, and other Deep Learning classification techniques for object detection and classification of Indian vehicles and see how well these deep learning algorithms and techniques affect prediction efficiency. This research stands out from others and makes its novelty clear thanks to the carefully collected dataset and the detailed analysis of the methodologies. [ABSTRACT FROM AUTHOR]

There are various paradigms of learning. One such paradigm is learning from knowledge assimilation. In machine learning, such a paradigm may be considered where concepts (classification models) generated from different algorithms applied to the same training data are combined to come up with a single integrated improved concept (classification model). This is different from combining outputs of various models as in Bagging or Boosting. Thus, learning from knowledge assimilation creates different alternative models that work on different parts of the search space. Such models can be separately optimized so that the best-performing model can be selected for the given problem. For optimization there are several algorithms and Chemical Reaction Optimization (CRO) is a chemistry-based nature-inspired optimization algorithm. In this algorithm, a set of optimization approaches are introduced corresponding to various types of chemical reactions. Classification models in our approach are optimized using a technique called Elitist CRO(ECRO). ECRO is an improvement over CRO, where the optimization approaches are modified making the convergence of the algorithm better than CRO. Although for classification CRO models based on neural networks exist, however, they suffer from interpretability. This paper proposes an application of a new Hybrid Elitist Chemical Reaction Optimization (HECRO) algorithm to generate interpretable classification rules. The proposed algorithm is an extension of CRO and ECRO, in the manner of region exploration of the search space, which is expanded by combining classification rules generated from various algorithms as the initial population following learning from knowledge assimilation. Experimental results with 20 datasets drawn from the UCI Machine Learning data repository show improvement over several performance measures in comparison to the base classifiers used for population generation in HECRO. [ABSTRACT FROM AUTHOR]

Techniques for classifying data using data mining are now a day prevalent in agriculture. The method of classifying seeds involves grouping various seed varieties according to their morphological characteristics. To accomplish categorization of the typical Charotar region (generally comprising Anand and Kheda districts of the Gujarat State of India) Gujarat Wheat (GW) varieties (TRITICUM – AESTIVUM) viz. GW 273, GW 496, GW 322, LOK-1, and GDW 1255 (TRITICUM – DURUM), Weka Explorer was used. The features used are area, perimeter, solidity, aspect ratio, major and minor axis of seed kernel, Hue, Saturation, Value, and SF1 (empirical). Features reduction was done using Information Gain (IG) and its modified version Gain Ratio (GR). This paper compares performance of Tree based data mining algorithms in classifying wheat varieties. For classification we used purely tree-based machine learning algorithms viz. J48, Random Forest, Hoeffding Tree, Logistic Model Tree (LMT), and REPTree. LMT- logistics regression method gives higher accuracy 96.4% compared to other classifiers. Hoeffding Tree classifiers stood second with 96% accuracy. For validation 10-fold cross validation was used. By reducing the number of folds in cross validation performance of most algorithms decreased except J48. The percentage of correctly classified instance increased for all algorithms when features were selected by GR except for J48. [ABSTRACT FROM AUTHOR]

The implementation of intelligent techniques produces good results in automating fault finding and predicting future outcomes. These approaches have been on the increase in the past years, especially so to detect faults within Compressed Air Systems (CASs). With the use of intelligent techniques, one could minimise the manual and time-consuming aspect of CAS maintenance, improve the environmental impact of the system, while minimising downtime. This paper proposes a general framework for the implementation of intelligent analysis techniques within a real-world system. Such an approach has been implemented on the demand-side of a CAS. In literature, no open datasets are available for use by artificial intelligence models. Hence, as part of this research, a fault generating and monitoring system has been connected to an existing production machine in a manufacturing site to collect the required data. Two classification machine learning methods were implemented and compared across a number of performance metrics. Both the general framework, and its implementation, provide a stepping stone in integrating smart systems with real-time intelligent data analytics for the demand-side of a CAS. These systems would provide a sustainable CAS operation through the effective detection of anomalies and their timely repair. [ABSTRACT FROM AUTHOR]

• The article proposed a novel methodology for automated surface electromyography (sEMG) signal analysis focusing on diverse machine learning models, and hyperparameter optimization achieving an F1-Score of 98.71 % with the XGBoost algorithm. • Hyperparameter tuning was performed for each model using the scikit-learn library. The paper provides detailed information on the best hyperparameter settings for XGBoost, Extra Trees, LGBM, SVM, and Neural Networks. • The models were trained on a dataset featuring muscle contractions and extensions in distinct body regions. This diverse training set aimed to capture the complexities and variations encountered in real-world surface electromyography (sEMG) applications. • The paper employs non-parametric tests, including Friedman's test and post-hoc tests, to assess the significance of differences among the models. Visualizations and statistical analysis provide insights into algorithm performance based on F1-Score, Precision, and Recall. • The models showcased practicality for real-world applications, supporting clinicians in diagnosing neuromuscular disorders and advancing human–machine interfaces. This paper presents a methodology for automatically detecting muscular activity by denoising, extracting features, and classifying surface electromyography (sEMG) signals. The proposed methodology utilizes the Discrete Wavelet Transform (DWT) and Willison's Amplitude Algorithm (WAMP) for feature extraction. Five classification methods, including Neural Networks (NN), Classification Vector, XGBoost, Light Gradient Boosting Machine (LGBM), and ExtraTree, were evaluated using F-Measure, Precision, and Recall as performance metrics. Through k-fold cross-validation, the XGBoost algorithm, when combined with the Eigen values feature, achieved the highest training performance with an F1-Score of 98.71 %. For the test group, the LGBM classifier using WAMP, and NN with both WAMP and Eigen values as features, demonstrated the best average performance with F1-Scores of 96.52 ± 3.45 % and 96.52 ± 3.07 %, respectively. These results highlight the precision and performance of the proposed approach in detecting EMG signals. Moreover, the framework has the potential to support clinicians in diagnosing neuromuscular disorders and developing human–machine interfaces. [ABSTRACT FROM AUTHOR]

This paper proposes a novel algorithm for incremental learning over streaming data in a non-stationary environment. The idea refers to the applicability of Probabilistic Neural Networks (PNNs), commonly used as a fast and robust method for solving classification problems in a stationary scenario. It is well known that PNNs have solid mathematical foundations but they fail in the non-stationary scenario and are not able to deal with concept drift. In this paper, the method based on the orthogonal series expansions of unknown probability densities is proposed. This approach significantly extends the applicability of the PNNs. The nonparametric procedures called Incremental Probabilistic Neural Networks (IPNNs) for tracking drifting probability densities or conditional class densities, in the case of classification, are presented. We prove their convergence as the stream data size is growing to infinity. More precisely, we show convergence in probability and with probability one as the sample size tends to infinity. Compared to the existing literature, almost exclusively based on various heuristics, the proposed method is mathematically justified and has solid theoretical foundations. Simulations performed on synthetic and air pollution data confirm the effectiveness of the algorithm. • The incremental version of the Probabilistic Neural Network (IPNN) based on the orthogonal series, able to work in non-stationary environments. • Mathematical proofs of the convergence of the proposed estimators for different types of concept drift. • Extension to the classification task, using estimated density functions as discriminant functions. • Application of the proposed IPNN to air pollution monitoring. [ABSTRACT FROM AUTHOR]

Emotion recognition based on electroencephalography (EEG) signal features is now one of the booming big data research areas. As the number of commercial EEG devices in the current market increases, there is a need to understand current trends and provide researchers and young practitioners with insights into future investigations of emotion recognition systems. This paper aims to evaluate popular consumer-grade EEG devices' status and review relevant studies that examined the reliability of these low-cost devices for emotion recognition over the last five years. Additionally, a comparison with research-grade devices is conducted. This paper also highlights EEG-based emotion recognition research's key areas, including different feature extraction capabilities, characteristics, and machine learning algorithms. Finally, the main challenges for building an EEG-based emotion recognition system, focusing on the data collection process with commercial EEG devices and machine learning algorithms' performance, are presented. [ABSTRACT FROM AUTHOR]

Cardiotocogram (CTG) is one of the monitoring tools to estimate the fetus health in womb. CTG mainly yields two results fetal health rate (FHR) and uterine contractions (UC). In total, there are 21 attributes in the measurement of FHR and UC on CTG. These attributes can help obstreticians to clasify whether the fetus health is normal, suspected, or pathological. This paper compares 7 algorithms to predict the fetus health: Artificial Neural Network (ANN), Long-short Term Memory (LSTM), XG Boost (XGB), Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Light GBM (LGBM), and Random Forest (RF). By employing three scenarios, this paper reports the performance measurements among those algorithms. The results show that 5 out of 7 algorithms perform very well (89-99% accurate). Those five algorithms are XGB, SVM, KNN, LGBM, RF. Furthermore, only one from five algorithm that always performs well through three scenarios: LGBM. [ABSTRACT FROM AUTHOR]

Sensor technologies for mastitis detection have resulted in the collection and availability of a large amount of data. As a result, scientific publications reporting mastitis detection research have become less driven by approaches based on biological assumptions and more by data-driven modeling. Most of these approaches try to predict mastitis events from (combinations of) raw sensor data to which a wide variety of methods are applied originating from machine learning and classical statistical approaches. However, an even wider variety in terminologies is used by researchers for methods that are similar in nature. This makes it difficult for readers from other disciplines to understand the specific methods that are used and how these differ from each other. The aim of this paper was to provide a framework (filtering, transformation, and classification) for describing the different methods applied in sensor data–based clinical mastitis detection research and use this framework to review and categorize the approaches and underlying methods described in the scientific literature on mastitis detection. We identified 40 scientific publications between 1992 and 2020 that applied methods to detect clinical mastitis from sensor data. Based on these publications, we developed and used the framework and categorized these scientific publications into the 2 data processing techniques of filtering and transformation. These data processing techniques make raw data more amendable to be used for the third step in our framework, that of classification, which is used to distinguish between healthy and nonhealthy (mastitis) cows. Most publications (n = 34) used filtering or transformation, or a combination of these 2, for data processing before classification, whereas the remaining publications (n = 6) classified the observations directly from raw data. Concerning classification, applying a simple threshold was the most used method (n = 19 publications). Our work identified that within approaches several different methods and terminologies for similar methods were used. Not all publications provided a clear description of the method used, and therefore it seemed that different methods were used between publications, whereas in fact just a different terminology was used, or the other way around. This paper is intended to serve as a reference for people from various research disciplines who need to collaborate and communicate efficiently about the topic of sensor-based mastitis detection and the methods used in this context. The framework used in this paper can support future research to correctly classify approaches and methods, which can improve the understanding of scientific publication. We encourage future research on sensor-based animal disease detection, including that of mastitis detection, to use a more coherent terminology for methods, and clearly state which technique (e.g., filtering) and approach (e.g., moving average) are used. This paper, therefore, can serve as a starting point and further stimulates the interdisciplinary cooperation in sensor-based mastitis research. [ABSTRACT FROM AUTHOR]

Environmental Sound classification (ESC) is crucial in various fields such as audio surveillance, wildlife conservation, and acoustic monitoring. However, traditional methods often struggle to handle the curse of dimensionality and the limitations of classical machine learning algorithms. In the paper, a novel approach is proposed for ESC using a Quantized Hybrid Quantum-Classical Neural Network (QQNN), which leverages the potential advantages of quantum computing. The Hybrid QQNN architecture aims to reduce the required parameters and achieve performance comparable to traditional methods. It uses a set of pre-trained layers to reduce the number of features for the parameterized quantum circuit (PQC). This approach was evaluated using the ESC-10 dataset in Pennylane's environment to train the hybrid quantum model. The results demonstrate that the proposed Hybrid QQNN approach achieves comparable accuracy with the classical machine learning methods. This opens up the possibility of performing additional transfer learning in the future. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to investigate whether it is possible to predict text readability with ensemble-based classifiers. In this article, the authors calculated and analyzed the readability indices. In the next stage, they defined additional features for each text and determined the relationships between readability and features. Among the various tasks of machine learning, they chose the classification problem. The authors calculated and compared the accuracy of different machine learning models. After building the models, they proceeded to the Random decision forests model interpretation step using the SHAP method. The authors show that machine learning models based on only three features are capable of predicting text readability. Long sentences and a low percentage of stop words can cause low readability. The machine learning model shown in this paper allows to classify texts according to readability with a model accuracy of 0.9. [ABSTRACT FROM AUTHOR]

Weather data of Kashmir province has 6 attributes recorded at three different substations. This paper proposes a distributed decision tree algorithm and its implementation on Historical Geographical data of Kashmir province. The machine learning Decision tree algorithm applied on the Kashmir province dataset generates the accuracy of 81.54%. The distributed decision tree generates multiple trees based on the partitions of the original dataset in which the data is segregated according to the substations (42026, 42027 and 42044). The ratio between generated data sets was distributed in 32.38%, 34.19% and 33.42% respectively which is appropriate for the parallelism. Its distributed implementation, i.e. Distributed Decision Tree produces a specified number of sub-trees (depending upon number of partitions of input dataset) and at the end collects votes or averages the prediction or classification. In this paper, we have implemented the hard- voting approach to calculate the overall performance of the n-number of trees in distributed environment. The empirical results demonstrate that distributed decision trees approach has not improved the overall accuracy as compared to the original dataset without partitioning. [ABSTRACT FROM AUTHOR]

• Pinch force strength is accurately predicted using sEMG. • Different pinch movements are accurately classified using sEMG. • Similarity of EMG features is evaluated. • An EMG feature-to-image method is proposed. The movement of intelligent EMG-driven prosthesis mainly relies on the synergy of different fingers to achieve function of grasping objects. The paper proposes a novel scheme for force prediction and movement classification about pinch between different fingers based on surface electromyography (sEMG) using machine learning. The pinch force and sEMG signals are recorded synchronously by a data acquisition device. Eight features are extracted, which are proven to have better performance in the estimation of sEMG-to-force. We present a novel feature selection method that uses the one-dimensional time series similarity assessment based on Manhattan distance to eliminate the repetitive information between features. Three optimal features carrying less repetitive information are retained. Seven machine learning algorithms are used to predict force strength. The results show that the Long Short Term Memory (LSTM) has the best performance of force prediction, achieving a R 2 of 0.9517 and RMSE of 3.2723. The paper proposes a novel method of converting EMG feature sequences to the normalized gray image in order to classify the finger movement. Five classifiers based on image feature extraction and the Convolutional Neural Network (CNN) are developed respectively. The experimental results indicate that the CNN performs best, achieving an accuracy of 97.66%. In this way, it not only realizes the accurate force prediction, but also realizes the movement classification between different fingers. The proposed methodology has the potential to realize simultaneous force and movement control of prosthetic hand. [ABSTRACT FROM AUTHOR]

Uncertainty and imprecision accompany the world we live in and occur in almost every event. How to better interpret and manage uncertainty and imprecision play a vital role in machine learning (ML). As an effective tool for modeling imperfection, the theory of belief functions (TBF) has attracted substantial attention by providing a flexible discernment of framework for effectively representing uncertainty and imprecision. To date, many TBF-based methods have been proposed in ML, but they have not yet been comprehensively summarized. This paper surveys TBF-based methods for representing uncertainty and imprecision in ML, focusing on clustering, classification and information fusion. First, we provide a formal definition of uncertainty and imprecision reasoning. On this basis, we survey the existing TBF-based methods in detail and explain how to characterize uncertainty and imprecision in the results. What is more, we discuss the current challenges in TBF-based ML and offer insightful perspectives for future research regarding clustering, classification and information fusion. This survey not only fills a critical gap in the existing literature but also serves as a guiding beacon for future explorations, emphasizing the transformative role of TBF in advancing ML methodologies. • The paper provides a survey of representing uncertainty and imprecision in machine learning with belief functions. • The paper proposes the formal definition of uncertainty and imprecision reasoning. • The paper covers popular and efficient methods in clustering, classification and information fusion with belief functions. • The paper summarizes the promising research directions in the future. [ABSTRACT FROM AUTHOR]

Mental health issues are focused on extensively and are an immense part of human life. As a result, formulating effective approaches for early detection and intervention is critical. Machine Learning algorithms have demonstrated promising results in clustering and categorizing mental health disorders in recent years This research are using a clustering approach to categorize and detect diverse patterns of mental health disorders among teenagers. To develop guidelines and selection of relevant articles for our paper, we follow PRISMA literature review guidelines. we also evaluated each Machine Learning model, including SVM, NGBoost, KNN, RNN, SGD, DT, RF, XGBoost, and logistic regression. The result is that XGBoost delivers very satisfying build results. However, there is another algorithm, namely LGBM, which is no less satisfying than XGBoost. [ABSTRACT FROM AUTHOR]

Class imbalance is a common problem with datasets relating to various areas of life. It causes many traditional machine learning algorithms to tend to misclassify minority samples as majority ones. Despite various studies, the class imbalance still remains a relevant problem for which no one-size-fits-all solution has been found. In this paper, an undersampling method based on clustering is presented. In the proposed approach K-means algorithm is used to cluster data. In homogenous "majority" clusters, i.e., clusters containing objects of only the majority class, objects within the specified distance from the center are removed. In the case of non-homogeneous clusters, objects located at the class decision boundary are removed using the KNN algorithm. As tests have shown, the clustering-based solution can improve classification quality. The results of experiments show that in many cases the proposed solution outperformed other undersampling techniques described in the literature. [ABSTRACT FROM AUTHOR]

In this paper, the problem of imbalanced data stream classification is considered. To eliminate the problem of imbalanced data, over- and under-sampling procedures are implemented within a dedicated framework called Weighted Ensemble with one-class Classification and Over-sampling and Instance selection (WECOI). To increase the quality of synthetic instance generation (carried out under the umbrella of an over-sampling procedure), an agent-based population algorithm is proposed. The problem is defined, and the agent-based algorithm is presented. A discussion of selected computational results is also included. [ABSTRACT FROM AUTHOR]

This paper presents a novel learning algorithm formulated as a classification problem with smartphone-inertial measurement as predictor. For this reason, we will focus on the Symbolic Aggregate approXimation (SAX) as a low-cost classification algorithm resulting from its ability of the data dimensionality reduction through symbolic discretization. Since the first publication of the SAX, a lot of extension with novel SAX-distance measure are published. Each of them attempts to integrate additional statistical features in order to improve original SAX average-based feature. However, none of them can fit the overall shape-characteristics of the data and give the superiority to an individual SAX-based classifier. In order to combine the prediction of each single SAX-based classifier, we propose a collection of several SAX-feature to compose a multi-SAX feature ensemble classification. The proposed algorithm is validated on experimental data addressing (i) the character recognition when using a smartphone as a pen and (ii) the road profile estimation using a smartphone mounted in the interior of a vehicle while driving. [ABSTRACT FROM AUTHOR]

Recently, solving ordinal classification problems using machine learning and deep learning techniques has acquired important attention. There are many real-world problems in different areas of knowledge where a categorical variable needs to be predicted, and the existing categories follow an order associated with the nature of the problem: e.g. medical diagnosis with different states of a disease, or industrial quality assessment with different levels of quality. In these problems, it is quite common that the final label for each sample is determined by a group of experts with different opinions, and all opinions are usually summarised in a single crisp label by means of a given statistic (e.g. the median or the mode). Applying standard ordinal classifiers to these crisp labels could result in overfitting, as the labelling information is considered as totally certain. In this work, we propose a unimodal regularisation approach based on soft labelling, i.e. the ordinal information is used to introduce the inherent uncertainty of the label fusion. Specifically, said regularisation is based on using triangular distributions to simulate the aforementioned fusion of the expert opinions, where a parameter is used to decide the amount of probability that is assigned to the target category and the adjacent ones (according to the ordinal scale). The strategy could be applied to the loss function used by any ordinal classification learning algorithm, but we focus on deep learning in this paper. The proposal is compared to a baseline approach for nominal classification tasks and other state-of-the-art unimodal regularisation methods, and the experimental validation includes six benchmark datasets and five performance metrics. The results along with the statistical analysis show that the proposed methodology significantly outperforms the rest of the methods. • Unimodal regularised loss function based on triangular distributions. • Application to different CNN models and ordinal benchmark datasets. • Comparison with other regularisation methods based on different distributions. • Improvement of state-of-the-art classification performance regarding different metrics. [ABSTRACT FROM AUTHOR]

In this paper, as a new application of machine learning, a K- Nearest Neighbor (KNN) classification model is proposed to recognize artifacts in Electrocardiography (ECG) signal using 3-axis accelerometer signals. A fine KNN model using wavelet scattering coefficients as features of 3-axis accelerometer sensor captured training dataset have been proposed as alternative to other machine learning methods to classify artifacts. In wearable health-monitoring devices, artifact noise results signal deformations and it is not possible to employ filtering methods all the time due to data loss. As a result, wearable ECG monitoring devices are not reliable for critical medical usages. Our proposed model classifies accelerometer sensor samples with high probability of having artifact noises in ECG signal with positive predictive value of 94.7%. High accuracy rate of the proposed model in this work gives it an opportunity to be employed in ECG monitoring wearable devices to capture patients ECG history and labeling artifact samples for noise filtration or signal reconstruction systems to cancel the noise without having signal deformations. [ABSTRACT FROM AUTHOR]

Overweight and obesity are considered epidemic problems. The number of factors involved in developing extra body fat makes harder the detection of this problem. Therefore, among the several variables and their levels presented in overweight and obese people, there is a need to improve the classification of people with these conditions. To this aim, in this paper, we conducted a variable analysis from biochemical and lipid profiles in young Chileans with normal weight, overweight, and obesity using machine learning techniques. XGBoost library was selected as the classifier. 21 variables (13 from biochemical and 8 from lipid profiles) were chosen as features. 100 iterations were conducted, and an 80% cross-validation was obtained. The variables with greater relevance in the classification task were total cholesterol, glycemia, LDH enzyme, bilirubin, and VLDL cholesterol. All of these, except bilirubin, are consistent with previous research in which these features have been used to assess risk factors for developing overweight or obesity. Then, further research must include a deep study regarding bilirubin's influence over these conditions. [ABSTRACT FROM AUTHOR]

Agriculture is the major occupation and the main origin of income in India, and most of the population depends on agriculture for their living. The smart farming system's foremost goal is to monitor farmlands by automatically rinsing the lands with appropriate water and a pest detection framework. The conventional agricultural methods lack higher crop productivity with increased human efforts. Hence, the paper proposes an IoT-based solution for smart farming. The proposed system focuses on automatic irrigation of water and plant disease detection. It uses machine learning algorithms to accurately predict adequate water required by the fields and automatic pest identification based on the requirements of the farmland. K-Nearest Neighbour and support vector machine learning algorithms in the pest detection module are used to precisely predict plant diseases. The convenient features from the leaves of the plants were obtained. Then the obtained features are used for classification purposes. Extracting the suitable features and classifying them helps detect whether the plant is pest infected or not. The proposed system monitors, analyses, assesses and controls agricultural fields for the automatic irrigation of the water and disease identification of the plants. The numerical analysis of the machine learning algorithms and the significance of the classification with accuracy are investigated. From the numerical results, it is demonstrated that an accuracy of 84 % is achieved. [ABSTRACT FROM AUTHOR]

Breast cancer was the most diagnosed form of cancer in 2020. Early diagnosis of breast cancer results in a significant improvement in long-term survival rates. Current methods require consultation with experts, which is expensive and time-consuming and thus may not be accessible to all. This paper seeks to train and evaluate supervised machine learning models for the accurate and efficient detection of breast cancer. The Wisconsin Breast Cancer Database dataset describes 30 attributes of cell nuclei, including, but not limited to, their radius, texture, and concavity. It contains 569 instances, 212 of which are malignant tumors. The Random Forest algorithm outperforms other algorithms in classifying breast tumors as either malignant or benign and is thus selected as our primary model. It is trained on two different subsets of the dataset having 16 and 8 features, respectively, identified with the help of multiple feature selection methods. The Random Forest models are tested post hyperparameter tuning on a holdout set, and accuracies of 100% and 99.30% respectively. The models are also compared with four other machine learning classification algorithms: Support Vector Machine (SVM), Decision Tree, Multilayer Perceptron, and K-Nearest Neighbors. The results confirm that Random Forest is the superior method for breast cancer diagnosis. [ABSTRACT FROM AUTHOR]

In this paper, we implement the AdaBoost algorithm to optimize the classifications results of precipitations intensities carried out by One versus All strategy using Support Vector Machine (OvA-SVM). The model developed which combines the AdaBoost algorithm with a multiclass SVM is applied to images from the MSG (Meteosat Second Generation) satellite. Other variants to build multiclass SVMs, such as the OvO-SVM (One versus One SVM), SBT-SVM (Slant Binary Tree SVM) and DDAG-SVM (Decision Directed Acyclic Graph) are also implemented on which we tested the AdaBoost algorithm. The study showed that the AdaBoost algorithm performed better in the case of the OvA-SVM variant compared to the other variants. In order to evaluate the elaborated model, some classification techniques, such as the ECST Enhanced Convective Stratiform Technique (ECST), the SART where the Support vector machine, Artificial neural network and Random forest classifiers are combined, the Convective/Stratiform Rain Area Delineation Technique (CS-RADT) and the Random Forest technique (RFT) are applied. The classification results obtained show that AdaBoost with OvA-SVM (AdaOvA-SVM) presents very interesting performances where the evaluation parameters POD, POFD, FAR, BIAS, CSI and PC indicate the values 95.2%, 12.4%, 14.7%, 0.9, 88.1% and 96.5% respectively. Indeed, the AdaOvA-SVM technique has surpassed the CS-RADT, ECST and RFT techniques. As for the comparison with the SART, we noted that OvA-SVM presents very close results. The same trend was also observed when estimating precipitation. At the end of this study, it is shown that the AdaBoost algorithm performs better on a weak classifier or on a strong classifier operating in an unfavorable environment. [ABSTRACT FROM AUTHOR]

This paper presents an intuitive, robust and efficient One-Class Classification algorithm. The method developed is called OCENCH (One-class Classification via Expanded Non-Convex Hulls) and bases its operation on the construction of subdivisible and expandable non-convex hulls to represent the target class. The method begins by reducing the dimensionality of the data to two-dimensional spaces using random projections. After that, an iterative process based on Delaunay triangulations is applied to these spaces to obtain simple polygons that characterizes the non-convex shape of the normal class data. In addition, the method subdivides the non-convex hulls to represent separate regions in space if necessary. The method has been evaluated and compared to several main algorithms of the field using real data sets. In contrast to other methods, OCENCH can deal with non-convex and disjointed shapes. Finally, its execution can be carried out in a parallel way, which is interesting to reduce the execution time. • A method is proposed for anomaly detection through expanded non-convex hulls. • The training algorithm is based on One-Class Classification. • The method can be applied over high dimensional data sets using random projections. • The boundaries of the projected data are computed using a Delaunay triangulation. • Non-convex hulls can be subdivided to represent disjointed regions if necessary. [ABSTRACT FROM AUTHOR]

Detecting COVID-19 as early as possible and quickly is one way to stop the spread of COVID-19. Machine learning development can help to diagnose COVID-19 more quickly and accurately. This report aims to find out how far research has progressed and what lessons can be learned for future research in this sector. By filtering titles, abstracts, and content in the Google Scholar database, this literature review was able to find 19 related papers to answer two research questions, i.e. what medical images are commonly used for COVID-19 classification and what are the methods for COVID-19 classification. According to the findings, chest X-ray were the most commonly used data to categorize COVID-19 and transfer learning techniques were the method used in this study. Researchers also concluded that lung segmentation and use of multimodal data could improve performance. [ABSTRACT FROM AUTHOR]

Technology development has been getting more advanced and greatly facilitated human life. One of them is machine learning automation which has been proven to be consistent for doing various computations against extensive data such as transaction data in the e-commerce area. Seeing this opportunity, we implemented the machine learning approach to detect fraudulent cashback transactions in e-commerce that are currently rife in Indonesia. The training data used to build the machine learning model were the transaction data from one of the leading e-commerce in Indonesia that had been processed. The supervised classification algorithms used were K-Nearest Neighbor (k-NN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM). In the end, the best steps and methods that could be taken against fraudulent cashback activities in the future are shown in this paper. [ABSTRACT FROM AUTHOR]

Analyzing sensor data from a production environment is quite challenging because of the high-dimensional nature of the data. In addition, the generated data is in the form of time-series, where the sequence of registrations may be of utmost significance. One of the main goals of the paper is to determine if the given time-series of feature combinations is normal or rare. This goal could successfully be achieved by combining multiple machine learning models. In this paper, a sliding window based ensemble method is proposed to detect outliers in a streaming fashion. The proposed method uses a combination of clustering algorithms to construct subgroups (clusters) representing different data structures. These structures are later used in a one-class classification algorithm to identfy the outliers. Thus, if a pattern does not belong to any of the common structures or clusters, it is an outlier. Further, based on the rare pattern classification, machine failures could be predicted in advance. [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]

Since the present era is entirely computer and Internet of Things (IoT) oriented, enormous amounts of data are produced quickly from many sources. Machine learning's primary function, which is widely applicable to these high-dimensional datasets, is classification. One of the well-known approaches for improving classification effectiveness is ensemble learning. The splitting of huge datasets vertically based on the feature set partitioning (FSP) method is known as views. Multi-view ensemble learning (MEL) is the process of applying different classification models to these views and then combining their predictions. The FSP methods used to create views are the backbone of MEL. This review has been done to study, present, analyze, and collectively compare various FSP methods. Several issues and challenges related to FSP and MEL are also highlighted in this paper. The classification performance of recent FSP methods for the MEL framework is compared as an auxiliary experiment using fifteen high-dimensional datasets. A nonparametric statistical analysis is used for the comparison of FSP methods. • The feature set partitioning (FSP) method creates views by splitting the dataset. • Multi-view ensemble learning combines model predictions over these views. • This review aims to study, present, analyze, and collectively compare various FSPs. • Several issues and challenges related to FSP are highlighted in this paper. • The classification performance of recent FSP methods is compared. [ABSTRACT FROM AUTHOR]

Recently, deep learning has proven to be a successful technique especially in medical image analysis. This paper aims to highlight the importance of deep learning architectures in lung disease diagnosis using CXR images. Related articles were identified through searches of electronic resources, including IEEE, Springer, Elsevier, PubMed, Nature and, Hindawi digital library. The inclusion of articles was based on high-performance artificial intelligence models, developed for the classification of possible findings in CXR images published from 2018 to 2023. After the quality assessment of papers, 129 articles were included according to PRISMA guidelines. Papers were studied by types of lung disease, data source, algorithm type, and outcome metrics. Three main categories of computer-aided lung disease detection were covered: traditional machine learning, deep learning-based methods, and combination of aforementioned methods for all lung diseases. The results showed that various pre-trained networks including ResNet, VGG, and DenseNet, are the most frequently used CNN architectures and would result in a notable increase in sensitivity and accuracy. Recent research suggests that utilizing a combination of deep networks with a robust machine learning classifier can outperform deep learning approaches that rely solely on fully connected neural networks as their classifier. Finally, the limitations of the existing literature and potential future research opportunities in possible findings in CXR images using deep learning architectures are discussed in this systematic review. • A systematic review based on PRISMA framework on machine learning applications to analyze chest X-ray images. • Trends of architectures used in last 5 years. • Preprocessing and processing techniques used by the researchers. • Future trends and open problems. [ABSTRACT FROM AUTHOR]

Over the last decade Deep learning-based models surpasses classical machine learning models in a variety of text classification tasks. The primary challenge with text classification is determining the most appropriate deep learning classifier. Numerous research initiatives incorporated ensemble learning to boost the performance, minimize errors and avoid overfitting. However, the performance of the ensemble-methods is limited by the baseline classifiers and the fusion method. The current study makes the following contributions: First, it proposes a new meta-learning ensemble method that fuses baseline deep learning models using 2-tiers of meta-classifiers. Second, it conducts several experiments on six public benchmark datasets to evaluate the performance of the proposed ensemble. For each benchmark dataset, committees of different deep baseline classifiers are trained, and their best performance is compared with the performance of the proposed ensemble. Furthermore, the paper extends the results by comparing the performance of the proposed ensemble method to other state-of-the-art ensemble methods. The findings indicate that the proposed ensemble method significantly improve the classification accuracy of the baseline deep models. Furthermore, the proposed method outperforms the state-of-art ensemble methods. Finally, using the probability distributions for each class label of the deep baseline models improves the performance of the proposed ensemble method. [ABSTRACT FROM AUTHOR]

In the field of machine learning, the issue of class imbalance is a common problem. It refers to an imbalance in the quantity of data collected, where one class has a significantly larger number of data compared to another class, which can negatively affect the classification efficiency of algorithms. Under-sampling methods address class imbalance by reducing the quantity of data in the majority class, thereby achieving a balanced dataset and mitigating the class imbalance problem. Traditional under-sampling methods based on k-means clustering either set the unified value of k (number of clusters) or determine it directly based on the quantity of data in the minority or majority class. This paper proposes an adaptive k-means clustering under-sampling algorithm that calculates an appropriate k for each dataset. After clustering the majority class dataset into k clusters, our algorithm calculates the distances between the data within each cluster and the cluster centroids from two perspectives and selects data based on these distances. Subsequently, the subset of the majority class dataset are combined with the minority class dataset to generate a new balanced dataset, which is then used for classification algorithms. The performance of our algorithm is evaluated on 45 datasets. Experimental results demonstrate that our algorithm can dynamically determine appropriate k for different datasets and output a balanced dataset, thus enhancing the classification efficiency of machine learning algorithms. This work can provide new algorithmic ensemble strategies for addressing class imbalance problem. [ABSTRACT FROM AUTHOR]

Imbalanced class distributions in machine learning, where the minority class is often under-represented, pose a substantial challenge. Synthetic Minority Over-sampling Technique (SMOTE) has been widely employed to address this issue by generating synthetic minority samples through interpolation. Despite its popularity, SMOTE exhibits certain drawbacks caused by the implementation of random interpolation samples. In this paper, we introduce a new data level technique for oversampling, called Fuzzy C-Means Center-SMOTE (FCM-CSMOTE), which generates synthetic samples in each cluster using its center considered as the memory of the main data components. We demonstrate that the proposed selective strategy has a very low probability to generate noise. The experimental results demonstrate that the proposed method performs better than the state-of-the-art approaches on 21 real unbalanced data sets (regular and large size data set) in terms of several metrics, including Geometric Mean (GM), F-Measure (FM), Area Under the Curve (AUC), and Accuracy. [ABSTRACT FROM AUTHOR]