Data Classification Techniques Research Articles

Arrhythmia Classification from ECG Signals Using Transformers and Data Balancing Techniques

While many arrhythmias pose minimal threat, certain heart rhythm irregularities elevate the potential for stroke or heart failure. The complexity arises particularly with the supraventricular premature heartbeat which has a resemblance to a normal beat and occurs infrequently. Consequently, this research proposes a data balancing and classification technique that enhances the accuracy of identifying mentioned hard-to-classify heartbeats while maintaining robust metrics for other classes. The study introduces a deep learning framework combined with a multi-head attention transformer, for balancing – under-sampling and synthetic minority oversampling are used. To evaluate the proposed model, various experiments based on real data were conducted. The results were compared with an existing model used in chest belt heartbeat monitoring, and the results show that the transformer model achieved better performance for supraventricular premature heartbeats, at the same time reaching high overall and per-class metrics.

Evolutionary Hybrid Machine Learning Techniques for DNA Cancer Data Classification

Evolutionary Hybrid Machine Learning Techniques for DNA Cancer Data Classification

Adaptive fuzzy-evidential classification based on association rule mining

As one of the most promising classification approaches, association classification (AC) integrates data classification and association discovery techniques for generating a compact set of classification association rules. Recently, the fuzzy set and evidence theories are successively applied into AC in order to improve the classification performance in terms of accuracy and interpretability. However, from the perspectives of applicability and universality, there still exists two important issues in the current AC framework. On one hand, several key parameters, such as the number of fused rules in classification and the minimum support threshold in association discovery, are difficult to be accurately predefined in practice. On the other hand, the fixed grid-based fuzzy partition is not benefit to adapt for those datasets with large number of features. In this paper, an association rule-based adaptive fuzzy-evidential classification framework (AR-AFEC) is developed for overcoming the above limitations. To do so, an optimal rule fusion strategy and a dynamic minimum support threshold setting scheme are proposed for adaptively learning the parameters during classification and association mining respectively. In addition, an entropy-based trapezoidal fuzzy partition technique is proposed to adaptively obtain the fuzzy sets defined on each continuous feature domain. Experiments on 26 benchmark datasets and a human activity recognition application demonstrate that the proposal can achieve better accuracy than some state-of-the-art rule-based classification approaches, using less rules with more general structure.

Solving a Class of Cut-Generating Linear Programs via Machine Learning

Cut-generating linear programs (CGLPs) play a key role as a separation oracle to produce valid inequalities for the feasible region of mixed-integer programs. When incorporated inside branch-and-bound, the cutting planes obtained from CGLPs help to tighten relaxations and improve dual bounds. However, running the CGLPs at the nodes of the branch-and-bound tree is computationally cumbersome due to the large number of node candidates and the lack of a priori knowledge on which nodes admit useful cutting planes. As a result, CGLPs are often avoided at default settings of branch-and-cut algorithms despite their potential impact on improving dual bounds. In this paper, we propose a novel framework based on machine learning to approximate the optimal value of a CGLP class that determines whether a cutting plane can be generated at a node of the branch-and-bound tree. Translating the CGLP as an indicator function of the objective function vector, we show that it can be approximated through conventional data classification techniques. We provide a systematic procedure to efficiently generate training data sets for the corresponding classification problem based on the CGLP structure. We conduct computational experiments on benchmark instances using classification methods such as logistic regression. These results suggest that the approximate CGLP obtained from classification can improve the solution time compared with that of conventional cutting plane methods. Our proposed framework can be efficiently applied to a large number of nodes in the branch-and-bound tree to identify the best candidates for adding a cut. History: Accepted by Andrea Lodi, Area Editor/Design & Analysis of Algorithms — Discrete. Supplemental Material: The e-companion is available at https://doi.org/10.1287/ijoc.2022.0241 .

Interpretable AI models for predicting distant metastasis development based on genetic data: Kidney cancer example

Kidney cancer has a high metastatic potential with up to 30% of patients developing distant metastasis after surgery. We assessed the value of AI models in predicting the metastatic potential of clear cell renal cell carcinoma (ccRCC), based on the genetic data. Tissue samples from patients with both metastatic and non-metastatic squamous cell carcinoma were analyzed, focusing on the expression and methylation levels of specific protein-coding (PC) and microRNA (miRNA) genes. Using quantitative PCR and data classification techniques, we found a correlation between metastasis and reduced expression of PC-genes CA9, NDUFA4L2, EGLN3, and BHLHE41, as well as increased methylation in miRNA genes MIR125B-1, MIR137, MIR375, MIR193A, and MIR34B. AI models were built for predicting distant metastases based on the expression values and methylation status of selected genes. One model is based on solving a regression problem and is non-interpretable, while another one is based on proposed decision rules and is interpretable. The quality of the models was assessed using sensitivity and specificity metrics, and cross-validation technology was used to ensure the reliability of the results.

Performance Comparison of Decision Tree and Support Vector Machine Algorithms for Heart Failure Prediction

Heart failure is a significant global cause of mortality and morbidity. This research article aims to evaluate the performance of decision tree (DTree) and support vector machine (SVM) methods in predicting heart disease. The study utilizes a dataset with diverse features and employs exploratory data analysis (EDA), clustering, and classification techniques to gain insights and evaluate the performance of the two methods. The results demonstrate the effectiveness of both DTree and SVM in predicting heart disease. Notably, SVM outperforms DTree in terms of accuracy, precision, recall, and F1-score. However, the performance of these methods is influenced by the preprocessing steps applied, indicating the importance of selecting appropriate data preprocessing techniques for optimal performance with specific machine learning algorithms. This study emphasizes the potential of machine learning algorithms in predicting heart disease and underscores the significance of thoughtful preprocessing technique selection to enhance performance.

Explainable Machine Learning for Malware Detection on Android Applications

The presence of malicious software (malware), for example, in Android applications (apps), has harmful or irreparable consequences to the user and/or the device. Despite the protections app stores provide to avoid malware, it keeps growing in sophistication and diffusion. In this paper, we explore the use of machine learning (ML) techniques to detect malware in Android apps. The focus is on the study of different data pre-processing, dimensionality reduction, and classification techniques, assessing the generalization ability of the learned models using public domain datasets and specifically developed apps. We find that the classifiers that achieve better performance for this task are support vector machines (SVM) and random forests (RF). We emphasize the use of feature selection (FS) techniques to reduce the data dimensionality and to identify the most relevant features in Android malware classification, leading to explainability on this task. Our approach can identify the most relevant features to classify an app as malware. Namely, we conclude that permissions play a prominent role in Android malware detection. The proposed approach reduces the data dimensionality while achieving high accuracy in identifying malware in Android apps.

An applied study of multi-layer decision tree optimization algorithms in machine learning

Abstract This paper investigates the multi-layer decision tree optimization algorithm in machine learning and explores its efficiency and accuracy in applying complex data classification. The focus is on the optimization strategy of the algorithm when dealing with large datasets with multiple types of records. The research adopts methods such as data set Discretization, fuzzification processing and hierarchical fuzzy decision tree construction algorithm. Through experimental verification, our constructed multilevel fuzzy decision tree performs well in two application scenarios: rainfall prediction and fingerprint identification. In the rainfall prediction experiment, using 5200 sample data, the algorithm achieves a classification accuracy of 61%. In the fingerprint recognition experiment, from 3,000 fingerprint images, a 100% recognition rate was performed, and the rejection rate was 25.2%. The results show that the multi-layer decision tree optimization algorithm can effectively handle large data sets of multiple types and significantly improve the accuracy and efficiency of classification. The algorithm offers high adaptability and accuracy when dealing with continuous type attributes. This study provides a new perspective and methodology for the application of multi-layer decision trees in machine learning, which is of great significance for the future development of data processing and classification techniques.

Case Study: Using Data Mining to Predict Student Performance Based on Demographic Attributes

This study predicts student performance at Universiti Pertahanan Nasional Malaysia (UPNM) based on their socio-demographic profile; it also determines how a prediction algorithm can be used to classify the student data for the most significant demographic attributes. The analytical pattern in academic results per batch has been identified using demographic attributes and the student's grades to improve short-term and long-term learning and teaching plans. Understanding the likely outcome of the education process based on predictions can help UPNM lecturers enhance the achievements of the subsequent batch of students by modifying the factors contributing to the prior success. This study identifies and predicts student performance using data mining and classification techniques such as decision trees, neural networks, and k-nearest neighbors. This frequently adopted method comprises data selection and preparation, cleansing, incorporating previous knowledge datasets, and interpreting precise solutions. This study presents the simplified output from each data mining method to facilitate a better understanding of the result and determine the best data mining method. The results show that the critical attributes influencing student performance are gender, age, and student status. The Neural Networks method has the lowest Root of the Mean of the Square of Errors (RMSE) for accuracy measurement. In contrast, the decision tree method has the highest RMSE, which indicates that the decision tree method has a lower performance accuracy. Moreover, the correlation coefficient for the k-nearest neighbor has been recorded as less than one.

Case Study: Using Data Mining to Predict Student Performance Based on Demographic Attributes

This study predicts student performance at Universiti Pertahanan Nasional Malaysia (UPNM) based on their socio-demographic profile; it also determines how a prediction algorithm can be used to classify the student data for the most significant demographic attributes. The analytical pattern in academic results per batch has been identified using demographic attributes and the student's grades to improve short-term and long-term learning and teaching plans. Understanding the likely outcome of the education process based on predictions can help UPNM lecturers enhance the achievements of the subsequent batch of students by modifying the factors contributing to the prior success. This study identifies and predicts student performance using data mining and classification techniques such as decision trees, neural networks, and k-nearest neighbors. This frequently adopted method comprises data selection and preparation, cleansing, incorporating previous knowledge datasets, and interpreting precise solutions. This study presents the simplified output from each data mining method to facilitate a better understanding of the result and determine the best data mining method. The results show that the critical attributes influencing student performance are gender, age, and student status. The Neural Networks method has the lowest Root of the Mean of the Square of Errors (RMSE) for accuracy measurement. In contrast, the decision tree method has the highest RMSE, which indicates that the decision tree method has a lower performance accuracy. Moreover, the correlation coefficient for the k-nearest neighbor has been recorded as less than one.

Capacity Building Model Strategy for Developing Lecturer Integrity and Competency in Efforts to Fulfill International Standards

This research aims to obtain a lecturer development model to increase the global competitiveness of higher education in the aspects of integrity and competency based on international (global) standards. World Class University (WCU) as a reference for ranking, recognition and assessment of universities on a world scale. In other words, universities are ranked by institutions that have an international reputation. This mixed method research with two quantitative and qualitative stages targeted 650 UPI lecturers who had doctoral qualifications. Next, a sample of 10% or 65 people from the population was taken. This research uses mixed methods with two quantitative and qualitative stages. The data collection stages were carried out first, Preparation for field studies, Focus Group Discussion (FGD) was carried out to analyze policy issues for developing the integrity and competence of international standard lecturers, Surveys, interviews and filling out questionnaires, documentation studies within the scope of the Indonesian University of Education (UPI) and finally carried out Analysis of Survey Results Data using descriptive statistical techniques and qualitative data classification techniques. The research results show that integrity, competence and performance are very important components and variables in developing human resources for UPI lecturers to achieve World Class Universities (WCU). The influence between variables according to SEM shows that the direct variable integrity on competence is only 0.458, the influence of integrity on performance is 0.446 and the influence of competence on performance is 0.460. or it can be concluded that everything is in a moderate position.

A Supervised Machine Learning Algorithms: Applications, Challenges, and Recommendations

Machine Learning (ML) is an advanced technology that empowers systems to acquire knowledge autonomously, eliminating the need for explicit programming. The fundamental objective of the machine learning paradigm is to equip computers with the ability to learn independently without human intervention. In the literature, categorization in data mining has received a lot of traction, with applications ranging from health to astronomy and finance to textual classification. The three learning methodologies in machine learning are supervised, unsupervised, and semi-supervised. Humans must give the appropriate input and output and offer feedback on the prediction accuracy throughout the training phase for supervised algorithms. Unsupervised learning methods differ from supervised learning methods because they do not require any training. However, supervised learning methods are more accessible to implement than unsupervised learning methods. This study looks at supervised learning algorithms commonly employed in data classification. The strategies are evaluated based on their objective, methodology, benefits, and drawbacks. It is anticipated that readers will be able to understand the supervised machine learning techniques for data classification.

A Survey of Motion Data Processing and Classification Techniques Based on Wearable Sensors

The rapid development of wearable technology provides new opportunities for action data processing and classification techniques. Wearable sensors can monitor the physiological and motion signals of the human body in real-time, providing rich data sources for health monitoring, sports analysis, and human-computer interaction. This paper provides a comprehensive review of motion data processing and classification techniques based on wearable sensors, mainly including feature extraction techniques, classification techniques, and future development and challenges. First, this paper introduces the research background of wearable sensors, emphasizing their important applications in health monitoring, sports analysis, and human-computer interaction. Then, it elaborates on the work content of action data processing and classification techniques, including feature extraction, model construction, and activity recognition. In feature extraction techniques, this paper focuses on the content of shallow feature extraction and deep feature extraction; in classification techniques, it mainly studies traditional machine learning models and deep learning models. Finally, this paper points out the current challenges and prospects for future research directions. Through in-depth discussions of feature extraction techniques and classification techniques for sensor time series data in wearable technology, this paper helps promote the application and development of wearable technology in health monitoring, sports analysis, and human-computer interaction.

Kesalahan kala bahasa Perancis mahasiswa dengan kemampuan bahasa tingkat menengah

French tenses are one of the most complex and varied aspects of the language, with different verb tenses and grammatical rules that can be challenging for learners to master. The purpose of this study is to analyze the forms of errors in the use of French tenses by learners with an intermediate level of language proficiency and also the factors of these errors. The method used in this research is descriptive qualitative with a morpho-syntax approach supported by questionnaire and questionnaire distribution techniques in the data collection process. In the process of data analysis, we performed data classification technique followed by mark reading technique. After analyzing the data, it was found that most errors were found in the past tense. The forms of errors found are divided into four types, namely omission of important elements, addition of unimportant elements, misinformation, and errors in arrangement. The factors causing the errors found are linguistic and sociolinguistic factors. One of the linguistic factors found is the adjustment of each verb in French while in Indonesian it is not. Regarding the sociolinguistic factors found, one of them is the lack of time in practicing French by the respondents.

Predicting Student Dropout with Minimal Information

Student dropout is a problem for both students and universities. However, in the crises that Lebanon is going through, it is becoming a serious financial problem for Lebanese private universities. To try to minimize it, it must be predicted in order to implement the appropriate actions. In this paper, a method to build the appropriate prediction system is presented. First, it generates a data source of predictor variables from student dataset collected from a faculty of economic sciences in Beirut between 2010 and 2020. Then, it will build a prediction model using data classification techniques based on identified predictor variables and validate it. Using open-source software and free cloud environments, a prediction program was developed. It consolidates, corrects, and normalizes the student's data. Then, it applies simple linear regression to show the correlation between the different variables and the student dropout, which allows us to select the factors that are highly correlated. From this point on, the program tries to predict the student dropout using different classification algorithms by machine learning on student dataset who left their courses either in success or in failure. Lastly, it measures the accuracy of the results and determines the best algorithm. In this study, the Artificial Neural Networks - Multilayer Perceptron showed an accuracy of 98.1% using only five variables. Finally, we evoke new avenues to further research and improve the model.

In-vehicle network intrusion detection systems: a systematic survey of deep learning-based approaches

Developments in connected and autonomous vehicle technologies provide drivers with many convenience and safety benefits. Unfortunately, as connectivity and complexity within vehicles increase, more entry points or interfaces that may directly or indirectly access in-vehicle networks (IVNs) have been introduced, causing a massive rise in security risks. An intrusion detection system (IDS) is a practical method for controlling malicious attacks while guaranteeing real-time communication. Regarding the ever-evolving security attacks on IVNs, researchers have paid more attention to employing deep learning-based techniques to deal with privacy concerns and security threats in the IDS domain. Therefore, this article comprehensively reviews all existing deep IDS approaches on in-vehicle networks and conducts fine-grained classification based on applied deep network architecture. It investigates how deep-learning techniques are utilized to implement different IDS models for better performance and describe their possible contributions and limitations. Further compares and discusses the studied schemes concerning different facets, including input data strategy, benchmark datasets, classification technique, and evaluation criteria. Furthermore, the usage preferences of deep learning in IDS, the influence of the dataset, and the selection of feature segments are discussed to illuminate the main potential properties for designing. Finally, possible research directions for follow-up studies are provided.

Land Use and Land Cover Change Detection Using the Random Forest Approach: The Case of The Upper Blue Nile River Basin, Ethiopia.

Monitoring land use change dynamics is critical for tackling food security, climate change, and biodiversity loss on a global scale. This study is designed to classify land use and land cover in the upper Blue Nile River Basin (BNRB) using a random forest (RF) algorithm. The Landsat images for Landsat 45, Landsat 7, and Landsat 8 are used for classification purposes. The study area is classified into seven land use/land cover classes: cultivated lands, bare lands, built-ups, forests, grazing lands, shrublands, and waterbodies. The accuracy of classified images is 83%, 85%, and 91% using the Kappa index of agreements. From 1983 to 2022 periods, cultivated lands and built-up areas increased by 47541 and 1777 km2, respectively, at the expense of grazing lands, shrublands, and forests. Furthermore, the area of water bodies has increased by 662 km2 due to the construction of small and large-scale irrigation and hydroelectric power generation dams. The main factors that determine agricultural land expansion are related to population growth. Therefore, land use and land cover change detection using a random forest is an important technique for multispectral satellite data classification to understand the optimal use of natural resources, conservation practices, and decision-making for sustainable development.

Metode Random Forest untuk Klasifikasi Penyakit Diabetes

Abstract. Random Forest is a supervised learning algorithm developed from decision trees with the application of boostrap aggregating (bagging). This method grows trees from decision trees to produce a forest or the best model called the random forest model. Tree growth is done with randomly selected data with returns through the bagging process. Random forest is considered to provide better performance results for diabetes data among other supervised learning methods, because random forest and has the lowest error rate compared to other methods. Random forest is also an important technique for medical data classification, especially for diagnosing diabetics. In this study, classification was carried out using Pima Indian Diabetes data, which is an American tribe that lives in Arizona and Mexico. Classification analysis was carried out using an algorithm to see the level of accuracy in random forest classification on Pima Indian diabetes data. The results show that the accuracy value of random forest classification is 74.78%, this value is in the accuracy category at the fair classification level. In this random forest classification, there are three main variables that become importance variables, namely glucose then BMI, and age.
 Abstract. Random Forest is a supervised learning algorithm developed from decision trees with the application of boostrap aggregating (bagging). This method grows trees from decision trees to produce a forest or the best model called the random forest model. Tree growth is done with randomly selected data with returns through the bagging process. Random forest is considered to provide better performance results for diabetes data among other supervised learning methods, because random forest and has the lowest error rate compared to other methods. Random forest is also an important technique for medical data classification, especially for diagnosing diabetics. In this study, classification was carried out using Pima Indian Diabetes data, which is an American tribe that lives in Arizona and Mexico. Classification analysis was carried out using an algorithm to see the level of accuracy in random forest classification on Pima Indian diabetes data. The results show that the accuracy value of random forest classification is 74.78%, this value is in the accuracy category at the fair classification level. In this random forest classification, there are three main variables that become importance variables, namely glucose then BMI, and age.

Prediction of Autism Spectrum Disorder in Children: A Detailed Systematic Review on Machine Learning and Deep Learning Methods

Autism spectrum disorder (ASD) is a serious, chronic neurodevelopmental illness characterized by developmental difficulties that are permanent or restrict the growth of thinking, behaviour, activities, and social-communication skills. The signs of autism are more pronounced and more straightforward to identify in youngsters between the ages of two and three. Although there is no permanent cure for ASD, it is still challenging to identify meltdowns or other difficulties in the early stages of medical care. In order to promote brain development and raise awareness of ASD among parents and caregivers, the survey’s objective was to identify ASD at an early stage. Methods like deep learning (DL) and machine learning (ML) are currently employed to predict autism spectrum illnesses. This study provides an in-depth review of papers that predict ASD using ML and DL, as well as data analysis and classification techniques. Additionally, this survey intends to categorize and examine the various ML and DL approaches, as well as to describe the characteristics of ASD, assess performance, and show the scope of future research. For upcoming academics who want to study ASD prediction using ML and DL, this publication offers a road map.

Digital Interventions to Reduce Distress Among Frontline Health Care Providers: Analysis of Self-Perceived Stress.

Due to the constraints of the COVID-19 pandemic, healthcare workers have reported behaving in ways that are contrary to their values, which may result in distress and injury. This work is the first of its kind to evaluate the presence of stress in the COVID-19 VR Healthcare Simulation for Distress dataset. The dataset collected passive physiological signals and active mental health questionnaires. This paper focuses on correlating electrocardiogram, respiration, photoplethysmography, and galvanic skin response with the Perceived Stress Scale (PSS)-10 questionnaire. The analysis involved data-driven techniques for a robust evaluation of stress among participants. Low-complexity pre-processing and feature extraction techniques were applied and support vector machine and decision tree models were created to predict the PSS-10 scores of users. Imbalanced data classification techniques were used to further enhance our understanding of the results. Decision tree with oversampling through Synthetic Minority Oversampling Technique achieved an accuracy, precision, recall, and F1 of 93.50%, 93.41%, 93.31%, and 93.35%, respectively. Our findings offer novel results and clinically valuable insights for stress detection and potential for translation to edge computing applications to enhance privacy, longitudinal monitoring, and simplify device requirements.