[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120263-en":3,"doc-seo-120263-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120263,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",6,"Technology","Feature Optimization for Machine Learning Based Bearing Fault Classification - Article","Bearing fault diagnosis relies on selecting effective features from vibration signals, since many extracted attributes are uninformative and high-dimensional feature sets degrade performance while slowing training. This study introduces a wavelet-entropy-based feature optimization approach to reduce input dimensionality and elapsed time, while improving learning efficiency. Four machine learning algorithms—Naive Bayes, SVM, ANN, and KNN—are trained using the optimized features. Experiments on the CWRU bearing dataset achieve up to 99.5% accuracy, and robustness is validated under different vibration noise levels by SNR perturbations.","Feature Optimization for Machine Learning Based Bearing  \nFault Classification  \nMohammad Mohiuddin1, Md Saiful Islam2,Jia Uddin3  \n1,2Department of Electronics & Telecommunication Engineering, Chittagong University of Engineering & Technology (CUET) . Chittagong, Bangladesh  \n3AI and BigData Department, Endicott College, Woosong University, Daejeon, South Korea  \nArticle history:  \nReceived Jun 29, 2024 Revised Aug 31, 2024 Accepted Sep 11, 2024  \nKeyword:  \nBearing fault  \nVibration signals Wavelet Transform Shannon Entropy Criterion Artificial Neural Networks  \nCorresponding Author:  \nThe most critical and essential parts of rotating machinery are bearings. The main problem of the bearing fault classification is to select the fault features effectively because all extracted features are not useful, and the highdimensional features give poor performances and slow down the training process. Due to the effective feature selection problem, the bearing fault diagnosis method does not achieve a satisfactory result. The main goal ofthis paper is to extract the effective fault features with an optimization technique to classify the bearing faults using machine learning algorithms. Since wavelet entropy can determine complexity and degree of order of a vibration signal, this research uses it in features optimization. The proposed wavelet entropybased optimization technique reduces the dimensionality of input, elapsed time and raises the learning process. Four Machine learning algorithms (naïve Bayes, support vector machine, artificial neural network and KNN) are applied to classify the bearing faults using the optimized features. To evaluate the proposed method, Case Western Reserve University’s (CWRU’s) bearing dataset is used which consists of three types of bearing faults. Based on the experimental data, it was shown that the proposed system reached 99.5% accuracy. The accuracy and robustness of the bearing fault classification are tested by adding noise to the vibration raw signals at various levels of Signalto-Noise Ratio (SNR). Experimental results show that the proposed method is very highly reliable in detecting bearing faults compared to the conventional methods.  \nCopyright © 2024 Institute of Advanced Engineering and Science.  \nAll rights reserved.  \nJia Uddin  \nAI and BigData Department, Endicott College, Woosong University Daejeon, South Korea  \nEmail: [jia.uddin@wsu.ac.kr](jia.uddin@wsu.ac.kr)  \nArticle Info ABSTRACT  \n1. INTRODUCTION  \nBearings are critical elements of rotating machinery. Bearing conditions have a significant impact on machines. Vibration analysis has been widely employed for bearing condition monitoring for many decades. Vibration signals caused by bearing problems have been intensively studied, and several diagnostic approaches have been used in the past [1] . Bearing faults diagnostics may be approached in three ways: predictive maintenance, reactive maintenance, and preventive maintenance. Real-time monitoring and diagnostics of bearings are the foundation of predictive maintenance. Reactive maintenance relies on repair activities conducted after a bearing failure has already been identified. Preventive maintenance relies on time bound approaches and best practices for planning and scheduling repair actions when the actual status of the bearing is unknown [2] .  \nArtificial Neural Network (ANN) has been used to detect and diagnosis machine conditions, which have been considered classification problems according to learning patterns [3] . An issue with classifying  \nmachine faults is divided into two sections. The first section deals with feature extraction from vibration signals, which is applied to extract some features exhibiting fault information. The second section is classification, which employs various artificial intelligence approaches to diagnose faults using the extracted features [4] .  \nThe features of vibration can be obtained using time-domain analysis, frequency-domain analysis, and","cbCaiiN7406vJsK9","https://ap.wps.com/l/cbCaiiN7406vJsK9","pdf",1047910,1,15,"English","en",105,"# Introduction\n## Bearing fault diagnosis and maintenance strategies\n## Feature extraction from vibration signals\n## Challenges in feature selection and high-dimensional features\n# Wavelet entropy-based feature optimization\n## Wavelet entropy for complexity and signal order\n## Dimensionality reduction and learning efficiency\n# Machine learning classification\n## Algorithms used\n# Experimental setup and results\n## Dataset and fault types\n## Accuracy under noise and robustness","[{\"question\":\"Why is feature selection critical for bearing fault classification?\",\"answer\":\"Only a subset of extracted features carries fault information, while others add noise and increase dimensionality. High-dimensional features reduce classification quality and slow training, leading to unsatisfactory results.\"},{\"question\":\"How does the proposed method optimize features?\",\"answer\":\"The approach uses wavelet entropy to evaluate the complexity and degree of order of vibration signals. It performs feature optimization to reduce dimensionality and improve learning efficiency.\"},{\"question\":\"Which machine learning algorithms are used and how well does the method perform?\",\"answer\":\"Naive Bayes, SVM, ANN, and KNN are applied using the optimized features. Results on the CWRU bearing dataset show accuracy reaching 99.5%.\"}]","Feature Optimization for Machine Learning Based Bearing Fault Classification - Article | PDF",1785729117,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"feature-optimization-for-machine-learning-based-bearing-fault-classification-article","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/feature-optimization-for-machine-learning-based-bearing-fault-classification-article/120263/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-06","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is feature selection critical for bearing fault classification?","Question",{"text":76,"@type":77},"Only a subset of extracted features carries fault information, while others add noise and increase dimensionality. High-dimensional features reduce classification quality and slow training, leading to unsatisfactory results.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed method optimize features?",{"text":81,"@type":77},"The approach uses wavelet entropy to evaluate the complexity and degree of order of vibration signals. It performs feature optimization to reduce dimensionality and improve learning efficiency.",{"name":83,"@type":74,"acceptedAnswer":84},"Which machine learning algorithms are used and how well does the method perform?",{"text":85,"@type":77},"Naive Bayes, SVM, ANN, and KNN are applied using the optimized features. Results on the CWRU bearing dataset show accuracy reaching 99.5%.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,114,119,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":112,"slug":113},50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},8,"Research & Report",30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]