{"title":"Depression Analysis using Electroencephalography Signals and Machine Learning Algorithms","authors":"N. V. Babu, E. G. Kanaga","doi":"10.1109/ICICICT54557.2022.9917751","DOIUrl":null,"url":null,"abstract":"Depression has been defined as a silent disease that affects everyone regardless of physical or biological state. More than 40% of the population is openly afflicted by the disease. Depression has become a troubling trend, affecting not just a person’s psychological well-being but also his or her physical well-being. Electroencephalography (EEG), for example, may identify the effects of depression in the brain. Doctors and researchers can use the tests to analyse the electrical activity of the brain. The electroencephalography signals are used to analyse depression in the proposed work. Data Collection, Data Preprocessing, Feature Extraction, and Classification are the tasks. In the procedure, three main sorts of data are employed. A total of five machine learning algorithms are deployed. Each dataset is compared to the associated algorithms. In all three datasets, the Random Forest method outperformed the other algorithms in terms of accuracy. Furthermore, depression is divided into three categories during the procedure.","PeriodicalId":246214,"journal":{"name":"2022 Third International Conference on Intelligent Computing Instrumentation and Control Technologies (ICICICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 Third International Conference on Intelligent Computing Instrumentation and Control Technologies (ICICICT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICICICT54557.2022.9917751","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Depression has been defined as a silent disease that affects everyone regardless of physical or biological state. More than 40% of the population is openly afflicted by the disease. Depression has become a troubling trend, affecting not just a person’s psychological well-being but also his or her physical well-being. Electroencephalography (EEG), for example, may identify the effects of depression in the brain. Doctors and researchers can use the tests to analyse the electrical activity of the brain. The electroencephalography signals are used to analyse depression in the proposed work. Data Collection, Data Preprocessing, Feature Extraction, and Classification are the tasks. In the procedure, three main sorts of data are employed. A total of five machine learning algorithms are deployed. Each dataset is compared to the associated algorithms. In all three datasets, the Random Forest method outperformed the other algorithms in terms of accuracy. Furthermore, depression is divided into three categories during the procedure.