{"title":"Technique for effective validation of bio sensor using auto-associative neural network","authors":"Subhas A. Meti, V. Sangam","doi":"10.1109/INDICON.2016.7839014","DOIUrl":null,"url":null,"abstract":"The major issue concerning the Wireless Body Area Network (WBAN) systems is that of the energy dissipation which directly affects the system longevity. One of the reasons for energy dissipation in WBAN system is due to interference of signals from other such networks which results in a dimensionality reduction problem. Another issue concerning the WBAN system is the prediction of data with respect to faults or misinterpretation of the signal. Many learning based algorithm are proposed for efficient prediction, however, these learning require large number of training samples often leading to increased computational time making it less preferred in practical applications. This paper intends to address the above mentioned issues by combining the method of principal component analysis with respect to nonlinearity along with Auto Associative Neural Network (AANN). Experimental observations shows an increase in the system efficiency considering the computational time and number of training samples considered for prediction and training phase with reduced mean absolute error.","PeriodicalId":283953,"journal":{"name":"2016 IEEE Annual India Conference (INDICON)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE Annual India Conference (INDICON)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INDICON.2016.7839014","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
The major issue concerning the Wireless Body Area Network (WBAN) systems is that of the energy dissipation which directly affects the system longevity. One of the reasons for energy dissipation in WBAN system is due to interference of signals from other such networks which results in a dimensionality reduction problem. Another issue concerning the WBAN system is the prediction of data with respect to faults or misinterpretation of the signal. Many learning based algorithm are proposed for efficient prediction, however, these learning require large number of training samples often leading to increased computational time making it less preferred in practical applications. This paper intends to address the above mentioned issues by combining the method of principal component analysis with respect to nonlinearity along with Auto Associative Neural Network (AANN). Experimental observations shows an increase in the system efficiency considering the computational time and number of training samples considered for prediction and training phase with reduced mean absolute error.