{"title":"Temporal sequence processing using recurrent SOM","authors":"T. Koskela, M. Varsta, J. Heikkonen, K. Kaski","doi":"10.1109/KES.1998.725861","DOIUrl":null,"url":null,"abstract":"Recurrent self-organizing map (RSOM) is studied in temporal sequence processing. RSOM includes a recurrent difference vector in each unit of the map, which allows storing temporal context from consecutive input vectors fed to the map. RSOM is a modification of the temporal Kohonen map (TKM). It is shown that RSOM learns a correct mapping from temporal sequences of a simple synthetic data, while TKM fails to learn this mapping. In addition, two case studies are presented, in which RSOM is applied to EEG based epileptic activity detection and to time series prediction with local models. Results suggest that RSOM can be efficiently used in temporal sequence processing.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"67","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/KES.1998.725861","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 67
Abstract
Recurrent self-organizing map (RSOM) is studied in temporal sequence processing. RSOM includes a recurrent difference vector in each unit of the map, which allows storing temporal context from consecutive input vectors fed to the map. RSOM is a modification of the temporal Kohonen map (TKM). It is shown that RSOM learns a correct mapping from temporal sequences of a simple synthetic data, while TKM fails to learn this mapping. In addition, two case studies are presented, in which RSOM is applied to EEG based epileptic activity detection and to time series prediction with local models. Results suggest that RSOM can be efficiently used in temporal sequence processing.