T. Kuremoto, T. Otani, S. Mabu, M. Obayashi, Kunikazu Kobayashi
{"title":"One-D-R-A-G-SOM and its Application to a Hand Shape Instruction Learning System","authors":"T. Kuremoto, T. Otani, S. Mabu, M. Obayashi, Kunikazu Kobayashi","doi":"10.2991/ijndc.2014.2.3.6","DOIUrl":null,"url":null,"abstract":"In this paper, a novel self-organizing map (SOM) named “One-D-R-A-G-SOM” is proposed. It is a kind of one dimensional ring type growing SOM using asymmetric neighborhood function. As the topology of one dimensional ring type feature map is more suitable to increase or decrease the number of units, and the disorder of the map is available to be solved by the asymmetric neighborhood function, the proposed model gives priority of learning performance to the conventional two dimensional growing SOM. Additionally, One-D-R-A-G-SOM is introduced to a hand shape recognition and instruction learning system. Experiment results showed the effectiveness of the novel system comparing with systems using the conventional SOMs.","PeriodicalId":318936,"journal":{"name":"Int. J. Networked Distributed Comput.","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Int. J. Networked Distributed Comput.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2991/ijndc.2014.2.3.6","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
In this paper, a novel self-organizing map (SOM) named “One-D-R-A-G-SOM” is proposed. It is a kind of one dimensional ring type growing SOM using asymmetric neighborhood function. As the topology of one dimensional ring type feature map is more suitable to increase or decrease the number of units, and the disorder of the map is available to be solved by the asymmetric neighborhood function, the proposed model gives priority of learning performance to the conventional two dimensional growing SOM. Additionally, One-D-R-A-G-SOM is introduced to a hand shape recognition and instruction learning system. Experiment results showed the effectiveness of the novel system comparing with systems using the conventional SOMs.