{"title":"Bottom-up Investigation: Human Activity Recognition Based on Feet Movement and Posture Information","authors":"Rafael de Pinho André, Pedro Diniz, H. Fuks","doi":"10.1145/3134230.3134240","DOIUrl":null,"url":null,"abstract":"Human Activity Recognition (HAR) research on feet posture and movement information has seen an intense growth during the last five years, drawing attention of fields such as healthcare systems and context inference. In this work, we tested our 6-activity classes machine learning HAR classifier using a foot-based wearable device in an experiment involving 11 volunteers. The classifier uses a Random Forest algorithm with Leave-one-out Cross Validation, achieving an average of 93.34% accuracy. Targeting at a replicable research, we provide full hardware information, system source code and a public domain dataset consisting of 800,000 samples.","PeriodicalId":209424,"journal":{"name":"Proceedings of the 4th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2017-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"16","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 4th International Workshop on Sensor-based Activity Recognition and Interaction","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3134230.3134240","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 16
Abstract
Human Activity Recognition (HAR) research on feet posture and movement information has seen an intense growth during the last five years, drawing attention of fields such as healthcare systems and context inference. In this work, we tested our 6-activity classes machine learning HAR classifier using a foot-based wearable device in an experiment involving 11 volunteers. The classifier uses a Random Forest algorithm with Leave-one-out Cross Validation, achieving an average of 93.34% accuracy. Targeting at a replicable research, we provide full hardware information, system source code and a public domain dataset consisting of 800,000 samples.