Integrating features for accelerometer-based activity recognition
dc.contributor.author | Erdas, C.Berke | |
dc.contributor.author | Atasoy, Isil | |
dc.contributor.author | Acici, Koray | |
dc.contributor.author | Ogul, Hasan | |
dc.contributor.orcID | 0000-0003-3467-9923 | en_US |
dc.date.accessioned | 2019-06-20T12:24:11Z | |
dc.date.available | 2019-06-20T12:24:11Z | |
dc.date.issued | 2016 | |
dc.description.abstract | Activity recognition is the problem of predicting the current action of a person through the motion sensors worn on the body. The problem is usually approached as a supervised classification task where a discriminative model is learned from known samples and a new query is assigned to a known activity label using learned model. The challenging issue here is how to feed this classifier with a fixed number of features where the real input is a raw signal of varying length. In this study, we consider three possible feature sets, namely time-domain, frequency domain and wavelet-domain statistics, and their combinations to represent motion signal obtained from accelerometer reads worn in chest through a mobile phone. In addition to a systematic comparison of these feature sets, we also provide a comprehensive evaluation of some preprocessing steps such as filtering and feature selection. The results determine that feeding a random forest classifier with an ensemble selection of most relevant time-domain and frequency-domain features extracted from raw data can provide the highest accuracy in a real dataset. (C) 2016 The Authors. Published by Elsevier B.V. | en_US |
dc.identifier.endpage | 527 | en_US |
dc.identifier.issn | 1877-0509 | |
dc.identifier.scopus | 2-s2.0-84992391447 | en_US |
dc.identifier.startpage | 522 | en_US |
dc.identifier.uri | https://www.sciencedirect.com/science/article/pii/S1877050916322153?via%3Dihub | |
dc.identifier.uri | http://hdl.handle.net/11727/3650 | |
dc.identifier.volume | 98 | en_US |
dc.identifier.wos | 000387551200074 | en_US |
dc.language.iso | eng | en_US |
dc.relation.isversionof | 10.1016/j.procs.2016.09.070 | en_US |
dc.relation.journal | 7TH INTERNATIONAL CONFERENCE ON EMERGING UBIQUITOUS SYSTEMS AND PERVASIVE NETWORKS (EUSPN 2016)/THE 6TH INTERNATIONAL CONFERENCE ON CURRENT AND FUTURE TRENDS OF INFORMATION AND COMMUNICATION TECHNOLOGIES IN HEALTHCARE (ICTH-2016) | en_US |
dc.rights | info:eu-repo/semantics/openAccess | en_US |
dc.subject | Activity recognition | en_US |
dc.subject | Accelerometer analysis | en_US |
dc.subject | Feature selection | en_US |
dc.title | Integrating features for accelerometer-based activity recognition | en_US |
dc.type | conferenceObject | en_US |