Loading…

KU-HAR: An open dataset for heterogeneous human activity recognition

•Describes the content of the KU-HAR dataset, and the associated data collection procedure in details.•Provides a comparison with other contemporary HAR datasets.•Presents some HAR classification results involving the KU-HAR dataset. In Artificial Intelligence, Human Activity Recognition (HAR) refer...

Full description

Saved in:

Bibliographic Details
Published in:	Pattern recognition letters 2021-06, Vol.146, p.46-54
Main Authors:	Sikder, Niloy, Nahid, Abdullah-Al
Format:	Article
Language:	English
Subjects:	Accelerometers Algorithms Artificial intelligence Datasets Electronic devices Human activity recognition Knowledge acquisition Learning algorithms Machine learning Moving object recognition Smartphones
Citations:	Items that this one cites Items that cite this one
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

cited_by	cdi_FETCH-LOGICAL-c334t-ac83b0d5a80a111b9a735c70834d3cb2ac4891967ff388ecfdba08d95230e93c3
cites	cdi_FETCH-LOGICAL-c334t-ac83b0d5a80a111b9a735c70834d3cb2ac4891967ff388ecfdba08d95230e93c3
container_end_page	54
container_issue
container_start_page	46
container_title	Pattern recognition letters
container_volume	146
creator	Sikder, Niloy Nahid, Abdullah-Al
description	•Describes the content of the KU-HAR dataset, and the associated data collection procedure in details.•Provides a comparison with other contemporary HAR datasets.•Presents some HAR classification results involving the KU-HAR dataset. In Artificial Intelligence, Human Activity Recognition (HAR) refers to the capability of machines to identify various activities performed by the users. The knowledge acquired from these recognition systems is integrated into many applications where the associated device uses it to identify actions or gestures and performs predefined tasks in response. HAR requires a large quantity of meticulously collected action data of diverse nature to fuel its learning algorithms. This paper aims to introduce a new set of HAR data collected from 90 participants who are 18 to 34 years old. The constructed dataset is named KU-HAR, and it contains 1945 raw activity samples that belong to 18 different classes. We used built-in smartphone sensors (accelerometer and gyroscope) to collect these HAR samples. Apart from the original (raw) time-domain samples, the dataset contains 20,750 subsamples (extracted from them) provided separately, each containing 3 seconds of data of the corresponding activity. Some classification results have been provided as well to propound the quality of the proposed dataset. The acquired results show that Random Forest (RF), an ensemble learning algorithm, can classify the subsamples with almost 90% accuracy. This dataset will enable smartphones and other smart devices to identify new activities and help researchers to design more delicate models based on practical HAR data.
doi_str_mv	10.1016/j.patrec.2021.02.024
format	article
fullrecord	<record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2533404915</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0167865521000933</els_id><sourcerecordid>2533404915</sourcerecordid><originalsourceid>FETCH-LOGICAL-c334t-ac83b0d5a80a111b9a735c70834d3cb2ac4891967ff388ecfdba08d95230e93c3</originalsourceid><addsrcrecordid>eNp9kF1LwzAYhYMoOKf_wIuA1635apt6IYz5MXEgiLsOaZpuKS6pSTrYvzejXgsH3pvnnMN7ALjFKMcIl_d9PsjotcoJIjhHJImdgRnmFckqytg5mCWsynhZFJfgKoQeIVTSms_A0_smWy0-H-DCQjdoC1sZZdARds7DnY7au6222o0B7sa9tFCqaA4mHmHqc1tronH2Glx08jvom787B5uX56_lKlt_vL4tF-tMUcpiJhWnDWoLyZHEGDe1rGihKsQpa6lqiFSM17guq66jnGvVtY1EvK0LQpGuqaJzcDflDt79jDpE0bvR21QpSJEqEKtxkSg2Ucq7ELzuxODNXvqjwEic9hK9mPYSp70EIkks2R4nm04fHIz2IiijrdKtSWgUrTP_B_wC8sh00g</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2533404915</pqid></control><display><type>article</type><title>KU-HAR: An open dataset for heterogeneous human activity recognition</title><source>ScienceDirect Freedom Collection</source><creator>Sikder, Niloy ; Nahid, Abdullah-Al</creator><creatorcontrib>Sikder, Niloy ; Nahid, Abdullah-Al</creatorcontrib><description>•Describes the content of the KU-HAR dataset, and the associated data collection procedure in details.•Provides a comparison with other contemporary HAR datasets.•Presents some HAR classification results involving the KU-HAR dataset. In Artificial Intelligence, Human Activity Recognition (HAR) refers to the capability of machines to identify various activities performed by the users. The knowledge acquired from these recognition systems is integrated into many applications where the associated device uses it to identify actions or gestures and performs predefined tasks in response. HAR requires a large quantity of meticulously collected action data of diverse nature to fuel its learning algorithms. This paper aims to introduce a new set of HAR data collected from 90 participants who are 18 to 34 years old. The constructed dataset is named KU-HAR, and it contains 1945 raw activity samples that belong to 18 different classes. We used built-in smartphone sensors (accelerometer and gyroscope) to collect these HAR samples. Apart from the original (raw) time-domain samples, the dataset contains 20,750 subsamples (extracted from them) provided separately, each containing 3 seconds of data of the corresponding activity. Some classification results have been provided as well to propound the quality of the proposed dataset. The acquired results show that Random Forest (RF), an ensemble learning algorithm, can classify the subsamples with almost 90% accuracy. This dataset will enable smartphones and other smart devices to identify new activities and help researchers to design more delicate models based on practical HAR data.</description><identifier>ISSN: 0167-8655</identifier><identifier>EISSN: 1872-7344</identifier><identifier>DOI: 10.1016/j.patrec.2021.02.024</identifier><language>eng</language><publisher>Amsterdam: Elsevier B.V</publisher><subject>Accelerometers ; Algorithms ; Artificial intelligence ; Datasets ; Electronic devices ; Human activity recognition ; Knowledge acquisition ; Learning algorithms ; Machine learning ; Moving object recognition ; Smartphones</subject><ispartof>Pattern recognition letters, 2021-06, Vol.146, p.46-54</ispartof><rights>2021 Elsevier B.V.</rights><rights>Copyright Elsevier Science Ltd. Jun 2021</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c334t-ac83b0d5a80a111b9a735c70834d3cb2ac4891967ff388ecfdba08d95230e93c3</citedby><cites>FETCH-LOGICAL-c334t-ac83b0d5a80a111b9a735c70834d3cb2ac4891967ff388ecfdba08d95230e93c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>315,783,787,27936,27937</link.rule.ids></links><search><creatorcontrib>Sikder, Niloy</creatorcontrib><creatorcontrib>Nahid, Abdullah-Al</creatorcontrib><title>KU-HAR: An open dataset for heterogeneous human activity recognition</title><title>Pattern recognition letters</title><description>•Describes the content of the KU-HAR dataset, and the associated data collection procedure in details.•Provides a comparison with other contemporary HAR datasets.•Presents some HAR classification results involving the KU-HAR dataset. In Artificial Intelligence, Human Activity Recognition (HAR) refers to the capability of machines to identify various activities performed by the users. The knowledge acquired from these recognition systems is integrated into many applications where the associated device uses it to identify actions or gestures and performs predefined tasks in response. HAR requires a large quantity of meticulously collected action data of diverse nature to fuel its learning algorithms. This paper aims to introduce a new set of HAR data collected from 90 participants who are 18 to 34 years old. The constructed dataset is named KU-HAR, and it contains 1945 raw activity samples that belong to 18 different classes. We used built-in smartphone sensors (accelerometer and gyroscope) to collect these HAR samples. Apart from the original (raw) time-domain samples, the dataset contains 20,750 subsamples (extracted from them) provided separately, each containing 3 seconds of data of the corresponding activity. Some classification results have been provided as well to propound the quality of the proposed dataset. The acquired results show that Random Forest (RF), an ensemble learning algorithm, can classify the subsamples with almost 90% accuracy. This dataset will enable smartphones and other smart devices to identify new activities and help researchers to design more delicate models based on practical HAR data.</description><subject>Accelerometers</subject><subject>Algorithms</subject><subject>Artificial intelligence</subject><subject>Datasets</subject><subject>Electronic devices</subject><subject>Human activity recognition</subject><subject>Knowledge acquisition</subject><subject>Learning algorithms</subject><subject>Machine learning</subject><subject>Moving object recognition</subject><subject>Smartphones</subject><issn>0167-8655</issn><issn>1872-7344</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp9kF1LwzAYhYMoOKf_wIuA1635apt6IYz5MXEgiLsOaZpuKS6pSTrYvzejXgsH3pvnnMN7ALjFKMcIl_d9PsjotcoJIjhHJImdgRnmFckqytg5mCWsynhZFJfgKoQeIVTSms_A0_smWy0-H-DCQjdoC1sZZdARds7DnY7au6222o0B7sa9tFCqaA4mHmHqc1tronH2Glx08jvom787B5uX56_lKlt_vL4tF-tMUcpiJhWnDWoLyZHEGDe1rGihKsQpa6lqiFSM17guq66jnGvVtY1EvK0LQpGuqaJzcDflDt79jDpE0bvR21QpSJEqEKtxkSg2Ucq7ELzuxODNXvqjwEic9hK9mPYSp70EIkks2R4nm04fHIz2IiijrdKtSWgUrTP_B_wC8sh00g</recordid><startdate>202106</startdate><enddate>202106</enddate><creator>Sikder, Niloy</creator><creator>Nahid, Abdullah-Al</creator><general>Elsevier B.V</general><general>Elsevier Science Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7TK</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>202106</creationdate><title>KU-HAR: An open dataset for heterogeneous human activity recognition</title><author>Sikder, Niloy ; Nahid, Abdullah-Al</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c334t-ac83b0d5a80a111b9a735c70834d3cb2ac4891967ff388ecfdba08d95230e93c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Accelerometers</topic><topic>Algorithms</topic><topic>Artificial intelligence</topic><topic>Datasets</topic><topic>Electronic devices</topic><topic>Human activity recognition</topic><topic>Knowledge acquisition</topic><topic>Learning algorithms</topic><topic>Machine learning</topic><topic>Moving object recognition</topic><topic>Smartphones</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Sikder, Niloy</creatorcontrib><creatorcontrib>Nahid, Abdullah-Al</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Pattern recognition letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Sikder, Niloy</au><au>Nahid, Abdullah-Al</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>KU-HAR: An open dataset for heterogeneous human activity recognition</atitle><jtitle>Pattern recognition letters</jtitle><date>2021-06</date><risdate>2021</risdate><volume>146</volume><spage>46</spage><epage>54</epage><pages>46-54</pages><issn>0167-8655</issn><eissn>1872-7344</eissn><abstract>•Describes the content of the KU-HAR dataset, and the associated data collection procedure in details.•Provides a comparison with other contemporary HAR datasets.•Presents some HAR classification results involving the KU-HAR dataset. In Artificial Intelligence, Human Activity Recognition (HAR) refers to the capability of machines to identify various activities performed by the users. The knowledge acquired from these recognition systems is integrated into many applications where the associated device uses it to identify actions or gestures and performs predefined tasks in response. HAR requires a large quantity of meticulously collected action data of diverse nature to fuel its learning algorithms. This paper aims to introduce a new set of HAR data collected from 90 participants who are 18 to 34 years old. The constructed dataset is named KU-HAR, and it contains 1945 raw activity samples that belong to 18 different classes. We used built-in smartphone sensors (accelerometer and gyroscope) to collect these HAR samples. Apart from the original (raw) time-domain samples, the dataset contains 20,750 subsamples (extracted from them) provided separately, each containing 3 seconds of data of the corresponding activity. Some classification results have been provided as well to propound the quality of the proposed dataset. The acquired results show that Random Forest (RF), an ensemble learning algorithm, can classify the subsamples with almost 90% accuracy. This dataset will enable smartphones and other smart devices to identify new activities and help researchers to design more delicate models based on practical HAR data.</abstract><cop>Amsterdam</cop><pub>Elsevier B.V</pub><doi>10.1016/j.patrec.2021.02.024</doi><tpages>9</tpages></addata></record>
fulltext	fulltext
identifier	ISSN: 0167-8655
ispartof	Pattern recognition letters, 2021-06, Vol.146, p.46-54
issn	0167-8655 1872-7344
language	eng
recordid	cdi_proquest_journals_2533404915
source	ScienceDirect Freedom Collection
subjects	Accelerometers Algorithms Artificial intelligence Datasets Electronic devices Human activity recognition Knowledge acquisition Learning algorithms Machine learning Moving object recognition Smartphones
title	KU-HAR: An open dataset for heterogeneous human activity recognition
url	http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-11-13T14%3A20%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=KU-HAR:%20An%20open%20dataset%20for%20heterogeneous%20human%20activity%20recognition&rft.jtitle=Pattern%20recognition%20letters&rft.au=Sikder,%20Niloy&rft.date=2021-06&rft.volume=146&rft.spage=46&rft.epage=54&rft.pages=46-54&rft.issn=0167-8655&rft.eissn=1872-7344&rft_id=info:doi/10.1016/j.patrec.2021.02.024&rft_dat=%3Cproquest_cross%3E2533404915%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c334t-ac83b0d5a80a111b9a735c70834d3cb2ac4891967ff388ecfdba08d95230e93c3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2533404915&rft_id=info:pmid/&rfr_iscdi=true