Collection of a Diverse, Realistic and Annotated Dataset for Wearable Activity Recognition
This paper discusses the opportunities and challenges associated with the collection of a large scale, diverse dataset for Activity Recognition. The dataset was collected by 141 undergraduate students, in a controlled environment. Students collected triaxial accelerometer data from a wearable accele...
Saved in:
Published in | 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) pp. 555 - 560 |
---|---|
Main Authors | , , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.03.2018
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | This paper discusses the opportunities and challenges associated with the collection of a large scale, diverse dataset for Activity Recognition. The dataset was collected by 141 undergraduate students, in a controlled environment. Students collected triaxial accelerometer data from a wearable accelerometer whilst each carrying out 3 of the 18 investigated activities, categorized into 6 scenarios of daily living. This data was subsequently labelled, anonymized and uploaded to a shared repository. This paper presents an analysis of data quality, through outlier detection and assesses the suitability of the dataset for the creation and validation of Activity Recognition models. This is achieved through the application of a range of common data driven machine learning approaches. Finally, the paper describes challenges identified during the data collection process and discusses how these could be addressed. Issues surrounding data quality, in particular, identifying and addressing poor calibration of the data were identified. Results highlight the potential of harnessing these diverse data for Activity Recognition. Based on a comparison of six classification approaches, a Random Forest provided the best classification (F-measure: 0.88). In future data collection cycles, participants will be encouraged to collect a set of "common" activities, to support generation of a larger homogeneous dataset. Future work will seek to refine the methodology further and to evaluate model on new unseen data. |
---|---|
AbstractList | This paper discusses the opportunities and challenges associated with the collection of a large scale, diverse dataset for Activity Recognition. The dataset was collected by 141 undergraduate students, in a controlled environment. Students collected triaxial accelerometer data from a wearable accelerometer whilst each carrying out 3 of the 18 investigated activities, categorized into 6 scenarios of daily living. This data was subsequently labelled, anonymized and uploaded to a shared repository. This paper presents an analysis of data quality, through outlier detection and assesses the suitability of the dataset for the creation and validation of Activity Recognition models. This is achieved through the application of a range of common data driven machine learning approaches. Finally, the paper describes challenges identified during the data collection process and discusses how these could be addressed. Issues surrounding data quality, in particular, identifying and addressing poor calibration of the data were identified. Results highlight the potential of harnessing these diverse data for Activity Recognition. Based on a comparison of six classification approaches, a Random Forest provided the best classification (F-measure: 0.88). In future data collection cycles, participants will be encouraged to collect a set of "common" activities, to support generation of a larger homogeneous dataset. Future work will seek to refine the methodology further and to evaluate model on new unseen data. |
Author | Hallberg, J. Espinilla, M. Garcia-Constantino, M. Cleland, I. Nugent, C. D. Donnelly, M. P. |
Author_xml | – sequence: 1 givenname: I. surname: Cleland fullname: Cleland, I. organization: School of Computing, Ulster University, Co. Antrim, Northern Ireland, United Kingdom – sequence: 2 givenname: M. P. surname: Donnelly fullname: Donnelly, M. P. organization: School of Computing, Ulster University, Co. Antrim, Northern Ireland, United Kingdom – sequence: 3 givenname: C. D. surname: Nugent fullname: Nugent, C. D. organization: School of Computing, Ulster University, Co. Antrim, Northern Ireland, United Kingdom – sequence: 4 givenname: J. surname: Hallberg fullname: Hallberg, J. organization: Department of Computer Science, Electrical and Space Engineering, Lulea University of Technology, Sweden – sequence: 5 givenname: M. surname: Espinilla fullname: Espinilla, M. organization: Department of Computer Science, University of Jaen, Jaen, Spain – sequence: 6 givenname: M. surname: Garcia-Constantino fullname: Garcia-Constantino, M. organization: School of Computing, Ulster University, Co. Antrim, Northern Ireland, United Kingdom |
BookMark | eNotj89KAzEYxCPoQWufQA95AHfNv-1mj8u2VqFSKUrBS_l280UCayLZUOjbG7GnYRjmx8wNufTBIyH3nJWcs-bxbbXrtq_7UjCuS600k0JckHlTa15Jvciurq_JZxfGEYfkgqfBUqBLd8Q44QPdIYxuSm6g4A1tvQ8JEhq6hAQTJmpDpHuECP2ItM2Eo0un3BrCl3d_vFtyZWGccH7WGfl4Wr13z8Vmu37p2k3hBBOiqBoj0CrRM7mwyCrBELliuqoMz9sb4NDnsB640rZGoSQHY7QyudwoBDkjd_9ch4iHn-i-IZ4O58fyF04DT-M |
ContentType | Conference Proceeding |
DBID | 6IE 6IL CBEJK RIE RIL |
DOI | 10.1109/PERCOMW.2018.8480322 |
DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEL IEEE Proceedings Order Plans (POP All) 1998-Present |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
EISBN | 9781538632277 1538632276 |
EndPage | 560 |
ExternalDocumentID | 8480322 |
Genre | orig-research |
GroupedDBID | 6IE 6IL CBEJK RIE RIL |
ID | FETCH-LOGICAL-i2022-59d2ef42b036fe0520ee140855d12019a1ab2b07c148f7e2431add84d02294ea3 |
IEDL.DBID | RIE |
IngestDate | Thu Jun 29 18:39:29 EDT 2023 |
IsDoiOpenAccess | false |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-i2022-59d2ef42b036fe0520ee140855d12019a1ab2b07c148f7e2431add84d02294ea3 |
OpenAccessLink | https://pure.ulster.ac.uk/ws/files/12417038/PID5182937.pdf |
PageCount | 6 |
ParticipantIDs | ieee_primary_8480322 |
PublicationCentury | 2000 |
PublicationDate | 2018-03 |
PublicationDateYYYYMMDD | 2018-03-01 |
PublicationDate_xml | – month: 03 year: 2018 text: 2018-03 |
PublicationDecade | 2010 |
PublicationTitle | 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) |
PublicationTitleAbbrev | PERCOMW |
PublicationYear | 2018 |
Publisher | IEEE |
Publisher_xml | – name: IEEE |
Score | 1.7683166 |
Snippet | This paper discusses the opportunities and challenges associated with the collection of a large scale, diverse dataset for Activity Recognition. The dataset... |
SourceID | ieee |
SourceType | Publisher |
StartPage | 555 |
SubjectTerms | Accelerometers Activity recognition Cleaning Crowd Sourcing Data Annotaion Data collection Data models Data Quality Data Sharing Feature extraction |
Title | Collection of a Diverse, Realistic and Annotated Dataset for Wearable Activity Recognition |
URI | https://ieeexplore.ieee.org/document/8480322 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LS8NAEF5aT55UWvHNHjw2aR6bZvdY-qAI1VIsLV7KPiYgwkYkvfjrnd2kFcWDt5AHCbNDvpnZ75sh5L7gIBkGbYHUURSwASYoMtODQIDJIZWYjGlXh5w_DmYr9rDJNi3SO2hhAMCTzyB0h34v35R650plfc54hA7YJm0eJbVWq1HDxZHoLybL0dN87ehaPGxu_TEzxUPG9ITM9y-rmSJv4a5Sof781Yfxv19zSrrf4jy6OMDOGWmB7ZAXXwDwGgVaFlTSsedbQI8uwbU4RPeg0ho6tLZ04aWhY1khgFUUg1a6Rnd3Eio61PUwCbrc84pK2yWr6eR5NAuasQnBa-K4-ZkwCRQsUQhOBTieC0DsGpllJkbbCBlLhRdzjZlQkUOCIQT-5Dgz-LBgINNzcmRLCxeECsVUylKTpTmGfjpXTrSXyVgbEIZzc0k6zi7b97ozxrYxydXfp6_JsVubmsF1Q46qjx3cIqRX6s6v5Re6BaMj |
link.rule.ids | 310,311,786,790,795,796,802,27958,55109 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8JAEJ4gHvSkBoxv9-CRlj62tD0SHkGlSAgE4oVsd6cJMWmNKRd_vbNtwWg8eOszbWYn_Wam3zcD8JAEKDgFbYaQlmXwDiUowpMdI0TloysoGZO6DhlNOqMFf1p5qxq09loYRCzIZ2jqzeJfvsrkVpfK2gEPLHLAAzgknLfCUq1V6eFovz0dzHov0VITtgKzuvjH1JQCNIYnEO0eV3JF3sxtHpvy81cnxv--zyk0v-V5bLoHnjOoYdqA16IEUKgUWJYwwfoF4wJbbIa6ySE5CBOpYt00zXSAqVhf5ARhOaOwlS3J4bWIinVlOU6CzXbMoixtwmI4mPdGRjU4wdg4mp3vhcrBhDsxwVOCmumCaOtWZp6yyTahsEVMJ31JuVDio0NBBH3mAq7o5pCjcM-hnmYpXgALYx673FWe61PwJ_1Yy_Y8YUuFoQoCdQkNbZf1e9kbY12Z5Orvw_dwNJpH4_X4cfJ8Dcd6nUo-1w3U848t3hLA5_Fdsa5fhHOmeQ |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2018+IEEE+International+Conference+on+Pervasive+Computing+and+Communications+Workshops+%28PerCom+Workshops%29&rft.atitle=Collection+of+a+Diverse%2C+Realistic+and+Annotated+Dataset+for+Wearable+Activity+Recognition&rft.au=Cleland%2C+I.&rft.au=Donnelly%2C+M.+P.&rft.au=Nugent%2C+C.+D.&rft.au=Hallberg%2C+J.&rft.date=2018-03-01&rft.pub=IEEE&rft.spage=555&rft.epage=560&rft_id=info:doi/10.1109%2FPERCOMW.2018.8480322&rft.externalDocID=8480322 |