Physical activity recognition from smartphone accelerometer data for user context awareness sensing
dc.contributor.author | Wannenburg, Johann | |
dc.contributor.author | Malekian, Reza | |
dc.date.accessioned | 2018-04-09T05:11:44Z | |
dc.date.available | 2018-04-09T05:11:44Z | |
dc.date.issued | 2017-12 | |
dc.description.abstract | Physical activity recognition of everyday activities such as sitting, standing, laying, walking, and jogging was performed, through the use of smartphone accelerometer data. Activity classification was done on a remote server through the use of machine learning algorithms, data was received from the smartphone wirelessly. The smartphone was placed in the subject's trouser pocket while data was gathered. A large sample set was used to train the classifiers and then a test set was used to verify the algorithm accuracies. Ten different classifier algorithm configurations were evaluated to determine which performed best overall, as well as, which algorithms performed best for specific activity classes. Based on the results obtained, very accurate predictions could be made for offline activity recognition. The kNN and kStar algorithms both obtained an overall accuracy of 99.01%. | en_ZA |
dc.description.department | Electrical, Electronic and Computer Engineering | en_ZA |
dc.description.librarian | hj2018 | en_ZA |
dc.description.uri | http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6221021 | en_ZA |
dc.identifier.citation | Wannenburg, J. & Malekian, R. 2017, 'Physical activity recognition from smartphone accelerometer data for user context awareness sensing', IEEE Transactions on Systems, Man, and Cybernetics : Systems, vol. 47, no. 12, pp. 3 142-3149. | en_ZA |
dc.identifier.issn | 2168-2216 (print) | |
dc.identifier.issn | 2168-2232 (online) | |
dc.identifier.other | 10.1109/TSMC.2016.2562509 | |
dc.identifier.uri | http://hdl.handle.net/2263/64425 | |
dc.language.iso | en | en_ZA |
dc.publisher | Institute of Electrical and Electronics Engineers | en_ZA |
dc.rights | © 2017 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. | en_ZA |
dc.subject | Accelerometer | en_ZA |
dc.subject | Activity recognition | en_ZA |
dc.subject | Machine learning | en_ZA |
dc.subject | Machine learning algorithms | en_ZA |
dc.subject | Feature extraction | en_ZA |
dc.subject | Hidden Markov models | en_ZA |
dc.subject | Sensors | en_ZA |
dc.subject | Ubiquitous computing | en_ZA |
dc.subject | Pattern classification | en_ZA |
dc.subject | Learning (artificial intelligence) | en_ZA |
dc.subject | Smart phone | en_ZA |
dc.title | Physical activity recognition from smartphone accelerometer data for user context awareness sensing | en_ZA |
dc.type | Postprint Article | en_ZA |