Automated Detection of Activity Transitions for Prompting. Feuz, K. D., Cook, D. J., Rosasco, C., Robertson, K., & Schmitter-Edgecombe, M. IEEE Transactions on Human-Machine Systems, 45(5):575–585, October, 2015. Conference Name: IEEE Transactions on Human-Machine Systemsdoi abstract bibtex Individuals with cognitive impairment can benefit from intervention strategies like recording important information in a memory notebook. However, training individuals to use the notebook on a regular basis requires a constant delivery of reminders. In this study, we design and evaluate machine-learning-based methods for providing automated reminders using a digital memory notebook interface. Specifically, we identify transition periods between activities as times to issue prompts. We consider the problem of detecting activity transitions using supervised and unsupervised machine-learning techniques and find that both techniques show promising results for detecting transition periods. We test the techniques in a scripted setting with 15 individuals. Motion sensors data are recorded and annotated as participants perform a fixed set of activities. We also test the techniques in an unscripted setting with eight individuals. Motion sensor data are recorded as participants go about their normal daily routine. In both the scripted and unscripted settings, a true positive rate of greater than 80% can be achieved while maintaining a false positive rate of less than 15%. On average, this leads to transitions being detected within 1 min of a true transition for the scripted data and within 2 min of a true transition on the unscripted data.
@article{feuz_automated_2015,
title = {Automated {Detection} of {Activity} {Transitions} for {Prompting}},
volume = {45},
issn = {2168-2305},
doi = {10.1109/THMS.2014.2362529},
abstract = {Individuals with cognitive impairment can benefit from intervention strategies like recording important information in a memory notebook. However, training individuals to use the notebook on a regular basis requires a constant delivery of reminders. In this study, we design and evaluate machine-learning-based methods for providing automated reminders using a digital memory notebook interface. Specifically, we identify transition periods between activities as times to issue prompts. We consider the problem of detecting activity transitions using supervised and unsupervised machine-learning techniques and find that both techniques show promising results for detecting transition periods. We test the techniques in a scripted setting with 15 individuals. Motion sensors data are recorded and annotated as participants perform a fixed set of activities. We also test the techniques in an unscripted setting with eight individuals. Motion sensor data are recorded as participants go about their normal daily routine. In both the scripted and unscripted settings, a true positive rate of greater than 80\% can be achieved while maintaining a false positive rate of less than 15\%. On average, this leads to transitions being detected within 1 min of a true transition for the scripted data and within 2 min of a true transition on the unscripted data.},
number = {5},
journal = {IEEE Transactions on Human-Machine Systems},
author = {Feuz, Kyle D. and Cook, Diane J. and Rosasco, Cody and Robertson, Kayela and Schmitter-Edgecombe, Maureen},
month = oct,
year = {2015},
note = {Conference Name: IEEE Transactions on Human-Machine Systems},
keywords = {Activity recognition, Intelligent sensors, Sensor phenomena and characterization, Smart homes, Supervised learning, TV, Temperature sensors, change-point detection, machine learning, prompting systems, smart environments},
pages = {575--585},
}
Downloads: 0
{"_id":"YjQ7xMkBaydHfeNCG","bibbaseid":"feuz-cook-rosasco-robertson-schmitteredgecombe-automateddetectionofactivitytransitionsforprompting-2015","author_short":["Feuz, K. D.","Cook, D. J.","Rosasco, C.","Robertson, K.","Schmitter-Edgecombe, M."],"bibdata":{"bibtype":"article","type":"article","title":"Automated Detection of Activity Transitions for Prompting","volume":"45","issn":"2168-2305","doi":"10.1109/THMS.2014.2362529","abstract":"Individuals with cognitive impairment can benefit from intervention strategies like recording important information in a memory notebook. However, training individuals to use the notebook on a regular basis requires a constant delivery of reminders. In this study, we design and evaluate machine-learning-based methods for providing automated reminders using a digital memory notebook interface. Specifically, we identify transition periods between activities as times to issue prompts. We consider the problem of detecting activity transitions using supervised and unsupervised machine-learning techniques and find that both techniques show promising results for detecting transition periods. We test the techniques in a scripted setting with 15 individuals. Motion sensors data are recorded and annotated as participants perform a fixed set of activities. We also test the techniques in an unscripted setting with eight individuals. Motion sensor data are recorded as participants go about their normal daily routine. In both the scripted and unscripted settings, a true positive rate of greater than 80% can be achieved while maintaining a false positive rate of less than 15%. On average, this leads to transitions being detected within 1 min of a true transition for the scripted data and within 2 min of a true transition on the unscripted data.","number":"5","journal":"IEEE Transactions on Human-Machine Systems","author":[{"propositions":[],"lastnames":["Feuz"],"firstnames":["Kyle","D."],"suffixes":[]},{"propositions":[],"lastnames":["Cook"],"firstnames":["Diane","J."],"suffixes":[]},{"propositions":[],"lastnames":["Rosasco"],"firstnames":["Cody"],"suffixes":[]},{"propositions":[],"lastnames":["Robertson"],"firstnames":["Kayela"],"suffixes":[]},{"propositions":[],"lastnames":["Schmitter-Edgecombe"],"firstnames":["Maureen"],"suffixes":[]}],"month":"October","year":"2015","note":"Conference Name: IEEE Transactions on Human-Machine Systems","keywords":"Activity recognition, Intelligent sensors, Sensor phenomena and characterization, Smart homes, Supervised learning, TV, Temperature sensors, change-point detection, machine learning, prompting systems, smart environments","pages":"575–585","bibtex":"@article{feuz_automated_2015,\n\ttitle = {Automated {Detection} of {Activity} {Transitions} for {Prompting}},\n\tvolume = {45},\n\tissn = {2168-2305},\n\tdoi = {10.1109/THMS.2014.2362529},\n\tabstract = {Individuals with cognitive impairment can benefit from intervention strategies like recording important information in a memory notebook. However, training individuals to use the notebook on a regular basis requires a constant delivery of reminders. In this study, we design and evaluate machine-learning-based methods for providing automated reminders using a digital memory notebook interface. Specifically, we identify transition periods between activities as times to issue prompts. We consider the problem of detecting activity transitions using supervised and unsupervised machine-learning techniques and find that both techniques show promising results for detecting transition periods. We test the techniques in a scripted setting with 15 individuals. Motion sensors data are recorded and annotated as participants perform a fixed set of activities. We also test the techniques in an unscripted setting with eight individuals. Motion sensor data are recorded as participants go about their normal daily routine. In both the scripted and unscripted settings, a true positive rate of greater than 80\\% can be achieved while maintaining a false positive rate of less than 15\\%. On average, this leads to transitions being detected within 1 min of a true transition for the scripted data and within 2 min of a true transition on the unscripted data.},\n\tnumber = {5},\n\tjournal = {IEEE Transactions on Human-Machine Systems},\n\tauthor = {Feuz, Kyle D. and Cook, Diane J. and Rosasco, Cody and Robertson, Kayela and Schmitter-Edgecombe, Maureen},\n\tmonth = oct,\n\tyear = {2015},\n\tnote = {Conference Name: IEEE Transactions on Human-Machine Systems},\n\tkeywords = {Activity recognition, Intelligent sensors, Sensor phenomena and characterization, Smart homes, Supervised learning, TV, Temperature sensors, change-point detection, machine learning, prompting systems, smart environments},\n\tpages = {575--585},\n}\n\n","author_short":["Feuz, K. D.","Cook, D. J.","Rosasco, C.","Robertson, K.","Schmitter-Edgecombe, M."],"key":"feuz_automated_2015","id":"feuz_automated_2015","bibbaseid":"feuz-cook-rosasco-robertson-schmitteredgecombe-automateddetectionofactivitytransitionsforprompting-2015","role":"author","urls":{},"keyword":["Activity recognition","Intelligent sensors","Sensor phenomena and characterization","Smart homes","Supervised learning","TV","Temperature sensors","change-point detection","machine learning","prompting systems","smart environments"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["activity recognition","intelligent sensors","sensor phenomena and characterization","smart homes","supervised learning","tv","temperature sensors","change-point detection","machine learning","prompting systems","smart environments"],"search_terms":["automated","detection","activity","transitions","prompting","feuz","cook","rosasco","robertson","schmitter-edgecombe"],"title":"Automated Detection of Activity Transitions for Prompting","year":2015}