Hand, belt, pocket or bag: Practical activity tracking with mobile phones. Antos, S., a., Albert, M., V., & Kording, K., P. Journal of neuroscience methods, 231:22-30, Elsevier B.V., 7, 2014. Paper Website abstract bibtex For rehabilitation and diagnoses, an understanding of patient activities and movements is important. Modern smartphones have built in accelerometers which promise to enable quantifying minute-by-minute what patients do (e.g. walk or sit). Such a capability could inform recommendations of physical activities and improve medical diagnostics. However, a major problem is that during everyday life, we carry our phone in different ways, e.g. on our belt, in our pocket, in our hand, or in a bag. The recorded accelerations are not only affected by our activities but also by the phone's location. Here we develop a method to solve this kind of problem, based on the intuition that activities change rarely, and phone locations change even less often. A hidden Markov model (HMM) tracks changes across both activities and locations, enabled by a static support vector machine (SVM) classifier that probabilistically identifies activity-location pairs. We find that this approach improves tracking accuracy on healthy subjects as compared to a static classifier alone. The obtained method can be readily applied to patient populations. Our research enables the use of phones as activity tracking devices, without the need of previous approaches to instruct subjects to always carry the phone in the same location.
@article{
title = {Hand, belt, pocket or bag: Practical activity tracking with mobile phones.},
type = {article},
year = {2014},
identifiers = {[object Object]},
keywords = {activity recognition},
pages = {22-30},
volume = {231},
websites = {http://www.ncbi.nlm.nih.gov/pubmed/24091138},
month = {7},
publisher = {Elsevier B.V.},
day = {15},
id = {52cf7f05-d950-3f2e-bd4e-9780809b6944},
created = {2016-04-14T18:02:28.000Z},
accessed = {2014-09-16},
file_attached = {true},
profile_id = {d28af011-5164-3af4-8522-822cff4de1eb},
group_id = {e39cd875-9ef8-3fee-ad92-c9d084a63048},
last_modified = {2017-10-14T23:14:07.736Z},
read = {true},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {Antos2014},
folder_uuids = {dc34bb65-a794-457d-b88a-9687552166f4},
private_publication = {false},
abstract = {For rehabilitation and diagnoses, an understanding of patient activities and movements is important. Modern smartphones have built in accelerometers which promise to enable quantifying minute-by-minute what patients do (e.g. walk or sit). Such a capability could inform recommendations of physical activities and improve medical diagnostics. However, a major problem is that during everyday life, we carry our phone in different ways, e.g. on our belt, in our pocket, in our hand, or in a bag. The recorded accelerations are not only affected by our activities but also by the phone's location. Here we develop a method to solve this kind of problem, based on the intuition that activities change rarely, and phone locations change even less often. A hidden Markov model (HMM) tracks changes across both activities and locations, enabled by a static support vector machine (SVM) classifier that probabilistically identifies activity-location pairs. We find that this approach improves tracking accuracy on healthy subjects as compared to a static classifier alone. The obtained method can be readily applied to patient populations. Our research enables the use of phones as activity tracking devices, without the need of previous approaches to instruct subjects to always carry the phone in the same location.},
bibtype = {article},
author = {Antos, Stephen a and Albert, Mark V and Kording, Konrad P},
journal = {Journal of neuroscience methods}
}
Downloads: 0
{"_id":"HMuZdBuEmRtbmR2Ca","bibbaseid":"antos-albert-kording-handbeltpocketorbagpracticalactivitytrackingwithmobilephones-2014","downloads":0,"creationDate":"2018-01-02T16:38:25.309Z","title":"Hand, belt, pocket or bag: Practical activity tracking with mobile phones.","author_short":["Antos, S., a.","Albert, M., V.","Kording, K., P."],"year":2014,"bibtype":"article","biburl":null,"bibdata":{"title":"Hand, belt, pocket or bag: Practical activity tracking with mobile phones.","type":"article","year":"2014","identifiers":"[object Object]","keywords":"activity recognition","pages":"22-30","volume":"231","websites":"http://www.ncbi.nlm.nih.gov/pubmed/24091138","month":"7","publisher":"Elsevier B.V.","day":"15","id":"52cf7f05-d950-3f2e-bd4e-9780809b6944","created":"2016-04-14T18:02:28.000Z","accessed":"2014-09-16","file_attached":"true","profile_id":"d28af011-5164-3af4-8522-822cff4de1eb","group_id":"e39cd875-9ef8-3fee-ad92-c9d084a63048","last_modified":"2017-10-14T23:14:07.736Z","read":"true","starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Antos2014","folder_uuids":"dc34bb65-a794-457d-b88a-9687552166f4","private_publication":false,"abstract":"For rehabilitation and diagnoses, an understanding of patient activities and movements is important. Modern smartphones have built in accelerometers which promise to enable quantifying minute-by-minute what patients do (e.g. walk or sit). Such a capability could inform recommendations of physical activities and improve medical diagnostics. However, a major problem is that during everyday life, we carry our phone in different ways, e.g. on our belt, in our pocket, in our hand, or in a bag. The recorded accelerations are not only affected by our activities but also by the phone's location. Here we develop a method to solve this kind of problem, based on the intuition that activities change rarely, and phone locations change even less often. A hidden Markov model (HMM) tracks changes across both activities and locations, enabled by a static support vector machine (SVM) classifier that probabilistically identifies activity-location pairs. We find that this approach improves tracking accuracy on healthy subjects as compared to a static classifier alone. The obtained method can be readily applied to patient populations. Our research enables the use of phones as activity tracking devices, without the need of previous approaches to instruct subjects to always carry the phone in the same location.","bibtype":"article","author":"Antos, Stephen a and Albert, Mark V and Kording, Konrad P","journal":"Journal of neuroscience methods","bibtex":"@article{\n title = {Hand, belt, pocket or bag: Practical activity tracking with mobile phones.},\n type = {article},\n year = {2014},\n identifiers = {[object Object]},\n keywords = {activity recognition},\n pages = {22-30},\n volume = {231},\n websites = {http://www.ncbi.nlm.nih.gov/pubmed/24091138},\n month = {7},\n publisher = {Elsevier B.V.},\n day = {15},\n id = {52cf7f05-d950-3f2e-bd4e-9780809b6944},\n created = {2016-04-14T18:02:28.000Z},\n accessed = {2014-09-16},\n file_attached = {true},\n profile_id = {d28af011-5164-3af4-8522-822cff4de1eb},\n group_id = {e39cd875-9ef8-3fee-ad92-c9d084a63048},\n last_modified = {2017-10-14T23:14:07.736Z},\n read = {true},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Antos2014},\n folder_uuids = {dc34bb65-a794-457d-b88a-9687552166f4},\n private_publication = {false},\n abstract = {For rehabilitation and diagnoses, an understanding of patient activities and movements is important. Modern smartphones have built in accelerometers which promise to enable quantifying minute-by-minute what patients do (e.g. walk or sit). Such a capability could inform recommendations of physical activities and improve medical diagnostics. However, a major problem is that during everyday life, we carry our phone in different ways, e.g. on our belt, in our pocket, in our hand, or in a bag. The recorded accelerations are not only affected by our activities but also by the phone's location. Here we develop a method to solve this kind of problem, based on the intuition that activities change rarely, and phone locations change even less often. A hidden Markov model (HMM) tracks changes across both activities and locations, enabled by a static support vector machine (SVM) classifier that probabilistically identifies activity-location pairs. We find that this approach improves tracking accuracy on healthy subjects as compared to a static classifier alone. The obtained method can be readily applied to patient populations. Our research enables the use of phones as activity tracking devices, without the need of previous approaches to instruct subjects to always carry the phone in the same location.},\n bibtype = {article},\n author = {Antos, Stephen a and Albert, Mark V and Kording, Konrad P},\n journal = {Journal of neuroscience methods}\n}","author_short":["Antos, S., a.","Albert, M., V.","Kording, K., P."],"urls":{"Paper":"http://bibbase.org/service/mendeley/d28af011-5164-3af4-8522-822cff4de1eb/file/655e5c63-3fe6-53d5-3cc5-1b963ec0a650/2014-Hand_belt_pocket_or_bag_Practical_activity_tracking_with_mobile_phones..pdf.pdf","Website":"http://www.ncbi.nlm.nih.gov/pubmed/24091138"},"bibbaseid":"antos-albert-kording-handbeltpocketorbagpracticalactivitytrackingwithmobilephones-2014","role":"author","keyword":["activity recognition"],"downloads":0},"search_terms":["hand","belt","pocket","bag","practical","activity","tracking","mobile","phones","antos","albert","kording"],"keywords":["activity recognition"],"authorIDs":[]}