%Aigaion2 BibTeX export from Idiap Publications %Saturday 23 November 2024 12:05:39 AM @INPROCEEDINGS{farrahi:iswc:2008, author = {Farrahi, Katayoun and Gatica-Perez, Daniel}, projects = {Idiap}, title = {Discovering Human Routines from Cell Phone Data with Topic Models}, booktitle = {{IEEE} International Symposium on Wearable Computers ({ISWC})}, year = {2008}, note = {IDIAP-RR 08-32}, crossref = {farrahi:rr08-32}, abstract = {We present a framework to automatically discover people's routines from information extracted by cell phones. The framework is built from a probabilistic topic model learned on novel bag type representations of activity-related cues (location, proximity and their temporal variations over a day) of peoples' daily routines. Using real-life data from the Reality Mining dataset, covering 68 000+ hours of human activities, we can successfully discover location-driven (from cell tower connections) and proximity-driven (from Bluetooth information) routines in an unsupervised manner. The resulting topics meaningfully characterize some of the underlying co-occurrence structure of the activities in the dataset, including ``going to work early/late", ``being home all day", ``working constantly", ``working sporadically" and ``meeting at lunch time".}, pdf = {https://publications.idiap.ch/attachments/papers/2008/farrahi-iswc-2008.pdf}, postscript = {ftp://ftp.idiap.ch/pub/papers/2008/farrahi-iswc-2008.ps.gz}, ipdmembership={vision}, } crossreferenced publications: @TECHREPORT{farrahi:rr08-32, author = {Farrahi, Katayoun and Gatica-Perez, Daniel}, projects = {Idiap}, title = {Discovering Human Routines from Cell Phone Data with Topic Models}, type = {Idiap-RR}, number = {Idiap-RR-32-2008}, year = {2008}, institution = {IDIAP}, abstract = {We present a framework to automatically discover people's routines from information extracted by cell phones. The framework is built from a probabilistic topic model learned on novel bag type representations of activity-related cues (location, proximity and their temporal variations over a day) of peoples' daily routines. Using real-life data from the Reality Mining dataset, covering 68 000+ hours of human activities, we can successfully discover location-driven (from cell tower connections) and proximity-driven (from Bluetooth information) routines in an unsupervised manner. The resulting topics meaningfully characterize some of the underlying co-occurrence structure of the activities in the dataset, including ``going to work early/late", ``being home all day", ``working constantly", ``working sporadically" and ``meeting at lunch time".}, pdf = {https://publications.idiap.ch/attachments/reports/2008/farrahi-idiap-rr-08-32.pdf}, postscript = {ftp://ftp.idiap.ch/pub/reports/2008/farrahi-idiap-rr-08-32.ps.gz}, ipdmembership={vision}, }