000199471 001__ 199471
000199471 005__ 20190331192655.0
000199471 0247_ $$2doi$$a10.1016/j.trc.2014.03.015
000199471 022__ $$a0968-090X
000199471 02470 $$2ISI$$a000339037100010
000199471 037__ $$aARTICLE
000199471 245__ $$aA Bayesian Approach to Detect Pedestrian Destination-Sequences from WiFi Signatures
000199471 260__ $$bElsevier$$c2014$$aOxford
000199471 269__ $$a2014
000199471 300__ $$a25
000199471 336__ $$aJournal Articles
000199471 520__ $$aIn this paper, we propose a methodology to use the communication network infrastructure, in particular WiFi traces, to detect the sequence of activity episodes visited by pedestrians. Due to the poor quality of WiFi localization, a probabilistic method is proposed that infers activity-episode locations based on WiFi traces and calculates the likelihood of observing these traces in the pedestrian network, taking into account prior knowledge. The output of the method consists of candidates of activity-episodes sequences associated with the likelihood to be the true one. The methodology is validated on traces generated by a known sequence of activities, while the performance being evaluated on a set of anonymous users. Results show that it is possible to predict the number of episodes and the activity-episodes locations and durations, by merging information about the activity locations on the map, WiFi measurements and prior information about schedules and the attractivity in pedestrian infrastructure. The ambiguity of each activity episode in the sequence is explicitly measured.
000199471 6531_ $$aNetwork traces
000199471 6531_ $$aActivity choice modeling
000199471 6531_ $$aPedestrians
000199471 6531_ $$aSemantically-enriched routing graph (SERG)
000199471 6531_ $$aPotential attractivity measure
000199471 6531_ $$aActivity-episode sequence
000199471 700__ $$0245395$$g161277$$aDanalet, Antonin
000199471 700__ $$0245136$$g207159$$aFarooq, Bilal
000199471 700__ $$0240563$$g118332$$aBierlaire, Michel
000199471 773__ $$j44$$tTransportation Research Part C: Emerging Technologies$$q146-170
000199471 8564_ $$uhttp://dx.doi.org/10.5281/zenodo.15798$$zResearch data
000199471 8564_ $$uhttp://blogs.epfl.ch/article/43972$$zURL
000199471 8564_ $$uhttp://blogs.epfl.ch/article/41547$$zURL
000199471 8564_ $$uhttp://blogs.epfl.ch/article/41546$$zURL
000199471 8564_ $$uhttp://blogs.epfl.ch/article/40392$$zURL
000199471 8564_ $$uhttps://infoscience.epfl.ch/record/199471/files/A%20Bayesian%20approach%20to%20detect%20pedestrian%20d%20-%20Antonin%20Danalet.mobi$$zPostprint as ebook$$s2757622$$yPostprint as ebook
000199471 8564_ $$uhttps://infoscience.epfl.ch/record/199471/files/DanaletFarooqBierlaire_2014.pdf$$zPostprint$$s8387773$$yPostprint
000199471 8564_ $$uhttps://infoscience.epfl.ch/record/199471/files/Data_2.zip$$zResearch data$$s181533851$$yResearch data
000199471 909C0 $$xU11418$$0252123$$pTRANSP-OR
000199471 909CO $$ooai:infoscience.tind.io:199471$$particle$$pGLOBAL_SET$$pENAC
000199471 917Z8 $$x161277
000199471 917Z8 $$x161277
000199471 917Z8 $$x161277
000199471 917Z8 $$x161277
000199471 917Z8 $$x161277
000199471 917Z8 $$x161277
000199471 917Z8 $$x161277
000199471 917Z8 $$x161277
000199471 917Z8 $$x161277
000199471 937__ $$aEPFL-ARTICLE-199471
000199471 970__ $$aIJ-DanaletFarooqBierlaire_2014/TRANSP-OR
000199471 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000199471 980__ $$aARTICLE