A method for predicting pedestrian movement on the basis of a mixed Markov-chain model (MMM) is proposed. MMM takes into account a pedestrian's personality as an unobservable parameter. It also takes into account the effects of the pedestrian's previous status. A promotional experiment in a major shopping mall demonstrated that the highest prediction accuracy of the MMM method is 74.4\%. In comparison with methods based on a Markov-chain model (MM) and a hidden-Markov model (HMM) (i.e., prediction rates of about 45\% and 2\%, respectively), the proposed MMM-based prediction method is substantially more accurate. This pedestrian-movement prediction based on MMM using tracking data will make it possible to provide so-called ädaptive mobile services" with proactive functions.
%0 Conference Paper
%1 asahara2011pedestrianmovement
%A Asahara, Akinori
%A Maruyama, Kishiko
%A Sato, Akiko
%A Seto, Kouichi
%B International Conference on Advances in Geographic Information Systems (SIGSPATIAL)
%C New York, NY, USA
%D 2011
%I ACM
%K chain diss inthesis markov mixed mixedtrails mobility model movement navigation pedestrian
%P 25--33
%R 10.1145/2093973.2093979
%T Pedestrian-movement Prediction Based on Mixed Markov-chain Model
%U http://doi.acm.org/10.1145/2093973.2093979
%X A method for predicting pedestrian movement on the basis of a mixed Markov-chain model (MMM) is proposed. MMM takes into account a pedestrian's personality as an unobservable parameter. It also takes into account the effects of the pedestrian's previous status. A promotional experiment in a major shopping mall demonstrated that the highest prediction accuracy of the MMM method is 74.4\%. In comparison with methods based on a Markov-chain model (MM) and a hidden-Markov model (HMM) (i.e., prediction rates of about 45\% and 2\%, respectively), the proposed MMM-based prediction method is substantially more accurate. This pedestrian-movement prediction based on MMM using tracking data will make it possible to provide so-called ädaptive mobile services" with proactive functions.
%@ 978-1-4503-1031-4
@inproceedings{asahara2011pedestrianmovement,
abstract = {A method for predicting pedestrian movement on the basis of a mixed Markov-chain model (MMM) is proposed. MMM takes into account a pedestrian's personality as an unobservable parameter. It also takes into account the effects of the pedestrian's previous status. A promotional experiment in a major shopping mall demonstrated that the highest prediction accuracy of the MMM method is 74.4\%. In comparison with methods based on a Markov-chain model (MM) and a hidden-Markov model (HMM) (i.e., prediction rates of about 45\% and 2\%, respectively), the proposed MMM-based prediction method is substantially more accurate. This pedestrian-movement prediction based on MMM using tracking data will make it possible to provide so-called "adaptive mobile services" with proactive functions.},
acmid = {2093979},
added-at = {2016-12-18T12:12:25.000+0100},
address = {New York, NY, USA},
author = {Asahara, Akinori and Maruyama, Kishiko and Sato, Akiko and Seto, Kouichi},
biburl = {https://www.bibsonomy.org/bibtex/2ec1bcaafe56d7066da0d8cfc641bad0f/becker},
booktitle = {International Conference on Advances in Geographic Information Systems (SIGSPATIAL)},
doi = {10.1145/2093973.2093979},
interhash = {58a06d2c349640ceefa838fc2b042331},
intrahash = {ec1bcaafe56d7066da0d8cfc641bad0f},
isbn = {978-1-4503-1031-4},
keywords = {chain diss inthesis markov mixed mixedtrails mobility model movement navigation pedestrian},
location = {Chicago, Illinois},
numpages = {9},
pages = {25--33},
publisher = {ACM},
series = {GIS '11},
timestamp = {2017-12-20T14:06:31.000+0100},
title = {Pedestrian-movement Prediction Based on Mixed Markov-chain Model},
url = {http://doi.acm.org/10.1145/2093973.2093979},
year = 2011
}