Context-aware personal route recognition

O. Mazhelis, I. Zliobaite, M. Pechenizkiy

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

9 Citations (Scopus)

Abstract

Personal route recognition is an important element of intelligent transportation systems. The results may be used for providing personal information about location-specific events, services, emergency or disaster situations, for location-specific advertising and more. Existing real-time route recognition systems often compare the current driving trajectory against the trajectories observed in past and select the most similar route as the most likely. The problem is that such systems are inaccurate in the beginning of a trip, as typically several different routes start at the same departure point (e.g. home). In such situations the beginnings of trajectories overlap and the trajectory alone is insufficient to recognize the route. This drawback limits the utilization of route prediction systems, since accurate predictions are needed as early as possible, not at the end of the trip. To solve this problem we incorporate external contextual information (e.g. time of the day) into route recognition from trajectory. We develop a technique to determine from the historical data how the probability of a route depends on contextual features and adjust (post-correct) the route recognition output accordingly. We evaluate the proposed context-aware route recognition approach using the data on driving behavior of twenty persons residing in Aalborg, Denmark, monitored over two months. The results confirm that utilizing contextual information in the proposed way improves the accuracy of route recognition, especially in cases when the historical routes highly overlap.
Original languageEnglish
Title of host publicationDiscovery Science (14th International Conference, DS 2011, Espoo, Finland, October 5-7, 2011. Proceedings)
EditorsT. Elomaa, J. Hollmén, H. Mannila
Place of PublicationBerlin
PublisherSpringer
Pages221-235
ISBN (Print)978-3-642-24476-6
DOIs
Publication statusPublished - 2011

Publication series

NameLecture Notes in Computer Science
Volume6926
ISSN (Print)0302-9743

Fingerprint

Trajectories
Disasters
Marketing

Cite this

Mazhelis, O., Zliobaite, I., & Pechenizkiy, M. (2011). Context-aware personal route recognition. In T. Elomaa, J. Hollmén, & H. Mannila (Eds.), Discovery Science (14th International Conference, DS 2011, Espoo, Finland, October 5-7, 2011. Proceedings) (pp. 221-235). (Lecture Notes in Computer Science; Vol. 6926). Berlin: Springer. https://doi.org/10.1007/978-3-642-24477-3_19
Mazhelis, O. ; Zliobaite, I. ; Pechenizkiy, M. / Context-aware personal route recognition. Discovery Science (14th International Conference, DS 2011, Espoo, Finland, October 5-7, 2011. Proceedings). editor / T. Elomaa ; J. Hollmén ; H. Mannila. Berlin : Springer, 2011. pp. 221-235 (Lecture Notes in Computer Science).
@inproceedings{bc3bbac2029c499d9ce4d55351d095c8,
title = "Context-aware personal route recognition",
abstract = "Personal route recognition is an important element of intelligent transportation systems. The results may be used for providing personal information about location-specific events, services, emergency or disaster situations, for location-specific advertising and more. Existing real-time route recognition systems often compare the current driving trajectory against the trajectories observed in past and select the most similar route as the most likely. The problem is that such systems are inaccurate in the beginning of a trip, as typically several different routes start at the same departure point (e.g. home). In such situations the beginnings of trajectories overlap and the trajectory alone is insufficient to recognize the route. This drawback limits the utilization of route prediction systems, since accurate predictions are needed as early as possible, not at the end of the trip. To solve this problem we incorporate external contextual information (e.g. time of the day) into route recognition from trajectory. We develop a technique to determine from the historical data how the probability of a route depends on contextual features and adjust (post-correct) the route recognition output accordingly. We evaluate the proposed context-aware route recognition approach using the data on driving behavior of twenty persons residing in Aalborg, Denmark, monitored over two months. The results confirm that utilizing contextual information in the proposed way improves the accuracy of route recognition, especially in cases when the historical routes highly overlap.",
author = "O. Mazhelis and I. Zliobaite and M. Pechenizkiy",
year = "2011",
doi = "10.1007/978-3-642-24477-3_19",
language = "English",
isbn = "978-3-642-24476-6",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "221--235",
editor = "T. Elomaa and J. Hollm{\'e}n and H. Mannila",
booktitle = "Discovery Science (14th International Conference, DS 2011, Espoo, Finland, October 5-7, 2011. Proceedings)",
address = "Germany",

}

Mazhelis, O, Zliobaite, I & Pechenizkiy, M 2011, Context-aware personal route recognition. in T Elomaa, J Hollmén & H Mannila (eds), Discovery Science (14th International Conference, DS 2011, Espoo, Finland, October 5-7, 2011. Proceedings). Lecture Notes in Computer Science, vol. 6926, Springer, Berlin, pp. 221-235. https://doi.org/10.1007/978-3-642-24477-3_19

Context-aware personal route recognition. / Mazhelis, O.; Zliobaite, I.; Pechenizkiy, M.

Discovery Science (14th International Conference, DS 2011, Espoo, Finland, October 5-7, 2011. Proceedings). ed. / T. Elomaa; J. Hollmén; H. Mannila. Berlin : Springer, 2011. p. 221-235 (Lecture Notes in Computer Science; Vol. 6926).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Context-aware personal route recognition

AU - Mazhelis, O.

AU - Zliobaite, I.

AU - Pechenizkiy, M.

PY - 2011

Y1 - 2011

N2 - Personal route recognition is an important element of intelligent transportation systems. The results may be used for providing personal information about location-specific events, services, emergency or disaster situations, for location-specific advertising and more. Existing real-time route recognition systems often compare the current driving trajectory against the trajectories observed in past and select the most similar route as the most likely. The problem is that such systems are inaccurate in the beginning of a trip, as typically several different routes start at the same departure point (e.g. home). In such situations the beginnings of trajectories overlap and the trajectory alone is insufficient to recognize the route. This drawback limits the utilization of route prediction systems, since accurate predictions are needed as early as possible, not at the end of the trip. To solve this problem we incorporate external contextual information (e.g. time of the day) into route recognition from trajectory. We develop a technique to determine from the historical data how the probability of a route depends on contextual features and adjust (post-correct) the route recognition output accordingly. We evaluate the proposed context-aware route recognition approach using the data on driving behavior of twenty persons residing in Aalborg, Denmark, monitored over two months. The results confirm that utilizing contextual information in the proposed way improves the accuracy of route recognition, especially in cases when the historical routes highly overlap.

AB - Personal route recognition is an important element of intelligent transportation systems. The results may be used for providing personal information about location-specific events, services, emergency or disaster situations, for location-specific advertising and more. Existing real-time route recognition systems often compare the current driving trajectory against the trajectories observed in past and select the most similar route as the most likely. The problem is that such systems are inaccurate in the beginning of a trip, as typically several different routes start at the same departure point (e.g. home). In such situations the beginnings of trajectories overlap and the trajectory alone is insufficient to recognize the route. This drawback limits the utilization of route prediction systems, since accurate predictions are needed as early as possible, not at the end of the trip. To solve this problem we incorporate external contextual information (e.g. time of the day) into route recognition from trajectory. We develop a technique to determine from the historical data how the probability of a route depends on contextual features and adjust (post-correct) the route recognition output accordingly. We evaluate the proposed context-aware route recognition approach using the data on driving behavior of twenty persons residing in Aalborg, Denmark, monitored over two months. The results confirm that utilizing contextual information in the proposed way improves the accuracy of route recognition, especially in cases when the historical routes highly overlap.

U2 - 10.1007/978-3-642-24477-3_19

DO - 10.1007/978-3-642-24477-3_19

M3 - Conference contribution

SN - 978-3-642-24476-6

T3 - Lecture Notes in Computer Science

SP - 221

EP - 235

BT - Discovery Science (14th International Conference, DS 2011, Espoo, Finland, October 5-7, 2011. Proceedings)

A2 - Elomaa, T.

A2 - Hollmén, J.

A2 - Mannila, H.

PB - Springer

CY - Berlin

ER -

Mazhelis O, Zliobaite I, Pechenizkiy M. Context-aware personal route recognition. In Elomaa T, Hollmén J, Mannila H, editors, Discovery Science (14th International Conference, DS 2011, Espoo, Finland, October 5-7, 2011. Proceedings). Berlin: Springer. 2011. p. 221-235. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-642-24477-3_19