Minimizing user involvement for learning human mobility patterns from location traces

Basma Alharbi, Abdulhakim Qahtan, Xiangliang Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Utilizing trajectories for modeling human mobility often involves extracting descriptive features for each individual, a procedure heavily based on experts' knowledge. In this work, our objective is to minimize human involvement and exploit the power of community in learning 'features' for individuals from their location traces. We propose a probabilistic graphical model that learns distribution of latent concepts, named motifs, from anonymized sequences of user locations. To handle variation in user activity level, our model learns motif distributions from sequence-level location co-occurrence of all users. To handle the big variation in location popularity, our model uses an asymmetric prior conditioned on per-sequence features. We evaluate the new representation in a link prediction task and compare our results to those of baseline approaches.

Original languageEnglish
Title of host publication30th AAAI Conference on Artificial Intelligence, AAAI 2016
PublisherAAAI press
Pages865-871
Number of pages7
ISBN (Electronic)9781577357605
Publication statusPublished - 1 Jan 2016
Externally publishedYes
Event30th AAAI Conference on Artificial Intelligence, AAAI 2016 - Phoenix, United States
Duration: 12 Feb 201617 Feb 2016

Other

Other30th AAAI Conference on Artificial Intelligence, AAAI 2016
CountryUnited States
CityPhoenix
Period12/2/1617/2/16

Fingerprint

Trajectories

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Alharbi, B., Qahtan, A., & Zhang, X. (2016). Minimizing user involvement for learning human mobility patterns from location traces. In 30th AAAI Conference on Artificial Intelligence, AAAI 2016 (pp. 865-871). AAAI press.

Minimizing user involvement for learning human mobility patterns from location traces. / Alharbi, Basma; Qahtan, Abdulhakim; Zhang, Xiangliang.

30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press, 2016. p. 865-871.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Alharbi, B, Qahtan, A & Zhang, X 2016, Minimizing user involvement for learning human mobility patterns from location traces. in 30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press, pp. 865-871, 30th AAAI Conference on Artificial Intelligence, AAAI 2016, Phoenix, United States, 12/2/16.
Alharbi B, Qahtan A, Zhang X. Minimizing user involvement for learning human mobility patterns from location traces. In 30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press. 2016. p. 865-871
Alharbi, Basma ; Qahtan, Abdulhakim ; Zhang, Xiangliang. / Minimizing user involvement for learning human mobility patterns from location traces. 30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press, 2016. pp. 865-871
@inproceedings{9246dd647c544c50bcf81d311224e64c,
title = "Minimizing user involvement for learning human mobility patterns from location traces",
abstract = "Utilizing trajectories for modeling human mobility often involves extracting descriptive features for each individual, a procedure heavily based on experts' knowledge. In this work, our objective is to minimize human involvement and exploit the power of community in learning 'features' for individuals from their location traces. We propose a probabilistic graphical model that learns distribution of latent concepts, named motifs, from anonymized sequences of user locations. To handle variation in user activity level, our model learns motif distributions from sequence-level location co-occurrence of all users. To handle the big variation in location popularity, our model uses an asymmetric prior conditioned on per-sequence features. We evaluate the new representation in a link prediction task and compare our results to those of baseline approaches.",
author = "Basma Alharbi and Abdulhakim Qahtan and Xiangliang Zhang",
year = "2016",
month = "1",
day = "1",
language = "English",
pages = "865--871",
booktitle = "30th AAAI Conference on Artificial Intelligence, AAAI 2016",
publisher = "AAAI press",

}

TY - GEN

T1 - Minimizing user involvement for learning human mobility patterns from location traces

AU - Alharbi, Basma

AU - Qahtan, Abdulhakim

AU - Zhang, Xiangliang

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Utilizing trajectories for modeling human mobility often involves extracting descriptive features for each individual, a procedure heavily based on experts' knowledge. In this work, our objective is to minimize human involvement and exploit the power of community in learning 'features' for individuals from their location traces. We propose a probabilistic graphical model that learns distribution of latent concepts, named motifs, from anonymized sequences of user locations. To handle variation in user activity level, our model learns motif distributions from sequence-level location co-occurrence of all users. To handle the big variation in location popularity, our model uses an asymmetric prior conditioned on per-sequence features. We evaluate the new representation in a link prediction task and compare our results to those of baseline approaches.

AB - Utilizing trajectories for modeling human mobility often involves extracting descriptive features for each individual, a procedure heavily based on experts' knowledge. In this work, our objective is to minimize human involvement and exploit the power of community in learning 'features' for individuals from their location traces. We propose a probabilistic graphical model that learns distribution of latent concepts, named motifs, from anonymized sequences of user locations. To handle variation in user activity level, our model learns motif distributions from sequence-level location co-occurrence of all users. To handle the big variation in location popularity, our model uses an asymmetric prior conditioned on per-sequence features. We evaluate the new representation in a link prediction task and compare our results to those of baseline approaches.

UR - http://www.scopus.com/inward/record.url?scp=85007165315&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85007165315&partnerID=8YFLogxK

M3 - Conference contribution

SP - 865

EP - 871

BT - 30th AAAI Conference on Artificial Intelligence, AAAI 2016

PB - AAAI press

ER -