A Context-aware Collaborative Filtering Approach for Urban Black Holes Detection
L. Jin, Z. Feng, and L. Feng. Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, page 2137--2142. New York, NY, USA, ACM, (2016)
DOI: 10.1145/2983323.2983655
Abstract
Urban black hole, as a traffic anomaly, has caused lots of catastrophic accidents in many big cities nowadays. Traditional methods only depend on the single source data (e.g., taxi trajectories) to design blackhole detection algorithm from one point of view, which is rather incomplete to describe the regional crowd flow. In this paper, we model the urban black holes in each region of New York City (NYC) at different time intervals with a 3-dimensional tensor by fusing cross-domain data sources. Supplementing the missing entries of the tensor through a context-aware tensor decomposition approach, we leverage the knowledge from geographical features, 311 complaint features and human mobility features to recover the blackhole situation throughout NYC. The information can facilitate local residents and officials' decision making. We evaluate our model with five datasets related to NYC, diagnosing the urban black holes that cannot be identified (or earlier than those detected) by a single dataset. Experimental results demonstrate the advantages beyond four baseline methods.
Description
A Context-aware Collaborative Filtering Approach for Urban Black Holes Detection
%0 Conference Paper
%1 Jin:2016:CCF:2983323.2983655
%A Jin, Li
%A Feng, Zhuonan
%A Feng, Ling
%B Proceedings of the 25th ACM International on Conference on Information and Knowledge Management
%C New York, NY, USA
%D 2016
%I ACM
%K colobarative filtering mobility traffic urban
%P 2137--2142
%R 10.1145/2983323.2983655
%T A Context-aware Collaborative Filtering Approach for Urban Black Holes Detection
%U http://doi.acm.org/10.1145/2983323.2983655
%X Urban black hole, as a traffic anomaly, has caused lots of catastrophic accidents in many big cities nowadays. Traditional methods only depend on the single source data (e.g., taxi trajectories) to design blackhole detection algorithm from one point of view, which is rather incomplete to describe the regional crowd flow. In this paper, we model the urban black holes in each region of New York City (NYC) at different time intervals with a 3-dimensional tensor by fusing cross-domain data sources. Supplementing the missing entries of the tensor through a context-aware tensor decomposition approach, we leverage the knowledge from geographical features, 311 complaint features and human mobility features to recover the blackhole situation throughout NYC. The information can facilitate local residents and officials' decision making. We evaluate our model with five datasets related to NYC, diagnosing the urban black holes that cannot be identified (or earlier than those detected) by a single dataset. Experimental results demonstrate the advantages beyond four baseline methods.
%@ 978-1-4503-4073-1
@inproceedings{Jin:2016:CCF:2983323.2983655,
abstract = {Urban black hole, as a traffic anomaly, has caused lots of catastrophic accidents in many big cities nowadays. Traditional methods only depend on the single source data (e.g., taxi trajectories) to design blackhole detection algorithm from one point of view, which is rather incomplete to describe the regional crowd flow. In this paper, we model the urban black holes in each region of New York City (NYC) at different time intervals with a 3-dimensional tensor by fusing cross-domain data sources. Supplementing the missing entries of the tensor through a context-aware tensor decomposition approach, we leverage the knowledge from geographical features, 311 complaint features and human mobility features to recover the blackhole situation throughout NYC. The information can facilitate local residents and officials' decision making. We evaluate our model with five datasets related to NYC, diagnosing the urban black holes that cannot be identified (or earlier than those detected) by a single dataset. Experimental results demonstrate the advantages beyond four baseline methods.},
acmid = {2983655},
added-at = {2016-12-07T15:52:23.000+0100},
address = {New York, NY, USA},
author = {Jin, Li and Feng, Zhuonan and Feng, Ling},
biburl = {https://www.bibsonomy.org/bibtex/2e82deb576b286c6fef52711353290144/ntempelmeier},
booktitle = {Proceedings of the 25th ACM International on Conference on Information and Knowledge Management},
description = {A Context-aware Collaborative Filtering Approach for Urban Black Holes Detection},
doi = {10.1145/2983323.2983655},
interhash = {f471c542395744649da441674ec6cd98},
intrahash = {e82deb576b286c6fef52711353290144},
isbn = {978-1-4503-4073-1},
keywords = {colobarative filtering mobility traffic urban},
location = {Indianapolis, Indiana, USA},
numpages = {6},
pages = {2137--2142},
publisher = {ACM},
series = {CIKM '16},
timestamp = {2016-12-07T15:52:23.000+0100},
title = {A Context-aware Collaborative Filtering Approach for Urban Black Holes Detection},
url = {http://doi.acm.org/10.1145/2983323.2983655},
year = 2016
}