sophisticated automatic incident detection (AID) technology plays a key role in contemporary transportation systems. Though many papers were devoted to study incident classification algorithms, few study investigated how to enhance feature representation of incidents to improve AID performance. In this paper, we propose to use an unsupervised feature learning algorithm to generate higher level features to represent incidents. We used real incident data in the experiments and found that effective feature mapping function can be learnt from the data crosses the test sites. With the enhanced features, detection rate (DR), false alarm rate (FAR) and mean time to detect (MTTD) are significantly improved in all of the three representative cases. This approach also provides an alternative way to reduce the amount of labeled data, which is expensive to obtain, required in training better incident classifiers since the feature learning is unsupervised.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    An unsupervised feature learning approach to improve automatic incident detection


    Contributors:
    Ren, Jimmy SJ. (author) / Wang, Wei (author) / Wang, Jiawei (author) / Liao, Stephen (author)


    Publication date :

    2012-09-01


    Size :

    747106 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A Hybrid Approach for Automatic Incident Detection

    Wang, Jiawei / Li, Xin / Liao, Stephen Shaoyi et al. | IEEE | 2013



    Unsupervised Incident Detection Model in Urban and Freeway Networks

    Hernandez-Potiomkin, Yaroslav / Saifuzzaman, Mohammad / Bert, Emmanuel et al. | IEEE | 2018


    Automatic Incident Detection in HERMES

    Morello, E. / Sala, G. / Commission of the European Communities | British Library Conference Proceedings | 1993


    Automatic incident detection for tunnel management

    Brambilla, L. / Lemaire, F. / Versavel, J. | Tema Archive | 1996