Detection and Enrichment Service of Road Events Based on Heterogeneous Data Fusion for VANETs

• Paulo H. L. Rettore Universidade Federal de Minas Gerais
• Ígor Araújo Universidade Federal de Minas Gerais
• Guilherme Maia Universidade Federal de Minas Gerais
• Leandro A. Villas Universidade de Campinas
• Antonio A. F. Loureiro Universidade Federal de Minas Gerais

DOI: https://doi.org/10.5753/sbrc.2019.7372

Abstract

This paper introduces T-Incident, a robust, low-cost architecture for detecting and enriching road events based on heterogeneous data fusion. A spatiotemporal model for merging incident, non-incident and social media data has been developed. In addition, this latter data source was filtered using natural language processing methods for pattern detection capable of describing the event and its vicinity. A learning-based model was also developed to identify these patterns and detect the types of events. The methodology results showed the best parameters for the T-Incident approach, providing an accurate incident detection and description service above 90% for the F1 score, Recall and Precision metrics.

Keywords: VANET, Social Media Data,Participatory Sensors, Event Detection, Data Fusion

References

Bazzan, A. L. and Klügl, F. (2013). Introduction to intelligent systems in traffic and transportation. Morgan & Claypool Publishers.

Hsu, C.-W., Chang, C.-C., Lin, C.-J., et al. (2003). A practical guide to support vector classification.

Jockers, M. (2017). syuzhet: Extracts sentiment and sentiment-derived plot arcs from text.

Khaleghi, B., Khamis, A., Karray, F., and Razavi, S. (2013a). Multisensor data fusion: A review of the state-of-the-art. Information Fusion.

Khaleghi, B., Khamis, A., Karray, F. O., and Razavi, S. N. (2013b). Multisensor data fusion: A review of the state-of-the-art. Information Fusion, 14(1):28–44.

Kotthoff, L., Thornton, C., and Hutter, F. (2017). User guide for auto-weka version 2.6. Dept. Comput. Sci., Univ. British Columbia, BETA lab, Vancouver, BC, Canada, Tech. Rep, 2.

Nguyen, H., Liu, W., Rivera, P., and Chen, F. (2016). Trafficwatch: Real-time traffic incident detection and monitoring using social media. In PAKDD, pages 540–551. Springer.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011).
Scikit-learn: Machine learning in Python. Journal of MLR, 12:2825–2830.

Pereira, F. C., Rodrigues, F., and Ben-Akiva, M. (2013). Text analysis in incident duration prediction. Transportation Research Part C: Emerging Technologies, 37:177–192.

Rettore, P. H., Santos, B. P., Campolina, A. B., Villas, L. A., and Loureiro, A. A. (2016). Towards Intra- Vehicular Sensor Data Fusion. 19th International Conference on ITS.

Santos, B. P., Rettore, P. H., Ramos, H. S., Vieira, L. F. M., and A.F. Loureiro, A. (2018). Enriching traffic information with a spatiotemporal model based on social media. In ISCC, Natal, Brazil.

Xu, S., Li, S., and Wen, R. (2018). Sensing and detecting traffic events using geosocial media data: A review. Computers, Environment and Urban Systems, (June).

Yazici, M. A., Mudigonda, S., and Kamga, C. (2017). Incident detection through twitter: Organization versus personal accounts. TRR: Journal of the TRB, (2643):121–128.

Zhang, Z., He, Q., Gao, J., and Ni, M. (2018). A deep learning approach for detecting traffic accidents from social media data. Transportation research part C: emerging technologies, 86:580–596.