Unsupervised Classification of Routes and Plates from the Trap-2017 Dataset
This paper describes the efforts, pitfalls, and successes of applying unsupervised classification techniques to analyze the Trap-2017 dataset. Guided by the informative perspective on the nature of the dataset obtained through a set of specifically-written perl/bash scripts, we devised an automated clustering tool implemented in python upon openly-available scientific libraries. By applying our tool on the original raw data it is possibile to infer a set of trending behaviors for vehicles travelling over a route, yielding an instrument to classify both routes and plates. Our results show that addressing the main goal of the Trap-2017 initiative (“to identify itineraries that could imply a criminal intent”) is feasible even in the presence of an unlabelled and noisy dataset, provided that the unique characteristics of the problem are carefully considered. Albeit several optimizations for the tool are still under investigation, we believe that it may already pave the way to further research on the extraction of high-level travelling behaviors from gates transit records.
- 2.Koller, D., J. Weber, T. Huang, J. Malik, G. Ogasawara, B. Rao, and S. Russell. 1994. Towards robust automatic traffic scene analysis in real-time. Proceedings of the 33rd IEEE Conference on Decision and Control, 3776–3781.Google Scholar
- 7.Tanvi Jindal, Prasanna Giridhar, Lu An Tang, Jun Li, and Jiawei Han. 2013. Spatiotemporal periodical pattern mining in traffic data.Google Scholar
- 9.Uday Kiran, R., Haichuan Shang, Masashi Toyoda, and Masaru Kitsuregawa. 2017. Discovering partial periodic itemsets in temporal databases. Proceedings of the 29th International Conference on Scientific and Statistical Database Management,SSDBM ’17, 30:1–30:6. New York: ACM.Google Scholar
- 11.Emilian Necula. Analyzing Traffic Patterns on Street Segments Based on GPS Data Using R. Transportation Research Procedia, 10:276–285. 2015. 18th Euro Working Group on Transportation, EWGT 2015, 14–16 July 2015. The Netherlands: Delft.Google Scholar
- 12.Grossi, Valerio, Anna Monreale, Mirco Nanni, Dino Pedreschi, Franco Turini, et al. 2015. Clustering formulation using constraint optimization. Selected Papers of SEFM 2015 Workshop on Software Engineering and Formal Methods, 93–107. New York: Springer.Google Scholar