Detecting Suspects from large scale transit records are the ultimate aim of the proposed system. Handling large scale transit records are possible by applying data mining techniques, because, the transit records are too dynamic and frequently increasing. From this dynamic data, a new level of application is developed to detect the suspect/anomaly. This can detect the various anomaly behaviors of passenger data. This helps in various applications like pickpocket suspects, buglers from the large scale transit records. To achieve this, a new technique is proposed. The followings are the contribution of the system. Firstly, a number of important features that may be extracted from transit data records and are potentially useful for distinguishing thieves from regular passengers. In existing, the automatic fare collection.........
Key words: classification, Detecting Suspects, class imbalance, anomaly detection, Multi Model Batch-SVM.
[1]. Yang Zhou , Zhixiang Fang , Qingming Zhan, "Inferring Social Functions Available in the Metro Station Area from Passengers' Staying Activities in Smart Card Data" , International Journal of Geo Information, 2017.
[2]. Yanchi Liu, Chuanren Liu, Nicholas Jing Yuan, "Intelligent bus routing with heterogeneous human mobility patterns", Knowledge and Information Systems, 2017.
[3]. Tu, W.; Cao, J.; Yue, Y.; Shaw, S.-L.; Zhou, M.; Wang, Z.; Chang, X.; Xu, Y.; Li, Q. "Coupling mobile phone and social media data: A new approach to understanding urban functions and diurnal patterns". International. J. Geogr.Information Science, 2017.
[4]. El Mahrsi, M.K.; Côme, E.; Oukhellou, L.; Verleysen, "M. Clustering Smart Card Data for Urban Mobility Analysis. IEEE Trans", Intell. Transp. Syst. 2017.
[5]. Ma, X.; Liu, C.; Wen, H.; Wang, Y.; Wu, Y.J. "Understanding commuting patterns using transit smart card data". J. Transp. Geogr. 2017.