Design and Implementation of Intelligent Transportation System using Machine Learning Techniques

Abstract:
Machine learning, a branch of artificial Intelligence, is about the construction and study of systems that can learn from data. There are mainly two machine learning approaches: supervised approach, where pre-dened category labels are assigned to documents based on the likelihood suggested by a training set of labelled patterns; and unsupervised approach, where there is no need for human intervention or labelled patterns [1]. Machine Learning and Intelligence are being applied in multiple ways to address difficult challenges in multiple fields and few of them are listed below [8, 10, 12]. Speech recognition: Currently available commercial systems for speech recognition all use machine learning in one fashion or another to train the system to recognize speech. Computer vision: Many current vision systems, from face recognition systems, to systems that automatically classify microscope images of cells, are developed using machine learning. One massive-scale application of computer vision trained using machine learning is its use for automatic identification of sort letters containing handwritten addresses. Robot control: Machine learning methods have been successfully used in a number of robot systems. For example, several researchers have demonstrated the use of machine learning to acquire control strategies for stable helicopter ight and helicopter aerobatics. Healthcare: Machine Learning provides methods, techniques, and tools that can help solving diagnostic and prognostic problems in a variety of medical domains. It is being used for the analysis of the importance of clinical parameters and of their combinations for prognosis, e.g. prediction of disease progression, for the extraction of medical knowledge for outcomes research, for therapy planning and support, and for overall patient management Transportation: The research, development and design of Intelligent Transportation Systems worldwide relies on efficient machine learning methods that are able to enhance security and safety, increase efficiency, reduce congestion and promote environmental sustainability. In addition, transportation systems are becoming increasingly complex as they are required to deliver mobility to large, diverse and densely populated areas across multiple modes of transportation, e.g. cars, public transport, bicycles, electric cars, etc. Transportation systems able to cope with these challenges and scale will necessarily rely on smart sensors that monitor and act upon stimuli from the environment [2, 3, 4, 5].

Currently, transportation systems are an indispensable part of human activities. As people have become much more dependent on transportation systems in recent years, transportation systems themselves face not only several opportunities but several challenges as follows [8, 9, 10]. Congestion has become an increasingly important issue. Accident risks increase with the expansion of transportation systems. Automated vehicle detection and access control to safety systems for red-light, lane or speed management passing through traffic condition monitoring, incident detection, etc In recent years, many advanced sensor techniques have been adopted to collect real-time trafc information, such as loop detectors, Global Positioning System (GPS) probe vehicles, cameras, cell networks, and magnetic sensors. Machine Learning algorithms are applied to optimize the use of the existing transportation system by analyzing the data that are collected from a large amount of such auxiliary instruments [6,7,10]. Many methods have been proposed by various researchers to improve the efficiency of the existing transportation systems[10] . However, these methods did not answer all the challenges as mentioned earlier Recently Hegyi et.al., presented a fuzzy decision support system that can be used in tra c control centers to provide a limited list of appropriate combinations of tra c control measures for a

given trac situation[12]. However, there is a need for more intelligent transportation methods which can handle both highway traffic data and urban traffic data to cater various challenges [11]. The scope of the proposed work is to design and Implement Intelligent Transportation System using supervised and the unsupervised machine learning algorithms, incorporating the measures of uncertainty for efficient traffic prediction and monitoring. References: 1) Christian S. Jensen, Dan Lin, and Heng Chin Ooi, Continuous Clustering of Moving Objects, IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, VOL. 19, NO. 9, SEPTEMBER 2007. 2) Wu Jun , Zhong Luo, Analysis of Data Mining Algorithms on Image Processing for the Intelligent Traffic System, 2010 International Conference on Computer Application and System Modeling (ICCASM 2010). 3) Wendy Weijermars and Eric van Berkum, Analyzing highway flow patterns using cluster analysis, In Proceedings of the 8th International IEEE Conference on Intelligent Transportation Systems, Vienna, Austria, September 13-16, 2005. 4) Li liu, Mohammed Khalilia, Huachun Tan, Peng Zhuang , Traffic pattern forecasting using time series analysis between spatially adjacent sensor clusters, In Proceedings of the Eighth International Conference on Machine Learning and Cybernetics, Baoding, 12-15 July 2009. 5) Xia Chuang-wen, Huang Zhijun Hu cuiyun, Improved FP-Growth Algorithm for Freeway Surveillance Network Intrusion Detection System. In Proceedings of Second International Conference on Digital Manufacturing & Automation, 2011. 6) M. P. Hunter, S. K. Wu, H. K. Kim, and W. Suh, A probe-vehicle-based evaluation of adaptive trafc signal control, IEEE Trans. Intell. Transp. Syst., vol. 13, no. 2, pp. 704713, Jun. 2012. 7) C. Stauffer and W. E. L. Grimson, Learning patterns of activity using real-time tracking, IEEE Trans. Pattern Anal. Mach. Intell., vol. 22, no. 8, pp. 747757, Aug. 2000. 8) J. W. Hsieh, S. H. Yu, Y. S. Chen, and W. F. Hu, Automatic trafc surveillance system for vehicle tracking and classication, IEEE Trans.Intell. Transp. Syst., vol. 7, no. 2, pp. 175 187, Jun. 2006. 9) Karim, Asim, and Hojjat Adeli. "Incident detection algorithm using wavelet energy representation of traffic patterns." Journal of Transportation Engineering128.3 (2002): 232242. 10) Junping Zhang, Member, IEEE, Fei-Yue Wang, Fellow, IEEE, Kunfeng Wang, Data-Driven Intelligent Transportation Systems: A Survey, IEEE transactions on Intelligent Transportation Systems, vol. 12, no. 4, December 2011 11) Qing-Jie Kong, Member, IEEE, Qiankun Zhao, Chao Wei, and Yuncai Liu, Member, IEEE, Efcient Trafc State Estimation for Large-Scale Urban Road Networks, IEEE Transactions on Intelligent Transportation Systems, vol. 14, no. 1, march 2013 12) J. M. Sussman,Perspectives on Intelligent Transportation Systems (ITS). New York: Springer-Verlag, 2005.