Abstract   The  rapid  proliferation  of  Global  Position  Service   (GPS)  devices  and  mounting  number  of  traffic  monit oring  systems employed by municipalities have opened the  door for advanced traffic control and personalized route planning. Most  state of the art traffic management and information  systems focus on data analysis, and very little has been done in the sense  of  prediction.  In  this  article,  we  devise  an  effici ent  system  for  the  prediction  of  peak  traffic  flow  using  machine  learning  techniques. In the proposed system, the traffic flo w of a locality is predicted with the aid of the geospatial data obtained from  aerial  images.  The  proposed  system  comprises  of  two   significant  phases:  Geospatial  data  extraction  from  aerial  images,  and  traffic  flow  prediction  using  See5.0  decision  tree.   Firstly,  geographic  information  essential  for  traf fic  flow  prediction  are  extracted from aerial images like traffic maps, usi ng suitable image processing techniques. Subsequent ly, for a user query, the  trained See5.0 decision tree predicts the traffic s tate of the intended location with relevance to the  date and time specified. The  experimental results portray the effectiveness of t he proposed system in predicting traffic flow.      

References

[1] Australia M., Review of Urban Congestion Trends, Impacts and Solutions, Technical Report, Competition and Regulation Working Group, 2006.

[2] Bazzan A., Wahle J., and Kl gl F., Agents in Traffic Modelling-From Reactive to Social Behaviour, in Proceedings of the 23 rd Annual German Conference on Artificial Intelligence Bonn , Germany, vol. 1701, pp. 303-306, 1999.

[3] Chen Y., Zhang Y., and Hu J., Multi- Dimensional Traffic Flow Time Series Analysis with Self-Organizing Maps, Tsinghua Science and Technology , vol. 13, no. 2, pp. 220-228, 2008.

[4] Chong M., Abraham A., and Paprzycki M., Traffic Accident Data Analysis using Machine Learning Paradigms, Informatica: An International Journal of Computing and Informatics , vol. 29, no. 1, pp. 89-98, 2005.

[5] Dong H., Jia L., Sun X., Li C., and Qin Y., Road Traffic Flow Prediction with a Time- Oriented ARIMA Model, in Proceedings of the 5 th International Joint Conference on INC , Korea, pp. 1649-1652, 2009.

[6] Joksimovic D., Bliemler M., and Bovy P., Optimal Toll Design Problem in Dynamic Traffic Networks with Joint Route and Departure Time Choice, Transportation Research Board of the National Academies , Washington, USA, vol. 1923, pp. 61-72, 2006.

[7] Kaur M., Singh M., Girdhar A., and Sandhu P., Fingerprint Verification System using Minutiae Extraction Technique, in Proceedings of World An Efficient Traffic Forecasting System Based on Spatial Data and Decision Trees 193 Academy of Science, Engineering and Technology , vol. 36, pp. 1-6, 2008.

[8] Kaysi I., Akiva M., and Koutsopoulos H., Integrated Approach to Vehicle Routing and Congestion Predictions for Real-time Driver Guidance , Transportation Research Board, pp. 66-74, 1993.

[9] Kriegel H., Renz M., Schubert M., and Zuefle A., Statistical Density Prediction in Traffic Networks, in Proceedings of the 8 th SIAM Conference on Data Mining , USA, pp. 692-703, 2008.

[10] Kohavi R. and Quinlan R., Decision Tree Discovery, in Handbook of Data Mining and Knowledge Discovery , pp. 267-276, 1999.

[11] Kusrini and Hartati S., Implementation of C4.5 Algorithm to Evaluate the Cancellation Possibility of New Student Applicants at Stmik Amikom Yogyakarta, in Proceedings of the International Conference on Electrical Engineering and Informatics , Indonesia, pp. 17- 19, 2007.

[12] Lam L., Lee S., and Suen C., Thinning Methodologies-A Comprehensive Survey, IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 14, no. 9, pp. 869-885, 1992.

[13] Lavrac N., Jesenovec D., Trdin N., and Kosta N., Mining Spatio-Temporal Data of Traffic Accidents and Spatial Pattern Visualization, Metodolo ki Zvezki , vol. 5, no. 1, pp. 45-63, 2008.

[14] Lee B., Park K., Kang H., Kim H., and Kim C., Adaptive Local Binarization Method for Recognition of Vehicle License Plates, in Proceedings of the 10 th International Workshop on Combinatorial Image Analysis , New Zealand, vol. 3322, pp. 646-655, 2004.

[15] Li D. and Wang S., Concepts, Principles and Applications of Spatial Data Mining and Knowledge Discovery, in Proceedings of ISSTM 2005 , China, pp. 27-29, 2005.

[16] Min W., Wynter L., and Amemiya Y., Road Traffic Prediction with Spatio-Temporal Correlations, IBM Research Report , Thomas J. Watson Research Center, New York, USA, 2007.

[17] Neto M., Jeong Y., Jeong M., and Han L., Online-SVR for Short-term Traffic Flow Prediction under Typical and Atypical Traffic Conditions, Expert Systems with Applications: an International Journal , vol. 36, no. 3, pp. 6164-6173, 2009.

[18] Nguyen M., Shi D., Quek C., and Ng G., Traffic Prediction using Ying-Yang Fuzzy Cerebellar Model Articulation Controller, in Proceedings of the 18 th International Conference on Pattern Recognition , Hong Kong, vol. 3, pp. 258-261, 2006.

[19] Otsu N., A Threshold Selection Method from Gray-Level Histograms, IEEE Transactions on System, Man, Cyber , vol. 9, pp. 62- 66, 1979.

[20] Quinlan J., Improved Use of Continuous Attributes in c4.5, Journal of Artificial Intelligence Research , vol. 4, pp. 77-90, 1996.

[21] Roozenburg A. and Turner S., Accident Prediction Models for Signalised Intersections, available at: https://www.ipenz.org.nz/ipenztg/ papers/2005/03_Roozenburg.pdf, last visited 2004.

[22] Shekhar S., Zhang P., Huang Y., and Vatsavai R., Trends in Spatial Data Mining , MIT Press, pp. 1- 24, 2004.

[23] Sun S., Zhang C., and Zhang Y., Traffic Flow Forecasting using a Spatio-Temporal Bayesian Network Predictor, in Proceedings of the 15 th International Conference , Poland, vol. 3697, pp. 273-278, 2005.

[24] Tan M., Wong S., Xu J., Guan Z., and Zhang P., An Aggregation Approach to Short-Term Traffic Flow Prediction, IEEE Transactions on Intelligent Transportation Systems , vol. 10, no. 1, pp. 60-69, 2009.

[25] Tesema T., Abraham A., and Grosan C., Rule Mining and Classification of Road Traffic Accidents using Adaptive Regression Trees, the International Journal of Simulation: Systems , Science & Technology , vol. 6, no. 10, pp. 80-94, 2005.

[26] Thai R., Fingerprint Image Enhancement and Minutiae Extraction, available at: http://www.peterkovesi.com/studentprojects/ray mondthai/RaymondThai.pdf, last visited 2003.

[27] Wang Y., Tian Y., Tai X., and Shu L., Extraction of Main Urban Roads from High Resolution Satellite Images by Machine Learning, in Proceedings of the 7 th Asian Conference on Computer Vision , India, vol. 3851, pp. 236-245, 2006.

[28] Wikipedia., C4.5 Algorithm, available at: http://en.wikipedia.org/wiki/C4.5_algorithm, last visited 2013.

[29] Wu X., Chuin H., and Lau., Traffic Prediction in Intelligent Vehicle Highway Systems, in Proceedings of International Conference System Science and System Engineering , Beijing, China, pp. 424-429, 1998.

[30] Yang T., Bai P., and Gong Y., Spatial Data Mining Features between General Data Mining, Ettandgrs, in Proceedings of International Workshop on Education Technology and Training & International Workshop on Geoscience and Remote Sensing , Shanghai, vol. 2, pp. 541-544, 2008.

[31] Yin H., Wong S., Xu J., and Wong C., Urban Traffic Flow Prediction using a Fuzzy-Neural Approach, Transportation Research Part C: 194 The Internationa l Arab Journal of Information Technology, Vol. 11, No. 2, March 2014 Emerging Technologies, vol. 10, no. 2, pp. 85-98, 2002.

[32] Zhao L. and Wang F., Short-Term Traffic Flow Prediction based on Ratio-Median Lengths of Intervals Two-Factors High-Order Fuzzy Time Series, in Proceedings of IEEE International Conference on Vehicular Electronics and Safety , Beijing, China, pp. 1-7, 2007.

[33] Zhou H., Mabu S., Wei W., Shimada K., and Hirasawa K., Traffic Flow Prediction with Genetic Network Programming, Journal of Advanced Computational Intelligence and Intelligent Informatics , vol. 13, no. 6, pp. 713- 725, 2009. Kalli Srinivasa Prasad has completed his MSc (Tech), MSc, MS (Software Systems), PGDCS. He is currently pursuing his PhD degree in the field of data mining at Sri Venkateswara University, India. He has published ten research papers in international journals. He has also attend three national conferences. Seelam Ramakrishna is currently working as a professor in the Department of Computer Science, College of Commerce, Management & Computer Sciences in Sri Venkateswara University, India. He has completed his MSc, MPhil, PhD, M.Tech (IT). He is specialized in fluid dynamics an d theoretical computer science. His area of research includes artificial intelligence, data mining and computer networks. He has an experience of 26 years in teaching field. He has published 44 research pap ers in national & international journals. He has also attended 13 national conferences and 3 internationa l conferences. He has guided 17 PhD scholars and 18 MPhil Scholars.