A comparative study on machine learning algorithms for green context-aware intelligent transportation systems

In this work, a green adaptive transportation decision system is proposed for choosing the best transportation route calculated for different means of transportation (train, metro and bus) to reach a certain destination at time t. This selection will be based on significant parameters like CO2 emissions of these transport means, travel duration, ticket tariff, waiting connection time to catch such a transport mean, connection time between the different transport means to reach the destination, and comfortability feedback. Q-Learning, a reinforcement learning technique based reward is applied for validating the first phase in this work. The second contribution is to build the prediction of the best transport route by using Support Vector Machine (SVM) learning techniques.

[1]  Vijay K. Madisetti,et al.  Configuration for Predicting Travel-Time Using Wavelet Packets and Support Vector Regression , 2013 .

[2]  Zhao Jin,et al.  Implementing traffic signal optimal control by multiagent reinforcement learning , 2011, Proceedings of 2011 International Conference on Computer Science and Network Technology.

[3]  Yao Chen,et al.  Travel time prediction on urban networks based on combining rough set with support vector machine , 2010, 2010 International Conference on Logistics Systems and Intelligent Management (ICLSIM).

[4]  Daehyon Kim.  Prediction Performance of Support Vector Machines with Fused Data in Road Scene Analysis , 2015 .

[5]  Zhao Jin,et al.  Q-learning based multi-intersection traffic signal control model , 2011, 2011 International Conference on System science, Engineering design and Manufacturing informatization.

[6]  Marti A. Hearst.  Trends & Controversies: Support Vector Machines , 1998, IEEE Intell. Syst..

[7]  Jian Sun,et al.  Dynamic Bus Travel Time Prediction Models on Road with Multiple Bus Routes , 2015, Comput. Intell. Neurosci..

[8]  Hossam Afifi,et al.  Context-aware multi-modal traffic management in ITS: A Q-learning based algorithm , 2015, 2015 International Wireless Communications and Mobile Computing Conference (IWCMC).

[9]  Yong Qin,et al.  A Partial Least Square Based Support Vector Regression Rail Transit Passenger Flow Prediction Method , 2014 .

[10]  Derek Fagan,et al.  Intelligent time of arrival estimation , 2011, 2011 IEEE Forum on Integrated and Sustainable Transportation Systems.

[11]  Baher Abdulhai,et al.  An agent-based learning towards decentralized and coordinated traffic signal control , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[12]  Jan-Ming Ho,et al.  Travel time prediction with support vector regression , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[13]  Kurt Hornik,et al.  Support Vector Machines in R , 2006 .

[14]  Baher Abdulhai,et al.  Multiagent Reinforcement Learning for Integrated Network of Adaptive Traffic Signal Controllers (MARLIN-ATSC): Methodology and Large-Scale Application on Downtown Toronto , 2013, IEEE Transactions on Intelligent Transportation Systems.

[15]  R. Brereton,et al.  Support vector machines for classification and regression. , 2010, The Analyst.

[16]  Baozhen Yao,et al.  A Hybrid Model Based on Support Vector Machine for Bus Travel-Time Prediction , 2015 .