A COMPREHENSIVE REVIEW FOR ARTIFICAL NEURAL NETWORK APPLICATION TO PUBLIC TRANSPORTATION

Year 2017, Volume: 35 Issue: 1, 157 - 179, 01.03.2017

Engin Pekel Selin Soner Kara

Abstract

This paper presents a comprehensive review of research studies related to the application of artificial neural networks (ANNs) to public transportation (PT) since 2000. PT applications with ANNs have a great prominence because it provides an opportunity of prediction, comparison and evaluation in PT. A short introduction for applied studies in public transportation based on NN is included to guide the unfamiliar readers and a detailed review table has been presented in the paper. More than a thousand studies have been viewed, however, 72 studies of PT are related to ANN. It is observed that multi-layer feed forward network with gradient descent training has been commonly used by now. In contrast, the other less known methods are prone to increase. This paper guides future research directions and presents the methods to be exerted in PT for input determination.

Keywords

Artificial neural network, multi-layer perceptron, public transportation, radial basis function.

References

• [1] Alan T. Murray, Rex Davis, Robert J. Stimson and Luis Ferreira. Public Transportation Access. Transportation Research Part D: Transport and Environment 1998; 3(5), 319-328, Doi: 10.1016/S1361-9209(98)00010-8.
• [2] James F. Sallis, Lawrence D. Frank, Brian E. Saelens and M. Katherine Kraft. Active transportation and physical activity: opportunities for collaboration on transportation and public health research. Transportation Research Part A: Policy and Practice 2004; 38(4), 249-268, Doi: 10.1016/j.tra.2003.11.003.
• [3] Anil K. Jain, Jianchang Mao and Mohiuddin K.M. Artificial neural networks: a tutorial. Computer 1996; 29(3), 31-44, Doi: 10.1109/2.485891.
• [4] Colin Fyfe. Artificial Neural Networks. Department of Computing and Information Systems, 1996.
• [5] Mei Chen, Xiaobo Liu, Jingxin Xia and Steven I. Chien. A Dynamic Bus-Arrival Time Prediction Model Based on APC Data. Computer-Aided Civil and Infrastructure Engineering 2004; 19(5), 364-376, Doi: 10.1111/j.1467-8667.2004.00363.x.
• [6] Abbas Khosravi, Ehsan Mazloumi, Saeid Nahavandi, Doug Creighton and J.W.C Van Lint. A genetic algorithm-based method for improving quality of travel time prediction intervals. Transportation Research Part C 2011; 19(6), 1364-1376, Doi: 10.1016/j.trc.2011.04.002.
• [7] B. Gültekin Çetiner, Murat Sari and Oğuz Borat. A Neural Network Based Traffic-Flow Prediction Model. Mathematical and Computational Applications 2010; 15(2), 269-278
• [8] Sudarmanto Budi Nugroho, Akimasa Fujiwara and Junyi Zhang. An empirical analysis of the impact of a bus rapid transit system on the concentration of secondary pollutants in the roadside areas of the TransJakarta corridors. Stochastic Environmental Research and Risk Assessment 2011;25(5), 655-669, Doi: 10.1007/s00477-011-0472-x.
• [9] Fabio Stella, Vittorio Vigano, Davide Bogni and Matteo Benzoni. An Integrated Forecasting and Regularization Framework for Light Rail Transit Systems. Journal of Intelligent Transportation Systems 2006; 10(2), 59-73,Doi: 10.1080/15472450600626240.
• [10] Ehsan Mazloumi, Geoff Rose, Graham Currie and Majid Sarvi. An Integrated Framework to Predict Bus Travel Time and Its Variability Using Traffic Flow Data. Journal of Intelligent Transportation Systems 2011;15(2), 75-90, Doi: 10.1080/15472450.2011.570109.
• [11] J.K.K. Yuen, E.W.M. Lee, S.M. Lo and R.K.K. Yuen. An Intelligence-Based Optimization Model of Passenger Flow in a Transportation Station. IEEE Transactions on Intelligent Transportation Systems 2013; 14(3), 1290-1300, Doi: 10.1109/TITS.2013.2259482.
• [12] Hilmi Berk Celikoglu. Application of radial basis function and generalized regression neural networks in non-linear utility function specification for travel mode choice modeling. Mathematical and Computer Modelling 2006; 44(7-8), 640-658, Doi: 10.1016/j.mcm.2006.02.002.
• [13] Zegeye Kebede Gurmu and Wei (David) Fan. Artificial Neural Network Travel Time Prediction Model for Buses. Journal of Public Transportation 2014; 17(2), 45-65.
• [14] Kelvin Chun Keong Goh, Graham Currie, Majid Sarvi and David Logan. Bus accident analysis of routes with/without bus priority. Accident Analysis and Preventation 2014; 65, 18-27, Doi: 10.1016/j.aap.2013.12.002.
• [15] Bin Yu, William H.K. Lam and Mei Lam Tam. Bus arrival time prediction at bus stop with multiple routes. Transportation Research Part C 2011;19(6), 1157-1170, Doi: 10.1016/j.trc.2011.01.003.
• [16] Ranhee Jeong and Laurance R. Rilett. Bus Arrival Time Prediction Using Artificial Neural Network Model. IEEE Intelligent Transportation Systems Conference 2004;988-993, Washington, USA, Doi: 10.1109/ITSC.2004.1399041.
• [17] Lei Wang, Zhongyi Zuo and Junhao Fu. Bus Arrival Time Prediction Using RBF Neural Networks Adjusted by Online Data. Procedia-Social and Behavioral Sciences 2014; 138, 67-75, Doi: 10.1016/j.sbspro.2014.07.182.
• [18] Felipe Jimenez, Francisco Serradilla, Alfonso Roman and Roman Jose Eugenio Naranjo. Bus Line Classification Using Neural Networks. Transportation Research Part D 2014;30, 32-37, Doi: 10.1016/j.trd.2014.05.008.
• [19] Akhil Kadiyala, Devinder Kaur and Ashok Kumar. Development of hybrid genetic-algorithm-based neural networks using regression trees for modeling air quality inside a public transportation bus. Journal of Air& Waste Management Association 2013;63(2), 205-218, Doi: 10.1080/10962247.2012.741054.
• [20] Steven I-JyChien, Yuqing Ding and Chienhung Wei. Dynamic Bus Arrival Time Prediction with Artificial Neural Networks. Journal of Transportation Engineering 2002;128(5), 429-439, Doi: 10.1061/(ASCE)0733-947X(2002)128:5(429).
• [21] AAzadeh, M Saberi, R Noorossana, Mohammad Saidi Mehrabad, M Anvari and H Izadbakhsh. Estimating efficient value of controllable variable using an adaptive neural network algorithm: Case of a railway system. Journal of Scientific and Industrial Research 2012;71(1), 45-50.
• [22] H. Berk Çelikoğlu and Murat Akad. Estimation of Public Transport Trips by Feed Forward Back Propagation Artificial Neural Networks; a Case Study for Istanbul. Soft Computing: Methodologies and Applications Advances in Soft Computing 2005; 32, 27-36, Doi: 10.1007/3-540-32400-3_3.
• [23] Yung-Cheng Lai, Yung-An Huang and Hong-Yu. Estimation of Rail Capacity Using Regression and Neural Network. Neural Computing and Applications 2014;25(7-8), 2067-2077, Doi: 10.1007/s00521-014-1694-x.
• [24] Alvaro Costa and Raphael N. Markellos. Evaluating Public Transport Efficiency with Neural Network Models. Transportation Research Part C: Emerging Technologies 1997;5(5), 301-312, Doi: 10.1016/S0968-090X(97)00017-X.
• [25] Ehsan Mazloumi, Sara Moridpour, Graham Currie and Geoff Rose. Exploring the Value of Traffic Flow Data in Bus Travel Time Prediction. Journal of Transportation Engineering 2012;138(4), 436-446, Doi: 10.1061/(ASCE)TE.1943-5436.0000329.
• [26] Juan de Ona and Concepcion Garrido. Extracting the Contribution of Independent Variables in Neural Network Models: a New Approach to Handle Instability. Neural Computing and Applications 2014; 25(3-4), 859-869, Doi: 10.1007/s00521-014-1573-5.
• [27] Teng Jing. Forecasting Railway Network Data Traffic: a Model and a Neural Network Solution Algorithm. 2008 Workshop on Power Electronics and Intelligent Transportation System2-3 August 2008; 203-208, place Guangzhou, Doi: 10.1109/PEITS.2008.23.
• [28] Yu Wei and Mu-Chen Chen. Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks. Transportation Research Part C 2012; 21(1), 148-162, Doi: 10.1016/j.trc.2011.06.009.
• [29] Mei-Quan Xie, Xia-Miao Li, Wen-Liang Zhou and Yan-Bing Fu. Forecasting the Short-Term Passenger Flow on High-Speed Railway with Neural Networks. Computational Intelligence and Neuroscience 2014;2014,Doi: 10.1155/2014/375487.
• [30] Junyan Liu, Honglian Yin, Wangling Qiu and Zhuofu Wang.GA-Hopfield Network for Transportation Problem. Wireless Communications, Networking and Mobile Computing 12-14 October 2008;1-4, place Dalian, Doi: 10.1109/WiCom.2008.1525.
• [31] Aleksandar D. Jovanovic, Dragan S. Pamucar and Snezana Pejcic-Tarle. Green vehicle routing in urban zones- A neuro-fuzzy approach. Expert Systems with Applications 2014;41(7), 3189-3203, Doi: 10.1016/j.eswa.2013.11.015.
• [32] Bin Yu, Zhong-Zhen Yang, Kang Chen and Bo Yu. Hybrid model for prediction of bus arrival times at next station. Journal of Advanced Transportation 2010;44(3), 193-204, Doi: 10.1002/atr.136.
• [33] Dilay Çelebi, Bersam Bolat and Demet Bayraktar. Light Rail Passenger Demand Forecasting by Artificial Neural Networks. Computer & Industrial Engineering year 6-9 July2009; 239-243, place Troyes, Doi: 10.1109/ICCIE.2009.5223851.
• [34] Hilmi Berk Celikoglu. Modeling Public Transport Trips with General Regression Neural Networks; A Case Study for Istanbul Metropolitan Area. Applications of Soft Computing: Advances in Intelligent and Soft Computing 2006;36, 271-280, Doi: 10.1007/978-3-540-36266-1_26.
• 35] Hilmi Berk Celikoglu and Hikmet Kerem Cigizoglu. Modelling public transport trips by radial basis function neural networks. Mathematical and Computer Modelling 2007;45, 480-489, Doi: 10.1016/j.mcm.2006.07.002. [36] Concepcion Garrido, Rocio de Ona and Juan de Ona. Neural networks for analyzing service quality in public transportation. Expert Systems with Applications 2014;41, 6830-6838, Doi: 10.1016/j.eswa.2014.04.045.
• [37] Mustafa Özuysal, Gökmen Tayfur and Serhan Tanyel. Passenger Flows Estimation of Light Rail Transit (LRT) System in Izmir, Turkey Using Multiple Regression and ANN Methods. Promet-Traffic & Transportation 2012; 24(1), 1-14, Doi: 10.7307/ptt.v24i1.264.
• [38] Zhenliang Ma, Jianping Xing, Mahmoud Mesbah and Luis Ferreira. Predicting short-term bus passenger demand using a pattern hybrid approach. Transportation Research Part C 2014; 39, 148-163, Doi: 10.1016/j.trc.2013.12.008.
• [39] Ehsan Mazloumi, Geoff Rose, Graham Currie and Sara Moridpour. Prediction intervals to account for uncertainties in neural network predictions: Methodology and application in bus travel time prediction. Engineering Applications of Artificial Intelligence 2011; 24, 534-542, Doi: 10.1016/j.engappai.2010.11.004.
• [40] Amer Shalaby and Ali Farhan. Prediction Model of Bus Arrival and Departure Times Using AVL and APC data. Journal of Public Transportation 2004; 7(1), 41-61.
• [41] YU-LONG Pei, KAN Zhou and TING Peng. Prediction model of Passenger Waiting Time in High-Speed Rail Hub Based on BP Neural Network. Applied Mechanics and Materials 2013;321-324, 1903-1906, Doi: 10.4028/www.scientific.net/AMM.321-324.1903.
• [42] Jan Peters, Bastian Emig, Marten Jung and Stefan Schmidt. Control and Automation 2005, Prediction of Delays in Public Transportation using Neural Networks. Computer Intelligence for Modelling28-30 November 2005;2, 92-97, place Vienna, Doi: 10.1109/CIMCA.2005.1631451.
• [43] Hilmi Berk Celikoglu and Hikmet Kerem Cigizoglu. Public transportation trip flow modeling with generalized regression neural networks. Advances in Engineering Software 2007;38, 71-79, Doi: 10.1016/j.advengsoft.2006.08.003.
• [44] Hilmi Berk Celikoglu. Radial Basis Function Neural Network Approach to Estimate Public Transport Trips in Istanbul. Soft Computing as Transdisciplinary Science and Technology Advances in Soft Computing 2005;29, 31-40, Doi: 10.1007/3-540-32391-0_11.
• [45] Yongjie Lin, Xianfeng Yang, Nan Zou and Lei Jia. Real-Time Bus Arrival Time Prediction: Case Study for Jinan, China. Journal of Transportation Engineering 2013;139(11), 1133-1140, Doi: 10.1061/(ASCE)TE.1943-5436.0000589.
• [46] HU Jian-ming, SONG Jing-yan, ZHANG Yi and YANG Zhao-sheng. Study on Automatic Creating Method of Public Transportation Dispatching From Based on BP Neural Network. The IEEE 5th International Conference on Intelligent Transportation Systems3-6 September 2002; 863-867, place Singapore, Doi: 10.1109/ITSC.2002.1041333.
• [47] Guojiang Shen and Xiangjie Kong. Study on Road Network Traffic Coordination Control Technique with Bus Priority. IEEE Transactions on Systems, man, and Cybernetics-part c: applications and reviews 2009;39(3), 343-351, Doi: 10.1109/TSMCC.2008.2005842.
• [48] Sheng-Tzong Cheng, Jian-pan Li, Gwo-Jiun Horng and Kuo-Chuan Wang. The Adaptive Road Routing Recommendation for Traffic Congestion Avoidance in Smart City. Wireless Personal Communications 2014;77(1), 225-246, Doi: 10.1007/s11277-013-1502-4.
• [49] Yong LIAO and Tao Wu. The Analysis of Demand Characteristics of Passenger Transportation Based on BP Neural Network. Applied Mechanics and Materials2013;409-410, 1292-1295, Doi: 10.4028/www.scientific.net/AMM.409-410.1292.
• [50] Mei Chen, Jason Yaw, Steven I. Chien and Xiaobo Liu. Using Automatic Passenger Counter Data in Bus Arrival Time Prediction. Journals of Advanced Transportation 2007;41(3), 267-283, Doi: 10.1002/atr.5670410304.
• [51] Wei Guan, Jinsheng Shen and Wanping Wang. Using S-ANN Method to Forecast the Ridership of Beijing Public Transportation. International Conference on Traffic and Transportation Studies (ICTTS)23-25 July 2002; 877-882, place Guilin China, Doi: 10.1061/40630(255)122.
• [52] Daniel Graupe. Principles of Artificial Neural Networks. Advanced Series in Circuits and Systems Vol. 6, 2rd Edt. Chicago, USA. Word Scientific Publishing Co. Pte. Ltd (Singapore), 1995.
• [53] Mark J. L. Orr. Introduction to Radial Basis Function Networks. Centre for Cognitive Science, 1996.
• [54] Simon Haykin. Signal Processing, Kalman Filtering and Neural Networks, a Wiley-Interscience Publication, John Wiley & sons inc., 2001.
• [55] Michael R. Chernick. Wiley Series in Probability and Statistics, Bootstrap Methods: A Guide for Practitioners and Researcher, Second Edt., year 30 April 2007, John Wiley & SONS INC., Doi: 10.1002/9780470192573.
• [56] Martin Riedmiller and Heinrich Braun. A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm. IEEE International Conference on Neural Networks28 March-01 April 1993; 1, 586-59, place San Francisco, Doi: 10.1109/ICNN.1993.298623.
• [57] Asif Ullah Khan, T.K. Bandopadhyaya and Sudhir Sharma. Genetic Algorithm Based Backpropagation Neural Network Performs Better than Backpropagation Neural Network in Stock Rates Prediction. International Journal of Computer Science and Network Security 2008;8(7), 162-166
• [58] Xin Yao. Evolving artificial neural network. Proceedings of the IEEE 1999; 87(9), 1423-1447, Doi: 10.1109/5.784219.
• [59] Vojislav Kecman. Neural Networks and Fuzzy Logic Models. Learning and Soft Computing: Support Vector Machines. 1st edition, The MIT Press, 2001.
• [60] Jyh-Shing Roger Jang.ANFIS: Adaptive-Network-Based Fuzzy Inference System. IEEE Transactions on Systems, Man, and Ceybernetics 1993; 23(3), Doi: 10.1109/21.256541.
• [61] Ting Liu, Andrew W. Moore and Alexander Gray. New Algorithms for Efficient High-Dimensional Nonparametric Classification. The Journal of Machine Learning Research 2006,7, 1135-1158, 2006.
• [62] Nader Salari, Shamarina Shohaimi, Farid Najafi, Meenakshii Nallappan and Isthrinayagy Karishnarajah. A Novel Hybrid Classification Model of Genetic Algorithms, Modified k-Nearest Neigbor and Developed Backpropagation Neural Network. Plus One 2014;9(11), Doi: 10.1371/journal.pone.0112987.
• [63] Victoria J. Hodge, Rajesh Krishnan, Jim Austin, John Polak and Tom Jackson. Short-term prediction of traffic flow using a binary neural network. Neural Computing and Applications 2014;25(7-8), 1639-1655, Doi: 10.1007/s00521-014-1646-5.
• [64] Russell Reed. Pruning Algorithms-A Survey. IEEE Transactions on Neural Networks 1993;4(5), 740-747, Doi: 10.1109/72.248452.
• [65] Visakan Kadirkamanathan and Mahesan Niranjan. A Function Estimation Approach to Sequential Learning with Neural Networks. Neural Computation 1993;5(6), 954-975, Doi: 10.1162/neco.1993.5.6.954.
• [66] Chen, Mei, Xiaobo Liu, and Jingxin Xia. “Dynamic prediction method with schedule recovery impact for bus arrival time.” Transportation Research Record: Journal of the Transportation Research Board 1923 (2005): 208-217.
• [67] Padmanaban, R. P., Lelitha Vanajakshi, and Shankar C. Subramanian. “Estimation of bus travel time incorporating dwell time for APTS applications.” Intelligent Vehicles Symposium, 2009 IEEE. IEEE, 2009.
• [68] Vanajakshi, Lelitha, Shankar C. Subramanian, and R. Sivanandan. “Travel time prediction under heterogeneous traffic conditions using global positioning system data from buses.” IET intelligent transport systems 3.1(2009):1-9.
• [69] Bhatta, B. P., & Larsen, O. I. Errors in variables in multinomial choice modeling: A simulation study applied to a multinomial logit model of travel mode choice. Transport policy (2011); 18(2), 326-335.
• [70] Ap. Sorratini, J., Liu, R., & Sinha, S. Assessing bus transport reliability using micro simulation. Transportation Planning and Technology 2008; 31(3), 303-324.
• [71] Bilişik, Ö. N., Erdoğan, M., Kaya, İ., & Baraçlı, H. (2013). A hybrid fuzzy methodology to evaluate customer satisfaction in a public transportation system for Istanbul. Total Quality Management & Business Excellence, 24(9-10), 1141-1159.
• [72] Cascetta, E., & Cartenì, A. (2014). A quality-based approach to public transportation planning: theory and a case study. International Journal of Sustainable Transportation, 8(1), 84-106.
• [73] Nuzzolo, A., & Comi, A. (2016). Advanced public transport and intelligent transport systems: new modelling challenges. Transportmetrica A: Transport Science, 1-26.
• [74] Moreira-Matias, L., Cats, O., Gama, J., Mendes-Moreira, J., & de Sousa, J. F. (2016). An online learning approach to eliminate Bus Bunching in real-time. Applied Soft Computing, 47, 460-482.
• [75] Freitas, A. L. P. (2013). Assessing the quality of intercity road transportation of passengers: An exploratory study in Brazil. Transportation Research Part A: Policy and Practice, 49, 379-392.
• [76] Islam, M. R., Hadiuzzaman, M., Banik, R., Hasnat, M. M., Musabbir, S. R., & Hossain, S. (2016). Bus service quality prediction and attribute ranking: a neural network approach. Public Transport, 8(2), 295-313.
• [77] Shen, J., & Li, W. (2014). Discrete Hopfield Neural Networks for Evaluating Service Quality of Public Transit. International Journal of Multimedia and Ubiquitous Engineering, 9(2), 331-340.
• [78] León, M., Mkrtchyan, L., Depaire, B., Ruan, D., & Vanhoof, K. (2014). Learning and clustering of fuzzy cognitive maps for travel behaviour analysis. Knowledge and information systems, 39(2), 435-462.
• [79] Liang, V. C., Ma, R. T., Ng, W. S., Wang, L., Winslett, M., Wu, H., ... & Zhang, Z. (2016, May). Mercury: Metro density prediction with recurrent neural network on streaming CDR data. In Data Engineering (ICDE), 2016 IEEE 32nd International Conference on (pp. 1374-1377). IEEE.
• [80] Dong, J., Zou, L., & Zhang, Y. (2013, June). Mixed model for prediction of bus arrival times. In 2013 IEEE Congress on Evolutionary Computation (pp. 2918-2923). IEEE.
• [81] Kadiyala, A., & Kumar, A. (2016). Univariate time series based radial basis function neural network modeling of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy, 35(2), 320-324.
• [82] Dadula, C. P., & Dadios, E. P. (2015, December). Neural network classification for detecting abnormal events in a public transport vehicle. In Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM), 2015 International Conference on(pp. 1-6). IEEE.
• [83] Segundo, F. R., e Silva, E. S., & Farines, J. M. (2014, October). Predicting journeys for DTN routing in a public transportation system. In 2014 IEEE 10th international conference on wireless and mobile computing, networking and communications (WiMob) (pp. 494-499). IEEE.
• [84] Dou, M., He, T., Yin, H., Zhou, X., Chen, Z., & Luo, B. (2015, June). Predicting passengers in public transportation using smart card data. In Australasian Database Conference (pp. 28-40). Springer International Publishing.
• [85] Zhou, C., Dai, P., Wang, F., & Zhang, Z. (2016). Predicting the passenger demand on bus services for mobile users. Pervasive and Mobile Computing, 25, 48-66.
• [86] Omrani, H. (2015). Predicting Travel Mode of Individuals by Machine Learning. Transportation Research Procedia, 10, 840-849.
• [87] Ghanim, M. S., & Abu-Lebdeh, G. (2015). Real-time dynamic transit signal priority optimization for coordinated traffic networks using genetic algorithms and artificial neural networks. Journal of Intelligent Transportation Systems, 19(4), 327-338.
• [88] Düzenli, G. (2015). RFID card security for public transportation applications based on a novel neural network analysis of cardholder behavior characteristics. Turkish Journal of Electrical Engineering & Computer Sciences, 23(4), 1098-1110.
• [89] Deng, L., He, Z., & Zhong, R. (2013, November). The Bus Travel Time Prediction Based on Bayesian Networks. In Information Technology and Applications (ITA), 2013 International Conference on (pp. 282-285). IEEE.
• [90] Wang, S., Zhou, R., & Zhao, L. (2015). Forecasting Beijing Transportation Hub Areas’s Pedestrian Flow Using Modular Neural Network. Discrete Dynamics in Nature and Society, 2015.
• [91] Kadiyala, A., & Kumar, A. (2015). Univariate time series based back propagation neural network modeling of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy, 34(2), 319-323.
• [92] Kadiyala, A., & Kumar, A. (2016). Univariate time series based radial basis function neural network modeling of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy, 35(2), 320-324.
• [93] Tu, J. V. (1996). Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. Journal of clinical epidemiology, 49(11), 1225-1231.