Exploiting Machine Learning for the Identification of Locomotives’ Position in Large Freight Trains

ABSTRACT Accurate identification of locomotives’ position in large freight trains is important due to maintenance and management aspects. Current solutions employ RFIDs, image cameras or GPS, while the first two are expensive, the third is not an off-the-shelf hardware for all locomotives. In this paper we investigate a data driven solution to automatically identify locomotives’ position in large freight trains. We take into account off-the-shelf hardware alone (that gather instant fuel consumption) seeking for a less expensive solution. We evaluate different machine learning approaches and algorithms and different inputs attributes, achieving significant results.

[1]  Abhijit Ghatak,et al.  Machine Learning with R , 2017, Springer Singapore.

[2]  Gavin C. Cawley,et al.  Efficient leave-one-out cross-validation of kernel fisher discriminant classifiers , 2003, Pattern Recognit..

[3]  Luis Pedro Coelho,et al.  Building Machine Learning Systems with Python , 2013 .

[4]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[5]  Xiaorong Gao,et al.  Visual Monitoring-Based Railway Grade Crossing Surveillance System , 2008, 2008 Congress on Image and Signal Processing.

[6]  Ral Garreta,et al.  Learning scikit-learn: Machine Learning in Python , 2013 .

[7]  A. Auler,et al.  Carajás National Forest: Iron Ore Plateaus and Caves in Southeastern Amazon , 2015 .

[8]  Chunsheng Yang,et al.  Learning to predict train wheel failures , 2005, KDD '05.

[9]  Deepak Vohra.  Using PostgreSQL Database , 2016 .

[10]  A. B. M. Shawkat Ali,et al.  Predicting Vertical Acceleration of Railway Wagons Using Regression Algorithms , 2010, IEEE Transactions on Intelligent Transportation Systems.

[11]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[12]  Torsten Braun,et al.  Combining Wireless Sensor Networks and Machine Learning for Flash Flood Nowcasting , 2014, 2014 28th International Conference on Advanced Information Networking and Applications Workshops.

[13]  Yanfeng Ouyang,et al.  Optimal fueling strategies for locomotive fleets in railroad networks , 2010 .

[14]  S.E. Martin.  Overview of the Operation for the Proposed Locomotive Worker Identification with Cameras , 2008, 2008 IEEE Conference on Technologies for Homeland Security.

[15]  Phil Howlett,et al.  Optimal strategies for the control of a train , 1996, Autom..

[16]  Shaozi Li,et al.  The application of UHF RFID technology in mine locomotive positioning system , 2008, 2008 IEEE International Symposium on IT in Medicine and Education.

[17]  Tom Levine.  Working on the Railroad , 2015, IEEE Potentials.

[18]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[19]  Michel Hermelin,et al.  Landscapes and Landforms of Colombia , 2016 .

[20]  Phil G. Howlett,et al.  Local energy minimization in optimal train control , 2009, Autom..

[21]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[22]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[23]  Carajás.  Structural assessment of a RC Bridge over Sororó river along the Carajás railway , 2015 .

[24]  Kristin P. Bennett,et al.  Support vector machines: hype or hallelujah? , 2000, SKDD.

[25]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  Building binary-tree-based multiclass classifiers using separability measures , 2010, Neurocomputing.

[26]  Mohan M. Trivedi,et al.  A General Active-Learning Framework for On-Road Vehicle Recognition and Tracking , 2010, IEEE Transactions on Intelligent Transportation Systems.