Anomaly Sign Detection for Automatic Ticket Gates by the Histogram Limitation Method

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Oct 8, 2024
Ken Ueno Shigeru Maya Kiyoku Endo

Abstract

It is crucial to appropriately maintain automatic ticket gates (ATGs) to keep transportation operating smoothly in urban areas. Although the average failure rate of new ATGs is extremely low, continuous operation for many years might lead to unstable performance due to deterioration, and the need for periodic maintenance to avoid fatal faults might halt operations for extended periods. To detect anomalies at an early stage, “anomaly signs” can be utilized to flag ATGs for maintenance by service engineers before anomalies occur. In addition, to minimize the cost of ATG monitoring, the necessary computing resources should be minimized, which means using only light-weight statistical methods rather than deep learning or machine learning. In this paper, we focus on the automatic separation modules inside ATGs that separate multiple tickets by complicated mechatronic controls because this module is the major cause of maintenance calls from station attendants. We propose a simple anomaly sign detection, called the histogram limitation method (HLM). We evaluated the anomaly sign scores over time with maintenance timing and compared them with the conventional fast unsupervised anomaly detection method, Histogram-Based Outlier Score (HBOS) widely used in various domains. The experimental results using real field ATG monitoring data show that HLM successfully detected anomaly signs before a maintenance call was necessary, which is better performance compared with HBOS. Despite being a simple modification based on HBOS, HLM also provides anomaly sign scores that agree adequately with assessments by maintenance service engineers.

Abstract 52 | PDF Downloads 21

##plugins.themes.bootstrap3.article.details##

Keywords

Anomaly Sign Detection, histogram, mechatronics, automatic ticket gates, fare collection system, railway

References
Aguilera-Martos, I., Garcia-Barzana, M., Garcia-Gil, D., Carrasco, J., Lopez, D., Luengo, J., & Herrera, F. (2023). Multi-step histogram based outlier scores for unsupervised anomaly detection: ArcelorMittal engineering dataset case of study. Neurocomputing, vol. 544, pp. 1-32. doi:10.1016/j.neucom.2023.126228
Barbariol, T., Feltresi, E., & Suusto, G. A. (2019). Machine learning approaches for anomaly detection in multiphase flow meters. IFAC-PapersOnLine, vol. 52, Issue 11, pp.212-217. doi:10.1016/j.ifacol.2019.09.143
Braei, M., & Wagner I. S. (2020). Anomaly detection in univeriate time-series: a survey on the state-of-the-art. arXiv. doi:10.48550/arXiv.2004.00433
Carrasco, J., Lopez, D., Aguilera-Martos, I., Garcia-Gil, D., Markova I., Garcia-Barzana, M., Arias-Rodil M., Luengo, J., & Herrera, F. (2021). Anomaly detection in predictive maintenance: A new evaluation framework for temporal unsupervised anomaly detection algorithms. Neurocomputing, Vol. 462, pp.440-452. doi:10.1016/j.neucom.2021.07.095
Goldstein, M., & Dengel, A. (2012). Histogram-based Outlier Score (HBOS): A fast unsupervised anomaly detection algorithm. Proceedings of the German Conference on Artificial Intelligence Poster and Demo Track (KI) (pp.59-63), September 24, Saarbrücke, Germany.
Gurung, R. B, Lindgren, T., & Boström, H. (2017). Predicting NOx sensor failure in heavy duty trucks using histogram-based random forests. International Journal of Prognostics and Health Management, Vol. 8 No. 1. doi:10.36001/ijphm.2017.v8i1.2535
Hirata, T., Hachiya, Y., & Suzuki, N. (2021). Anomaly-sign detection techniques for steel manufacturing facilities utilizing data science. JFE TECHNICAL REPORT, No. 26, pp.15-20.
Maya, S., Ueno, & Nishikawa T. (2019). dLSTM: a new approach for anomaly detection using deep learning with delayed prediction. International Journal of Data Science and Analytics, Vol. 8, pp.137-164. doi:10.1007/s41060-019-00186-0
Naito, S., Taguchi, Y., Kato, Y., Nakata, K., Miyake R., Nagura, I., Tominaga, S., & Aoki, T. (2021). Anomaly sign detection by monitoring thousands of process values using a two-stage autoencoder. Mechanical Engineering Journal, Vol. 8, Issue 4, pp.20-00534. doi:10.1299/mej.20-00534
Shimamura, N., Inuiguchi, M., Seki, H., Inoue, M., Takagi, S., & Kishine, D. (2019). If-then rule induction from historical data about automatic ticket gate machines. Proceedings on Fuzzy System Symposium 2019. August 29-31, Osaka, Japan. doi:10.14864/fss.35.0_772
Ueno, K., Ishikawa, M., Kobayashi, Y., Sunaoshi, T., & Endo, K. (2023). Failure sign detection by state path analysis for fare collection system - evaluation by sequential pattern mining with mechatronics knowledge -, IEICE Technical Report, Vol.122, No. 420, R2022-50, pp. 13-18.
Xie, Z., Zhu, J., Wang, F., Li, W., & Wang, T. (2020). Long short-term memory based anomaly detection: A case study of China railway passenger ticketing system. IET Intelligent Transportation Systems, vol. 15, Issue 1, pp. 98-106. doi:10.1049/itr2.12007
Yokoyama, R., Kono, R., Matsuda, A., & Shiomi, Y. (2023). Predictive maintenance for station equipment and applications for the space field. Proceedings of the 4th Asia Pacific Conference of the Prognostics and Health Management. September 11-14, Tokyo, Japan. doi: 10.36001/phmap.2023.v4i1.3675
Section
Technical Papers