Identification of the accidenttype at critical infrastructure facilities using hidden Markov models.

Keywords: critical infrastructure objects, emergency state, anomalous patterns, probability density function, hidden Markov model, hidden semi-Markov model, mixed Gauss model

Abstract

Modern methods of recognizing anomalous patterns in samples of code sequences for identifying the type of accident at critical infrastructure facilities using hidden Markov models are considered. A complex technique based on the analysis of the probability density function of anomalous patterns, which is based on a hidden Markov and semi-Markov model, is presented. It is indicated that this approach makes it possible to determine the function of the time dependence of the data series; accordingly, the classification is carried out on the basis of sets of anomalous data that do not correspond to the classes of the training sample. On the basis of a mathematical model, it is shown that the presented methodology makes it possible to optimize the efficiency of recognizing anomalous patterns when identifying an emergency state at an infrastructure facility.

References

Ji, Y., &Zheng, S. (2021). Distributed Mode-Dependent Event-Triggered Passive Filtering for Flexible Manipulator with Semi-Markov Parameters. Sensors, 21(6), 2058. https://doi.org/10.3390/s21062058.

Cubero, S. N. (2015). A Mobile Manipulator Arm for Assisting the Frail Elderly and Infirm. Machine Vision and Mechatronics in Practice, 135–147. https://doi.org/10.1007/978-3-662-45514-2_12.

Siddique, M.N., Hossain, M.A., Alam, M.S., &Tokhi, M.O. (2007). Hidden Markov Model based Fuzzy Controller for Flexible-link Manipulator. Advances in Climbing and Walking Robots. https://doi.org/10.1142/9789812770189_0074.

Putra, P. U., Shima, K., &Shimatani, K. (2018). Markerless Human Activity Recognition Method Based on Deep Neural Network Model Using Multiple Cameras. 2018 5th International Conference on Control, Decision and Information Technologies (CoDIT). https://doi.org/10.1109/codit.2018.8394780.

Luísa Gomes, A., Paixão, V., &Gamboa, H. (2015). Human Activity Recognition Based on Novel Accelerometry Features and Hidden Markov Models Application. Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing. https://doi.org/10.5220/0005215800760085.

Uddin, Z., & Kim, T.S. (2011). Continuous Hidden Markov Models for Depth Map-Based Human Activity Recognition. Hidden Markov Models, Theory and Applications. https://doi.org/10.5772/14993.

Tao Xiang,&Shaogang Gong. (2008). Video Behavior Profiling for Anomaly Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(5), 893–908. https://doi.org/10.1109/tpami.2007.70731.

Shima, K., & Aoki, T. (2014). A novel classification method with unlearned-class detection based on a gaussian mixture model. 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC). https://doi.org/10.1109/smc.2014.6974510

Lee, S., Shin, D., & Shin, D. (2019). Sensor-based Abnormal Behavior Detection Using Autoencoder. Proceedings of the Tenth International Symposium on Information and Communication Technology -SoICT 2019. https://doi.org/10.1145/3368926.3369661

Bae, J., &Tomizuka, M. (2010). Gait Phase Analysis based on a Hidden Markov Model. IFAC Proceedings Volumes, 43(18), 746–751. https://doi.org/10.3182/20100913-3-us-2015.00014.

Mukaeda, T., &Shima, K. (2017). A novel hidden Markov model-based pattern discrimination method with the anomaly detection for EMG signals. 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). https://doi.org/10.1109/embc.2017.8036975.

Shun-Zheng Yu, & Kobayashi, H. (2006). Practical implementation of an efficient forward-backward algorithm for an explicit-duration hidden Markov model. IEEE Transactions on Signal Processing, 54(5), 1947–1951. https://doi.org/10.1109/tsp.2006.872540

Mukaeda, T., Shima, K., Miyajima, S., Hashimoto, Y., Tanaka, T., Tani, N., & Izumi, H. (2020). Development of an anomaly detection method with a novel hidden semi-Markov model incorporating unlearned states. 2020 IEEE/SICE International Symposium on System Integration (SII). https://doi.org/10.1109/sii46433.2020.9026303.

Luati, A., &Novelli, M. (2021). Explicit-duration Hidden Markov Models for quantum state estimation. Computational Statistics & Data Analysis, 158, 107183. https://doi.org/10.1016/j.csda.2021.107183.

Yu, S.-Z. (2016). Conventional HSMMs**To distinguish the conventional HSMMs from HMMs, we will call explicit duration HMM as “explicit duration HSMM,” variable transition HMM as “variable transition HSMM,” and residual time HMM as “residual time HSMM” in the rest of this book. Hidden Semi-Markov Models, 103–120. https://doi.org/10.1016/b978-0-12-802767-7.00005-x.

Gao, J., Teng, D., &Ertin, E. (2018). A Probabilistic Approach for Heart Rate Variability Analysis Using Explicit Duration Hidden Markov Models. 2018 IEEE Statistical Signal Processing Workshop (SSP). https://doi.org/10.1109/ssp.2018.8450781.

Dewar, M., Wiggins, C., & Wood, F. (2012). Inference in Hidden Markov Models with Explicit State Duration Distributions. IEEE Signal Processing Letters, 19(4), 235–238. https://doi.org/10.1109/lsp.2012.2184795.

Abstract views: 0
PDF Downloads: 0
Published
2021-10-28
How to Cite
Labzhynskyi , V. (2021). Identification of the accidenttype at critical infrastructure facilities using hidden Markov models. COMPUTER-INTEGRATED TECHNOLOGIES: EDUCATION, SCIENCE, PRODUCTION, (44), 25-29. https://doi.org/10.36910/6775-2524-0560-2021-44-04