A Novel Parameter Reduction Method for Simplifying Improved RC-IDeepRT

T Rajalakshmi; S Sathappan

doi:10.17485/IJST/v14i1.1311

Article

A Novel Parameter Reduction Method for Simplifying Improved RC-IDeepRT

VIEWS 1129
PDF 251

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v14i1.1311

Year: 2021, Volume: 14, Issue: 1, Pages: 22-32

Original Article

A Novel Parameter Reduction Method for Simplifying Improved RC-IDeepRT

T Rajalakshmi^1*, S Sathappan²

¹Research scholar, Department of Computer Science, Erode Arts & Science College, Erode, Tamil Nadu, India
²Associate Professor, Department of Computer Science, Erode Arts & Science College, Erode,Tamil Nadu, India

*Corresponding Author
Email: [email protected]

Received Date:26 September 2020, Accepted Date:20 December 2020, Published Date:11 January 2021

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Objectives: To decrease the model parameters in Reinforcement learning with Compressed Improved DeepRT (RC-IDeepRT) for Cyber-Physical System (CPS) data analysis, a method is proposed in this study. Methods: A parameter reduction method is proposed to decrease the model parameter by combining pruning and factorization. The pruning may not save the memory usage in traditional computers unless sparse matrices are supported and explicitly used. However, it directly reduces the usage of synapses in neuromorphic architecture. This method minimizes the total number of required neurons and synapses given a trained model. Findings: The integration of factorization and pruning allows creating sparsely connected reinforcement learning with deep learning network from a given trained network. The dangling connections in the network are determined and the remaining connections of the dangling neurons are further pruned. The pruned network is cost-effective and it classifies the CPS data effectively. Novelty: This proposed method tries to minimize the number of parameters in RC-IDeepRT. The number of parameters becomes a good surrogate metric assuming the deep learning architecture accommodates sparse networks effectively. The reduced model parameters are used for CPS data classification.

Keywords: Cyber-physical system; deep learning; DeepRT; reinforcement with compressed improved DeepRT; parameter reduction method; pruning; factorization

References

De S, Zhou Y, Abad IL, Moessner K. Cyber–Physical–Social Frameworks for Urban Big Data Systems: A Survey. Applied Sciences. 2017;7:1017. Available from: https://dx.doi.org/10.3390/app7101017
Basarabă L, Pescaru D. Using decision tree for efficient data classification in Cyber-physical systems. IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI). 2011;p. 385–390. Available from: https://doi.org/10.1109/SACI.2011.5873034
Charalamboskonstantinou M, Saqib F, Hu S, Plusquellic J, Y. Cyber-physical systems: A security perspective. In: 20th IEEE European Test Symposium (ETS). (pp. 1-8) 2015.
Kang W, Chung J. DeepRT: predictable deep learning inference for cyber-physical systems. Real-Time Systems. 2019;55(1):106–135. Available from: https://dx.doi.org/10.1007/s11241-018-9314-y
Giaimo F, Andrade H, Berger C. Continuous Experimentation and the Cyber-Physical Systems challenge. An overview in literature and the industrial perspective, arXiv preprint arXiv. 2020. Available from: https://doi.org/10.1016/j.jss.2020.110781
Rajalakshmi T, Sathappan S. Feature Space Selection for Cyber-Physical System Based on Improved Feature Space Partitioning Tree. International Journal of Advanced Science and Technology. 2019;28(17):401–410.
Petarradanliev DC, Roure JRD, Nurse RM, Montalvo S, Cannady O, Santos P, et al. Future developments in standardisation of cyber risk in the Internet of Things (IoT) SN Applied Sciences . 2. Available from: https://doi.org/10.1007/s42452-019-1931-0
Rajalakshmi T, Sathappan S. Hybridized Convolutional Neural Network and Recurrent Neural Network for Classification of Cyber-Physical System Data. In: International Conference on Machine Learning and Data Analytics. Sri Venkateswara University. 2020.
Patan R, Ghantasala GSP, Sekaran R, Gupta D, Ramachandran M. Smart healthcare and quality of service in IoT using grey filter convolutional based cyber physical system. Sustainable Cities and Society. 2020;59. Available from: https://dx.doi.org/10.1016/j.scs.2020.102141
Rajalakshmi T, Sathappan S. Incorporation of Reinforcement Learning and Compression of DeepRT for Accurate and Fast classification of CPS data. Journal of Critical Reviews. 2020;7(3). Available from: https://doi.org/10.31838/jcr.07.03.214
Pasqualetti F, Dorfler F, Bullo F. Attack Detection and Identification in Cyber-Physical Systems. IEEE Transactions on Automatic Control. 2013;58(11):2715–2729. Available from: https://dx.doi.org/10.1109/tac.2013.2266831
Spezzano G, Vinci A. Pattern Detection in Cyber-Physical Systems. Procedia Computer Science. 2015;52:1016–1021. Available from: https://dx.doi.org/10.1016/j.procs.2015.05.096
Ntalampiras S. Automatic identification of integrity attacks in cyber-physical systems. Expert Systems with Applications. 2016;58:164–173. Available from: https://dx.doi.org/10.1016/j.eswa.2016.04.006
Shin J, Youngmibaek Y, YongsoonEun, Son SH. Sang Hyuk Son, Intelligent sensor attack detection and identification for automotive cyber-physical systems. In: IEEE Symposium Series on Computational Intelligence. (pp. 1-8) 2017.
Zhao L, Chen Z, Yang Y. Parameter-Free Incremental Co-Clustering for Multi-Modal Data in Cyber-Physical-Social Systems. IEEE Access. 2017;5:21852–21861. Available from: https://dx.doi.org/10.1109/access.2017.2758798
Yuan X, Sun M, Chen Z, Gao J, Li P. Semantic Clustering-Based Deep Hypergraph Model for Online Reviews Semantic Classification in Cyber-Physical-Social Systems. IEEE Access. 2018;6:17942–17951. Available from: https://dx.doi.org/10.1109/access.2018.2813419
Amuthadevi C, Priya JS, Madhusudhanan B. Validation of multicast routing in cyber physical systems monitoring air quality. Cluster Computing. 2019;22:3917–3923. Available from: https://dx.doi.org/10.1007/s10586-018-2512-5
Ruan J, Jiang H, Li X, Shi Y, Chan FTS, Rao W. A Granular GA-SVM Predictor for Big Data in Agricultural Cyber-Physical Systems. IEEE Transactions on Industrial Informatics. 2019;15(12):6510–6521. Available from: https://dx.doi.org/10.1109/tii.2019.2914158
Arafsha F, Laamarti F, Saddik AE. Cyber-Physical System Framework for Measurement and Analysis of Physical Activities. Electronics. 2019;8(2):248. Available from: https://dx.doi.org/10.3390/electronics8020248
Li P, Niggemann O. A Non-Convex Archetypal Analysis for One-class Classification based Anomaly Detection in Cyber-Physical Systems. IEEE Transactions on Industrial Informatics. 2020. Available from: https://dx.doi.org/10.1109/tii.2020.3009106
Patan R, Ghantasala GSP, Sekaran R, Gupta D, Ramachandran M. Smart healthcare and quality of service in IoT using grey filter convolutional based cyber physical system. Sustainable Cities and Society. 2020;59. Available from: https://dx.doi.org/10.1016/j.scs.2020.102141
Zhang W, Chen X, Liu Y, Xi Q. A Distributed Storage and Computation k-Nearest Neighbor Algorithm Based Cloud-Edge Computing for Cyber-Physical-Social Systems. IEEE Access. 2020;8:50118–50130. Available from: https://dx.doi.org/10.1109/access.2020.2974764
Sajan KS, Bariya M, Sanchitabasak A, Srivastava A, Dubey A, Meier G, et al. Realistic Synchrophasor Data Generation for Anomaly Detection and Event Classification. In: IEEE 8th Workshop on Modeling and Simulation of Cyber-Physical Energy Systems. (pp. 1-6) 2020.

Copyright

© 2021 Rajalakshmi & Sathappan.This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)