1.3.2 SIR Model (Susceptible-Infected-Recovered)
The outbreak prediction has become highly complicated for emerging scientific science due to the pandemic scenario of COVID-19 disease cases around the world. To accurately forecast the forecasts, many epidemiological mathematical models of spread are growing daily. In this analysis, to analysis the various parameters of this model for India, the classical susceptible-infected-recovered (SIR) modelling method was used. By considering various governmental lockdown initiatives in India, this method was studied [14].
Estimation of parameters of SIR model of India using an actual data set:
Fundamental models based on compartments, as seen in the following, were used for the epidemic mathematical model:
1 (Susceptible->Infectible) SI model,
2 (Susceptible->Infectible-> Susceptible) SIS model, and
3 (Susceptible->Infectible-> Recovery/Removed) SIR model.
The standard SIR model is basically a series of differential equations that can be classified as susceptible (if previously unexposed to pandemic disease), infected (if presently conquered by pandemic disease), and removed (either by death or recovery) [15].
1.4 Conclusion
The goal of this chapter was to present some of the machine learning and AI principles and methodologies and explore some of their possible applications in different aspects of computational mechanics. The methodologies outlined herein are maturing rapidly, and many new applications are likely to be found in computational mechanics. Undoubtedly, AI methodologies would inevitably become, to the same degree as today’s “traditional” algorithmic devices, a natural and indispensable part of the set of computer-based engineering resources. These instruments would then greatly elevate the role of computers in engineering from the current focus on calculation to the much wider field of reasoning.
References
1. Min Cai, Huan-Shui Zhang and Wei Wang, “A power control algorithm based on SIR with multiplicative stochastic noise,” Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826), Shanghai, China, 2004, pp. 2743-2746 vol. 5, doi: 10.1109/ICMLC.2004.1378324.
2. M. Muselli, A. Bertoni, M. Frasca, A. Beghini, F. Ruffino and G. Valentini, “A Mathematical Model for the Validation of Gene Selection Methods,” in IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 8, no. 5, pp. 1385-1392, Sept.-Oct. 2011, doi: 10.1109/TCBB.2010.83.
3. Dutta, Nabanita & Subramaniam, Umashankar & Sanjeevikumar, P.. (2018). Mathematical models of classification algorithm of Machine learning. 10.5339/qproc.2019.imat3e2018.3.
4. KNN Model-Based Approach in Classification, Gongde Guo1, Hui Wang 1, David Bell 2, Yaxin Bi 2, and Kieran Greer 1, School of Computing and Mathematics, University of Ulster, Newtownabbey, BT37 0QB, Northern Ireland, UK.
5. S. Ji, L. T. Watson and L. Carin, “Semi supervised Learning of Hidden Markov Models via a Homotopy Method,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 2, pp. 275-287, Feb. 2009, doi: 10.1109/TPAMI.2008.71.
6. Pavithra, M., Rajmohan, R., Kumar, T. A., & Ramya, R. (2021). Prediction and Classification of Breast Cancer Using Discriminative Learning Models and Techniques. Machine Vision Inspection Systems, Volume 2: Machine Learning-Based Approaches, 241-262.
7. SanghamitraMohanty, HimadriNandini Das Bebartta, “Performance Comparison of SVM and K-NN for Oriya Character Recognition”, (IJACSA) International Journal of Advanced Computer Science and Applications, Special Issue on Image Processing and Analysis, 2011, pp. 112-115
8. D. Bouchoffra and F. Ykhlef, “Mathematical models for machine learning and pattern recognition,” 2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA), Algiers, 2013, pp. 27-30, doi: 10.1109/WoSSPA.2013.6602331.
9. R. Veena, S. Fauziah, S. Mathew, I. Petra and J. Hazra, “Data driven models for understanding the wind farm wake propagation pattern,” 2016 International Conference on Cogeneration, Small Power Plants and District Energy (ICUE), Bangkok, 2016, pp. 1-5, doi: 10.1109/COGEN.2016.7728969.
10. H. J. Vishnukumar, B. Butting, C. Müller and E. Sax, “Machine learning and deep neural network — Artificial intelligence core for lab and real-world test and validation for ADAS and autonomous vehicles: AI for efficient and quality test and validation,” 2017 Intelligent Systems Conference (IntelliSys), London, 2017, pp. 714-721, doi: 10.1109/IntelliSys.2017.8324372.
11. A. Salaün, Y. Petetin and F. Desbouvries, “Comparing the Modeling Powers of RNN and HMM,” 2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA), Boca Raton, FL, USA, 2019, pp. 1496-1499, doi: 10.1109/ICMLA.2019.00246.
12. S. A. Selvi, T. A. kumar, R. S. Rajesh and M. A. T. Ajisha, “An Efficient Communication Scheme for Wi-Li-Fi Network Framework,” 2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), Palladam, India, 2019, pp. 697-701, doi: 10.1109/I-S MAC47947.2019.9032650.
13. Mathematical models and deep learning for predicting the number of individuals reported to be infected with SARS-CoV-2‵ A. S. Fokas, N. Dikaios and G. A. Kastis.
14. M. A. Bahloul, A. Chahid and T. -M. Laleg-Kirati, “Fractional-Order SEIQRDP Model for Simulating the Dynamics of COVID-19 Epidemic,” in IEEE Open Journal of Engineering in Medicine and Biology, vol. 1, pp. 249-256, 2020, doi: 10.1109/OJEMB.2020.3019758.
15. Y. Yang, W. Yu and D. Chen, “Prediction of COVID-19 spread via LSTM and the deterministic SEIR model,” 2020 39th Chinese Control Conference (CCC), Shenyang, China, 2020, pp. 782-785, doi: 10.23919/CCC50068.2020.9189012.
1 *Corresponding author: [email protected]
2 † Corresponding author: [email protected]
2
Edge Computing Optimization Using Mathematical Modeling, Deep Learning Models, and Evolutionary Algorithms
P. Vijayakumar*, Prithiviraj Rajalingam and S. V. K. R. Rajeswari
ECE Department, SRMIST, Kattankulathur, Chennai, India
Abstract
The rapid growth of the Internet of Things (IoT) with advanced applications requires high speed and real-time computing power. Edge computing brings the computation of data closer to the machine where it is being collected. It leads to a decrease in latency, bandwidth usage, and resources for the server and its cost. The significant challenges in edge computing are 1) optimal offloading decision making, 2) resource allocation, 3) Meeting Quality-of-Service (QoS) and Experience (QoE). This chapter addresses the above challenges using mathematical models, Deep Learning and the Evolutionary algorithm. The deep learning algorithm solves the highly complex problem by developing a model from the training data or observation (reinforcement learning). The deep learning approach converts the optimization problem of edge computing into classification or regression or intelligent decision-making problems and solves them. The Evolution algorithm finds an optimum solution for the given problem through the natural process of evaluation, which is used to solve the edge computing multi-optimization problem. An evolution algorithm like a genetic algorithm and ant colony can solve a few research problems