Soft Computing Particle Swarm Optimization based Approach for Classification of Handwritten Characters using Deep Learning Model
Soft Computing Particle Swarm Optimization based Approach for Classification of Handwritten Characters using Deep Learning Model |
||
 |
 |
|
| © 2023 by IJETT Journal | ||
| Volume-71 Issue-7 |
||
| Year of Publication : 2023 | ||
| Author : B. Meena, K. Venkata Rao, Suresh Chittineni |
||
| DOI : 10.14445/22315381/IJETT-V71I7P212 | ||
How to Cite?
B. Meena, K. Venkata Rao, Suresh Chittineni, "Soft Computing Particle Swarm Optimization based Approach for Classification of Handwritten Characters using Deep Learning Model," International Journal of Engineering Trends and Technology, vol. 71, no. 7, pp. 117-123, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I7P212
Abstract
Applications of Deep Learning have proved successful in a number of fields, including Pattern Recognition, Automated Manufacturing and Translation. Deep Learning needs to have its parameters set up correctly in order to provide results of a high calibre. The number of neurons and hidden layers have a significant impact on the performance of a Deep Learning Network. However, manual parameter setup makes configuring important settings simpler for users. However, this technique is tedious. In the present work, it is shown that Particle Swarm Optimization (PSO) is used to optimize parameter values and configure the network. It is allowed for the fine-tuning of the Deep Learning Model by utilizing minimal computational resources. Several machine learning techniques are evaluated, including Decision Trees, K-Nearest Neighbour, and Support Vector Machines (SVM) for image classification. SURF descriptor image features are extracted during the feature extraction process. This work aims to clarify the correct classifier selection procedure and emphasize the importance of picking the appropriate classifier parameters using optimization methods. It is demonstrated in the basic experiment done in our work that PSO gives an excellent method for altering the appropriate Deep Learning algorithm with a number of hidden layers and the number of neurons in each layer compared with other machine learning classifiers like SVM, DT, and KNN. When compared to other classification algorithms, the findings indicate that the methodology has an overall precision of 98 - 100 % for image categorization. Our work demonstrates that PSO actually generates results with a great deal greater precision.
Keywords
Image Classification, Deep Learning, Parameter Optimization, PSO, Support Vector Machine.
References
[1] Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, Cambridge, MA: the MIT Press, 2016.
[Publisher Link]
[2] Berry, Michael, “Machine Learning and Understanding for Intelligent Extreme Scale Scientific Computing And Discovery,” Advanced Scientific Computing Research (ASCR) Division of the Office of Science, U.S. Department of Energy, Workshop Report, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Yuri Malitsky et al., “Tuning Parameters of Large Neighborhood Search for the Machine Reassignment Problem,” International Conference on AI And OR Techniques in Constriant Programming for Combinatorial Optimization Problems, pp. 176–192, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Yasser Ganjisaffar et al., “Distributed Tuning of Machine Learning Algorithms Using Mapreduce Clusters,” Proceedings of the Third Workshop on Large Scale Data Mining: Theory and Applications, pp. 1-8, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[5] J. Kennedy, and R. Eberhart, "Particle Swarm Optimization,” Proceedings of the IEEE International Conference on Neural Networks, pp. 1942-1948, 1995.
[CrossRef] [Google Scholar] [Publisher Link]
[6] C. W. De Silva, Mechatronic Systems: Devices, Design, Control, Operation and Monitoring, Boca Raton: CRC Press, 2007.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Jan Karwowski, Michał Okulewicz, and Jarosław Legierski, “Application of Particle Swarm Optimization Algorithm to Neural Network Training Process in the Localization of the Mobile Terminal,” Engineering Applications of Neural Networks, pp. 122–131, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Yana Mazwin Mohmad Hassim, and Rozaida Ghazali, “Solving a Classification Task Using Functional Link Neural Networks with Modified Artificial Bee Colony,” 2013 Ninth International Conference on Natural Computation (ICNC), pp. 189–193, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Habib Shah, and Rozaida Ghazali, “Prediction of Earthquake Magnitude by an Improved ABC-MLP,” 2011 Developments in E-Systems Engineering, pp. 312–317, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[10] L. Qiongshuai, and W. Shiqing, “A Hybrid Model of Neural Network and Classification in Wine,” 2011 3rd International Conference on Computer Research and Development, vol. 3, pp. 58–61, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Beatriz A. Garro et al., "Artificial Neural Network Synthesis By Means of Artificial Bee Colony (ABC) Algorithm," 2011 IEEE Congress of Evolutionary Computation (CEC), New Orleans, LA, pp. 331-338, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[12] K. Bovis et al., "Identification of Masses in Digital Mammograms with MLP And RBF Nets," Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, pp. 342-347, 2000.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Ankit Sharma, and Dipti R Chaudhary, "Character Recognition Using Neural Network,” International Journal of Engineering Trends And Technology, vol. 4, no. 4, pp. 662-667, 2013.
[Google Scholar] [Publisher Link]
[14] SeyedAli Mirjalili et al., “Training Feedforward Neural Networks Using Hybrid Particle Swarm Optimization and Gravitational Search Algorithm,” Applied Mathematics and Computation, vol. 218, no. 22, pp. 11125–11137.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Seyed Mojtaba Hosseini Bamakan et al., “Parameters Optimization for Nonparallel Support Vector Machine by Particle Swarm Optimization,” Procedia Computer Science, vol. 91, pp.482–491, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Adam Blum, Neural Networks in C++: An Object-Oriented Framework for Building Connectionist Systems, 1st Edition. New York: Wiley, 1992.
[Google Scholar] [Publisher Link]
[17] Z. Boger, and H. Guterman, “Knowledge Extraction from Artificial Neural Network Models,” 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation, vol. 4, pp. 3030–3035, 1997.
[CrossRef] [Google Scholar] [Publisher Link]
[18] K. Swingler, Applying Neural Networks: A Practical Guide, Pap/Dsk Edition. San Francisco: Morgan Kaufmann, 1996.
[Google Scholar]
[19] M. Gnaneswari, and T. Chaitanya Kumar, "Application of Deep Convolutional Neural Networks to Telugu Scripts for Optical Character Recognition," International Journal of Computer Trends and Technology, vol. 71, no. 1, pp. 50-55, 2023.
[CrossRef] [Publisher Link]
[20] Gordon S. Linoff, and Michael J. A. Berry, Data Mining Techniques: for Marketing, Sales, and Customer Relationship Management, 3 Edition. Indianapolis, IN: Wiley, 2011.
[Google Scholar] [Publisher Link]
[21] Anisha Arora et al., Deep Learning with H2O, 2015.
[Google Scholar] [Publisher Link]
[22] Carmelo J. A. Bastos-Filho et al., “Multi-Ring Particle Swarm Optimization,” Evolutionary Computation, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Varick L. Erickson et al., “Occupancy Modeling and Prediction for Building Energy Management,” ACM Transactions on Sensor Networks, vol. 10, no. 3, pp. 1-28, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Yuhui Shi, and Russell C. Eberhart, “Parameter Selection in Particle Swarm Optimization,” Proceedings of the 1998 Annual Conference on Evolutionary Computation, pp. 591-600, 1998.
[Google Scholar] [Publisher Link]
[25] Y. Shi, and R.C. Eberhart, “Empirical Study of Particle Swarm Optimization,” Proceedings of the 1999 Congress on Evolutionary Computation, vol. 3, pp. 1945-1950, 1999.
[CrossRef] [Google Scholar] [Publisher Link]
[26] J. Kennedy, and W.M, “Spears Matching Algorithms to Problems: An Experimental Test of the Particle Swarm And Some Genetic Algorithms on the Multimodal Problem Generator,” 1998 IEEE International Conference on Evolutionary Computation Proceedings, IEEE World Congress on Computational Intelligence (Cat. No.98TH8360), pp. 78-83, 1998.
[CrossRef] [Google Scholar] [Publisher Link]