A Novel Fuzzy Neuro Deep Neural Network Model (FNDNN) for Classification of COPD Severity Levels.
Keywords:
Chronic Obstructive Pulmonary Disease (COPD), Spirometry, Deep Neural Network, Fuzzification, Defuzzification, Over fitting, Bayesian RegularizationAbstract
In recent years, there has been an increase in the mortality rate due to lung diseases like Chronic Obstructive Pulmonary Disease (COPD), and it is estimated that it will increase in upcoming years. The majority of deaths (80%) occurred in most of the nations having low and middle income hence, there is a need for a system that can help to reduce the mortality rate by providing proper treatment to the needy patient. Deep learning has shown outstanding performance in solving many real life problems in the healthcare domain. But it does not handle uncertain data. Its black box nature imposes restrictions on understanding its structure. In this study, a novel optimized fuzzy neuro deep-learning approach called FNDNN is proposed for classification. The main idea is the fusion of fuzzy logic and DNN model to deal with data uncertainty and rule extraction. To overcome overfitting of model different techniques like cross fold validation, changing learning rate is applied but the best result is achieved using L2 regularization. Pre-training and optimizing methods for learning parameters of the FNDNN are proposed. The proposed model for classification of COPD severity levels has better performance as compared with other classifiers as shown in results. This FNDNN model is very beneficial to the society and healthcare providers to accurately diagnose the severity levels of COPD and serve the emergency treatment to the needy one. .
Downloads
References
Jarhyan P, Hutchinson A, Khaw D, Prabhakaran D, Mohan S.,” Prevalence of chronic obstructive pulmonary disease and chronic bronchitis in eight countries: a systematic review and meta-analysis.”, Bull World Health Organ. 2022 Mar 1;100(3):216-230. doi: 10.2471/BLT.21.286870. Epub 2022 Jan 19. PMID: 35261410; PMCID: PMC8886252.
Murray CJ, Lopez AD. ,”Alternative projections of mortality and disability by cause 1990-2020: Global Burden of Disease Study.”, Lancet. 1997 May 24;349(9064):1498-504. doi: 10.1016/S0140-6736(96)07492-2. PMID: 9167458, 1997.
Nielsen, K. G. & Bisgaard, H ,” The effect of inhaled budesonide on symptoms, lung function, and cold air and methacholine responsiveness in 2- to 5-year-old asthmatic children.”, American Journal of Respiratory and Critical Care Medicine 162, 1500–1506,2005.
Anthonisen, N. R., & Wright, E. C. ,” Bronchodilator response in chronic obstructive pulmonary disease.”, The American review of respiratory disease, 133(5), 814-819,1986,
Song TW,”Correlation between spirometry and impulse oscillometry in children with asthma.” Acta Pediatr, 97:51-54, 2008.
Barúa M, Nazeran H, Nava P, Granda V, Diong B.,” Classification of Pulmonary Diseases Based on Impulse Oscillometric Measurements of Lung Function Using Neural Networks.”, Proceedings of the 26th Annual International Conference of the IEEE EMBS San Francisco, CA, USA,2004
Winkler J, Hagert-Winkler A, Wirtz H, Schauer J, Kahn T, Hoheisel G,”Impulse oscillometry in the diagnosis of the severity of obstructive pulmonary disease. “, Pneumol, 63:266-75, 2009.
Asaithambi M, Manoharan SC, Subramanian S.,”Classification of respiratory abnormalities using adaptive neuro fuzzy inference system.”, Int Inf and Database Sys Lecture Notes in Computer Science, 2012, 7198:65-73.
Meraz E, Nazeran H, Goldman M, Nava P, Diong B.,” Impulse Oscillometric features of lung function: towards computer-aided classification of respiratory diseases in children.”, 30th Annual International IEEE EMBS Conference Vancouver British Columbia, Canada,2008.
Hafezi N.,”An integrated software package for model-based neuro-fuzzy classification of small airway dysfunction.” ETD Collection for University of Texas, El Paso Paper AI1473869, 2009.
S. Zhou, Q. Chen, X. Wang.,” Fuzzy deep belief networks for semi-supervised sentiment classification”, Neurocomputing 131, 312–322, 2014.
Y. Deng, Z. Ren, Y. Kong, F. Bao, Q. Dai,” A hierarchical fused fuzzy deep neural network for data classification”, IEEE Trans. Fuzzy Syst.2016.
J. An, L. Xinzhi, G. Wen,”Stability analysis of delayed takagi-sugeno fuzzy systems: a new integral inequality approach.”, J. Nonlinear Sci. Appl. 10 (4) 1941–1959, 2017.
N.K. Kasabov, Q. Song, Denfis,”dynamic evolving neural-fuzzy inference system and its application for time-series prediction”, IEEE Trans. Fuzzy Syst. 10 (2) 144–154, 2002.
D.P. Kingma, J. Ba,”Adam a method for stochastic optimization”, Comput. Sci. ,2014
Fu, L.,” Rule generation from neural networks. Systems, Man and Cybernetics”, IEEE Transactions on, 24(8):1114–1124, 1994.
Tsukimoto H., “Extracting rules from trained neural networks.” Neural Net-works, IEEE Transactions on, 11(2):377–389, 2000.
Sato M. and Tsukimoto, H.,” Rule extraction from neural networks via decision tree induction. “, Neural Networks, Proceedings. IJCNN’01. International Joint Conference on, volume 3, pages 1870–1875, 2001.
Tickle A. B., Andrews R., Golea, M., and Diederich, J., “The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks.” IEEE Transactions on Neural Networks, 9(6):1057–1068, 1998.
Thrun S. (1995): Extracting rules from artificial neural networks with distributed representations. Advances in neural information processing systems.
Craven, M. and Shavlik, J. W. ,” Using sampling and queries to extract rules from trained neural networks”. In ICML, pages 37–45, 1994.
Johansson, U., Lofstrom, T., Konig, R., Sonstrod, C., and Niklasson, L.,”.Rule extraction from opaque models–a slightly different perspective. In Machine Learning and Applications”, 2006. ICMLA’06. 5th International Conference on, pages 22–27.
Craven, M. and Shavlik, J.,” Rule extraction: Where do we go from here?,” University of Wisconsin Machine Learning Research Group Working Paper, pages 99–108.1999.
Sethi, K. K., Mishra, D. K., and Mishra, B.” KDRuleEx: A novel approach for enhancing user comprehensibility using rule extraction.”, In Intelligent Systems, Modelling and Simulation (ISMS),Third International Conference, pages 55–60,2012.
J. Ngiam, A. Khosla, M. Kim, J. Nam, H. Lee, A.Y. Ng, “Multimodal deep learning”, in: Proceedings of the 28th International Conference on Machine Learning (ICML-11), 2011, pp. 689–696.
E. Lázaro, C. Armero, and D. Alvares, “Bayesian regularization for flexible baseline hazard functions in Cox survival models,” Biometrical Journal, vol. 63, no. 1, pp. 7–26, 2021.
R. Mbuvha, M. Jonsson, N. Ehn, and P. Herman, “Bayesian neural networks for one-hour ahead wind power forecasting,” in 6th International Conference on Renewable Energy Research and Applications, ICRERA, 2017, pp. 591–596.
F. Burden and D. Winkler, “Bayesian Regularization of Neural Networks,” 2008, pp. 23–42.
Pandey, J.K., Ahamad, S., Veeraiah, V., Adil, N., Dhabliya, D., Koujalagi, A., Gupta, A. Impact of call drop ratio over 5G network (2023) Innovative Smart Materials Used in Wireless Communication Technology, pp. 201-224.
Anand, R., Ahamad, S., Veeraiah, V., Janardan, S.K., Dhabliya, D., Sindhwani, N., Gupta, A. Optimizing 6G wireless network security for effective communication (2023) Innovative Smart Materials Used in Wireless Communication Technology, pp. 1-20.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
