A Comparative Study of Deep Learning Parameters for Arcus Senilis Classification

Authors

  • Nur Farahin AH Faculty of Electronics and Computer Engineering, Universiti Teknikal Malaysia Melaka (UTeM), Durian Tunggal, Melaka, Malaysia.
  • RA Ramlee Faculty of Electronics and Computer Engineering, Universiti Teknikal Malaysia Melaka (UTeM), Durian Tunggal, Melaka, Malaysia.4Advanced Sensors Embedded Control System Research Group (ASECs), Durian Tunggal, Melaka, Malaysia.
  • MZ Mas’ud Faculty of Information and Communication Technology, UTeM, Durian Tunggal, Melaka, Malaysia.
  • M. A. Alias Faculty of Manufacturing Engineering, UTeM, Durian Tunggal, Melaka, Malaysia

Keywords:

Arcus Senilis, Convolutional Neural Network, Deep Learning, Hyperparameters, Non-invasive

Abstract

Deep learning technique has recently yielded positive results that have increased productivity system for artificial intelligent task, especially the digital image processing and advance machine vision. The popularity of deep learning technique  has a major impact on solving complex problems in many fields, particularly the medical science owing to its applications in medical imaging, disease diagnosis, and much more. However, successful application of deep learning depends upon the appropriate setting of the parameters to achieve better result. Therefore, this paper presents a comparative analysis of different base learning rate and batch size configurations for arcus senilis (AS) classification using deep learning techniques. In this analytical study, a dataset of 402 eye images comprising 158 normal and 244 abnormal eye images was employed. Two well-known ResNet-50, VGG-19 and pre-trained convolutional neural network (CNN) models have been trained and validated with 10-fold cross validation using the proposed dataset. Furthermore, base learning rate and batch size were adjusted accordingly to determine the optimal convergence of each model by observing the validation accuracy and error. Experimental result shows that the best combined system has achieved an overall accuracy of 99.78% with a base learning rate of 0.0001 and a batch size of 20 on CNN pre-trained model validation set. Moreover, CNN produces the best result on F1-score and standard deviation of 99.77% and 0.464 respectively. Thus, it can be concluded that CNN requires a considerably smaller number of parameters and reasonable computing time to achieve state-of-the-art performances. This study shows that CNN has the tendency to consistently improve inaccuracy with growing number of epochs, with no signs of overfitting and performance.

References

L. Deng and D. Yu, “Deep learning: Methods and applications,” Foundations and Trends in Signal Processing, vol. 7, no. 3–4. Now Publishers Inc, pp. 197–387, 2013. doi: 10.1561/2000000039.

L. N. Smith, “A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay,” Mar. 2018, [Online]. Available: http://arxiv.org/abs/1803.09820.

L. N. Smith, “A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay,” Mar. 2018, [Online]. Available: http://arxiv.org/abs/1803.09820.

Y. Bengio, “Practical Recommendations for Gradient-Based Training of Deep Architectures. In: Montavon, G., Orr, G.B., Müller, KR. (eds),” in Neural Networks: Tricks of the Trade. Lecture Notes in Computer Science., vol. 7700, Springer, Berlin, Heidelberg, 2012, pp. 437–478. doi: https://doi.org/10.1007/978-3-642-35289-8_26.

L. N. Smith, “Cyclical Learning Rates for Training Neural Networks,” Jun. 2015, [Online]. Available: http://arxiv.org/abs/1506.01186.

I. Kandel and M. Castelli, “The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset,” ICT Express, vol. 6, no. 4, pp. 312–315, Dec. 2020, doi: 10.1016/j.icte.2020.04.010.

C. Banowati, A. Novianty, and C. Setianingsih, “Cholesterol Level Detection Based on Iris Recognition Using Convolutional Neural Network Method,” 2019 IEEE Conference on Sustainable Utilization and Development in Engineering and Technologies, CSUDET 2019, pp. 116–121, 2019, doi: 10.1109/CSUDET47057.2019.9214690.

T. Kocejko, J. Ruminski, M. Mazur-Milecka, M. Romanowska-Kocejko, K. Chlebus, and K. H. Jo, “Using convolutional neural networks for corneal arcus detection towards familial hypercholesterolemia screening,” Journal of King Saud University - Computer and Information Sciences, no. xxxx, 2021, doi: 10.1016/j.jksuci.2021.09.001.

A. M. Dawud, K. Yurtkan, and H. Oztoprak, “Application of deep learning in neuroradiology: Brain haemorrhage classification using transfer learning,” Comput Intell Neurosci, vol. 2019, 2019, doi: 10.1155/2019/4629859.

K. Munadi, K. Muchtar, N. Maulina, and B. Pradhan, “Image Enhancement for Tuberculosis Detection Using Deep Learning,” IEEE Access, vol. 8, pp. 217897–217907, 2020, doi: 10.1109/ACCESS.2020.3041867.

I. D. Apostolopoulos and T. A. Mpesiana, “Covid-19: automatic detection from X-ray images utilizing transfer learning with convolutional neural networks,” Phys Eng Sci Med, vol. 43, no. 2, pp. 635–640, Jun. 2020, doi: 10.1007/s13246-020-00865-4.

A. Musha, A. al Mamun, A. Tahabilder, Md. J. Hossen, B. Hossen, and S. Ranjbari, “A deep learning approach for COVID-19 and pneumonia detection from chest X-ray images,” International Journal of Electrical and Computer Engineering (IJECE), vol. 12, no. 4, p. 3655, Aug. 2022, doi: 10.11591/ijece.v12i4.pp3655-3664.

J. Ma, X. Fan, S. X. Yang, X. Zhang, and X. Zhu, “Contrast Limited Adaptive Histogram Equalization-Based Fusion in YIQ and HSI Color Spaces for Underwater Image Enhancement,” Intern J Pattern Recognit Artif Intell, vol. 32, no. 7, 2018, doi: 10.1142/S0218001418540186.

S. M. Pizer et al., “Adaptive Histogram Equalization and Its Variations,” 1987.

G. F. C. Campos, S. M. Mastelini, G. J. Aguiar, R. G. Mantovani, L. F. de Melo, and S. Barbon, “Machine learning hyperparameter selection for Contrast Limited Adaptive Histogram Equalization,” EURASIP J Image Video Process, vol. 2019, no. 1, Dec. 2019, doi: 10.1186/s13640-019-0445-4.

U. Kuran and E. Can Kuran, “Parameter selection for CLAHE using multi-objective cuckoo search algorithm for image contrast enhancement,” Intelligent Systems with Applications, vol. 12, p. 51, 2021, doi: 10.1016/j.iswa.2021.20.

N. Kharel, A. Alsadoon, P. W. C. Prasad, and A. Elchouemi, “Early diagnosis of breast cancer using contrast limited adaptive histogram equalization (CLAHE) and Morphology methods,” in 2017 8th International Conference on Information and Communication Systems, ICICS 2017, May 2017, pp. 120–124. doi: 10.1109/IACS.2017.7921957.

A. M. Reza, “Realization of the Contrast Limited Adaptive Histogram Equalization (CLAHE) for Real-Time Image Enhancement,” 2004.

B. K. Umri, M. Wafa Akhyari, and K. Kusrini, “Detection of COVID-19 in Chest X-ray Image using CLAHE and Convolutional Neural Network,” Oct. 2020. doi: 10.1109/ICORIS50180.2020.9320806.

Downloads

Published

2022-12-30

How to Cite

AH, N. F. ., Ramlee, R. ., Mas’ud, M. ., & Alias, M. A. . (2022). A Comparative Study of Deep Learning Parameters for Arcus Senilis Classification. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 14(4), 21–24. Retrieved from https://jtec.utem.edu.my/jtec/article/view/6251