Learning Rate Analysis for Pain Recognition Through Viola-Jones and Deep Learning Methods

  • Raihan Islamadina Prodi Pendidikan Teknologi Informasi, Fakultas Tarbiyah dan Keguruan, Universitas Islam Negeri Ar-Raniry, Banda Aceh, Aceh 23111, Indonesia
  • Khairun Saddami Department of Electrical and Computer Engineering, Faculty of Engineering, Syiah Kuala University, Banda Aceh, Aceh 23111, Indonesia
  • Fitri Arnia Department of Electrical and Computer Engineering, Faculty of Engineering, Syiah Kuala University, Banda Aceh, Aceh 23111, Indonesia
  • Taufik Fuadi Abidin Department of Electrical and Computer Engineering, Faculty of Engineering, Syiah Kuala University, Banda Aceh, Aceh 23111, Indonesia
  • Rusdha Muharar Department of Electrical and Computer Engineering, Faculty of Engineering, Syiah Kuala University, Banda Aceh, Aceh 23111, Indonesia
  • Muhammad Irwandi Prodi Pendidikan Teknologi Informasi, Fakultas Tarbiyah dan Keguruan, Universitas Islam Negeri Ar-Raniry, Banda Aceh, Aceh 23111, Indonesia
  • Aulia Syarif Aziz Prodi Pendidikan Teknologi Informasi, Fakultas Tarbiyah dan Keguruan, Universitas Islam Negeri Ar-Raniry, Banda Aceh, Aceh 23111, Indonesia
DOI: https://doi.org/10.22146/jnteti.v13i2.9466
Keywords: Pain Recognition, Viola-Jones Method, Learning Rate, Deep Learning, Accuracy

Abstract

Deep learning is growing and widely used in various fields of life. One of which is the recognition of pain through facial expressions for patients with communication difficulties. Viola-Jones is a simple algorithm that has real-time detection capabilities with relatively high accuracy and low computational power requirements. The learning rate is a significant number that has an impact on the deep learning result. This study recognized pain using the Viola-Jones and deep learning methods. The dataset used was a thermal image from the Multimodal Intensity Pain (MIntPAIN) database. The steps taken consisted of segmentation, training, and testing. Segmentation was conducted using the Viola-Jones method to get the significant area of the face image. The training process was carried out using four deep learning benchmarks model, which were DenseNet201, MobileNetV2, ResNet101, and EfficientNetb0. Besides that, deep learning has a very important number to determine that is learning rate, which impact the deep learning results. There were five learning rates, which were 10-1, 10-2, 10-3, 10-4, and 10-5. Learning rate values were then compared with four deep models learning to obtain high accuracy results in a short time and simple algorithm. Finally, the testing process was carried out on test data using a deep learning benchmark model in accordance with the training process. The research results showed that a learning rate of 10-2 from the MobileNetV2 method produced an optimal performance with a training validation accuracy of 99.60% within a time of 312 min and 28 s.

References

K.D. Craig, “The facial expression of pain better than a thousand words?” APS J., vol. 1, no. 3, pp. 153–162, 1992, doi: 10.1016/1058-9139(92)90001-S.

M.A. Lazarini, R. Rossi, and K. Hirama, “A systematic literature review on the accuracy of face recognition algorithms,” EAI Endorsed Trans. IoT, vol. 8, no. 30, pp. 1–11, Sep. 2022, doi: 10.4108/eetiot.v8i30.2346.

P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” Proc. 2001 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. (CVPR), 2001, pp. I-511–I-518, doi: 10.1109/CVPR.2001.990517.

P. Viola and M. Jones, “Robust real-time face detection,” Int. J. Comput. Vis., vol. 57, no. 2, pp. 137–154, May 2004, doi: 10.1023/B:VISI.0000013087.49260.fb.

M.F. Hirzi, S. Efendi, and R.W. Sembiring, “Literature study of face recognition using the Viola-Jones algorithm,” 2021 Int. Conf. Artif. Intell. Mechatronics Syst. (AIMS), 2021, pp. 1–6, doi: 10.1109/AIMS52415.2021.9466010.

F. Elgendy, M. Alshewimy, and A. Sarhan, “Pain detection/classification framework including face recognition based on the analysis of facial expressions for e-health systems,” Int. Arab J. Inf. Technol., vol. 18, no. 1, pp. 125–132, Jan. 2021, doi: 10.34028/iajit/18/1/14.

R.M. Al-Eidan, H. Al-Khalifa, and A. Al-Salman, “Deep learning-based models for pain recognition: A systematic review,” Appl. Sci., vol. 10, no. 17, pp. 1–15, Aug. 2020, doi: 10.3390/app10175984.

M.N. Chaudhari, M. Deshmukh, G. Ramrakhiani, and R. Parvatikar, “Face detection using Viola Jones algorithm and neural networks,” 2018 4th Int. Conf. Comput. Commun. Control Autom. (ICCUBEA), 2018, pp. 1–6, doi: 10.1109/ICCUBEA.2018.8697768.

P. Rodriguez et al., “Deep pain: Exploiting long short-term memory networks for facial expression classification,” IEEE Trans. Cybern., vol. 52, no. 5, pp. 3314–3324, May 2022, doi: 10.1109/TCYB.2017.2662199.

D.L. Martinez, O. Rudovic, and R. Picard, “Personalized automatic estimation of self-reported pain intensity from facial expressions,” 2017 IEEE Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), 2017, pp. 2318–2327, doi: 10.1109/CVPRW.2017.286.

G. Bargshady et al., “Ensemble neural network approach detecting pain intensity from facial expressions,” Artif. Intell. Med., vol. 109, pp. 1–12, Sep. 2020, doi: 10.1016/j.artmed.2020.101954.

G. Bargshady et al., “The modeling of human facial pain intensity based on temporal convolutional networks trained with video frames in HSV color space,” Appl. Soft Comput., vol. 97, pp. 1–14, Dec. 2020, doi: 10.1016/j.asoc.2020.106805.

R. Islamadina et al., “Performance of deep learning benchmark models on thermal imagery of pain through facial expressions,” 2022 IEEE Int. Conf. Commun. Netw. Satell. (COMNETSAT), 2022, pp. 374–379, doi: 10.1109/COMNETSAT56033.2022.9994546.

G. Huang, Z. Liu, L.V.D. Maaten, and K.Q. Weinberger, “Densely connected convolutional networks,” 2017 IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 2261–2269, doi: 10.1109/CVPR.2017.243.

M. Sandler et al., “MobileNetV2: Inverted residuals and linear bottlenecks,” 2018 IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 4510–4520, doi: 10.1109/CVPR.2018.00474.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” 2016 IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 770–778, doi: 10.1109/CVPR.2016.90.

M. Tan and Q.V. Le, “EfficientNet: Rethinking model scaling for convolution neural networks,” 2019, arXiv.1905.11946.

J. Brownlee (2020) “Understand the Impact of Learning Rate on Neural Network Performance,” [Online], https://machinelearningmastery.com/understand-the-dynamics-of-learning-rate-on-deep-learning-neural-networks/, access date: 22-Jun-2023.

M.A. Haque et al., “Deep multimodal pain recognition: A database and comparison of spatio-temporal visual modalities,” 2018 13th IEEE Int. Conf. Autom. Face Gesture Recognit. (FG 2018), 2018, pp. 250–257, doi: 10.1109/FG.2018.00044.

M.H. Beale, M.T. Hagan, and H.B. Demuth, Deep Learning Toolbox™ User’s Guide. (2020). Access date: 19-Aug-2023. [Online]. Available: https://www.mathworks.com/help/deeplearning/index.html

A. Schoenauer-Sebag, M. Schoenauer, and M. Sebag, “Stochastic gradient descent: Going as fast as possible but not faster,” 2017, arXiv:1709.01427.

A.G. Lalkhen and A. McCluskey, “Clinical tests: Sensitivity and specificity,” Contin. Educ. Anaesth. Crit. Care Pain, vol. 8, no. 6, pp. 221–223, Dec. 2008, doi: 10.1093/bjaceaccp/mkn041.

Published
2024-05-29
How to Cite
Raihan Islamadina, Khairun Saddami, Fitri Arnia, Taufik Fuadi Abidin, Rusdha Muharar, Muhammad Irwandi, & Aulia Syarif Aziz. (2024). Learning Rate Analysis for Pain Recognition Through Viola-Jones and Deep Learning Methods. Jurnal Nasional Teknik Elektro Dan Teknologi Informasi, 13(2), 77-83. https://doi.org/10.22146/jnteti.v13i2.9466
Issue
Vol 13 No 2: May 2024
Section
Articles

© Jurnal Nasional Teknik Elektro dan Teknologi Informasi, under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License.