ANN Models for Shoulder Pain Detection based on Human Facial Expression Covered by Mask

Main Article Content

Rizka Hadelina Muhammad Ilhamdi Rusydi Mutia Firza Oluwarotimi Williams Samuel


Facial expressions are a method to communicate if someone feels pain. Moreover, coding facial movements to assess pain requires extensive training and is time-consuming for clinical practice. In addition, in Covid 19 pandemic, it was difficult to determine this expression due to the mask on the face. There for, it needs to develop a system that can detect the pain from facial expressions when a person is wearing a mask. There are 41 points used to form 19 geometrical features. It used 20.000 frames of 24 respondents from the dataset as secondary data . From these data, training, and testing were carried out using the ANN (Artificial Neural Network) method with a variation of the number of neurons in the hidden layer, i.e., 5, 10, 15, and 20 neurons. The results obtained from testing these data are the highest accuracy of 86% with the number of 20 hidden layers.


Download data is not yet available.

Article Details

How to Cite
Hadelina, R., Rusydi, M., Firza, M., & Samuel, O. (2023, March 31). ANN Models for Shoulder Pain Detection based on Human Facial Expression Covered by Mask. JITCE (Journal of Information Technology and Computer Engineering), 7(01), 49-55.


[1] S. E. E. Mills, K. P. Nicolson, and B. H. Smith, �Chronic pain: a review of its epidemiology and associated factors in population-based studies,� Br. J. Anaesth., vol. 123, no. 2, pp. e273�e283, 2019.
[2] A. Pathak, S. Sharma, and M. P. Jensen, �The utility and validity of pain intensity rating scales for use in developing countries,� Pain Reports, vol. 3, no. 5, pp. 1�8, 2018.
[3] D. Liu, D. Cheng, T. T. Houle, L. Chen, W. Zhang, and H. Deng, �Machine learning methods for automatic pain assessment using facial expression information: Protocol for a systematic review and meta-analysis,� Med. (United States), vol. 97, no. 49, pp. 0�5, 2018
[4] M. Lee et al., �Pain Intensity Estimation from Mobile Video Using 2D and 3D Facial Keypoints,� 2020
[5] J. Wang and H. Sun, �Pain intensity estimation using deep spatiotemporal and handcrafted features,� IEICE Trans. Inf. Syst., vol. E101D, no. 6, pp. 1572�1580, 2018.
[6] K. Herr, P. J. Coyne, E. Ely, C. G�linas, and R. C. B. Manworren, �Pain Assessment in the Patient Unable to Self-Report: Clinical Practice Recommendations in Support of the ASPMN 2019 Position Statement,� Pain Manag. Nurs., vol. 20, no. 5, pp. 404�417, 2019
[7] T. Li, W. Hou, F. Lyu, Y. Lei, and C. Xiao, �Face detection based-on depth information using HOG-LBP,� Proc. - 2016 6th Int. Conf. Instrum. Meas. Comput. Commun. Control. IMCCC 2016, pp. 779�784, 2016.
[8] O. M. Al-Omair and S. Huang, �A comparative study of algorithms and methods for facial expression recognition,� SysCon 2019 - 13th Annu. IEEE Int. Syst. Conf. Proc., pp. 1�6, 2019.
[9] A. I. Gaidar and P. Y. Yakimov, �Real-time fatigue features detection,� J. Phys. Conf. Ser., vol. 1368, no. 5, 2019.
[10] M. J. M. Zedan and M. A. Al-jbaar, �Face Recognition Security System Based on Convolutional Neural Networks Face Recognition Security System Based on Convolutional Neural Networks,� no. June, 2020.
[11] J. Jeon et al., �A real-time facial expression recognizer using deep neural network,� ACM IMCOM 2016 Proc. 10th Int. Conf. Ubiquitous Inf. Manag. Commun., 2016.
[12] R. Fitzgerald, J. Carqueville, and P. T. Yang, �An approach to structural facial rejuvenation with fillers in women,� Int. J. Women�s Dermatology, vol. 5, no. 1, pp. 52�67, 2019.
[13] P. W. Hashim, J. K. Nia, M. Taliercio, and G. Goldenberg, �Ideals of facial beauty,� Cutis, vol. 100, no. 4, pp. 222�224, 2017.
[14] C. M. Sadacharan, �Facial Proportions of Indian Americans and Its Clinical Applications,� MOJ Anat. Physiol., vol. 1, no. 4, 2015.