Safi’e, Siti Nur Safira and Zainul Azlan, Norsinnira and Tasneem, Zabina and Mohammed Shweesh, Osamah Ebrahim and Suwarno, Iswanto (2025) Facial expression recognition using stretchable sensor and multilayer feedforward backpropagation neural network. International Journal of Advanced Research in Computational Thinking and Data Science, 7 (1). pp. 44-57. E-ISSN 3030-5225
|
PDF (Journal)
- Published Version
Download (6MB) | Preview |
Abstract
Facial expression recognition plays a crucial role in enabling natural human–computer interaction, emotion identification systems and finds diverse applications in healthcare, security, marketing and social robotics. Traditionally, facial expression recognition relies on vision-based systems, which are often limited by sensitivity to lighting and pose variations, occlusions and high computational cost. Therefore, this study proposes a facial expression recognition system based on stretchable sensor data for controlling the movement of a robotic hand. Stretchable sensors are capable of conforming to complex and dynamic surfaces such as human skin while maintaining sensing accuracy under deformation. In this study, four stretchable sensors are placed on the forehead, upper lip, lower lip, and right cheek. The sensors are interfaced with an Arduino Mega 2560 microcontroller for data acquisition. Statistical features including mean, root mean square (RMS), variance and standard deviation are extracted and used to train a multilayer feedforward backpropagation neural network algorithm in classifying four expressions: neutral, happy, sad, and disgust. The trained model outputs are mapped to control four servo motors attached to the robotic hand’s fingers and wrist, producing peace, thumbs-up, fist gestures, and wrist rotation. The validation results demonstrate that the proposed system achieved 100% accuracy in the training phase but a significantly low accuracy of 25% in the testing stage. This shows that further improvement is needed to improve the stretchable sensor-based facial expression recognition system.
| Item Type: | Article (Journal) |
|---|---|
| Additional Information: | 4494/126011 |
| Uncontrolled Keywords: | Facial expression recognition, stretchable sensor, multilayer feedforward backpropagation algorithm, neural network |
| Subjects: | T Technology > T Technology (General) T Technology > TA Engineering (General). Civil engineering (General) T Technology > TJ Mechanical engineering and machinery T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button): | Kulliyyah of Engineering Kulliyyah of Engineering > Department of Mechatronics Engineering |
| Depositing User: | Norsinnira Zainul Azlan |
| Date Deposited: | 29 Dec 2025 10:07 |
| Last Modified: | 29 Dec 2025 16:14 |
| Queue Number: | 2025-12-Q1031 |
| URI: | http://irep.iium.edu.my/id/eprint/126011 |
Actions (login required)
 |
View Item |
Download Statistics
Download Statistics