Bulletin of Electrical Engineering and Informatics Vol. 14, No. 1, February 2025, pp. 307~315 ISSN: 2302-9285, DOI: 10.11591/eei.v14i1.8048  307 Journal homepage: http://beei.org Facial micro-expression classification through an optimized convolutional neural network using genetic algorithm Krishna Santosh Naidana, Yaswanth Yarra, Lakshmi Prasanna Divvela Department of Computer Science and Engineering, Velagapudi Ramakrishna Siddhartha Engineering College, Vijayawada, Andhra Pradesh, India Article Info ABSTRACT Article history: Received Dec 19, 2023 Revised Sep 2, 2024 Accepted Sep 28, 2024 Computer vision facilitates machines to interpret the visual world using various computer aided detection (CAD)-based techniques. It plays a crucial role in micro-expression auto classification. A micro-expression is a brief facial movement which reveals a genuine emotion that a person tries to conceal, it usually lasts for a short duration and is imperceptible with normal vision. To reveal people’s genuine emotions, an automatic micro-expression screening using convolutional neural network (CNN) is in great need. Traditional methods for micro-expression recognition (MER) suffer from low classification accuracy due to inadequate CNN hyperparameters selection. The proposed approach addresses these challenges by using an optimized CNN with adequate learning rate, batch size, epochs, and dropout rate. Real-coded genetic algorithm (RCGA) has been employed for the hyperparameter optimization. In this experimentation, features are extracted from the onset and apex frames of microexpression video clips of CASME II dataset. The proposed model's performance is measured using various metrics, including accuracy, precision, and recall. The proposed approach’s performance is then compared with an optimized CNN using random search algorithm. The empirical investigation of existing CNN-based methods has proven efficacy of our proposed model. Keywords: Convolutional neural network Hyperparameters Micro-expression Optimization Random search Real-coded genetic algorithm This is an open access article under the CC BY-SA license. Corresponding Author: Yaswanth Yarra Department of Computer Science and Engineering Velagapudi Ramakrishna Siddhartha Engineering College Kanuru, Vijayawada, Andhra Pradesh, 520007, India Email: yaswanthyarra7112@gmail.com 1. INTRODUCTION Facial expressions are vital in human interactions for non-verbal communication of emotions and intentions. Micro-expressions [1] are involuntary, subtle, and fleeting facial expressions that reveal the genuine emotions of an individual. Common applications of recognizing micro-expressions include deception detection in various scenarios, such as investigations, understanding patient emotions to improve medical care, evaluating interviewee loyalty and enhancing customer service interactions. Automated facial micro-expression recognition (MER) presents a significant deep learning (DL) challenge due to its complexity and multi-dimensional nature. Prior studies have addressed this challenge through the integration of spatial and temporal features for effective micro-expression classification. These methods consider both visual cues such as facial appearance and muscular movements, as well as motion- related factors like speed and duration [2]-[5] but they often overlook the intricacies the challenges associated with processing complete video sequences. Usually, the computer aided detection (CAD)-based MER process comprises several crucial steps, including data preprocessing, pertinent feature extraction, and the