Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Emerging Science Journal
Ahmad Fudholi
Pusat Pengajian Citra Universiti, Universiti Kebangsaan Malaysia, Bangi, Selangor 43600
Environmental Science

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Multimodal Emotion Recognition Using Hybrid Large Language Models and Metaheuristic Algorithms Andino Maseleno; M. Teduh Uliniansyah; Agung Santosa; Lyla Ruslana Aini; Rini Wijayanti; Ahmad Fudholi; Chotirat Ann Ratanamahatana
Emerging Science Journal Vol. 10 No. 2 (2026): April
Publisher : Ital Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28991/ESJ-2026-010-02-015

Abstract

Emotion recognition is a vital component of human–computer interaction and intelligent systems, yet robust multimodal emotion recognition remains challenging due to high-dimensional input space, noisy features, and the complexity of integrating heterogeneous modalities. This study proposes a novel hybrid multimodal framework that enhances both accuracy and computational efficiency by combining the semantic representation capability of Large Language Models (LLMs) with the optimization strengths of metaheuristic algorithms. In the proposed approach, an LLM is utilized to extract high-level contextual features from text and audio streams, while the Binary Artificial Hummingbird Algorithm (BAHA) performs feature selection to remove redundant attributes. Subsequently, the Goose Algorithm (GA) optimizes classifier hyperparameters, and the Komodo Mlipir Algorithm (KMA) conducts late fusion of the final multimodal outputs. Experiments conducted on the Interactive Emotional Dyadic Motion Capture (IEMOCAP) dataset, evaluated on six emotion categories, demonstrate that this hybrid approach successfully captures subtle affective cues and surpasses state-of-the-art baselines, achieving an accuracy of 87.5%. Integrating LLMs with multiple specialized metaheuristics therefore yields a substantially more robust emotion recognition pipeline and represents a promising direction toward the development of more emotionally intelligent systems.
Metaheuristic Hyperparameter Optimization and Explainable Deep Learning for Baggage Threat Detection Andino Maseleno; Miftachul Huda; Ahmad Fudholi; Chotirat Ann Ratanamahatana
Emerging Science Journal Vol. 10 No. 1 (2026): February
Publisher : Ital Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28991/ESJ-2026-010-01-06

Abstract

The American Statistical Association reports that Bangkok, the capital and largest city of Thailand, holds the top spot as the most visited city worldwide in 2023. X-ray imaging for security screening plays a crucial role in upholding transportation security by detecting a diverse range of threats or prohibited items carried by passengers. This study introduces an advanced deep learning model leveraging YOLOv8, renowned for its enhanced efficiency in automating baggage detection processes. To enhance the model's hyperparameters and adjust them finely during the training process using the baggage dataset, the system utilized a metaheuristic optimization algorithm known as Evolutionary Genetic Algorithm, which is based on evolutionary principles. Incorporating explainable artificial intelligence techniques such as Local Interpretable Model-Agnostic Explanations (LIME) and Gradient-weighted Class Activation Mapping (Grad-CAM) allows for visual interpretation of predictions, aiding operators in utilizing the model effectively. We trained and tested the baggage dataset, which included 8,312 images and five classes: gun, knife, pliers, scissors, and wrench. The YOLOv8 model achieved the following metrics for the detection of prohibited objects in baggage inspection: an overall precision of 90.5%, recall of 83.3%, mAP50 of 91.3%, and mAP50-95 of 67%. The proposed method can fully automate the recognition of prohibited objects during baggage inspection. This approach is beneficial for designing an integrated, automatic, and non-destructive X-ray image-based classification system.
Co-Authors Agung Santosa Andino Maseleno Andino Maseleno Chotirat Ann Ratanamahatana Chotirat Ann Ratanamahatana Lyla Ruslana Aini M. Teduh Uliniansyah Miftachul Huda Rini Wijayanti