Trung Kien Do, Thanh Long Duong,
Volume 21, Issue 1 (March 2025)
Abstract
Frequency instability is one of the causes of severe disturbances in the power system, including load shedding and widespread blackouts. Especially in modern power systems, frequency instability has even more serious consequences due to the propagation occurring in interconnected regions. Load frequency control (LFC) is a powerful tool in power system operation to ensure that the frequency is always within the allowable limits. The control parameters of LFC must be optimally adjusted for stable system operation. However, researchers are currently unable to find a suitable and robust method for optimal tuning of LFC control parameters. The paper proposes the Puma Optimizer (PO) algorithm to optimize the parameters of PID, FOPID, and FOPTID+1 controllers for solving the LFC problem. The proposed PO algorithm is evaluated through two models of single-area and two-area power systems with different power sources, including thermal power, hydropower, and gas power. The simulation results show that the integral time absolute error (ITAE) value of the proposed PO method is smaller by 5.25%, 18.16%, 28.35%, and 59.92% compared to Particle Swarm Optimization (PSO), Crested Porcupine Optimization (CPO), Newton-Raphson-based optimization (NRBO), and Global Neighborhood Algorithm (GNA), respectively. The results obtained demonstrate that the PO algorithm is a reliable and efficient tool for finding solutions to the LFC problem.
Manh-Hung Ha, Duc-Chinh Nguyen, Thai-Kim Dinh, Tran Tien-Tam, Do Tien Thanh , Oscal Tzyh-Chiang Chen,
Volume 22, Issue 1 (March 2026)
Abstract
This paper develops a robust and efficient method for the classification of Vietnamese Sign Language gestures. The study focuses on leveraging deep learning techniques, specifically a Graph Convolutional Network (GCN), to analyze hand skeletal points for gesture recognition. The Vietnamese Sign Language custom dataset (ViSL) of 33 characters and numbers, conducting experiments to validate the model's performance, and comparing it with existing architectures. The proposed approach integrates multiple streams of GCN, based on the lightweight MobileNet architecture. The custom dataset is preprocessed to extract key skeletal points using Mediapipe, forming the input for the multiple GCN. Experiments were conducted to evaluate the proposed model's accuracy, comparing its performance with traditional architectures such as VGG and ViT. The experimental results highlight the proposed model superior performance, achieving an accuracy of 99.94% test on the custom ViSL dataset, reach accuracy of 0.993% and 0.994% on American Sign Language (ASL) and ASL MINST dataset, respectivly. The multi-stream GCN approach significantly outperformed traditional architectures in terms of both accuracy and computational efficiency. This study demonstrates the effectiveness of using multi-stream GCNs based on MobileNet for ViSL recognition, showcasing their potential for real-world applications.
