Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jurnal Teknik Informatika (JUTIF) Scientific Journal of Informatics
Saba Mehmood
Department of Mathematics, University of Management and Technology, Pakistan
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering

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

Found 2 Documents
Search

 1 
Hybrid Genetic Algorithm and Adaptive Momentum Backpropagation Model with Support Vector Regression Kernel Function for Short-Term Electricity Load Forecasting Safitri Laela; Sirajuddin; Abdillah; Syaharuddin; Saba Mehmood; Wasim Raza
Scientific Journal of Informatics Vol. 13 No. 2: May 2026
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v13i2.41475

Abstract

Purpose: Short-term electricity load forecasting (STLF) plays an important role in power system management because electricity demand is dynamic and influenced by factors such as community activities, weather conditions, and seasonal patterns. However, conventional forecasting methods often have limitations in modeling nonlinear and fluctuating electricity load data. Therefore, this study aims to develop a more accurate and stable forecasting model by integrating artificial intelligence methods within a Graphical User Interface (GUI)-based system. Methods: This research proposes a hybrid model combining Genetic Algorithm (GA), Adaptive Momentum Backpropagation (AMBP), and Support Vector Regression (SVR). GA is used to optimize SVR parameters, SVR performs nonlinear regression forecasting, and AMBP improves learning stability. The dataset consists of electricity load data from Gunung Sari District, Lombok, collected during 2015–2024 with 3,650 daily samples, divided into 80% training data and 20% testing data. Model performance was evaluated using MSE, RMSE, and MAPE. Result: The experimental results show that the proposed GA–SVR–AMBP hybrid model achieves better forecasting performance than single and partial hybrid models. In the testing phase, the model produced an MSE of 0.1556, RMSE of 0.3945, and MAPE of 1.13%, with an accuracy of 98.86%. Using the entire dataset, the model achieved an MSE of 0.4213, RMSE of 0.6491, and MAPE of 1.6953% with an accuracy of 98.30%, indicating good generalization capability and low prediction error. Novelty: The novelty of this study lies in the development of a hybrid GA–SVR–AMBP forecasting model integrated into a MATLAB-based GUI system that facilitates data analysis, model execution, and visualization of prediction results for short-term electricity load forecasting and decision support in power system management.
Neural Network Performance Enhancement Using the Modified Orca Predation Algorithm for Time Series Forecasting: A Comparative Review Syaharuddin Syaharuddin; Mariono Mariono; Alfiana Sahraini; Saba Mehmood; Wasim Raza
Jurnal Teknik Informatika (Jutif) Vol. 7 No. 4 (2026): JUTIF Volume 7, Number 4, August 2026
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2026.7.4.4951

Abstract

Neural Networks (NNs) are extensively used in time series forecasting due to their ability to learn nonlinear and complex temporal relationships. However, NN performance is frequently limited by training challenges, including slow convergence and suboptimal parameter optimization. This study aims to systematically examine the role of the Modified Orca Predation Algorithm (MOPA) in enhancing neural network performance for time series forecasting, particularly in comparison with other metaheuristic optimization approaches. This research employed a qualitative method using a Systematic Literature Review (SLR) approach. Relevant journal and conference articles published between 2015 and 2025 were collected from reputable scientific databases. The selected studies were analyzed thematically and bibliometrically using VOSviewer to identify research trends, application domains, and performance characteristics of MOPA-based neural network optimization. The results indicate that the integration of MOPA into neural network training consistently improves convergence speed, forecasting accuracy, and model stability across various application domains. Compared to conventional optimization methods, MOPA demonstrates superior capability in handling nonlinear and volatile time series data, particularly in energy forecasting, financial time series analysis, and climate-related prediction. The findings also reveal that MOPA-based optimization contributes to better generalization performance by reducing prediction error and output variance. This study provides a structured synthesis of recent research on MOPA-enhanced neural networks and contributes to the understanding of metaheuristic optimization strategies in time series forecasting. The results serve as a reference for researchers in selecting effective optimization methods for neural network-based forecasting models.
Co-Authors Abdillah Alfiana Sahraini Mariono Mariono Safitri Laela Sirajuddin Syaharuddin Syaharuddin Syaharuddin Wasim Raza Wasim Raza