Dr. Elayaraja Aruchunan started his carrier at Curtin University Malaysia in March 2008. Based on his excellent track record in research, he was awarded a full scholarship to pursue his Ph.D. by the Australian Government in 2012. Upon completion of his Ph.D., he joined the University of Malaya in November 2020. He has vast experience in the fields of numerical analysis, computational applied mathematics, and machine learning. Currently, he is working on developing new algorithms for solving various complex scientific, engineering, and industrial mathematical models. Over the last 12 years, he has also conducted various mathematics courses at the undergraduate and postgraduate levels in Malaysian and Australian higher education institutions.
RESEARCH, TEACHING, or OTHER INTERESTS
Decision Sciences, Applied Mathematics, Numerical Analysis, Statistics, Probability and Uncertainty
59
Scopus Publications
827
Scholar Citations
14
Scholar h-index
18
Scholar i10-index
Scopus Publications
HETEROGENEOUS GRAPH NEURAL NETWORKS FOR STOCK PRICE PREDICTION: MODELING TEMPORAL AND CROSS-STOCK DEPENDENCIES Hilmi Aziz Bukhori, Elayaraja Aruchunan, Syaiful Anam, Saiful Bukhori, Avin Maulana Barekeng, 2026 Stock price prediction remains a challenging task due to the complex interplay of temporal trends and relational dependencies within financial markets. This study proposes the GNN-LSTM Hybrid model, a novel framework that integrates Graph Neural Networks (GNNs) with Long Short-Term Memory (LSTM) units to simultaneously capture heterogeneous graph structures and temporal dynamics in stock data, leveraging GNNs to model relational dependencies and LSTMs to address long-term temporal patterns, with graph construction based on stock correlation and temporal edge features. Using a dataset covering 1,270 trading days from March 2015 to April 2020, we evaluate the model against traditional methods (ARIMA, LSTM) and modern graph-based approaches (T-GCN, GAT, Transformer-TS, Base GraphSAGE, SAGE-IS). The GNN-LSTM Hybrid achieves superior performance, with a Mean Absolute Error (MAE) of 0.740 (±0.13), Root Mean Squared Error (RMSE) of 1.100 (±0.21), Mean Absolute Percentage Error (MAPE) of 4.92% (±1.16), and Directional Accuracy (DA) of 67.0% (±2.7), and significantly outperforms all baselines, as confirmed by paired t-tests (p < 0.05). Hyperparameter analysis reveals that a configuration of 6 GNN layers and a hidden dimension size of 128 optimizes predictive accuracy, balancing computational efficiency (training time: 16.0 ± 0.7 s) and performance. Validation across 100 training epochs further confirms the model’s robust convergence across all metrics. With an inference time of 20.0 ± 1.0 ms, which is competitive compared to baselines like ARIMA (23.5 ± 1.1 ms) and GAT (20.5 ± 1.0 ms), the GNN-LSTM Hybrid demonstrates strong potential for practical financial forecasting, offering a scalable and accurate solution for capturing the multifaceted dynamics of stock markets, with implications for real-time applications and broader economic modeling.
CAN CHINA’S FOREIGN DIRECT INVESTMENT CAUSE ECONOMIC GROWTH IN ASEAN? LI PING, FUMITAKA FURUOKA, RAJAH RASIAH, ELAYARAJA ARUCHUNAN Singapore Economic Review, 2026 This paper uses systematic panel data methods to scrutinize the impact of China’s foreign direct investment (FDI) on economic growth in eight Association of Southeast Asian Nations (ASEAN) countries from 2004 to 2018. The findings indicate a statistically significant causal association between these countries’ economic growth and Chinese investment, which shows that China’s FDI is not a cause but rather a result of the economic expansion. Specifically, the results show that there was a causal chain running from fixed capital to Chinese FDI, through trade openness, in the relatively wealthier ASEAN countries; also, there was a causal chain running from economic growth to Chinese FDI, through trade openness, in relatively poorer ASEAN countries.
A Novel Variant of Weighted Quadratic Mean Iterative Methods for Fredholm Integro-Differential Equations Wei Li Ng, Elayaraja Aruchunan, Zailan Siri Sains Malaysiana, 2025 Integro-differential equations are critical for modelling real-world phenomena in physics, engineering, and biology. This paper introduces a Quadratic Mean iterative method to solve dense linear systems derived from the discretization of second- and fourth-order Fredholm integro-differential equations (FIDEs). The solution of the FIDEs is approximated using finite difference, composite trapezoidal, and composite Simpson’s 1/3 and 3/8 schemes. The quadratic mean iterative method then solves the discretized system with different mesh sizes. As the resulting systems are large, a complexity reduction approach is implemented on the quadratic mean method to develop the half-sweep quadratic mean iterative method. The newly proposed iterative method includes a novel theorem, comprehensive proofs, and a detailed convergence analysis. The numerical results indicate that the quadratic mean method significantly outperforms the Gauss-Seidel iterative method in terms of efficiency, making it a promising solution for FIDEs.
Predictive and Interpretative Analysis of Gold Price Using Long Short-Term Memory and Opti-LIME Agrippina Nicola Putra, Nughthoh Arfawi Kurdhi, Zailan Siri, Elayaraja Aruchunan 2025 International Conference on Artificial Intelligence and Technological Solutions for Good Health Well Being and Sustainable Water Management in Support of Sdgs 3 6 and 9 Icaitech 2025 Proceeding, 2025
Quarter-Sweep Successive Over-relaxation Approximation to the Solution of Porous Medium Equations Iaeng International Journal of Applied Mathematics, 2022
A New Algorithm of Geometric Mean for Solving High-Order Fredholm Integro-differential Equations E. Aruchunan, N. Khajohnsaksumeth, B. Wiwatanapataphee Proceedings 2016 IEEE 14th International Conference on Dependable Autonomic and Secure Computing Dasc 2016 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing Picom 2016 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing Datacom 2016 and 2016 IEEE Cyber Science and Technology Congress Cyberscitech 2016 Dasc Picom Datacom Cyberscitech 2016, 2016
Preliminary investigation on electrochemical parameters of lake waters in and around Miri city, Malaysia Pertanika Journal of Science and Technology, 2014
Half-Sweep Conjugate Gradient method for solving first order linear fredholm integro-differential equations Australian Journal of Basic and Applied Sciences, 2011
Heterogeneous Graph Neural Networks for Stock Price Prediction : Modeling Temporal and Cross-Stock Dependencies HA Bukhori, E Aruchunan, S Anam, S Bukhori, A Maulana BAREKENG: Jurnal Ilmu Matematika dan Terapan 20 (2), 0981–1000-0981–1000 , 2026 2026
Forecasting NVIDIA Stock Prices Using LSTM and Random Forest: A Comparative Study with XAI-Based KernelSHAP Interpretation Z Oktaviani, NA Kurdhi, Z Siri, E Aruchunan 2025 IEEE International Conference on Artificial Intelligence and … , 2025 2025
Forecasting Tesla Stock Price Using XGBoost, Random Forest, and CatBoost: A Comparative Study with TreeSHAP Interpretation of the Best Model IG Assaduddiari, NA Kurdhi, Z Siri, E Aruchunan 2025 IEEE International Conference on Artificial Intelligence and … , 2025 2025
Predictive and Interpretative Analysis of Gold Price Using Long Short-Term Memory and Opti-LIME AN Putra, NA Kurdhi, Z Siri, E Aruchunan 2025 IEEE International Conference on Artificial Intelligence and … , 2025 2025
Antecedents of purchase intentions in digital marketing: A case of TikTok shop A Awang Jual, A Paramasivam, SS Kandasamy, P Wajindram, ... African Journal of Science, Technology, Innovation and Development, 1-11 , 2025 2025 Citations: 1
Comparative Study of LSGAN and WGAN-GP for Data Augmentation in Aircraft Damage Detection AH Zaky, NA Kurdhi, Z Siri, E Aruchunan, I Ni'mah 2025 IEEE International Conference on Artificial Intelligence and … , 2025 2025
Modeling and analysis of dynamical behavior in a fractional-order COVID-19 epidemic model with media coverage: A case study of Malaysia R Hu, MHN Aziz, NA Mohamed, E Aruchunan Alexandria Engineering Journal 127, 1081-1095 , 2025 2025 Citations: 5
Modeling and analysis of a delayed fractional order COVID-19 SEIHRM model with media coverage in Malaysia R Hu, MHN Aziz, E Aruchunan, NA Mohamed Scientific Reports 15 (1), 25305 , 2025 2025 Citations: 7
Can Chinese Investments Contribute to Accelerating Economic Growth in Europe? L Ping, R Rasiah, F Furuoka, E Aruchunan Institutions and Economies 17 (2), 87-119 , 2025 2025
Leveraging dynamics informed neural networks for predictive modeling of COVID-19 spread: a hybrid SEIRV-DNNs approach C Cheng, E Aruchunan, MH Noor Aziz Scientific Reports 15 (1), 2043 , 2025 2025 Citations: 18
A Novel Variant of Weighted Quadratic Mean Iterative Methods for Fredholm Integro-Differential Equations WL Ng, E Aruchunan, Z Siri Sains Malaysiana 54 (9), 2301-2313 , 2025 2025 Citations: 1
Dynamic analysis and optimal control of a fractional-order epidemic model with nucleic acid detection and individual protective awareness: A Malaysian case study R Hu, E Aruchunan, MHN Aziz, C Cheng, B Wiwatanapataphee AIMS Math 10, 16157-16199 , 2025 2025 Citations: 5
Intelligent LASSO regression modelling for seaweed drying analysis PY Ng, E Aruchunan, F Furuoka, SA Abdul Karim, JVL Chew, MKM Ali Intelligent systems modeling and simulation III: Artificial intelligent … , 2024 2024 Citations: 3
Intelligent Approximation for Climate Differential Equations JVL Chew, E Aruchunan, A Sunarto Intelligent Systems Modeling and Simulation III: Artificial Intelligent … , 2024 2024
New clusterization of global seaport countries based on their DEA and FDEA network efficiency scores D Nadarajan, E Aruchunan, NF Mohd Noor Plos one 19 (7), e0305146 , 2024 2024
Intelligent System Design for the Solutions of Nonlinear Diffusion in the Two-Dimensional Porous Medium JVL Chew, E Aruchunan, A Sunarto, J Sulaiman Intelligent Systems of Computing and Informatics, 177-191 , 2024 2024
Intelligence random forest application in developing regression model from lamb carcass C-site fat depth data S Jie, E Aruchunan, NAMA Rahman, MKM Ali, SM Ali, MA Khalid, ... Intelligent Systems of Computing and Informatics, 133-150 , 2024 2024 Citations: 1
Intelligence predictive model for lamb carcass C-Site fat depth using support vector machine WY Jinq, E Aruchunan, NAMA Rahman, K Naganthran, MS Muthuvalu, ... Intelligent Systems of Computing and Informatics, 80-97 , 2024 2024 Citations: 1
Intelligent Application of Partial Least Square Algorithm in Developing Model of Fat Depth Measurement SCS Yee, E Aruchunan, NAMA Rahman, K Naganthran, AA Ghapor, ... Intelligent Systems of Computing and Informatics, 12-22 , 2024 2024 Citations: 1
A new fractional integration approach based on neural network nonlinearity with an application to testing unemployment hysteresis F Furuoka, LA Gil-Alana, OOS Yaya, E Aruchunan, AE Ogbonna Empirical Economics 66 (6), 2471-2499 , 2024 2024 Citations: 13
MOST CITED SCHOLAR PUBLICATIONS
Evaluation of water quality pollution indices for heavy metal contamination monitoring: a case study from Curtin Lake, Miri City, East Malaysia MV Prasanna, SM Praveena, S Chidambaram, R Nagarajan, A Elayaraja Environmental Earth Sciences 67 (7), 1987-2001 , 2012 2012 Citations: 340
Half-sweep conjugate gradient method for solving first order linear Fredholm integro-differential equations E Aruchunan, J Sulaiman Australian Journal of Basic and Applied Sciences 5 (3), 38-43 , 2011 2011 Citations: 42
Assessment of metals distribution and microbial contamination at selected Lake waters in and around Miri city, East Malaysia MV Prasanna, R Nagarajan, S Chidambaram, A Elayaraja Bulletin of environmental contamination and toxicology 89 (3), 507-511 , 2012 2012 Citations: 38
Numerical solution of second-order linear fredholm integro-differential equation using generalized minimal residual method E Aruchunan, J Sulaiman American Journal of Applied Sciences 7 (6), pp. 780-783 , 2010 2010 Citations: 38
Iterative method for solving one-dimensional fractional mathematical physics model via quarter-sweep and PAOR A Sunarto, P Agarwal, J Sulaiman, JVL Chew, E Aruchunan Advances in Difference Equations 2021 (1), 147 , 2021 2021 Citations: 34
Improved of forecasting sea surface temperature based on hybrid arima and support vector machines models W Nawi, MS Lola, R Zakariya, NH Zainuddin, AAK Abd Hamid, ... Malaysian Journal of Fundamental and Applied Sciences 17 (5), 609-620 , 2021 2021 Citations: 27
Leveraging dynamics informed neural networks for predictive modeling of COVID-19 spread: a hybrid SEIRV-DNNs approach C Cheng, E Aruchunan, MH Noor Aziz Scientific Reports 15 (1), 2043 , 2025 2025 Citations: 18
A New Variant of Arithmetic Mean Iterative Method for Fourth Order Integro-differential Equations Solution E Aruchunan, Y Wu, B Wiwatanapataphee, P Jitsangiam 2015 IEEE International Conference on Artificial Intelligence, Modelling … , 2015 2015 Citations: 17
Enrichment pattern of leachable trace metals in roadside soils of Miri City, Eastern Malaysia R Nagarajan, MP Jonathan, PD Roy, MV Prasanna, A Elayaraja Environmental Earth Sciences, 1-9 , 2014 2014 Citations: 17
Application of the Central-Difference with Half-Sweep Gauss-Seidel Method for Solving First Order Linear Fredholm Integro-Differential Equations E Aruchunan, J Sulaiman International Journal of Engineering and Applied Sciences 6, 296-300 , 2012 2012 Citations: 17
Half-sweep quadrature-difference schemes with iterative method in solving linear fredholm integro-differential equations E Aruchunan, J Sulaiman Progress in Applied Mathematics 5 (1), 11-21 , 2013 2013 Citations: 16
Assessing the sustainability of the homestay industry for the East Coast of Malaysia using the Delphi approach FA Zamzuki, MS Lola, E Aruchunan, MS Muthuvalu, RVW Jubilee, ... Heliyon 9 (11) , 2023 2023 Citations: 15
Drip water geochemistry of Niah Great Cave, NW Borneo, Malaysia: a base line study MV Prasanna, R Nagarajan, S Chidambaram, S Manikandan, A Elayaraja Carbonates and evaporites 29 (1), 41-54 , 2014 2014 Citations: 15
Improvement of time forecasting models using machine learning for future pandemic applications based on COVID-19 data 2020–2022 AA K Abdul Hamid, WIA Wan Mohamad Nawi, MS Lola, WA Mustafa, ... Diagnostics 13 (6), 1121 , 2023 2023 Citations: 14
A new fractional integration approach based on neural network nonlinearity with an application to testing unemployment hysteresis F Furuoka, LA Gil-Alana, OOS Yaya, E Aruchunan, AE Ogbonna Empirical Economics 66 (6), 2471-2499 , 2024 2024 Citations: 13
Quarter-Sweep Iteration Concept on Conjugate Gradient Normal Residual Method via Second Order Quadrature - Finite Difference Schemes for Solving Fredholm Integro-Differential … E ARUCHUNAN, MS MUTHUVALU, J SULAIMAN Sains Malaysiana 44 (1), 139-146 , 2015 2015 Citations: 13
An Iterative Solution for Second Order Linear Fredholm Integro-Differential Equations E Aruchunan, S Muthuvalu, J Sulaiman, WS Koh, MKM Akhir Malaysian Journal of Mathematical Sciences 8 (2), 158-170 , 2014 2014 Citations: 11
Quarter-Sweep Gauss-Seidel Method for Solving First Order Linear Fredholm Integro-differential Equations E Aruchunan, J Sulaiman MATEMATIKA 27 (2), 199-208 , 2011 2011 Citations: 11
Developing forecasting model for future pandemic applications based on COVID-19 data 2020–2022 WIA Wan Mohamad Nawi, AA K. Abdul Hamid, MS Lola, S Zakaria, ... PloS one 18 (5), e0285407 , 2023 2023 Citations: 9
Enhancing COVID-19 classification accuracy with a hybrid SVM-LR model NI Nordin, WA Mustafa, MS Lola, EN Madi, AA Kamil, MD Nasution, ... Bioengineering 10 (11), 1318 , 2023 2023 Citations: 8