Citation :

Mary Joy Daniel Viñas, "Enhanced Artificial Neural Networks Using QHAdamW in Air Quality Forecasting," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 7, pp. 352-371, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I7P122

Abstract

The study employed an Artificial Neural Network in combination with the optimized Adaptive Moment Estimation (Adam) algorithm, currently the only AQI forecasting model available in the Philippines. The modified QHAdamW - Quasi-Hyperbolic Momentum (QHAdam) and Adam with decoupled weight decay (AdamW) were both extensions of the Adam optimizer, and both offer unique advantages for training ANN. The proposed QHAdamW optimizer addresses the issues on convergence, generalization, and forecasting performance of Adam. Hyperparameter tuning results revealed that 0.01 and 0.001 were the most effective optimal values for the generalization performance of QHAdamW. The comparative analysis results using seven evaluation metrics revealed that the error value range is lower, and the regression coefficient, having a value approximately equal to 1, improved the model accuracy performance. Likewise, the model converges to a satisfactory level of performance with the convergence performance results of lower loss values as obtained from training and validation losses. Based on data from a real-time air quality tracking station in Manila, a feed-forward neural network is used to predict the AQI of PM2.5 and PM10 separately. This model can be used to forecast Particulate Matter (PM), to help the Department of Environment and Natural Resources - Environmental Monitoring Bureau (DENR-EMB) implement a comprehensive air quality management.

Keywords

Adam Optimizers, Air Pollutant, Artificial Neural Network, Forecasting, Particulate Matters Air Quality Index.

References

[1] Frank J. Kelly, and Julia C. Fussell, “Air Pollution and Public Health: Emerging Hazards and Improved Understanding of Risk,” Environmental Geochemistry and Health, vol. 37, no. 4, pp. 631-649, 2015.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Adil Masood, and Kafeel Ahmad, “A Review on Emerging Artificial Intelligence (AI) Techniques for Air Pollution Forecasting: Fundamentals, Application and Performance,” Journal of Cleaner Production, vol. 322, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Yun Bai et al., “Air Pollutants Concentrations Forecasting using Back Propagation Neural Network based on Wavelet Decomposition with Meteorological Conditions,” Atmospheric Pollution Research, vol. 7, no. 3, pp. 557-566, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Shirshendu Roy, and Pratyay Mukherjee, “Air Quality Index Forecasting using Hybrid Neural Network Model with Lstm on AQI Sequences,” Proceedings on Engineering Sciences, vol. 2, no. 4, pp. 431-440, 2020.
[CrossRef] [Google Scholar]

[5] Yanlai Zhou, Li-Chiu Chang, and Fi-John Chang, “Explore a Multivariate Bayesian Uncertainty Processor Driven by Artificial Neural Networks for Probabilistic PM2.5 Forecasting,” Science of the Total Environment, vol. 711, pp. 1-14, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Canyang Guo, Genggeng Liu, and Chi-Hua Chen, “Air Pollution Concentration Forecast Method based on the Deep Ensemble Neural Network,” Wireless Communications and Mobile Computing, vol. 2020, no. 1, pp. 1-13, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Sales G. Aribe Jr., Bobby D. Gerardo, and Ruji P. Medina, “Time Series Forecasting of HIV/AIDS in the Philippines using Deep Learning: Does COVID-19 Epidemic Matter?,” arXiv preprint, pp. 144-157, 2022.
[CrossRef] [Google Scholar]

[8] Sales G. Aribe Jr., Bobby D. Gerardo, and Ruji P. Medina, “Neural Network-based Time Series Forecasting of HIV Epidemics: The Impact of Antiretroviral Therapies in the Philippines,” Journal of Positive School Psychology, vol. 6, no. 5, pp. 7844-7855, 2022.
[Google Scholar] [Publisher Link]

[9] Alexander Baklanov, and Yang Zhang, “Advances in Air Quality Modeling and Forecasting,” Global Transitions, vol. 2, pp. 261-270, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Dipayan Guha, Provas Kumar Roy, and Subrata Banerjee, “Application of Backtracking Search Algorithm in Load Frequency Control of Multi-Area Interconnected Power System,” Ain Shams Engineering Journal, vol. 9, no. 2, pp. 257-276, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Chunhui Li, “RETRACTED: Biodiversity Assessment based on Artificial Intelligence and Neural Network Algorithms,” Microprocessors and Microsystems, vol. 79, pp. 1-8, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Jolitte A. Villaruz, Bobby D. Gerardo, and Ruji P. Medina, “Philippine Stock Exchange Index Forecasting using a Tuned Artificial Neural Network Model with a Modified Firefly Algorithm,” 2023 IEEE 6^th International Conference on Pattern Recognition and Artificial Intelligence, Haikou, China, pp. 1039-1044, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Jolitte A. Villaruz et al., “Scouting Firefly Algorithm and its Performance on Global Optimization Problems,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 3, pp. 445-451, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Rishika Chauhan et al., “Experimental and Theoretical Evaluation of Thermophysical Properties for Moist Air within Solar Still by using Different Algorithms of Artificial Neural Network,” Journal of Energy Storage, vol. 30, pp. 1-17, 2020.
[CrossRef] [Google Scholar] [Publisher Link]          

[15]  Jiaxin Yang, and Qiang Long, “A Modification of Adaptive Moment Estimation (Adam) for Machine Learning,” Journal of Industrial and Management Optimization, vol. 20, no. 7, pp. 2516-2540, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Nuttapong Attrapadung et al., “Adam in Private: Secure and Fast Training of Deep Neural Networks with Adaptive Moment Estimation,” arXiv preprint, pp. 1-24, 2021.
[CrossRef] [Google Scholar] [Publisher Link]  

[17] Jerry Ma, and Denis Yarats, “Quasi-Hyperbolic Momentum and Adam for Deep Learning,” arXiv preprint, pp. 1-38, 2018.
[CrossRef] [Google Scholar] [Publisher Link]  

[18] Ilya Loshchilov, and Frank Hutter, “Decoupled Weight Decay Regularization,” arXiv preprint, pp. 1-19, 2017.
[CrossRef] [Google Scholar] [Publisher Link]  

[19] R. Paje, and J.M. Cuna, “Department of Environment and Natural Resources,” Water Quality Guidelines and General Effluent Standard of 2016, pp. 1-8, 2016.
[Google Scholar]

[20] Environmental Management Bureau - NCR, Regional State of Brown Environment National Capital Region, 2021. [Online]. Available: https://ncr.emb.gov.ph/wp-content/uploads/2021/08/2020-EMB-NCR-RSOBER-COMPRESSED.pdf

[21] Sales G. Aribe Jr., “Explainable Hybrid Framework for Deepfake Detection using Forensic and Deep Neural Features,” SSRN, pp. 1-19, 2025.
[CrossRef] [Google Scholar] [Publisher Link]   

[22] Sales Aribe Jr., and Gil Nicholas Cagande, “Benchmarking Federated Learning in Edge Computing Environments: A Systematic Review and Performance Evaluation,” Journal of Advances in Information Technology, vol. 17, no. 2, pp. 378-389, 2026.
[CrossRef] [Google Scholar] [Publisher Link]   

[23] Zahraa E. Mohamed, “Using the Artificial Neural Networks for Prediction and Validating Solar Radiation,” Journal of the Egyptian Mathematical Society, vol. 27, no. 1, pp. 1-13, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Jinghui Chen et al., “Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks,” arXiv preprint, pp. 1-17, 2018.
[CrossRef] [Google Scholar] [Publisher Link]