Optimized Prediction of Airflow Volume in Under-Actuated Zones through Multilayer Perceptron Artificial Neural Network

Yaddarabullah and Arif, Abiyyu Muhammad and Lestari, Dewi and Arifitama, Budi and Fitria, Dina Nurul and Krishnasari, Erneza Dewi and Aedah, Abd Rahman and Saad, Amna (2024) Optimized Prediction of Airflow Volume in Under-Actuated Zones through Multilayer Perceptron Artificial Neural Network. International Journal of Intelligent Engineering & Systems, 18 (1). pp. 391-408.

Text 2025022929-2.pdf Download (848kB)

Abstract

This study addresses the challenge of predicting airflow volume in under-actuated zones, where occupant behavior and environmental factors complicate standard models. To improve prediction accuracy, we propose the Sigmoid Parametric Shifted ReLU (SPS-ReLU) with custom weight scaling as a novel activation function within a Multi-Layer Perceptron Artificial Neural Network (MLP-ANN) model. The model was trained and tested on a time-series dataset from a controlled environment, using optimal time intervals (5, 15, and 30 minutes) identified through polynomial regression analysis. These intervals best capture airflow patterns: the 5-minute interval effectively handles rapid fluctuations in Zones 1 and 2, while the 15-minute interval is better suited for the gradual changes in Zone 3. Results show that SPS-ReLU, particularly with a weight scale of 1.5, significantly improves accuracy, achieving an RMSE of 2.3891 and R² of 0.9974, outperforming both standard and advanced activation functions. Comparatively, DPReLU achieved an RMSE of 3.0469 and R² of 0.9957, while ReLU’s RMSE was 22.5458 with an R² of 0.7741. This demonstrates SPS-ReLU’s capability to balance smoothness and flexibility, enabling it to capture intricate airflow dynamics within dynamic environments. The findings highlight SPS-ReLU with custom scaling and optimal time intervals as an effective solution for enhanced airflow predictions in under-actuated zones.

Item Type:	Journal
Uncontrolled Keywords:	Airflow volume, The under-actuated zone, Neural network, Occupant behavior, Time interval, Polynomial regression, System optimization, Environmental control
Divisions:	School of Science and Technology
Depositing User:	Muhamad Aizat Nazmi Mohd Nor Hamin
Date Deposited:	24 Aug 2026 03:41
Last Modified:	24 Aug 2026 03:41
URI:	http://ur.aeu.edu.my/id/eprint/1502

Actions (login required)

View Item