Citation

Zhao, Gezhi and Tan, Yi Fei and Abdul Karim, Hezerul and Chia, Ching King (2025) Investigating the Impact of Correlated Variables in Building a Virtual Sensor Model. In: 2025 Multimedia University Engineering Conference, MECON 2025, 21 July 2025 - 23 July 2025, Cyberjaya, Malaysia.

Text 16.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

Sensors play a vital role in modern technology, enabling the acquisition and measurement of various physical quantities. Traditional sensors are physical devices that interact directly with the environment (physical sensors) to detect physical phenomena and convert them into electrical signals. However, with advances in computing and data-driven technologies, virtual sensors have become a complementary approach. Virtual sensors rely on mathematical models, machine learning algorithms, and data fusion to infer physical quantities without having to make physical measurements directly. This paper gives an overview of traditional sensors and virtual sensors, focusing on a method based on the combination of machine learning and correlation analysis to develop virtual sensors. Through correlation analysis, the model is divided into five groups for detailed investigation. The results showed that using highly correlated data to predict results is better than using all data. Removing poorly correlated data through correlation analysis can help the model achieve better performance.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Machine learning
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	18 Mar 2026 08:27
Last Modified:	19 Mar 2026 02:44
URII:	http://shdl.mmu.edu.my/id/eprint/15596

Downloads

Edit (login required)