Prof. Yajun Liu

South China University of Technology, China

Bio: Prof. Yajun Liu was born on September 20, 1974 in Jiangxi, China. Native speaker of Chinese, fluent in English. His Education and Academic Research Experiences is as follows:

December, 2016- Now Professor in South China University of Technology School of Mechanical and Automotive Engineering.

December, 2009- December, 2010. Visiting Professor in Fluid Power Research Center (FPRC) Purdue University at West Lafayette, USA.

Feb, 2005 – July, 2016. Post-doctoral Research Fellow, Tokheim JV company in China.

June, 2002 Ph. D. in Mechanical Engineering. South China University of Technology, Guangzhou,China.

His research interests include Digital signal processing technology and its application in mechanical systems (such as hydraulic System for Energy Saving.); Intelligence control and Manufacturing Engineering. Moreover, Prof. Yajun Liu has published more than270 papers in Journals and proceedings of international conferences. 40+ patents on Mechanical System design and manufacturing.

TItle：An Intelligent Fire Detection Technology Based on Acceleration Signal and Machine Learning

Abstract：Fire is a common and destructive disaster in modern society, and traditional fire detection methods have limitations in terms of accuracy and speed. In this study, an artificial intelligence-based fire detection technique is proposed, which utilizes the vibration features of fireproof materials during combustion. Signal processing techniques, such as time-domain analysis and wavelet packet decomposition, are used to analyze the acceleration signals generated during burning and identify unique features that distinguish fire signals from other disturbances. Machine learning algorithms are then applied to train the feature data and perform parameter tuning to optimize the detection performance. The effectiveness of the method is validated through simulated fire experiments, demonstrating that the technique can detect actual fire signals more quickly and accurately than traditional methods. This proposed method provides a new perspective for fire detection technology and has the potential to minimize the damage caused by fires.