Study on a Fire Detection System Based on Support Vector Machine

^1, ² Faculty of Electronic and Electrical Engineering, Huaiyin Institute of Technology, Huaian Jiangsu 223003, China
³ Department of Electrical Engineering, Jiangsu Huaian Technician College, Huaian Jiangsu 223001, China
¹ Tel.: 13511551985

E-mail: xiaotingye@163.com

Received: 16 September 2014 /Accepted: 30 October 2014 /Published: 30 November 2014

Abstract: It is very important to research the prediction of fire, which is significant to the people and nation. The traditional fire detection system based on neural network has the disadvantages of over learning, trapped in local minimum, etc. This paper proposes a new fire detection system based on support vector machine (SVM). Gas sensors, smoke sensor and temperature sensor are composed to be a sensor array. The fire detection model is established, including sample selection, prediction model training prediction, output modules, etc. The SVM transform the complicated nonlinear problem into the linear problem in the high dimensional plane. The experimental results show that fire detection system based on support vector machine had high recognition rate and reliability, it overcomes the disadvantages of traditional methods.

Keywords: Support vector machine, Fire detection, Sensor array, Pattern recognition.

Click <here> or title of paper to download the full pages article in pdf format

Subscribe the full-page Sensors & Transducers journal in print (paper) or pdf formats

(shipping cost by standard mail for paper version is included)

(25 % discount for IFSA Members)

Alternatively we accept a money transfer to our bank account. Please contact for details: sales@sensorsportal.com

Download <here> the Library Journal Recommendation Form

Home - News - Links - Archives - Tools - Voltage-to-Frequency Converters - Standardization - Patents - Marketplace - Projects - Wish List - e-Shop - Sensor Jobs - Membership - Videos - Publishing - Site Map - Subscribe - Search

Members Area -Sensors Portal -Training Courses - S&T Digest - For advertisers - Bookstore - Forums - Polls - Submit Press Release - Submit White Paper - Testimonies - Twitter - Facebook - LinkedIn