Int. J. of Wireless and Mobile Computing   »   2017 Vol.12, No.2

 

 

Title: An object classification method based on the improved bacterial foraging optimisation algorithm

 

Authors: Zhigao Zeng; Lianghua Guan; Shengqiu Yi; Yanhui Zhu; Qiang Liu; Qi Tong; Sanyou Zeng

 

Addresses:
College of Computer and Communication, Hunan University of Technology, Hunan 412007, China; Intelligent Information Perception and Processing Technology, Hunan Province Key Laboratory, Hunan, China
College of Computer and Communication, Hunan University of Technology, Hunan 412007, China
College of Computer and Communication, Hunan University of Technology, Hunan 412007, China
College of Computer and Communication, Hunan University of Technology, Hunan 412007, China
College of Computer and Communication, Hunan University of Technology, Hunan 412007, China
College of Computer and Communication, Hunan University of Technology, Hunan 412007, China
Department of Computer Science, China University of GeoSciences, Wuhan, Hubei, China

 

Abstract: This paper proposes a new object classification method based on an improved bacterial foraging optimisation algorithm. Firstly, a dynamic step size is used instead of the fixed step size of the chemotaxis. Secondly, the fixed elimination-dispersal probability is replaced by the dynamic probability. Features are extracted to distinguish the objects, such as pedestrians, cars and pets. Ultimately, all the objects are classified using the improved bacterial foraging optimisation algorithm. The experimental results prove that the effectiveness of the object classification method proposed in this paper is better than that of other algorithms.

 

Keywords: object classification; BFO; bacterial foraging optimisation; feature extraction.

 

DOI: 10.1504/IJWMC.2017.10004965

 

Int. J. of Wireless and Mobile Computing, 2017 Vol.12, No.2, pp.166 - 173

 

Submission date: 06 May 2016
Date of acceptance: 06 Dec 2016
Available online: 08 May 2017

 

 

Editors Full text accessAccess for SubscribersPurchase this articleComment on this article