Title :
Road type recognition based on SOM and SVM
Author :
Li, Zhongguo ; Hou, Jie ; Wang, Qi ; Liu, Qinghua
Author_Institution :
Sch. of Mech. Eng., Jiangsu Univ. of Sci. & Technol., Zhenjiang, China
Abstract :
It has the great significance to recognition road type based on vehicle load. In this paper, it is proposed that Self-Organizing feature Map (SOM) network is used to determine sample IDentity (ID) and Support Vector Machine (SVM) is employed to recognize road types based on vehicle load. Experiment results indicate that the improved Particle Swarm Optimization (PSO) algorithm gives best performance among all used methods in parameter optimization of SVM and Radial Basis Function (RBF) is the ideal kernel function of SVM. By cross-validation, the highest average recognition rate is 72.5%. This paper present a useful research for road type recognition based on dynamic load.
Keywords :
object recognition; particle swarm optimisation; radial basis function networks; road vehicles; self-organising feature maps; support vector machines; IDentity; RBF; SOM; SVM; particle swarm optimization; radial basis function; road type recognition; self-organizing feature map network; support vector machine; vehicle load; Educational institutions; Expert systems; Fault diagnosis; Particle swarm optimization; Roads; Support vector machines; Vehicles; PSO; RBF hyper-sphere; dynamic load;
Conference_Titel :
Consumer Electronics, Communications and Networks (CECNet), 2011 International Conference on
Conference_Location :
XianNing
Print_ISBN :
978-1-61284-458-9
DOI :
10.1109/CECNET.2011.5768757
