A new data classification method based on chaotic particle swarm
optimization and least square-support vector machine
Fang Liu
a,b,c,d,
⁎
, Zhiguang Zhou
a
a
Institute of information, Zhejiang University of Finance & Economics, Hangzhou 310018, China
b
The State Key Laboratory of Mechanical Transmissions, Chongqing University, Chongqing 400044, China
c
Guangxi Key Laboratory of Hybrid Computation and IC Design Analysis, Guangxi University for Nationalities, Nanning 530006, China
d
The Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, Suzhou 215006, China
abstractarticle info
Article history:
Received 3 June 2015
Received in revised form 28 July 2015
Accepted 17 August 2015
Available online 23 August 2015
Keywords:
Chaotic optimization algorithm
Particle swarm optimization algorithm
Least square-support vector machine (LS-SVM)
Data classification
Generalization ability
Classification accuracy
In order to improve the classification accuracy in chemometrics data, chaotic optimization algorithm (COA) and
particle swarm optimization (PSO) algorithm are introduced into least square-support vector machine (LS-SVM)
model in order to propose an optimized LS-SVM model and a novel data classification (CPL-SVM) method in this
paper. In the proposed CPL-SVM method, the COA with the randomness and ergodicity is used to chaotically
process the initial position and local extreme position of particle in the PSO algorithm in order to obtain a chaotic
particle swarm optimization (CPSO) algorithm, and the CPSO is used to select and optimize the important param-
eters of LS-SVM, then the optimized parameters are used to obtain a better CPL-SVM classification method. The
choice randomness of parameters is avoided and the selection workload of parameters is reduced. And this meth-
od can not only overcome the time-consuming and blindness of cross validation method, but also reflect small
sample learning ability. In order to verify the effectiveness of CPL-SVM method, binary classification data, IRIS
flower data and three relevant data sets with pharmacodynamic properties of drug are selected in this paper.
The experiment results show that the proposed CPL-SVM method takes on the better learning performance,
strong generalization ability, best sensitivity, Matthews correlation coefficient and classification accuracy. And
it can effectively avoid the isolated effects of sample in the learning process.
© 2015 Elsevier B.V. All rights reserved.
1. Introduction
Chemometrics has been defined as the chemical discipline that uses
mathematic al and statistical methods to design and select optimal
procedures and experiments, and provide the maximum chemical in-
formation based on analyzing chemical data. The most prominent part
of chemometrics is data classification by using some intelligent methods
for all obtained data. The chemometrics has mainly involved the infor-
mation extraction from these obtained data. The available data and
desired information often exist the hidden relationship, the analysi s
goal of chemometrics is to find out some relationship s and classify
these data by using new intelligent methods. These intelligent methods
include neural networks (NN), genetic algorithm (GA), simulated an-
nealing (SA), particle swarm optimization (PSO) algorithm, statistical
analysis, support vector machine (SVM) and so on. However, the data
of chemometrics have mostly multi-factors, high noise, nonlinear and
irregular, so these complex data are classified in order to discovery the
interdependent relationships and extract data model among these
features. The SVM model [1] is a machine learning method based on
the minimum structural risk principle for data classification by Vapnik.
This model is a convex optimization problem to find out the global op-
timiz ation s olution. It can effectively solve these complex problems
with the small sample, nonlinear, local minimum, avoid the slow
convergence speed, and easily fall into the local minimum value. On
the basis of SVM model, Suykens et al. [2,3] proposed a least square-
support vector mac hine (LS-SVM) method. The LS-SVM model is to
transform the SVM from the quadratic programming problem into the
linear equations in order to reduce the computational complexity and
improve the calculation speed in processing large sample. The LS-SVM
has been widely applied in the pattern recognition, data mi ning,
image analysis, network security and so on. However, the optimization
parameters of LS-SVM model have an important influence on its optimi-
zation performance and learning precision. So how to optimize param-
eters of LS-SVM model is an important research problem in machine
learning.
Chaotic optimization algorithm (COA) with the randomness and er-
godicity is introduced into the PSO algorithm in order to make up for the
low convergence speed, the late time oscillation and easy falling local
minimum value in this paper. And a chaotic particle swarm optimiza-
tion (CPSO) algorithm based on combining the COA and PSO is pro-
posed. In LS-SVM model, the regularization par ameter γ and radial
basis kernel width parameter σ are very important for the optimization
performance. It is an open problem in the field of LS-SVM how to find
Chemometrics and Intelligent Laboratory Systems 147 (2015) 147–156
⁎ Corresponding author. Tel.:+86 571 8755 7136.
E-mail address: puigpuig2010@gmail.com (F. Liu).
http://dx.doi.org/10.1016/j.chemolab.2015.08.015
0169-7439/© 2015 Elsevier B.V. All rights reserved.
Contents lists available at ScienceDirect
Chemometrics and Intelligent Laboratory Systems
journal homepage: www.elsevier.com/locate/chemolab
剩余9页未读，继续阅读
资源评论
