TY - JOUR
T1 - Experimental comparison of parametric, non-parametric, and hybrid multigroup classification
AU - Pai, Dinesh Ramdas
AU - Lawrence, Kenneth D.
AU - Klimberg, Ronald K.
AU - Lawrence, Sheila M.
PY - 2012/8/1
Y1 - 2012/8/1
N2 - This study evaluates the relative performance of some well-known classification techniques, as well as a proposed hybrid method. The proposed hybrid method is a combination of k-nearest neighbor (kNN) and linear programming (LP) method for four group classification. Computational experiments are conducted to evaluate the performances of these classification techniques. Monte Carlo simulation is used to generate dataset with varying characteristics such as multicollinearity, nonlinearity, etc. for the experiments. The experimental results indicate that LP approaches, in general, and the proposed hybrid method, in particular, consistently have lower misclassification rates for most data characteristics. Furthermore, the hybrid method utilizes the strengths of both methods - k-NN and linear programming - resulting in considerable improvement in the classification accuracy. The results of this study can aid in the design of various hybrid techniques that combine the strengths of different methods to improve classification accuracy and reliability.
AB - This study evaluates the relative performance of some well-known classification techniques, as well as a proposed hybrid method. The proposed hybrid method is a combination of k-nearest neighbor (kNN) and linear programming (LP) method for four group classification. Computational experiments are conducted to evaluate the performances of these classification techniques. Monte Carlo simulation is used to generate dataset with varying characteristics such as multicollinearity, nonlinearity, etc. for the experiments. The experimental results indicate that LP approaches, in general, and the proposed hybrid method, in particular, consistently have lower misclassification rates for most data characteristics. Furthermore, the hybrid method utilizes the strengths of both methods - k-NN and linear programming - resulting in considerable improvement in the classification accuracy. The results of this study can aid in the design of various hybrid techniques that combine the strengths of different methods to improve classification accuracy and reliability.
UR - http://www.scopus.com/inward/record.url?scp=84859217660&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84859217660&partnerID=8YFLogxK
U2 - 10.1016/j.eswa.2012.01.194
DO - 10.1016/j.eswa.2012.01.194
M3 - Article
AN - SCOPUS:84859217660
SN - 0957-4174
VL - 39
SP - 8593
EP - 8603
JO - Expert Systems With Applications
JF - Expert Systems With Applications
IS - 10
ER -