TY - JOUR
T1 - Optimizing Weighted Extreme Learning Machines for imbalanced classification and application to credit card fraud detection
AU - Zhu, Honghao
AU - Liu, Guanjun
AU - Zhou, Mengchu
AU - Xie, Yu
AU - Abusorrah, Abdullah
AU - Kang, Qi
N1 - Funding Information:
We thank Shoufei Han, a doctoral student at Nanjing University of Aeronautics and Astronautics for his help in experiments. This work was supported in part by National Natural Science Foundation of China ( 61374148 ), General Project of Natural Science Research in Anhui Province ( 113052015KJ05 , KJ2016A456 and KJ2014A150 , the Fundamental Research Funds for the Central Universities of China ( 22120190198 ) and the Deanship of Scientific Research (DSR) at King Abdulaziz University , Jeddah, under grant no. RG-20-135-38 .
Funding Information:
We thank Shoufei Han, a doctoral student at Nanjing University of Aeronautics and Astronautics for his help in experiments. This work was supported in part by National Natural Science Foundation of China (61374148), General Project of Natural Science Research in Anhui Province (113052015KJ05, KJ2016A456 and KJ2014A150, the Fundamental Research Funds for the Central Universities of China (22120190198) and the Deanship of Scientific Research (DSR) at King Abdulaziz University, Jeddah, under grant no. RG-20-135-38.
Funding Information:
Guanjun Liu (M’16–SM’19) received the Ph.D. degree in Computer Software and Theory from Tongji University, Shanghai, China, in 2011. He was a Post-Doctoral Research Fellow with the Singapore University of Technology and Design, Singapore, from 2011 to 2013. He was a Post-Doctoral Research Fellow with the Humboldt Universität zu Berlin, Germany, from 2013 to 2014, funded by the Alexander von Humboldt Foundation. In 2013, he joined in the Department of Computer Science of Tongji University as an Associate Professor, and now is a Professor. He has (co-)authored over 80 papers including 17 ones in IEEE/ACM Transactions and one book entitled Liveness of Petri Nets and its Application (Tongji University Press, 2019). His research interests include Petri net theory, model checking, Web service, workflow, discrete event systems, machine learning and credit card fraud detection.
Publisher Copyright:
© 2020 Elsevier B.V.
PY - 2020/9/24
Y1 - 2020/9/24
N2 - The classification problems with imbalanced datasets widely exist in real word. An Extreme Learning Machine is found unsuitable for imbalanced classification problems. This work applies a Weighted Extreme Learning Machine (WELM) to handle them. Its two parameters are found to affect its performance greatly. The aim of this work is to apply various intelligent optimization methods to optimize a WELM and compare their performance in imbalanced classification. Experimental results show that WELM with a dandelion algorithm with probability-based mutation can perform better than WELM with improved particle swarm optimization, bat algorithm, genetic algorithm, dandelion algorithm and self-learning dandelion algorithm. In addition, the proposed algorithm is applied to credit card fraud detection. The results show that it can achieve high detection performance.
AB - The classification problems with imbalanced datasets widely exist in real word. An Extreme Learning Machine is found unsuitable for imbalanced classification problems. This work applies a Weighted Extreme Learning Machine (WELM) to handle them. Its two parameters are found to affect its performance greatly. The aim of this work is to apply various intelligent optimization methods to optimize a WELM and compare their performance in imbalanced classification. Experimental results show that WELM with a dandelion algorithm with probability-based mutation can perform better than WELM with improved particle swarm optimization, bat algorithm, genetic algorithm, dandelion algorithm and self-learning dandelion algorithm. In addition, the proposed algorithm is applied to credit card fraud detection. The results show that it can achieve high detection performance.
KW - Credit card fraud detection
KW - Dandelion algorithm with probability-based mutation
KW - Imbalanced classification
KW - Weighted Extreme Learning Machine
UR - http://www.scopus.com/inward/record.url?scp=85085273720&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085273720&partnerID=8YFLogxK
U2 - 10.1016/j.neucom.2020.04.078
DO - 10.1016/j.neucom.2020.04.078
M3 - Article
AN - SCOPUS:85085273720
SN - 0925-2312
VL - 407
SP - 50
EP - 62
JO - Neurocomputing
JF - Neurocomputing
ER -