[1]YU Bencheng,DING Shifei.Hybrid reconstruction method for missing data[J].CAAI Transactions on Intelligent Systems,2019,14(5):947-952.[doi:10.11992/tis.201807037]
Copy

Hybrid reconstruction method for missing data

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 14 Number of periods: 2019 5 Page number: 947-952 Column: 学术论文—人工智能基础 Public date: 2019-09-05
Title:
Hybrid reconstruction method for missing data
Author(s):
YU Bencheng1; 2;  DING Shifei1
1. School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China;
2. School of Information and Electrical Engineering, Xuzhou College of Industrial Technology, Xuzhou 221004, China
Keywords:
data mining; covariance matrix; fitness function; particle swarm optimization; optimal threshold; evolving clustering method; data reconstruction; auto-associative extreme learning machine
CLC:
TP301.6
DOI:
10.11992/tis.201807037
Abstract:
The problem of missing data is inevitable in different areas. However, traditional data mining algorithms do not process incomplete data sets well. The covariance matrix and its determinant were applied to the fitness function of particle swarm optimization, and the optimal threshold was obtained through iteration. Then, the missing data were reconstructed based on the evolving clustering method using the optimal threshold, which solved the difficulty in optimal threshold selection and determined its influence on data reconstruction results. Furthermore, the randomness of the auto-associative extreme learning machine was removed by invoking the evolving clustering method with the optimal threshold. Finally, six UCI standard data sets and nine activation functions were selected to verify the method. The results showed that compared with most existing reconstruction methods, the proposed hybrid reconstruction method can complete the reconstruction of the missing data more effectively.
References:
[1] KENNEDY J. Particle swarm optimization[M]//SAMMUT C, WEBB G I. Encyclopedia of Machine Learning. Boston, MA:Springer, 2010.
[2] EBERHART R C, SHI Y. Comparing inertia weights and constriction factors in particle swarm optimization[C]//Proceedings of the 2000 Congress on Evolutionary Computation. La Jolla, USA, 2000:84?88.
[3] 张庆科. 粒子群优化算法及差分进行算法研究[D]. 济南:山东大学, 2017. ZHANG Qingke. Research on the particle swarm optimization and differential evolution algorithms[D]. Ji’nan:Shandong University, 2017.
[4] 王永贵, 林琳, 刘宪国. 基于改进粒子群优化的文本聚类算法研究[J]. 计算机工程, 2014, 40(11):172-177 WANG Yonggui, LIN Lin, LIU Xianguo. Research on text clustering algorithm based on improved particle swarm optimization[J]. Computer engineering, 2014, 40(11):172-177
[5] 徐林. 粒子群优化算法的改进及其应用研究[J]. 西安文理学院学报(自然科学版), 2017, 20(4):51-54 XU Lin. Research on improvement and application of the particle swarm optimization algorithm[J]. Journal of Xi’an University (natural science edition), 2017, 20(4):51-54
[6] KRISHNA M, RAVI V. Particle swarm optimization and covariance matrix based data imputation[C]//Proceedings of 2013 IEEE International Conference on Computational Intelligence and Computing Research. Enathi, India, 2013:1-6.
[7] KASABOV N K, SONG Qun. DENFIS:dynamic evolving neural-fuzzy inference system and its application for time-series prediction[J]. IEEE transactions on fuzzy systems, 2002, 10(2):144-154.
[8] KASABOV N, SONG Qun, MA Tianmin. Fuzzy-neuro systems for local and personalized modelling[M]//NIKRAVESH M, KACPRZYK J, ZADEH L A. Forging New Frontiers:Fuzzy Pioneers Ⅱ. Berlin, Heidelberg:Springer, 2008:175?197.
[9] NISHANTH K J, RAVI V. A computational intelligence based online data imputation method:an application for banking[J]. Journal of information processing systems, 2013, 9(9):633-650.
[10] GAUTAM C, RAVI V. Evolving clustering based data imputation[C]//Proceedings of 2014 International Conference on Circuits, Power and Computing Technologies. Nagercoil, Tamil Nadu, India, 2014:1763-1769.
[11] HUANG Guangbin, ZHU Qinyu, SIEW C K. Extreme learning machine:a new learning scheme of feedforward neural networks[C]//Proceedings of 2004 IEEE International Joint Conference on Neural Networks. Budapest, Hungary, 2004:985-990.
[12] HUANG Guangbin, ZHU Qinyu, SIEW C K. Extreme learning machine:theory and applications[J]. Neurocomputing, 2006, 70(1/2/3):489-501.
[13] 任阳晖. 极限学习机算法及应用研究[D]. 沈阳:沈阳航空航天大学, 2017. REN Yanghui. Extreme learning machine alorithm and application[D]. Shenyang:Shenyang Aerospace University, 2017.
[14] GAUTAM C, RAVI V. Data imputation via evolutionary computation, clustering and a neural network[J]. Neurocomputing, 2015, 156:134-142.
[15] RAVI V, KRISHNA M. A new online data imputation method based on general regression auto associative neural network[J]. Neurocomputing, 2014, 138:106-113.
[16] 申小征. 基于维数约简的区域协方差矩阵及其在人脸识别中的应用[D]. 云南:云南财经大学, 2017.
[17] ANKAIAH N, RAVI V. A novel soft computing hybrid for data imputation[C]//Proceedings of the 7th International Conference on Data Mining. Las Vegas, Nevada, USA, 2011.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems