An Improved BP Neural Network Algorithm for Text Classification

被引:0
作者
Lei, Fei [1 ]
Yu, Yongbin [1 ]
Guo, Yuxin [1 ]
Tashi, Nyima [2 ]
Zhang, Huan [1 ]
Dang, Bo [1 ]
机构
[1] Univ Elect Sci & Technol China, Sch Informat & Software Engineer, Chengdu, Sichuan, Peoples R China
[2] Tibet Univ Lhasa, Sch Informat Sci & Technol, Tibet, Peoples R China
来源
2018 37TH CHINESE CONTROL CONFERENCE (CCC) | 2018年
基金
中国国家自然科学基金;
关键词
text classification; BPNN; feature selection; initial weights; genetic algorithm;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper presents an improved back propagation neural network (BPNN), which highlights a novel feature selection metrics and the combination of Genetic Algorithm (GA) and BPNN. On one hand, feature selection metrics combined deflection speed and square error (DSSE) is designed to reduce dimensionality and optimize the weights of BPNN, which is capable of decreasing the training time. On the other hand, GA is introduced to optimize the hidden layer of BPNN. Experiment results demonstrate that our proposed algorithm reduces training time of 8% and improves the accuracy of prediction of 2.5%.
引用
收藏
页码:4474 / 4478
页数:5
相关论文
共 18 条
[1]   k-Information Gain Scaled Nearest Neighbors: A Novel Approach to Classifying Protein-Protein Interaction-Related Documents [J].
Ambert, Kyle H. ;
Cohen, Aaron M. .
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, 2012, 9 (01) :305-310
[2]  
Bahassine S., 2016, 11 INT C INTELLIGENT, P1, DOI DOI 10.1109/SITA.2016.7772289
[3]   A survey on feature selection methods [J].
Chandrashekar, Girish ;
Sahin, Ferat .
COMPUTERS & ELECTRICAL ENGINEERING, 2014, 40 (01) :16-28
[4]  
Forman G., 2003, Journal of Machine Learning Research, V3, P1289, DOI 10.1162/153244303322753670
[5]  
Guyon I., 2003, INTRO VARIABLE FEATU
[6]   Text document preprocessing with the Bayes formula for classification using the Support Vector Machine [J].
Isa, Dino ;
Lee, Lam Hong ;
Kallimani, V. P. ;
RajKumar, R. .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2008, 20 (09) :1264-1272
[7]   Neural Text Categorizer for Exclusive Text Categorization [J].
Jo, Taeho .
JOURNAL OF INFORMATION PROCESSING SYSTEMS, 2008, 4 (02) :77-86
[8]   Some effective techniques for naive Bayes text classification [J].
Kim, Sang-Bum ;
Han, Kyoung-Soo ;
Rim, Hae-Chang ;
Myaeng, Sung Hyon .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2006, 18 (11) :1457-1466
[9]   A Survey on Filter Techniques for Feature Selection in Gene Expression Microarray Analysis [J].
Lazar, Cosmin ;
Taminau, Jonatan ;
Meganck, Stijn ;
Steenhoff, David ;
Coletta, Alain ;
Molter, Colin ;
de Schaetzen, Virginie ;
Duque, Robin ;
Bersini, Hugues ;
Nowe, Ann .
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, 2012, 9 (04) :1106-1119
[10]  
Liu RZ, 2016, INT C WAVEL ANAL PAT, P25, DOI 10.1109/ICWAPR.2016.7731623