Evolutionary instance selection for text classification

NCU Institutional Repository > 管理學院 > 資訊管理學系 > 期刊論文 > Item 987654321/106662

請使用永久網址來引用或連結此文件: https://ir.lib.ncu.edu.tw/handle/987654321/106662

題名:	Evolutionary instance selection for text classification
作者:	柯士文;Tsai, Chih-Fong;Chen, Zong-Yao;Ke, Shih-Wen
貢獻者:	管理學院資訊管理學系
關鍵詞:	Algorithms;Artificial intelligence;BGA;Classification;Evolution;Evolutionary;Genetic algorithms;Information storage;Instance selection;Mathematical problems;Object repository;Studies;Text categorization;Text classification;Texts;Training
日期:	2014-01-13
上傳時間:	2026-04-23 13:35:16 (UTC+8)
出版者:	Elsevier Inc.;New York: Elsevier Inc
摘要:	摘要： •The effect of performing instance selection on text classification is examined.•A biological-based genetic algorithm (BGA) is proposed for effective instance selection.•BGA produces better instance selection results than GA and other state-of-the-art algorithms.•Moreover, BGA outperforms GA in terms of reduction rate and computational cost. Text classification is usually based on constructing a model through learning from training examples to automatically classify text documents. However, as the size of text document repositories grows rapidly, the storage requirement and computational cost of model learning become higher. Instance selection is one solution to solve these limitations whose aim is to reduce the data size by filtering out noisy data from a given training dataset. In this paper, we introduce a novel algorithm for these tasks, namely a biological-based genetic algorithm (BGA). BGA fits a “biological evolution” into the evolutionary process, where the most streamlined process also complies with the reasonable rules. In other words, after long-term evolution, organisms find the most efficient way to allocate resources and evolve. Consequently, we can closely simulate the natural evolution of an algorithm, such that the algorithm will be both efficient and effective. The experimental results based on the TechTC-100 and Reuters-21578 datasets show the outperformance of BGA over five state-of-the-art algorithms. In particular, using BGA to select text documents not only results in the largest dataset reduction rate, but also requires the least computational time. Moreover, BGA can make the k-NN and SVM classifiers provide similar or slightly better classification accuracy than GA. 出版者： New York: Elsevier Inc 出版日期： 2014-04-01 出處： Journal of Systems and Software, 2014-04, Vol.90, p.104-113 資源來源： Elsevier ScienceDirect Journals Complete 版權： 2014 Elsevier Inc. 版權： Copyright Elsevier Sequoia S.A. Apr 2014 識別號： ISSN: 0164-1212 識別號： EISSN: 1873-1228 識別號： DOI: 10.1016/j.jss.2013.12.034 識別號： CODEN: JSSODM
顯示於類別:	[資訊管理學系] 期刊論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
index.html		0Kb	HTML	31	檢視/開啟

在NCUIR中所有的資料項目都受到原著作權保護.

社群 sharing

資料載入中.....