1. NCCU Academic Hub
  2. 學術產出
  3. 資訊學院
  4. 期刊論文
  5. Item

學術產出-期刊論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 Feature selection using genetic algorithm and cluster validation
作者 Wu, Y.-L.;Tang, C.-Y.;Hor, Maw-Kae;Wu, P.-F.
何瑁鎧
貢獻者 資科系
關鍵詞 Cluster validation; Convergence time; Feature selection; Feature sets; Image retrieval systems; Low-level image features; Retrieval accuracy; Taguchi; Two directions; Clustering algorithms; Genetic algorithms; Image retrieval; Taguchi methods; Feature extraction
日期 2011-03
上傳時間 22-六月-2015 16:13:39 (UTC+8)
摘要 Feature selection plays an important role in image retrieval systems. The better selection of features usually results in higher retrieval accuracy. This work tries to select the best feature set from a total of 78 low level image features, including regional, color, and textual features, using the genetic algorithms (GA). However, the GA is known to be slow to converge. In this work we propose two directions to improve the convergence time of the GA. First we employ the Taguchi method to reduce the number of necessary offspring to be tested in every generation in the GA. Second we propose to use an alternative measure, the Hubert`s Γ statistics, to evaluate the fitness of each offspring instead of evaluating the retrieval accuracy directly. The experiment results show that the proposed techniques improve the feature selection results by using the GA in both time and accuracy. © 2010 Elsevier Ltd. All rights reserved.
關聯 Expert Systems with Applications, 38(3), 2727-2732
資料類型 article
DOI http://dx.doi.org/10.1016/j.eswa.2010.08.062
dc.contributor 資科系
dc.creator (作者) Wu, Y.-L.;Tang, C.-Y.;Hor, Maw-Kae;Wu, P.-F.
dc.creator (作者) 何瑁鎧zh_TW
dc.date (日期) 2011-03
dc.date.accessioned 22-六月-2015 16:13:39 (UTC+8)-
dc.date.available 22-六月-2015 16:13:39 (UTC+8)-
dc.date.issued (上傳時間) 22-六月-2015 16:13:39 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/76055-
dc.description.abstract (摘要) Feature selection plays an important role in image retrieval systems. The better selection of features usually results in higher retrieval accuracy. This work tries to select the best feature set from a total of 78 low level image features, including regional, color, and textual features, using the genetic algorithms (GA). However, the GA is known to be slow to converge. In this work we propose two directions to improve the convergence time of the GA. First we employ the Taguchi method to reduce the number of necessary offspring to be tested in every generation in the GA. Second we propose to use an alternative measure, the Hubert`s Γ statistics, to evaluate the fitness of each offspring instead of evaluating the retrieval accuracy directly. The experiment results show that the proposed techniques improve the feature selection results by using the GA in both time and accuracy. © 2010 Elsevier Ltd. All rights reserved.
dc.format.extent 1059083 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) Expert Systems with Applications, 38(3), 2727-2732
dc.subject (關鍵詞) Cluster validation; Convergence time; Feature selection; Feature sets; Image retrieval systems; Low-level image features; Retrieval accuracy; Taguchi; Two directions; Clustering algorithms; Genetic algorithms; Image retrieval; Taguchi methods; Feature extraction
dc.title (題名) Feature selection using genetic algorithm and cluster validation
dc.type (資料類型) articleen
dc.identifier.doi (DOI) 10.1016/j.eswa.2010.08.062
dc.doi.uri (DOI) http://dx.doi.org/10.1016/j.eswa.2010.08.062