Top > JACIII > Improving Classification Performance of Nursing-Care Text Clas ...

single-jc.php

JACIII Vol.14 No.2 pp. 142-149
doi: 10.20965/jaciii.2010.p0142
(2010)

Paper:

Views over last 60 days: 506

Improving Classification Performance of Nursing-Care Text Classification System by Using GA-Based Term Selection

Manabu Nii*,**, Takafumi Yamaguchi*, Yutaka Takahashi*,
Atsuko Uchinuno***, and Reiko Sakashita***

*Graduate School of Engineering, University of Hyogo, 2167 Shosha, Himeji, Hyogo, Japan

**WPI Immunology Frontier Research Center, Osaka University

***College of Nursing Art & Science, University of Hyogo, 13-71 Kitaouji-cho, Akashi, Hyogo, Japan

Received:
July 22, 2009
Accepted:
December 10, 2009
Published:
March 20, 2010
Creative Commons License
Keywords:
nursing-care, text classification, support vector machine, genetic algorithm
Abstract
In order to reduce evaluation workloads for nursingcare experts, we have proposed a Support Vector Machine (SVM) based classification system. In this paper, for improving the classification performance, we propose a Genetic Algorithm (GA) based attribute selection method. First, we extract nouns and verbs from nursing-care texts by using of the morphological analysis software and store the extracted terms into a “term list.” Next, some combinations of terms in the term list are selected by a GA with two objectives; (1) maximizing the number of correctly classified texts and (2) minimizing the number of selected terms. Then, we classify the nursing-care texts with these selected terms by using of a SVM-based classification system. From computer simulations, we show the effectiveness of a GA-based attribute selection method for classifying the nursing-care texts.
Cite this article as:
M. Nii, T. Yamaguchi, Y. Takahashi, A. Uchinuno, and R. Sakashita, “Improving Classification Performance of Nursing-Care Text Classification System by Using GA-Based Term Selection,” J. Adv. Comput. Intell. Intell. Inform., Vol.14 No.2, pp. 142-149, 2010.
Data files:
References
  1. [1] Y. Matsumoto et al., “Japanese Morphological Analysis System,” ChaSen Version 2.3.3, 2000. (in Japanese)
  2. [2] M. Asahara and Y. Matsumoto, “Error-driven extensions of Statistical Learning Models for POS tagging,” The Special Interest Group Notes of IPSJ, No.86, pp. 25-32, 2000. (in Japanese)
  3. [3] M. Asahara and Y. Matsumoto, “Extended Models and Tools for High-performance Part-of-Speech Tagger,” Proc. of 18th Int. Conf. on Computational Natural Language Learning, pp. 142-144, 2000.
  4. [4] M. Asahara and Y. Matsumoto, “Extended Hidden Markov Model for Japanese Morphological Analyzer,” The Special Interest Group Notes of IPSJ, No.54, pp. 1-8, 2000. (in Japanese)
  5. [5] MeCab, Yet Another Part-of-Speech and Morphological Analyzer
    http://mecab.sourceforge.jp/
  6. [6] JUMAN http://nlp.kuee.kyoto-u.ac.jp/nl-resource/juman.html
  7. [7] T. Sakaguchi, M. Nii, Y. Takahashi, A. Uchinuno, and R. Sakashita, “Nursing-care Data Classification using Fuzzy Systems,” Proc. of SCIS & ISIS 2006, Tokyo, Japan, pp. 2017-2022, 2006.
  8. [8] M. Nii, Y. Takahashi, A. Uchinuno, and R. Sakashita, “Nursing-care Data Classification Using Neural Networks,” Proc. of 2007 IEEE ICME Int. Conf. on Complex Medical Engineering, Beijing, China, pp. 431-436, 2007.
  9. [9] M. Nii, S. Ando, Y. Takahashi, A. Uchinuno, and R. Sakashita, “Nursing-care Freestyle Texts Classification using Support Vector Machines,” 2007 IEEE Int. Conf. on Granular Computing, CA, pp. 665-668, 2007.
  10. [10] M. Nii, S. Ando, Y. Takahashi, A. Uchinuno, and R. Sakashita, “Feature extraction from nursing-care texts for classification,” Proc. of 6th Int. Forum on Multimedia and Image Processing, in CDROM (6 pages), 2008.
  11. [11] K. Fukui, K. Saito, M. Kimura, and M. Numao, “Evaluation of Vector Representable Topics That were Extracted Automatically,” IPSJ Trans. on Mathematical Modeling and Its Applications, pp. 1-11, 2007.
  12. [12] N. Ashida, M. Takata, A. Sasaki, H. Kamo, N. Nide, and K. Joe, “Construction of a Paper Classification System Using SVM,” IPSJ SIG Technical Reports, pp. 21-24, 2007.
  13. [13] M. Nii, S. Ando, Y. Takahashi A. Uchinuno, and R. Sakashita, “GA based Feature Selection for Nursing-Care Freestyle Text Classification,” Proc. of Joint 4th Int. Conf. on Soft Computing and Intelligent Systems and 9th Int. Symposium on advanced Intelligent Systems, pp. 756-761, 2008.
  14. [14] C. C. Chang and C. J. Lin, “LIBSVM: a library for support vector machines,” 2001.
    http://www.csie.ntu.edu.tw/˜cjlin/libsvm/

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Apr. 22, 2024