A Classification Method Based on Similarity Measures of Generalized Fuzzy Numbers in Building Expert System for Postoperative Patients
In this research, we concentrate to build an expert system for a problem where task is to determine where patients in a postoperative recovery area should be sent to next. Data set created from postoperative patients is used to build proposed expert system to determine, based on hypothermia condition, whether patients in a postoperative recovery area should be sent to Intensive Care Unit (ICU), general hospital floor, or go home. What makes this task particularly difficult is that most of the measured attributes have linguistic values (e.g., stable, moderately stable, unstable, etc.). We are using generalized fuzzy numbers to model the data and introduce new fuzzy similarity based classification procedure which can deal with these linguistic attributes and classify them accordingly. Results are compared to existing result in literature, and this system provides mean classification accuracy of 66.2% which compared well to earlier results reported in literature.
KeywordsClassification methods Expert systems Generalized fuzzy numbers ICU Postoperative patients Similarity measures
- 1.Auephanwiriyakul, S., Theera-Umpon, N. (2004). Comparison of linguistic and regular hard C-means in postoperative patient data. Journal of Advanced Computational Intelligence and Intelligent Informatics 8(6), pp. 599–605.Google Scholar
- 3.Chen, S.H. (1999). Ranking generalized fuzzy number with graded mean integration. In Proceedings of the eighth international fuzzy systems association world congress, Vol. 2, pp. 899–902. Taipei, Taiwan, Republic of China.Google Scholar
- 7.Newman, D.J., Hettich, S., Blake, C.L., Merz, C.J. (1998). UCI Repository of machine learning databases [http://www.ics.uci.edu/mlearn/MLRepository.html]. Irvine, CA: University of California, Department of Information and Computer Science.