Research on Intelligent Diagnosing Model Based Similarity Distance

Abstract:

In order to help human expert solve the problem of disease diagnosing, we analyze the comparability and relativity between pattern similarity distance and diagnosis as to the solution means, and pioneer the theoretical model of similarity-distance on the basis of certainty factors vectors and fuzzy membership factors vectors, and its corresponding data structure mode. Furthermore, the software hierarchy of model and recognition algorithm are designed. Experimentation statistics demonstrate that compared with the human expert, the novel model could obtain a satisfying accuracy rate of diagnosis over 85%, and reduce a rate of misdiagnosis effectively.

• Periodical: Advanced Materials Research (Volumes 308-310)
• Pages: 432-435
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.308-310.432
• Online since: August 2011
• Authors: Wen Xue Tan, Xi Ping Wang
• Keywords: Auxiliary Diagnosing, Intelligent Diagnosis, Pattern Similarity, Similarity Distance

References

[1] Hu Jian-dong, Yu Yong-chang, Jiang Min, et al. Technology of a fertilizing expert system PDA for crop growing ,Transactions of The Chinese Society of Agricultural Engineering，Vol.22(2006),p.149.

[2] Liao Ying, Liang Jiahong, Liao Chaowei, et al. Research on the application of multi-combined technologies of fault diagnosis on missile seekers, Journal of Astronautics，Vol.3 (2006), p.30.

[3] Tan Wenxue, Chen Hongbo, Guo Guoqiang, et al. Multi-engine Animal Disease Diagnostic Expert System, Computer Engineering，Vol.34 (2008), p.193.

[4] D Randall Wilson. Improved heterogeneous distance functions ,Journal of Artificial Intelligence Research，Vol.6(1999), p.21.

[5] David Horn, Hava T.Siegelmann. Support vector clustering. Journal of Machine Learning Research, Vol.25 (2001), p.125.

[6] Xi Jin-ju, Li Shuhong, Research on sheep disease diagnostic expert system based on subjective Bayes algorithm with self-learning , Journal of Hunan University of Science ＆{TTP}-250 Technology：Natural Science Edition，Vol.24(2009),p.95.

[7] Srinivas Mukkamala, Andrew H. Sung. Identifying significant feature for network forensic analysis using artificial intelligence techniques. International Journal of Digital Evidence, Vol.1 (2003), p.543.

[8] Xiao Shanghais, Xiang Xuejun, Lei Bangjun, ET at, Research on a dynamic recurrent Elman neural network model for electric load forecasting and its Wilcoxon test, Journal of Computational Information Systems, Vol.6 (2010), p.959.

[9] Ding Shi-fei,Jin Feng-xiang,Shi Zhong-zhi, Information feature compression based on partial least squares, Journal of Computer Aided Design & Computer Graphics,Vol.17(2005), p.368.

DOI: 10.1109/icmlc.2005.1527229

[10] Liu Shu-wen, Wang Qing-wei, He Dong-yan, et al. Grape disease diagnosis system based on fuzzy neural network, Transactions of The Chinese Society of Agricultural Engineering，Vol.18 (2006),p.144.