Research on the weighted-related factors' forecasting CF computer diagnostic method of goat disease.
Wenxue Tan, XI Jin-ju, Rong Qiu-sheng, Jingren Wang · Jilin Nongye Daxue xuebao · 2009
Constructing and using intelligent computer systems to assist human experts to solve problems of disease diagnosis about people and livestock is one of the hot issues in the field of medical artificial intelligence research.Traditional diagnosing systems taking no consideration of timing and associability between clinical characteristics are of high rate of misdiagnosis,and lack of practicality.With the aim to improve the efficiency of machinery-diagnosis, we analyzed the clinical relevance of the disease in case of goats,and introduced mechanisms of associated factor into the method of Certainty-Factor-knowledge-representation;and predicted the CF-value of associate-factors with big weights through the channel of forecast by lowest-value,highest-value,weighted-value.Experimental results show that: the method conceived by us can significantly improve inference rule activation rate and reduce the rate of misdiagnosis.