基于相似度模型的动物疾病确诊方法研究

Research on method of diagnosing animal disease based on model of resemblance

为提高机器系统辅助诊断疾病的效率,分析了疾病诊断与模式识别的解决手段相似性,提出了基于可信度向量和模糊隶属度向量的疾病相似度的人工智能模式识别理论模型、数据结构模型、模式相似度构造算法与实践方法,并将其应用于计算机系统辅助诊断疾病的实践。数据显示结果表明,同自然人兽医专家个体相比,该模式能获得较高的诊断正确率,有效地降低了误诊率,具备较好的综合诊断性能。

In order to improve the efficiency of the machine system diagnosing disease, the similarity between disease diagnosis and pattern recognition is analyzed in view of the solution means, while the theoretical model of disease-resemblance pattern recognition based on certainty factors vectors and fuzzy membership factors, and its data structure model, and the pattern resemblance quantitative algorithm, and the practice method are proposed, and all of which are taken into the practice of computer system＇ s auxiliary diagnosing disease. Field data show that compared with the human individual experts, the model can obtain a higher diagnostic accuracy rate, effectively reduce the misdiagnosis rate has a preferential comprehensive diagnosis performance.