T-S模糊神经网络在冠心病智能诊断中的应用

 冠心病是一种最为常见的心血管疾病，近年来在中国的发病率与死亡率逐年升高，准确诊断和及时治疗是有效降低冠心病死亡率的主要措施。通过引入模糊系统的理论，在传统BP神经网络结构中加入了模糊层与模糊规则计算层，建立了T-S模糊神经网络模型。使用该模型对采集于克利夫兰诊所的297组数据进行分析预测，与传统BP神经网络预测结果对比显示，T-S模糊神经网络模型的平均准确率为82.93%，而传统BP神经网络的平均准确率为75.56%，表明T-S模糊神经网络模型在冠心病的智能诊断中具有较高的预测准确率。

Application of T-S fuzzy neural network to intelligent diagnosis of coronary heart disease

Coronary heart disease is one of the most common cardiovascular diseases. In recent years, the incidence and mortality of coronary heart disease in China have increased year by year. Accurate diagnosis and timely treatment are the main measures to effectively reduce the mortality of coronary heart disease. With the help of the fuzzy system theory and by adding a fuzzy layer and fuzzy rule calculation layer to the structure of a traditional BP neural network, a T-S fuzzy neural network model is established in this paper. Using this model, the 297 data sets of coronary heart disease collected from the Cleveland Clinic are analyzed for diagnostic prediction. The average accuracy of the fuzzy neural network model reaches 82.93%, which is higher than 75.56%, the average accuracy of the traditional BP neural network in intelligent diagnosis of coronary heart disease.