Detection of Myocardial Infarction Based on Novel Deep Transfer Learning Methods for Urban Healthcare in Smart Cities

. In this paper, an effective computer-aided diagnosis (CAD) system is to detect MI signals using the convolution neural network (CNN) for healthcare in smart cities. Two types of transfer learning techniques are to retrain the pre-trained VGG-Net (Fine-tuning and VGG-Net as fixed extractor) and obtained two new networks VGG-MI1 and VGG-MI2. In the-MI1 model, the last layer of the VGG-Net model is replaced with a specific according to our requirements and various functions are optimized to overfitting. In the VGG-MI2 model, one layer of the VGG-Net model is as a feature descriptor of the ECG images to describe it with features. Considering the limited availability of dataset, ECG data augmented which has increased the classification performance.-technische bundesanstalt (PTB) Diagnostic ECG database is used for, which has been widely employed in MI detection studies. In of using VGG-MI1, we achieved an accuracy, sensitivity, and specificity of99.02%, 98.76%, and 99.17%, respectively and we achieved an accuracy of 99.22%, sensitivity of 99.15%, and a specificity of 99.49% with VGG-MI2 model. results validate the efficiency of the proposed system in terms of sensitivity, and specificity.