A new intelligent ECG recognition approach based on CNN and improved ALO-SVM

Cardiovascular disease is one of the most common diseases, which seriously threatens people’s life and health. Therefore, cardiovascular prevention becomes attractive research topics in health care system design. Intelligent recognition electrocardiogram (ECG) signals represents an effective method for rapid diagnosis evaluation diseases medicine. Realization efficiency classification ECG real time play major roles detection diseases. This paper concerned with proposition intelligent signal based on a convolutional neural network (CNN) support vector machines (SVM) improved antlion algorithm (ALO). First, denoised pre-processed by lifting wavelet. Subsequently, CNN used to extract characteristics denoising signal, extracted are as input SVM. Finally, ALO optimize relevant functions SVM achieve better classification. In our algorithm, performance enhanced improving threshold estimation wavelet, improve filtering effect. The proposed architecture tested multi-lead from MIT-BIH data set. results display that has obtained average accuracy, sensitivity, specificity values \(99.97\%\), \(99.99\%\), respectively. Compared existing results, approach performance.