ECG abnormality detection Based on Multi-domain combination features and LSTM

Most scholars use fixed-length sample to ECG abnormalities based on MIT-BIH dataset, which lead to information loss. To address this problem, this paper proposes a method for ECG abnormality detection based on TSH-L method. The TSH-L method include:(1) Use the 3R ECG sample selection method to select ECG samples.(2) Extract multi-domain combination features including time-domain features, frequency domain features and time-frequency domain features.(3) LSTM is used for classification, and the algorithm is trained and tested based on the MIT-BIH dataset, obtain relatively optimal features as spliced normalized fusion features including kurtosis, skewness and RR interval time domain features, STFT-based sub-band spectrum features, and harmonic ratio features. Experiments show that: TSH-L method proposed in the paper has a high accuracy of 97.74% for the detection of ECG abnormalities of MIT-BIH dataset. The method 3R-TSH-L proposed in this paper is expected to be widely used in family-oriented healthcare.