Classification of heart signal using wavelet haar and backpropagation neural network

2017 1st International Conference on Engineering and Applied Technology

Hindarto, H.^1 ; Anshory, I.^1 ; Efiyanti, A.^1

Universitas Muhammadiyah Sidoarjo, Jl. Mojopahit 666B Sidoarjo Jl. Raya Gelam 250, Candi Sidoarjo, Indonesia^1

关键词: Back propagation neural networks;    Classification accuracy;    Classification process;    Feature extraction methods;    Haar features;    Haar wavelets;    Normal sinus rhythm;    Wavelet Haar;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/403/1/012069/pdf
DOI  :  10.1088/1757-899X/403/1/012069

来源: IOP

【 摘 要 】

Researchers used many methods to extract and classify heart signals. In this study wavelet haar is use to extract characteristics of heart signals. Artificial neural networks Backpropagation for the classification of heart signals. The data is taken from Physiobank namely MIT-BIH Arrhythmia Database and MIT-BIH Normal Sinus Rhythm Database. The data is processed using Haar wavelet method for its extraction. The results of feature extraction methods will be use for the classification process. The research found that by using Wavelet Haar feature extraction and classification using Backpropagation obtained classification accuracy rate of 92%.