Unsupervised classification of 12-lead ECG signals using wavelet tensor decomposition and two-dimensional Gaussian spectral clustering

• Published in: Knowledge-based systems Vol. 163; pp. 392 - 403
• Main Authors: He, Hong, Tan, Yonghong, Xing, Jianfeng
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.01.2019; Elsevier Science Ltd
• Subjects: 12-lead ECG signal; Classification; Clustering; Decomposition; Dimensionality reduction; Feature extraction; Mathematical analysis; Matrix methods; Normal distribution; Principal components analysis; Segmentation; Spectra; Spectral clustering; Tensor; Tensors; Wavelet packet transform; Wavelet transforms; Dimensionality reduction; Spectral clustering; 12-lead ECG signal; Tensor; Wavelet packet transform
• ISSN: 0950-7051; 1872-7409
• DOI: 10.1016/j.knosys.2018.09.001

Due to high dimensionality and multiple variables, unsupervised classification of 12-lead ECG signals involves challenges and difficulties. In order to automatically discover unknown physiological features from raw multivariate signals and detect abnormal cardiac activities of a subject, we proposed an unsupervised classification scheme of 12-lead ECG signals using wavelet tensor decomposition and two-dimensional Gaussian spectral clustering. After filtering and segmentation, each ECG sample is converted into a wavelet tensor by the Discrete Wavelet Packet Transform (DWPT). Main features of ECG samples can be clearly investigated in a multiple feature space constructed by the ECG lead, time and frequency sub-band. Then the Multilinear Principal Component Analysis (MPCA) is applied to reduce the dimensionality of ECG tensors as well as preserve the data interior structure. Taking account of both magnitude and orientation of feature vectors, a novel two-dimensional Gaussian spectral clustering (TGSC) is devised to cluster different 12-lead ECG samples. Furthermore, the dataset obtained from practical 12-lead ECG experiment and two datasets from PhysioBank are used to verify the efficiency of the proposed method. Clustering results show that more useful features of ECG signals can be extracted by the wavelet-tensor-based MPCA than by vector-based PCA. With the two-dimensional Gaussian proximity matrix, the clustering accuracy of TGSC is also higher than that of the traditional spectral clustering. •Developed a new feature extraction approach of 12-lead ECG signals in tensor space based on DWPT and MPCA.•Realized the tensorization of ECG samples and the dimensionality reduction of ECG wavelet tensors in a tensor space.•Devised a new hybrid distance measure for constructing the proximity matrix of spectral clustering.•Developed a novel two-dimensional Gaussian spectral clustering for 12-lead ECG signals.•The practical lab dataset and two datasets from PhysioBank are used to verify the efficiency of the proposed method.