The Applications of K-means Clustering and Dynamic Time Warping Average in Seismocardiography Template Generation

Abstract

The seismocardiography (SCG) is one of the noninvasive diagnostic approaches to detect the heart disease such as valvular heart disease (VHD) or heart failure (HF). The lack of operational guidelines to identify the SCG feature points in the signal waveform made the investigation of SCG feature-point-labeled template be one of the essential topics in SCG researches. For this reason, a new SCG template generation method was studied and proposed in this article. The new method leveraged the clustering skill of K-means algorithm and the waveform alignment capability of the dynamic time warping (DTW) algorithm. The merits of using the new method are the flexibility to average cardiac signal segments with different data lengths and the alleviation of the flattened template problem which often bother the conventional ensemble average method. The strategies to achieve the global minimum of the cost function in K-means clustering, to recognize the clustered groups and to improve the warping criteria for DTW averaging were addressed. Experimental results demonstrated the capabilities on the extraction of the frequent appearing SCG waveforms and the generation of DTW averaged templates from the clinical data of 16 subjects (8 healthy subjects and 8 heart failure subjects). The pros and cons of using DTW based averaging were compared with those of using conventional ensemble averaging.