Classification of temporal data using dynamic time warping and compressed learning

This study proposes an algorithm combining the dynamic time warping (DTW) and compressed learning (CL) techniques for temporal data classification. The DTW is used to address nonsynchronous effects in temporal data for determining an adequate reference trajectory. The CL is employed to represent the temporal data effectively and classify the data efficiently by cooperating with the reference trajectory. By applying the proposed algorithm and four other classification methods to several data sets, the proposed algorithm is shown to have satisfactory classification accuracies within a reasonable time. According to this advantage, the proposed algorithm is extended to establish an online monitoring system to detect abnormal types of cardiac arrhythmia for users with wearable healthcare devices. The numerical results indicate that the proposed classifier has satisfactory recognition results for detecting personal abnormal heartbeats in real time.