Search papers, labs, and topics across Lattice.
This paper introduces DTW-based Granular Ball Computing (DTW-GBC), a novel approach to time-series classification that organizes similar training samples into granular balls to enhance robustness against mislabeled data. By employing two granular-ball construction strategies, the method significantly reduces the number of DTW computations required during inference while maintaining classification accuracy. Experiments on benchmark datasets demonstrate that DTW-GBC effectively mitigates performance degradation due to label noise, achieving a favorable balance between robustness and efficiency compared to traditional DTW-based classifiers.
Organizing time-series data into granular balls can drastically reduce inference time while boosting resilience against mislabeled samples.
Dynamic Time Warping (DTW)-based Nearest-Neighbor (NN) classifiers are effective for time-series classification but are vulnerable to mislabeled training samples and require numerous DTW computations during inference. We propose DTW-based Granular Ball Computing (DTW-GBC), which organizes temporally similar training samples into granular balls and performs classification at the granule level. We further develop two granular-ball construction strategies for DTW-GBC. Experiments on four benchmark datasets with symmetric label noise show that the two DTW-GBC variants generally mitigate the performance degradation caused by label noise while requiring substantially fewer comparisons than DTW-based 1-NN during inference. These findings suggest that DTW-GBC provides a favorable balance between classification robustness and inference efficiency.
