<ul><li>Researchers propose a new approach called fuzzy cluster-aware contrastive clustering (FCACC) for unsupervised time series learning</li><li>FCACC combines representation learning and clustering objectives to capture complex patterns in unlabeled time series data</li><li>The approach uses a three-view data augmentation strategy and a cluster-aware hard negative sample generation mechanism to improve feature extraction and discriminative ability</li><li>Experimental results demonstrate that FCACC outperforms selected baseline methods on 40 benchmark datasets</li></ul>

Fuzzy Cluster-Aware Contrastive Clustering for Time Series

Discover more