Tag: time-series clustering

A nationwide time-series analysis of South Korean health insurance claims found that nearly two-thirds of evaluated medical procedures increased in ...

A new LSTM-based dynamic autoencoder achieves up to 97 percent accuracy on benchmark sequential datasets by mitigating feature instability.

A new federated framework called FedAE-KMeans trains autoencoders locally on each device and clusters compressed latent representations on a central ...

A new shapelet-based soft contrastive learning framework called SCLS improves multivariate time series clustering by avoiding noisy data augmentation and ...

A French research team has developed DiaSeg, a framework that extracts diagonal segments from Dynamic Time Warping paths to create ...

Researchers have developed a scalable machine learning method that uses time-series clustering to automatically identify visual search strategies from raw ...