Unsupervised Visual Time-Series Representation Learning and Clustering
This addresses the problem of handling large volumes of unlabeled time-series data for researchers and practitioners in fields like IoT and autonomous driving, but it appears incremental as it builds on existing transfer learning concepts.
The paper tackles unsupervised representation learning for time-series data from various sources like IoT and wearable devices, using a novel data transformation and learning regime to transfer knowledge from other domains, and demonstrates its potential through time-series clustering experiments.
Time-series data is generated ubiquitously from Internet-of-Things (IoT) infrastructure, connected and wearable devices, remote sensing, autonomous driving research and, audio-video communications, in enormous volumes. This paper investigates the potential of unsupervised representation learning for these time-series. In this paper, we use a novel data transformation along with novel unsupervised learning regime to transfer the learning from other domains to time-series where the former have extensive models heavily trained on very large labelled datasets. We conduct extensive experiments to demonstrate the potential of the proposed approach through time-series clustering.