Unsupervised Visual Time-Series Representation Learning and Clustering
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingClusteringRepresentation LearningTime SeriesTime Series AnalysisTime Series ClusteringSimilar Papers 제목 키워드 기반
Learning Representations for Time Series Clustering
Time series clustering is an essential unsupervised technique in cases when category information is not available. It has been widely applied to genome data, anomaly detection, and in general, in any domain where pattern…
Anomaly DetectionClusteringOpen-Ended Question AnsweringRepresentation Learning+3Learning Representations for Incomplete Time Series Clustering
Time-series clustering is an essential unsupervised technique for data analysis, applied to many real-world fields, such as medical analysis and DNA microarray. Existing clustering methods are usually based on the assump…
ClusteringImputationMissing ValuesRepresentation Learning+3Fuzzy Cluster-Aware Contrastive Clustering for Time Series
The rapid growth of unlabeled time series data, driven by the Internet of Things (IoT), poses significant challenges in uncovering underlying patterns. Traditional unsupervised clustering methods often fail to capture th…
ClusteringContrastive LearningData AugmentationRepresentation Learning+1$k$-Graph: A Graph Embedding for Interpretable Time Series Clustering
Time series clustering poses a significant challenge with diverse applications across domains. A prominent drawback of existing solutions lies in their limited interpretability, often confined to presenting users with ce…
ClusteringGraph EmbeddingTime SeriesTime Series ClusteringDeep Temporal Clustering: Fully unsupervised learning of time-domain features
Unsupervised learning of timeseries data is a challenging problem in machine learning. Here, we propose a novel algorithm, Deep Temporal Clustering (DTC), a fully unsupervised method, to naturally integrate dimensionali…
ClusteringDimensionality Reduction