DeepAI AI Chat
Log In Sign Up

Unsupervised Visual Time-Series Representation Learning and Clustering

by   Gaurangi Anand, et al.

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.


page 1

page 2

page 3

page 4


Unsupervised Representation Learning for Time Series: A Review

Unsupervised representation learning approaches aim to learn discriminat...

Semi-unsupervised Learning for Time Series Classification

Time series are ubiquitous and therefore inherently hard to analyze and ...

Application of machine learning to gas flaring

Currently in the petroleum industry, operators often flare the produced ...

Variational PSOM: Deep Probabilistic Clustering with Self-Organizing Maps

Generating visualizations and interpretations from high-dimensional data...

Higher-order Motif-based Time Series Classification for Forced Oscillation Source Location in Power Grids

Time series motifs are used for discovering higher-order structures of t...

Similarity Preserving Representation Learning for Time Series Analysis

A considerable amount of machine learning algorithms take instance-featu...

Sprintz: Time Series Compression for the Internet of Things

Thanks to the rapid proliferation of connected devices, sensor-generated...

Code Repositories


Unsupervised visual time-series representation learning and clustering, published in ICONIP 2020

view repo