From Time Series to Euclidean Spaces: On Spatial Transformations for Temporal Clustering

Abstract

Unsupervised clustering of temporal data is both challenging and crucial in machine learning. In this paper, we show that neither traditional clustering methods, time series specific or even deep learning-based alternatives generalise well when both varying sampling rates and high dimensionality are present in the input data. We propose a novel approach to temporal clustering, in which we (1) transform the input time series into a distance-based projected representation by using similarity measures suitable for dealing with temporal data,(2) feed these projections into a multi-layer CNN-GRU autoencoder to generate meaningful domain-aware latent representations, which ultimately (3) allow for a natural separation of clusters beneficial for most important traditional clustering algorithms. We evaluate our approach on time series datasets from various domains and show that it not only outperforms existing methods in all cases, by up to 32%, but is also robust and incurs negligible computation overheads.

arXiv comment8 pages

References in corpus (9)

• Sequence to Sequence Learning with Neural Networks
• Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
• Clustering with Deep Learning: Taxonomy and New Methods
• Joint Unsupervised Learning of Deep Representations and Image Clusters
• TimeNet: Pre-trained deep recurrent neural network for time series classification
• Deep Continuous Clustering
• Deep Unsupervised Clustering Using Mixture of Autoencoders
• Review and Perspective for Distance Based Trajectory Clustering
• Self-Similarity Based Time Warping