# Time Series Segmentation through Automatic Feature Learning

arXiv: https://arxiv.org/abs/1801.05394 · HTML: https://mlsanity.com/paper/1801.05394/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jan 2018.

## Built on by (most cited first, 11 of 11)

- [Active multi-fidelity Bayesian online changepoint detection](https://mlsanity.com/paper/2103.14224/) (2021)
- [Segmenting Hybrid Trajectories using Latent ODEs](https://mlsanity.com/paper/2105.03835/) (2021)
- [On Rank Energy Statistics via Optimal Transport: Continuity, Convergence, and Change Point Detection](https://mlsanity.com/paper/2302.07964/) (2023)
- [PromptTSS: A Prompting-Based Approach for Interactive Multi-Granularity Time Series Segmentation](https://mlsanity.com/paper/2506.11170/) (2025)
- [Self-Supervised Transformer Architecture for Change Detection in Radio Access Networks](https://mlsanity.com/paper/2302.02025/) (2023)
- [Identifying Stochasticity in Time-Series with Autoencoder-Based Content-aware 2D Representation: Application to Black Hole Data](https://mlsanity.com/paper/2304.11560/) (2023)
- [Deep State Inference: Toward Behavioral Model Inference of Black-box Software Systems](https://mlsanity.com/paper/2101.04948/) (2021)
- [Robust and efficient change point detection using novel multivariate rank-energy GoF test](https://mlsanity.com/paper/2111.00047/) (2021)
- [Cadence: A Practical Time-series Partitioning Algorithm for Unlabeled IoT Sensor Streams](https://mlsanity.com/paper/2112.03360/) (2021)
- [Latent Space Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2207.11067/) (2022)
- [Autoencoder Based Iterative Modeling and Multivariate Time-Series Subsequence Clustering Algorithm](https://mlsanity.com/paper/2209.04213/) (2022)

## Abstract (arXiv)

Internet of things (IoT) applications have become increasingly popular in recent years, with applications ranging from building energy monitoring to personal health tracking and activity recognition. In order to leverage these data, automatic knowledge extraction - whereby we map from observations to interpretable states and transitions - must be done at scale. As such, we have seen many recent IoT data sets include annotations with a human expert specifying states, recorded as a set of boundaries and associated labels in a data sequence. These data can be used to build automatic labeling algorithms that produce labels as an expert would. Here, we refer to human-specified boundaries as breakpoints. Traditional changepoint detection methods only look for statistically-detectable boundaries that are defined as abrupt variations in the generative parameters of a data sequence. However, we observe that breakpoints occur on more subtle boundaries that are non-trivial to detect with these statistical methods. In this work, we propose a new unsupervised approach, based on deep learning, that outperforms existing techniques and learns the more subtle, breakpoint boundaries with a high accuracy. Through extensive experiments on various real-world data sets - including human-activity sensing data, speech signals, and electroencephalogram (EEG) activity traces - we demonstrate the effectiveness of our algorithm for practical applications. Furthermore, we show that our approach achieves significantly better performance than previous methods.