# Pattern Discovery in Time Series with Byte Pair Encoding

arXiv: https://arxiv.org/abs/2106.00614 · HTML: https://mlsanity.com/paper/2106.00614/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 36 references that are in the map.
- First posted on arXiv 30 May 2021.

## Builds on (most cited first, 9 of 9)

- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels](https://mlsanity.com/paper/1910.13051/) (2019)
- [Unsupervised Scalable Representation Learning for Multivariate Time Series](https://mlsanity.com/paper/1901.10738/) (2019)
- [TimeNet: Pre-trained deep recurrent neural network for time series classification](https://mlsanity.com/paper/1706.08838/) (2017)
- [TILES-2018, a longitudinal physiologic and behavioral data set of hospital workers](https://mlsanity.com/paper/2003.08474/) (2020)
- [Having a Bad Day? Detecting the Impact of Atypical Life Events Using Wearable Sensors](https://mlsanity.com/paper/2008.01723/) (2020)
- [Characterizing Activity on the Deep and Dark Web](https://mlsanity.com/paper/1903.00156/) (2019)
- [Learning Behavioral Representations from Wearable Sensors](https://mlsanity.com/paper/1911.06959/) (2019)

## Built on by (most cited first, 1 of 1)

- [ECG-Byte: A Tokenizer for End-to-End Generative Electrocardiogram Language Modeling](https://mlsanity.com/paper/2412.14373/) (2024)

## Abstract (arXiv)

The growing popularity of wearable sensors has generated large quantities of temporal physiological and activity data. Ability to analyze this data offers new opportunities for real-time health monitoring and forecasting. However, temporal physiological data presents many analytic challenges: the data is noisy, contains many missing values, and each series has a different length. Most methods proposed for time series analysis and classification do not handle datasets with these characteristics nor do they offer interpretability and explainability, a critical requirement in the health domain. We propose an unsupervised method for learning representations of time series based on common patterns identified within them. The patterns are, interpretable, variable in length, and extracted using Byte Pair Encoding compression technique. In this way the method can capture both long-term and short-term dependencies present in the data. We show that this method applies to both univariate and multivariate time series and beats state-of-the-art approaches on a real world dataset collected from wearable sensors.