# Temporally aligned segmentation and clustering (TASC) framework for behavior time series analysis

## TL;DR

The TASC framework improves the analysis of behavior time series by accurately segmenting and clustering complex spatiotemporal behavior data.

## Contribution

A novel iterative framework for time series analysis that combines temporal alignment with segmentation and clustering.

## Key findings

- TASC demonstrates enhanced segmentation and clustering of behavior motifs in both synthetic and real-world data.
- The alternating-step process improves precision in identifying non-overlapping behavior segments.
- The framework is generalizable and can be applied to other domains requiring high-precision time series analysis.

## Abstract

Behavior exhibits a complex spatiotemporal structure consisting of discrete sub-behaviors, or motifs. Continuous behavior data requires segmentation and clustering to reveal these embedded motifs. The popularity of automatic behavior quantification is growing, but existing solutions are often tailored to specific needs and are not designed for the time scale and precision required in many experimental and clinical settings. Here we propose a generalized framework with an iterative approach to refine both segmentation and clustering. Temporally aligned segmentation and clustering (TASC) uses temporal linear alignment to compute distances between and align the recurring behavior motifs in a multidimensional time series, enabling precise segmentation and clustering. We introduce an alternating-step process: evaluation of temporal neighbors against current cluster centroids using linear alignment, alternating with selecting the best non-overlapping segments and their subsequent re-clustering. The framework is evaluated on semi-synthetic and real-world experimental and clinical data, demonstrating enhanced segmentation and clustering, offering a better foundation for consequent research. The framework may be used to extend existing tools in the field of behavior research and may be applied to other domains requiring high precision of time series segmentation.