Topic Modeling of Behavioral Modes Using Sensor Data

TL;DR

This paper introduces an unsupervised topic modeling approach using matrix factorization to analyze accelerometer data from bio-loggers, enabling identification of animal behavioral modes without labeled datasets.

Contribution

The authors propose a novel matrix factorization-based topic model for accelerometer data, addressing the challenge of unsupervised behavioral mode detection in movement ecology.

Findings

Validated method against labeled datasets

Compared favorably to standard clustering algorithms

Effective in identifying behavioral modes from sensor data

Abstract

The field of Movement Ecology, like so many other fields, is experiencing a period of rapid growth in availability of data. As the volume rises, traditional methods are giving way to machine learning and data science, which are playing an increasingly large part it turning this data into science-driving insights. One rich and interesting source is the bio-logger. These small electronic wearable devices are attached to animals free to roam in their natural habitats, and report back readings from multiple sensors, including GPS and accelerometer bursts. A common use of accelerometer data is for supervised learning of behavioral modes. However, we need unsupervised analysis tools as well, in order to overcome the inherent difficulties of obtaining a labeled dataset, which in some cases is either infeasible or does not successfully encompass the full repertoire of behavioral modes of interest. Here we present a matrix factorization based topic-model method for accelerometer bursts, derived using a linear mixture property of patch features. Our method is validated via comparison to a labeled dataset, and is further compared to standard clustering algorithms.