Bringing in the outliers: A sparse subspace clustering approach to learn a dictionary of mouse ultrasonic vocalizations

TL;DR

This paper introduces a spectral clustering method that effectively handles outliers to automatically generate a dictionary of mouse ultrasonic vocalizations, improving analysis accuracy over traditional methods.

Contribution

A novel two-step spectral clustering approach that separates inliers and outliers for better dictionary learning of ultrasonic vocalizations.

Findings

Outperforms k-means and spectral clustering baselines

Produces more distinct and variable clusters

Effective in handling outliers without ground truth

Abstract

Mice vocalize in the ultrasonic range during social interactions. These vocalizations are used in neuroscience and clinical studies to tap into complex behaviors and states. The analysis of these ultrasonic vocalizations (USVs) has been traditionally a manual process, which is prone to errors and human bias, and is not scalable to large scale analysis. We propose a new method to automatically create a dictionary of USVs based on a two-step spectral clustering approach, where we split the set of USVs into inlier and outlier data sets. This approach is motivated by the known degrading performance of sparse subspace clustering with outliers. We apply spectral clustering to the inlier data set and later find the clusters for the outliers. We propose quantitative and qualitative performance measures to evaluate our method in this setting, where there is no ground truth. Our approach outperforms two baselines based on k-means and spectral clustering in all of the proposed performance measures, showing greater distances between clusters and more variability between clusters.