Quantifying the Chaos Level of Infants' Environment via Unsupervised Learning

TL;DR

This paper introduces unsupervised machine learning methods to objectively quantify the level of chaos in infants' home environments, which can impact their cognitive development.

Contribution

It applies hierarchical clustering, SOM, and deep learning to measure household chaos, providing a novel quantitative approach to an otherwise subjective assessment.

Findings

Techniques successfully differentiate levels of household chaos.

Unsupervised methods show promise for objective chaos measurement.

Analysis of 197 hours of data from 9 homes supports feasibility.

Abstract

Acoustic environments vary dramatically within the home setting. They can be a source of comfort and tranquility or chaos that can lead to less optimal cognitive development in children. Research to date has only subjectively measured household chaos. In this work, we use three unsupervised machine learning techniques to quantify household chaos in infants' homes. These unsupervised techniques include hierarchical clustering using K-Means, clustering using self-organizing map (SOM) and deep learning. We evaluated these techniques using data from 9 participants which is a total of 197 hours. Results show that these techniques are promising to quantify household chaos.