Short-time, Wavelet-inspired Mouse Submovement Detection

TL;DR

This paper introduces a wavelet-inspired method for accurately detecting and analyzing submovements in human motion data, addressing challenges of overlapping movements and poor fit regions.

Contribution

The authors propose a novel wavelet-inspired technique with a self-weighted loss refinement for improved submovement detection from speed time series.

Findings

Method accurately locates submovements in synthetic and real data.

Compared to existing techniques, it offers improved fit quality and detection accuracy.

Demonstrates potential for analyzing complex human motion patterns.

Abstract

Submovements are ballistic components of human motion constituting a large part of motor interaction and arising from the cyclical and overlapping cognitive processes of perception, motor planning, and motor execution. Extracting submovements is challenging as the motions tend to overlap, or start before the previous ends. We propose and evaluate use of a wavelet-inspired technique to accurately locate and parameterize submovements from one-dimensional speed time series. Our method employs a self-weighted loss refinement step to identify and improve regions of poor quality of fit, a challenge for simpler wavelet transforms. We demonstrate the accuracy of our method by presenting analysis of ~6,400 1-2s trials of synthetic egocentric camera (first-person shooter) aim data for which we know ground truth, modeled from a similarly sized real data set of 13 users. We compare our method to dual-threshold and the persistence 1D segmentation techniques and note challenges and opportunities for future improvements.