Short-time, Wavelet-inspired Mouse Submovement Detection

2026-04-22

AI Summary

This study addresses the challenge of detecting and parameterizing overlapping, continuous submovements within one-dimensional mouse velocity time series. The authors propose a wavelet-inspired time–frequency analysis method augmented with a self-weighted loss function to optimize the fitting process. By dynamically adjusting loss weights during optimization, the approach substantially enhances submovement resolution in regions where conventional fitting quality is poor, thereby overcoming key limitations of standard wavelet transforms. Experimental evaluation on approximately 6,400 synthetic first-person aiming trajectories demonstrates that the proposed method significantly outperforms baseline techniques—including the dual-threshold method and Persistence1D—in both submovement localization accuracy and parameter estimation fidelity.

Technology Category

• Computer Vision: Motion & Tracking
• Search and Optimization: Mixed Discrete/Continuous Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

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.

Problem

• submovements
• motion segmentation
• overlapping movements
• speed time series
• motor interaction

Innovation

• submovement detection
• wavelet-inspired method
• self-weighted loss refinement
• motion segmentation
• egocentric aiming data