Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 14, 2026

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

Segmenting human motion for automated rehabilitation exercise analysis.

Jonathan Feng-Shun Lin¹, Dana Kulić

¹Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, N2L 3G1, Canada. jf2lin@uwaterloo.ca

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference

|February 1, 2013

Summary

This study introduces automated human movement analysis using velocity and Hidden Markov models for precise segmentation of motion data. This method achieves 89% accuracy, aiding real-time feedback in rehabilitation.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Making Sense of Shoulder Exercise: Measuring the Accuracy of an Artificial Intelligence Model to Classify Shoulder Exercise via Wearable Sensors Among People With and Without Rotator Cuff Tendinopathy.

European journal of sport science·2026

Same author

Multi-step first: A lightweight deep reinforcement learning strategy for robust continuous control with partial observability.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

PCNet: Accurate Surgical Workflow Recognition with Phase Consistency.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025

Same author

A biomechanics and energetics dataset of neurotypical adults walking with and without kinematic constraints.

Scientific data·2024

Same author

Experimental evaluation of accuracy and efficiency of two control strategies for a novel foot commanded robotic laparoscope holders with surgeons.

Scientific reports·2024

Same author

Adaptive auditory assistance for stride length cadence modification in older adults and people with Parkinson's.

Frontiers in physiology·2024

Area of Science:

Biomechanics and Human Movement Analysis
Signal Processing and Machine Learning

Background:

Continuous time series data from human movement, captured via motion capture and ambulatory sensors, presents challenges in automated segmentation and identification.
Accurate analysis of human movement is crucial for applications like physical rehabilitation and performance monitoring.

Purpose of the Study:

To develop and validate an automated approach for segmenting and identifying distinct movement patterns from continuous human motion data.
To enable real-time analysis for interactive feedback systems in clinical and research settings.

Main Methods:

A two-stage process involving velocity feature extraction (peaks, zero crossings) for candidate identification.
Application of Hidden Markov Models (HMMs) for accurate localization and classification of movement segments.

More Related Videos

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

Related Experiment Videos

Last Updated: May 14, 2026

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

On-line processing capability for immediate analysis and feedback.

Main Results:

The proposed approach successfully segments and identifies human movement segments from time series data.
Achieved a high segmentation accuracy of 89% on a rehabilitation movement dataset.
Demonstrated capability for on-line processing, suitable for interactive applications.

Conclusions:

The automated two-stage approach effectively segments human movement data with high accuracy.
The method's on-line capability supports interactive feedback systems, particularly in rehabilitation.
This technique offers a robust solution for analyzing complex human motion patterns from sensor data.