• Skip to primary navigation
  • Skip to main content
  • Skip to footer
  • Career
  • Alumni
  • Employers
  • News

Fung Institute for Engineering LeadershipFung Institute for Engineering LeadershipFung Institute for Engineering Leadership

  • Master of Engineering
    • Master of Engineering Program
      • Engineering Departments
      • Program Design
      • Leadership Development
      • Capstone Experience
      • Career Development
      • Learn More
      • How to Apply
  • Fung Fellowship
    • Fung Fellowship

      The Fung Fellowship is shaping a new generation of entrepreneurial leaders focused on transforming health and wellness.

      • Program Overview
    • The Fung Fellowship
    • Executive & Professional Education
  • Partners
    • Partners
    • Become a Partner
    • Propose a Project
    • Recruit a Student
  • Apply
  • About
  • Career
  • Alumni
  • News
Personalizing Neurological Patient’s Gait Therapy Using Machine-Learning-Based Electrical Stimulation

[Evolution Devices] Personalizing Neurological Patient’s Gait Therapy Using Machine-Learning-Based Electrical Stimulation

November 13, 2020 by

Team: George Durrant (BIOE), Elie Celnikier (BIOE), Rongbo Zhou (ME)

Advisors: Pierre Karashchuk (Evolution Devices), Aashyk Mohaiteen (Evolution Devices), Gabriel Gomes (ME)

Neurological damage such as stroke, multiple sclerosis, and spinal cord injury cause walking impairments. The EvoCode team is improving the EvoWalk, a medical device developed by Evolution Devices, which corrects abnormal gait patterns of patients by electrically stimulating lower-limb muscles. The team aims to use machine learning techniques such as clustering and neural networks to allow the EvoWalk to analyze the kinematics of patients’ gait patterns. Then the device determines each individual’s gait pattern, and provides a personalized stimulation algorithm that most efficiently improves their walking outcome.

Neurological conditions reduce mobility

Over 33 million adults in the US suffer from a walking disability, with diseases such as stroke, multiples clerosis, and traumatic brain injury. Many victims need to use assistive devices to ever walk again, greatly reducing quality of life. Physicians characterize common mobility issues such as foot drop by how these issues affect the gait cycle, such as swinging legs and dragging feet.

Classifying gait abnormalities from an IMU

By inputting kinematic data into a neural network, we can classify a patient’s gait using the Inertial Measurement Unit (IMU) on the EvoWalk device. We feed raw data from the IMU into a neural network to predict a gait pattern, verified by EvoVision and clinical standards. We can classify the gait pattern from a single IMU with 87% accuracy.

3D kinematic analysis with EvoVision

We must first find out what the gait abnormalities of patients are to improve them. So we look at 3D kinematic data to quantify the different gait patterns and abnormalities. A treadmill and camera setup uses neural networks to track 3D positions of joints during gait cycles. We use joint angle calculations and supervised learning techniques to classify kinematic data corresponding to gait abnormalities.

Personalizing electrical stimulation

After confirming a patient’s gait pattern, we can personalize stimulation, helping the patient to walk. We apply functional electrical stimulation to the anterior tibialis muscle to assist patients with foot-drop in lifting their foot. By combining the kinematic analysis and gait classifier we can adjust the stimulation precisely for each patient.

Project Brief


← View all Capstone Projects

Fung Institute For Engineering Leadership
Shires Hall
2451 Ridge Road Berkeley, CA 94709

Mudd Hall
1798 Scenic Avenue Berkeley, CA 94709

(510) 642-0633
funginstitute@berkeley.edu

Explore

  • Programs
  • Partners
  • Apply
  • Feedback
  • Job Opportunities

Experience

  • About
  • Career
  • Alumni
  • News
  • Donate

Connect

Copyright © 2023 Accessibility • Nondiscrimination • Privacy • Sitemap

berkeley_engineering

uc-berkeley

Copyright © 2023 Accessibility • Nondiscrimination • Privacy • Sitemap

berkeley_engineering

uc-berkeley

Prospective MEng Students

Sign up for our mailing list to receive program news and updates including information sessions, class visits and opportunities to connect with an admissions advisor.