Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Cost-effective, Stand-alone, and Real-time TinyML-Based Gait Diagnosis Unit Aimed at Lower-limb Robotic Prostheses and Exoskeletons

Zarin Anjum Madhiha, Antar Mazumder, Sohani Munteha Hiam

TL;DR

The developed wearable gait diagnosis stand-alone unit could be fitted to any prosthesis or exoskeleton and could effectively classify the gait scenarios with an overall accuracy of 92% and provide anomaly scores within 95-96 ms with only 3 seconds of gait data in real-time.

Abstract

Robotic prostheses and exoskeletons can do wonders compared to their non-robotic counterpart. However, in a cost-soaring world where 1 in every 10 patients has access to normal medical prostheses, access to advanced ones is, unfortunately, extremely limited especially due to their high cost, a significant portion of which is contributed to by the diagnosis and controlling units. However, affordability is often not a major concern for developing such devices as with cost reduction, performance is also found to be deducted due to the cost vs. performance trade-off. Considering the gravity of such circumstances, the goal of this research was to propose an affordable wearable real-time gait diagnosis unit (GDU) aimed at robotic prostheses and exoskeletons. As a proof of concept, it has also developed the GDU prototype which leveraged TinyML to run two parallel quantized int8 models into an ESP32 NodeMCU development board (7.30 USD) to effectively classify five gait scenarios (idle, walk, run, hopping, and skip) and generate an anomaly score based on acceleration data received from two attached IMUs. The developed wearable gait diagnosis stand-alone unit could be fitted to any prosthesis or exoskeleton and could effectively classify the gait scenarios with an overall accuracy of 92% and provide anomaly scores within 95-96 ms with only 3 seconds of gait data in real-time.

A Cost-effective, Stand-alone, and Real-time TinyML-Based Gait Diagnosis Unit Aimed at Lower-limb Robotic Prostheses and Exoskeletons

TL;DR

The developed wearable gait diagnosis stand-alone unit could be fitted to any prosthesis or exoskeleton and could effectively classify the gait scenarios with an overall accuracy of 92% and provide anomaly scores within 95-96 ms with only 3 seconds of gait data in real-time.

Abstract

Robotic prostheses and exoskeletons can do wonders compared to their non-robotic counterpart. However, in a cost-soaring world where 1 in every 10 patients has access to normal medical prostheses, access to advanced ones is, unfortunately, extremely limited especially due to their high cost, a significant portion of which is contributed to by the diagnosis and controlling units. However, affordability is often not a major concern for developing such devices as with cost reduction, performance is also found to be deducted due to the cost vs. performance trade-off. Considering the gravity of such circumstances, the goal of this research was to propose an affordable wearable real-time gait diagnosis unit (GDU) aimed at robotic prostheses and exoskeletons. As a proof of concept, it has also developed the GDU prototype which leveraged TinyML to run two parallel quantized int8 models into an ESP32 NodeMCU development board (7.30 USD) to effectively classify five gait scenarios (idle, walk, run, hopping, and skip) and generate an anomaly score based on acceleration data received from two attached IMUs. The developed wearable gait diagnosis stand-alone unit could be fitted to any prosthesis or exoskeleton and could effectively classify the gait scenarios with an overall accuracy of 92% and provide anomaly scores within 95-96 ms with only 3 seconds of gait data in real-time.

Paper Structure

This paper contains 13 sections, 14 equations, 8 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Methodology
  4. Development of GDU
  5. Data Collection and Preprocessing
  6. Model Architecture
  7. Deployment in Real-time Gait Diagnosis
  8. Results
  9. Performance Metrics
  10. Cost vs Performance Trade-off Comparison with Related Approaches
  11. Latency Analysis
  12. Discussion
  13. Conclusion

Figures (8)

  • Figure 1: Disparity in accessibility to prostheses and assistive devices: Demand vs. Access and the major catalyst.
  • Figure 2: Disparity in research focus: Robotic Prostheses vs. Affordable Robotic Prostheses based on the yearly number of publications.
  • Figure 3: The GDU physical form and schematics and raw acceleration data from A1 and A2 for the five gait scenarios considered.
  • Figure 4: Gait data preprocessing and feature generation.
  • Figure 5: The parallel models leverage ANN to classify gait scenarios and K-means clustering to throw an anomaly score.
  • ...and 3 more figures