<link rel="stylesheet" href="styles.cf390c6bfbe7555f.css">
⚠️ Scheduled Maintenance: Tuwhera Open Repository When: Wednesday, November 18 | 8:00 AM – 8:15 AM Impact: Service temporarily offline for server migration Please schedule any thesis deposits or resource downloads outside of this window. Thank you for your patience.
Repository logo

Smart Fitness Solutions: An Edge-Computing Approach for Biometric Monitoring and Real-Time Muscle Fatigue Detection

Loading...
Thumbnail Image

Files

Size: 1.59 MB, File format: Adobe PDF

Authors

El Ghazouly, Mohamed Ahmed

Al-Hamid, Duaa Zuhair

Gadelmawla, Omar

GholamHosseini, Hamid

Baig, Mirza Mansoor

Afifi, Shereen

Supervisor

Degree name

Journal Title

Journal ISSN

Volume Title

Publisher

MDPI AG

Abstract

Real-time monitoring of muscle fatigue could support safer strength training, yet most wearable systems depend on cloud processing, which adds latency and exposes physiological data. This work presents and evaluates an edge-based prototype for biometric monitoring during biceps curls. A wearable node integrating a nine-axis IMU (MPU-9250) and a photoplethysmography heart-rate sensor (MAX30102) streams data from an ESP32 microcontroller over UDP to a Raspberry Pi 5, which performs feature scaling and inference with a compact feedforward neural network (two hidden layers of 64 and 32 units) trained on a publicly available biceps-curl dataset. The classifier takes a 10-element feature vector of IMU, heart-rate and acceleration-derived inputs and outputs three fatigue levels. Under leave-one-subject-out cross-validation on ten participants, the three-class classifier attained a mean accuracy of 0.77 (SD 0.25; 95% CI 0.59–0.95), with a strongly bimodal per-subject distribution (0.40–0.98). Deployed on the edge node and evaluated end-to-end over 5172 annotated windows under a binary no fatigue versus fatigue formulation, the model recovered 91% of non-fatigued but only 10% of fatigued windows (balanced accuracy 0.51, Matthews correlation 0.02), which is no better than chance and below a majority-class baseline. In its current form the classifier is therefore not a reliable fatigue detector; we analyse candidate causes, including training-side class skew and differences between the source-dataset and deployment sensors, and compare them against majority-class and chance reference points. On the systems side, the pipeline runs fully locally with 10 ms model inference per sample, 42 ms gateway processing and a mean wireless round-trip time of 180 ms after rate-limiting the link. The implemented physical, communication and edge-inference layers are designed as the sensing foundation for a future Digital Twin, which is not implemented in this work.

Description

Keywords

4605 Data Management and Data Science, 46 Information and Computing Sciences, Bioengineering, muscle fatigue detection, edge computing, wearable sensors, IMU, feedforward neural network, real-time inference, Raspberry Pi, ESP32, IoT, class imbalance

Source

Future Internet, ISSN: 1999-5903 (Print); 1999-5903 (Online), MDPI AG, 18(11), 609-609. doi: 10.3390/fi18110609

Rights statement

© 2026 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article.

Endorsement

Review

Supplemented By

Referenced By

Creative Commons license

Except where otherwise noted, this item's license is described as Creative Commons Attribution (CC BY) license