Gait Recognition Based on Tiny ML and IMU Sensors

This project presents the development of a gait recognition system using Tiny Machine Learning (Tiny ML) and Inertial Measurement Unit (IMU) sensors. The system leverages the XIAO-nRF52840 Sense microcontroller and the LSM6DS3 IMU sensor to capture motion data, including acceleration and angular velocity, from four distinct activities: walking, stationary, going upstairs, and going downstairs. The data collected is processed through Edge Impulse, an edge AI platform, which enables the training of machine learning models that can be deployed directly onto the microcontroller for real-time activity classification.The data preprocessing step involves extracting relevant features from the raw sensor data using techniques such as sliding windows and data normalization, followed by training a Deep Neural Network (DNN) classifier for activity recognition. The model achieves over 80% accuracy on a test dataset, demonstrating its ability to classify the four activities effectively. Additionally, the platform enables anomaly detection, further enhancing the robustness of the system. The integration of Tiny ML ensures low-power operation, making it suitable for battery-powered or energy-harvesting devices.

Design of a Noval Wearable ECG Monitoring Device

The aim of this project is to develop a new wireless powered wearable ECG monitoring device. The main goal of the project is to provide a wireless, small-sized ECG monitoring device that can be worn for a long period of time by the monitored person. Electrocardiogram ECG reflects physiological and pathological information about heart activity and is commonly used to diagnose heart disease. Existing wearable smart ECG solutions suffer from high power consumption in both ECG diagnosis and transmission for high accuracy. Monitoring of ECG devices is mainly done by data extraction and acquisition, pre-processing, feature extraction, processing and analysis, visualisation and auxiliary procedures. During the pre-processing of the information, different kinds of noise generated during the signal collection need to be taken into account. The quality of the signal-to-noise ratio can usually be improved by optimising algorithms and reducing the noise power. The choice of electrodes usually has a direct impact on the signal-to-noise ratio and the user experience, and conventional Ag/AgCl gel electrodes are not suitable for long-term and dynamic monitoring as they are prone to skin irritation, inflammation and allergic reactions. Therefore, a completely new way of combining electrodes and wires will be used in the report. The electrodes and wires are cut in one piece from a silver-plated fabric. The wire portion is cut into a curved structure close to an S shape to ensure that it has good ductility for comfort and signal integrity during daily movement of the garment.