Hand Gesture Recognition for Sign Language
My undergraduate Final Year Project awarded as the Excellent Bachelor’s Project. It develops a vision-based sign language recognition system with multiple machine-learning models, which currently can recognize 10 static and 2 dynamic gesutures in ASL with testing accuracy of 99.68%.
Intelligent Multi-function Rover
The designed Rover won the 2nd Prize in the Glasgow College Robot Design Competition
[Python Package] Permutation Feature-based Frequency Response Analysis
PFFRA is an Interpretable Machine Learning technique to analyse the contribution of features in the frequency domain. This method is inspired by permutation feature importance analysis but aims to quantify and analyse the time-series predictive model’s mechanism from a global perspective.
Many-to-Many Data Trading Algorithm Based on Double Auction Theory
In this project, we propose the Many-to-Many Data Trading Algorithm (MMDTA), and then formulate a data trading model with multiple entities based on MMDTA. Simulations validate convergence behavior and economic properties of MMDTA which is effective in dierent market scales and with dierent market power.
Data analysis and interpretable machine learning for HVAC predictive control
this paper reports on a case study with a two-fold aim; first, to analyze the performance of a conventional HVAC system through data analytics; secondly, to explore the use of interpretable machine learning techniques for HVAC predictive control. A new Interpretable Machine Learning (IML) algorithm called Permutation Feature-based Frequency Response Analysis (PF-FRA) is also proposed. Results demonstrate that the proposed model can generate accurate forecasts of Room Temperature (RT) levels by taking into account historical RT information, as well as additional environmental and time-series features.
J. Mao's Tech House 