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.
Category Archives: Project Records
Data analysis and interpretable machine learning for HVAC predictive control
Energy efficiency and thermal comfort levels are key attributes to be considered in the design and implementation of a Heating, Ventilation and Air Conditioning (HVAC) system. With the increased availability of Internet of Things (IoT) devices, it is now possible to continuously monitor multiple variables that influence a user’s thermal comfort and the system’s energyContinue reading “Data analysis and interpretable machine learning for HVAC predictive control”
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%. Project Abstract Majority of deaf-and-mute people use sign language produced by body actions such asContinue reading “Hand Gesture Recognition for Sign Language”
Intelligent Multi-function Rover
The designed Rover won the 2nd Prize in the Glasgow College Robot Design Competition See details here.
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 different market scales and with dierent market power. Check the following peer-reviewed papers for more detail:
J. Mao's Tech House 