Scholarship: £13,590.00 PA for 3 years
Funder: Vice Chancellor Research Scholarship
Role: PhD Student
Supervisors: Professor Girijesh Prasad and Dr Hubert Cecotti
Non-stationary learning (NSL) refers to the process that can learn rules from data, adapt to shifts, and improve performance of the system with its experience while operating in the non-stationary environments (NSEs). While processing in NSEs, a covariate shift is a major challenge wherein the input-data distribution may shift during transitioning from training to testing phase. Covariate shift is one of the fundamental challenges in electroencephalogram (EEG) based brain-computer interface (BCI) systems and these can be often found during multiple trials over different sessions of EEG data recording. Due to these covariate shifts, low performance in terms of classification accuracy has been a confounding factor of conventional BCI systems for motor imagery detection.
This research proposes three different steps to designing a novel framework of adaptive learning for modelling non-stationary systems. Firstly, a covariate shift detection (CSD) test has been designed based on an exponentially weighted moving average (EWMA) control chart. The CSD test is a fully data-driven method, and it does not require any assumption on the data distribution to detect the covariate shift. Secondly, transductive-inductive learning based covariate shift adaptation (CSA) algorithms have been proposed, which are based on active and passive learning approaches. To estimate the effectiveness of the proposed adaptive algorithms, extensive experiments have been performed on both the toy and EEG datasets. The proposed methods are benchmarked against the state-of-the-art methods. In this way, the resulting system utilises unlabelled data for both the CSD and classifier adaptation purposes, and correspondingly implements motor imagery related classification of single-trial EEG. Lastly, an online active learning algorithm has been proposed for the covariate shift adaptation in EEG signals for the neuro-rehabilitation systems. The developed online BCI paradigm has been tested on 15 healthy subjects. The results for the active learning algorithm has shown a statistically significant improvement over the non-adaptive system. The research contributions collectively provide an efficient method for accounting non-stationarity in data during learning in NSEs.