Honours and Minor Thesis projects

In situ analysis of complex biochemical metrices, such as microbial fermentation products, has drawn substantial research interests in recent years. Compared to the commonly used chemical analysis technique, spectroscopic analysis has great potential for this purpose due to its advantages of being rapid, contactless, lossless, and solvent-free. The major obstacle for the further application of the spectroscopic technique in the analysis of biochemical samples is the lack of customized data mining methods for the highly complicated spectral signal of the organic mixtures.

Machine learning models have significantly improved the ability of autonomous systems to solve challenging tasks, such as image recognition, speech recognition and natural language processing. The rapid deployment of such models in safety critical systems resulted in an increased interest in the development of machine learning models that are robust and interpretable. 

Machine learning (ML) training and evaluation usually involve large-scale datasets and complicated computation. To process data efficiently, a promising solution is to outsource the processes to cloud platforms. However, traditional approaches of collecting users' data at cloud platforms are vulnerable to data breaches.

Using relevant available data-sets, we compare appliance usage across households of different demographics.  We then use machine learning techniques to infer how different households use different appliances at different times, resulting in diverse energy consumption behaviours. 

In Heuristic Search we tackle sequential decision-making problems (i.e., planning problems).  A simple case of a search problem is the shortest path problem - given a network (e.g., of roads) and a starting point and a goal or destination, the shortest path problem is to find the shortest path from the start to the goal.

Climate change will affect us all, and we have to do everything we can to minimize the magnitude of change. Investments in renewable generation help to reduce the impact of energy usage on the supply side, but that will not get us all the way there, especially in the near term. Consumers will also have to become much more efficient with their energy use.

Thanks to the widespread deployment of smart meters, high volumes of residential load data have been collected and made available to both consumers and utility companies. Smart meter data open up tremendous opportunities, and various analytical techniques have been developed to analyse smart meter data using machine learning. This project will provide a new angle toward energy data analytics and aims to discover the consumption patterns, lifestyle, and behavioural changes of consumers.

Behavioural manifestations of epileptic seizures (ESs) and certain non-epileptic seizures (psychogenic non-epileptic seizures, or PNESs) have considerable overlap, and so discerning between these solely based on clinical criteria is difficult.  Video EEG (electroencephalogram) monitoring (VEM) has high resource demands and is also expensive.  We endeavour to classify seizures based on non-invasive measures.

Low-code / no-code (LC) development platforms enable the creation of software apps with little to no need for in-depth programming skills. The platforms are often based on visual editors and target professional software developers and domain experts / citizen developers alike.

The world’s energy markets are transforming, and more renewable energy is integrated into the electric energy market. The intermittent renewable supply leads to unexpected demand-supply mismatches and results in highly fluctuating energy prices. Energy arbitrage aims to strategically operate energy devices to leverage the temporal price spread to smooth out the price differences in the market, which also generates some revenue.