Future Projects - Institute of Applied Data Analytics

Wave and Tide Prediction for Brunei Deep-Water Operation

Grant Details: UBD/RSCH/1.11/FICBF(b)/2020/004 Reliable and accurate predictions of deep-water wave conditions is crucial for any ocean engineering activities, for example, safe ship navigation, design of marine structures (like oil platforms and harbours), and design and management of marine energy systems as it has an impact on human safety, economics and clean energy production. Different empirical, numerical and soft-computing approaches have been proposed for wave height prediction. Wave conditions in regions where historical data is available and collected can be predicted using numerical and soft-computing methods. However, for new regions of interest, in this case Brunei sea, historical data of wave conditions is not available. Hence, there is a need for collecting and predicting the wave conditions data in Brunei sea. This project will employ advanced artificial intelligence (AI) algorithms and modelling methods to improve the accuracy of the wave conditions prediction.

Fuzzy and Evolutionary Algorithms for data clustering

Grant: UBD/RSCH/1.11/FICBF(b)/2019/001. In this project, we aim to develop an evolutionary algorithm which is capable of performing human activities analysis for an autonomous robot. (FOS/IADA/DS project) Research in developing novel fuzzy and/or evolutionary algorithms for data clustering (feature selection, metric learning, kernel-based approaches, constrained-based) or optimisation is also of interest.

1) Intelligent Modelling for Non-communicable diseases 2) Intelligent Modelling for Geoscience applications 3) Automatic Feature Extraction for Text Categorisation using unsupervised techniques

1) In this project, we plan to create a predictive model for determining risk of patients in non-communicable diseases such as cancer or cardiovascular diseases. (IHS/IADA/DS project) 2) Developing learning frameworks for decision-making support in geoscience problems such as prediction of TOC and other geochemical properties. (Geology/IADA/DS project) 3) In this project, we develop a novel unsupervised algorithm for extracting meaningful features to solve text categorisation problems.