External Research Grants

Control-Flow Integrity (CFI) enforcement is a promising technique in producing trustworthy software. This project focuses on function signature recovery, which is a critical step in CFI enforcement when source code is not available. Current approaches rely on the assumption of matching function signatures at caller and callee sites in an executable; however, various compiler optimisations violate well-known calling conventions and result in unmatched function signatures recovered. The project aims to design and implement an automatic system to produce CFI-enforced program executables.

Artificial Intelligence (AI) technologies have been under rapid development thanks to machine learning based on deep neural networks and their applications. Despite the exceptional performance of deep neural networks, these complex models are often beyond human understanding and thus work in a black-box manner. The research aims to address the problem of explaining AI for AI system designers and expert AI system users who are required to know how AI makes decisions.

This project aims to provide secure remote access control over identity information of Internet-of-Things (IoT) devices to prevent sensitive information from being stolen.

The research team will work with Singapore Chemical Industry Council (SCIC) on SCIC’s strategy creation. The objectives of the study are to:

• Solicit views on what SCIC’s member organizations consider as their important opportunities and threats in the next five years;
• Solicit views on what SCIC’s member organizations consider as SCIC’s roles in the next five years, beyond what SCIC has been doing;
• Highlight prevalent views from SCIC’s member organizations on SCIC’s roles in the next five years, with special notice on what they perceive as opportunities and threats; and
• Distil action items for SCIC based on views from its member organisations.

Software development today relies on Application Programming Interfaces (APIs), and identifying suitable APIs to use can directly influence the success or failure of a software development project. While a large number of third-party APIs are available on the internet, selecting suitable APIs for a project can be challenging. This research proposes a big-data, deep-learning, and exploratory-search approach for API recommendation called DeepSense to improve software developers’ productivity, and the success of this project will benefit the software engineering and artificial intelligence research community, software developers, and institutions developing IT solutions.

This research aims to explore ways in which employees who are low on positional power in an organisation can speak up or act when they witness moral transgressions in the workplace. One way to do so is by increasing employees’ personal power by increasing (a) others’ liking towards them, (b) others’ dependence on them, and (c) their centrality in formal and informal networks in the organisation. The research team will conduct both surveys and experimental studies in multiple countries to test their proposed model.

This project aims to show how an innovative multiple speed assessment approach permits more comprehensively assessing a key 21st century skill such as adaptability, and demonstrate that multiple speed assessment has added value over prior adaptability measurement approaches.

The project targets to improve the operational efficiency and medical decision outcomes in the intensive care units (ICUs) by leveraging healthcare data collected in the ICUs and advance data analytics techniques. The team aims to first focus on the extubation decision by extending existing predictive models that only predict the current risk of extubation failure to also predict the risk of extubation failure in the failure. Next, the team will develop a new decision-making framework that provides comprehensive decision support for extubation utilizing the predictive information to generate better early extubation recommendation for individual patients. Lastly, the team will investigate the other ICU applications (RRT and ICU discharge) to test and validate the generalizability of the methodologies developed.

Understanding what consumers want in experiential products and services is a fundamental challenge for businesses catering to the emerging ‘experience economy’. The proposed research aims to use state-of-the-art artificial intelligence (AI) and language processing methods to develop a novel method for assessing consumer preferences for experiential products and services. The proposed method will address current challenges to existing market research methods in measuring consumer preferences for experiential products and services. Our approach will enable closed-loop, real-time analytics for Singapore-based businesses in the entertainment, hospitality, and tourism industries, and beyond.

This research project aims to find out how thermal environment impacts the effectiveness of environmental/educational message retention by guests visiting current parks in the Mandai district – Singapore Zoo, Night Safari, River Safari, and will allow the research team to formulate suggestions that will help inform how and where educational messages can be deployed for maximum effectiveness within the new features of the Mandai project.