Research projects in Information Technology

Nowadays more and more intelligence software solutions emerge in our daily life, for example the face recognition, smart voice assitants, and autonomous vehicle. As a type of data-driven solutions, intelligent components learn their decision logic from data corpus in an end-to-end manner and act as a black box. Without rigorous validation and verification, intelligent solutions are error-prone especially when deployed in the real world environment. To monitor, identify, mitigate and fix these defects becomes extremely important to ensure their service quality and user experience.

Critical work to the future of healthcare ... exploring the role of #FHIR in interoperability and #datascience

Also allowing exploration and usage of the #SMART on #FHIR software paradigm 

Involves working with various real world health services and health IT partners 

#digitalhealth #health #EMR #hospital #software

With success stories ranging from speech recognition to self-driving cars, machine learning (ML) has been one of the most impactful areas of computer science. ML’s versatility stems from the wealth of techniques it offers, making ML seem an excellent tool for any task that involves building a model from data. Nevertheless, ML makes an implicit overarching assumption that severely limits its applicability to a broad class of critical domains: the data owner is willing to disclose the data to the model builder/holder.

Identifying vulnerabilities in real-world applications is challenging. Currently, static analysis tools are concerned with false positives; runtime detection tools are free of false positives but inefficient to achieve a full spectrum examination. A generic, scalable and effective vulnerability detection platform, taking advantage of both static and dynamic techniques, is desirable. To further overcome the shortcomings of these techniques, deep learning is more and more involved in static vulnerability localization and improving fuzzing efficiency.

Over the past decades, we have witnessed the emergence and rapid development of deep learning. DL has been successfully deployed in many real-life applications, including face recognition, automatic speech recognition, and autonomous driving, etc. However, due to the intrinsic vulnerability and the lack of rigorous verification, DL systems suffer from quality and security issues, such as the Alexa/Siri manipulation and the autonomous car accidents. Developing secure and trustworthy DL systems is challenging, especially given the limited time budget.

Machine learning is being used to make important decisions affecting people's lives, such as filter loan applicants, deploy police officers, and inform bail and parole decisions, among other things. Machine learning has been found to introduce and perpetuate discriminatory practices by unintentionally encoding existing human biases and introducing new ones. In this project, we will develop automated testing approaches that can be used to verify that machine learning models are not biased. 

Modern map-based systems and location-based services rely heavily on the ability to efficiently provide navigation services and the capability to search points of interests (POIs) based on their location or textual information. The aim of this project is to build a next-generation navigation system by addressing limitations in the current systems – such as allowing more meaningful distance measures, modeling uncertainty in data sources and queries, and exploiting rich information from several data sources.

On their own, traffic accidents cause 1.3 million fatalities every year – and improper situational awareness is often a major cause. This project aims to exploit big spatio-temporal data to design intelligent techniques for scheduling and offloading tasks to the cloud and peer vehicles. This will ultimately meet the Quality of Service (QoS) requirements of time-critical road safety applications and increase situational awareness by automatically identifying unsafe road conditions and risky driving behaviors – and sending alerts in real time to affected vehicles.

This project aims to harness big data from ubiquitous smartphone sensors to reduce the impact of road transport on the environment. Specifically, we’ll design novel data modelling and indexing techniques to exploit the data and create a next-generation, eco-friendly navigation system which will significantly reduce greenhouse gas emissions and result in fuel saving. The initiative also aims to study the citywide impact of adapting to eco-friendly navigation on traffic, environment and road safety – therefore supporting urban planning and decision-making.

This project heavily focuses on maps (e.g. GoogleMaps or Open Street Map). We will explore various properties of road networks, including the granularity of road networks, routes and trajectories on road networks, and query processing on road networks. 

A number of inter-disciplinary collaboration exists, including transportation to hospitals, urban sprawl analysis, and geospatial in sustainability (e.g. analysing placement of rubbish bins on streets).