Digital Technologies
Current Research
MIMIc: Multimodal Imitation Learning in MultI-Agent Environments
The aim of this project is to develop data-driven policy learning algorithms for multi-agent environments utilising multimodal data sources.
Intuitive learning: A new paradigm in AI for decision making in intelligent mobility
The aim of this project is to develop machine learning algorithms that can reason under uncertain situations that arise in driverless vehicles.
Trustworthiness and resilience of AI
This project aims to study the adaptation of software engineering techniques onto machine/deep learning systems to improve the safety and trustworthiness of machine learning models.
Privacy-preserving machine learning algorithms using lattice-based cryptography
This research aims to develop secure and scalable deep learning algorithms to perform data classification in encrypted domain.
Blockchain technology for trustworthy doping control data management
This research project aims to design and develop secure and private blockchain technology for doping control in sports.
HappierFeet
Disrupting the vicious cycle of healthcare decline in Diabetic Foot Ulceration through active prevention: The future of self-managed care
With a multidisciplinary research team, the HappierFeet project aims to address this significant and timely issue by co-designing, with patients, the self-managed use of smart shoe insoles.
Security and privacy analysis of mobile applications data traffic using deep learning techniques
This research aims to develop techniques to capture, analyse, and classify encrypted data traffic from smartphone applications.
Speech synthesis and recognition in robotic systems designed to help people
In this project, human-like natural speech synthesis, highly robust speech recognition, multimodal interaction, situation recognition, and complex dialogue management methods will be developed.
Multimodal data processing for learning analytics
The aim of this project is to take an analytical look into how the learners’ assessed performance is influenced by combinations of low-level detectable learner-related cues during the learning process, in order to inform instructional design processes and guide online learning system design adaptive to learners’ self-pace.
Anthropomorphistic digital agency’s human-related affection
This project aims to enrich the current understanding of how different humanlike characteristics and traits can be integrated into content presentation and impact the nonhuman agents and customer perception.
Self-construal and projection on brand image in digitalised advertising and customer recommendation
This project seeks to use manipulated traceable platform to trace user click-stream data and eye-tracking data on the simulated web contents of various user occasions such as e-commerce, virtual service, experiential entertainment (game playing), and information website.
Machine learning for asset pricing in digital finance
This project aims to use machine learning to improve the prediction accuracy of asset pricing in the context of digital finance.
Distributed Learning in wireless networks
The aim of this project is to develop new distributed learning architectures for training machine learning models in a distributed manner over wireless communications with naturally distributed dataset collected by the mobile users.