Skip to main content

Research Repository

Advanced Search

All Outputs (2319)

Heterogeneous Mutual Knowledge Distillation for Wearable Human Activity Recognition (2025)
Journal Article
Xiao, Z., Xing, H., Qu, R., Li, H., Cheng, X., Xu, L., Feng, L., & Wan, Q. (2025). Heterogeneous Mutual Knowledge Distillation for Wearable Human Activity Recognition. IEEE Transactions on Neural Networks and Learning Systems, 1-15. https://doi.org/10.1109/tnnls.2025.3556317

Recently, numerous deep learning algorithms have addressed wearable human activity recognition (HAR), but they often struggle with efficient knowledge transfer to lightweight models for mobile devices. Knowledge distillation (KD) is a popular techniq... Read More about Heterogeneous Mutual Knowledge Distillation for Wearable Human Activity Recognition.

Playing with Telepresence Robots for Design Speculation (2025)
Presentation / Conference Contribution
Avila, J. M., Boudouraki, A., Cameron, H., Reyes Cruz, G., Spors, V., Turmo Vidal, L., Windlin, C., Elmimouni, H., Rode, J. A., & Read, J. C. (2025, July). Playing with Telepresence Robots for Design Speculation. Presented at ACM Designing Interactive Systems Conference (DIS) 2025, Funchal, Madeira, Portugal

This workshop explores how telepresence robots can be used for playful design speculation, leveraging their inherent asymmetries to create engaging and innovative experiences. By focusing on playfulness instead of purely utilitarian applications this... Read More about Playing with Telepresence Robots for Design Speculation.

Directed Perturbations for Efficient Learning of Surrogate Losses (2025)
Presentation / Conference Contribution
Cargan, T. R., Landa-Silva, D., & Triguero, I. (2025, June). Directed Perturbations for Efficient Learning of Surrogate Losses. Presented at International Joint Conference on Neural Networks (IJCNN 2025), Rome, Italy

Decision-Focused Learning (DFL) is a paradigm to learn neural network-based predictive models tailored to a specific optimisation problem. A key challenge for DFL methods lies in the non-differentiable nature of most optimisation problems. Recent sol... Read More about Directed Perturbations for Efficient Learning of Surrogate Losses.

Responsible and Adaptive Robots in Care Home Settings: An Implementation Framework Analysis of a Workshop with Public and Professionals (2025)
Journal Article
Boudouraki, A., Waheed, M., Mestre, R., Landowska, A., Georgara, A., Deshmukh, J., Singh, L., Abioye, A. O., Tan, N., Tuyen, V., Dong, Y., Ao, S., Price, D., Fischer, J., & Gomez Bergin, A. (in press). Responsible and Adaptive Robots in Care Home Settings: An Implementation Framework Analysis of a Workshop with Public and Professionals. Frontiers in Robotics and AI,

As populations grow, research looks to emerging adaptive technologies for the urgent challenge in providing suitable care for older adults. Drawing on implementation science, we conducted a holistic examination looking at broader, contextual factors... Read More about Responsible and Adaptive Robots in Care Home Settings: An Implementation Framework Analysis of a Workshop with Public and Professionals.

Applying cross-modal plasticity principles in auditory training applications (2025)
Journal Article
Huang, Q., Stawarz, K., Zhao, L., Yang, S., Xie, W., Song, F., & Liu, H. (2025). Applying cross-modal plasticity principles in auditory training applications. International Journal of Human-Computer Studies, 203, Article 103570. https://doi.org/10.1016/j.ijhcs.2025.103570

Research indicates that a significant number of individuals are in a suboptimal auditory health state, yet their auditory function can potentially be improved through auditory training. To raise awareness of auditory health issues, auditory training... Read More about Applying cross-modal plasticity principles in auditory training applications.

Neuromorphic Data Transformations for Sustainable VR Art Applications (2025)
Presentation / Conference Contribution
Shvets, A., & Trzepizur, A. (2025, June). Neuromorphic Data Transformations for Sustainable VR Art Applications. Paper presented at 10th International XR-Metaverse Conference 2025, Maastricht, Netherlands

A previously proposed method for adapting 2D digital audiovisual artwork to Virtual Reality (VR) environments utilized time-distributed data (TDD) generators derived from the neuromorphic computing domain. This research advances that approach by emph... Read More about Neuromorphic Data Transformations for Sustainable VR Art Applications.

Ordinal Exponentiation in Homotopy Type Theory (2025)
Presentation / Conference Contribution
de Jong, T., Kraus, N., Nordvall Forsberg, F., & Xu, C. (2025, June). Ordinal Exponentiation in Homotopy Type Theory. Presented at Fortieth Annual ACM/IEEE Symposium on Logic in Computer Science (LICS 2025), Singapore

We present two seemingly different definitions of constructive ordinal exponentiation, where an ordinal is taken to be a transitive, extensional, and wellfounded order on a set. The first definition is abstract, uses suprema of ordinals, and is solel... Read More about Ordinal Exponentiation in Homotopy Type Theory.

Towards Accessible Auditory Health: A Cloud-Based fNIRS Solution for Auditory Training and Assessment (2025)
Journal Article
Huang, Q., Liu, J., Li, Y., Zhao, L., Stawarz, K., & Liu, H. (2025). Towards Accessible Auditory Health: A Cloud-Based fNIRS Solution for Auditory Training and Assessment. IEEE Transactions on Instrumentation and Measurement, https://doi.org/10.1109/tim.2025.3580795

Auditory training (AT) is a proactive intervention for managing auditory health and preventing hearing loss. However, in its current form, it requires significant financial and time resources. As the excellent performance of functional near-infrared... Read More about Towards Accessible Auditory Health: A Cloud-Based fNIRS Solution for Auditory Training and Assessment.

The Ethics of Data and Its Governance: A Discourse Theoretical Approach (2025)
Journal Article
Stahl, B. C. (2025). The Ethics of Data and Its Governance: A Discourse Theoretical Approach. Information, 16(6), Article 497. https://doi.org/10.3390/info16060497

The rapidly growing amount and importance of data across all aspects of organisations and society have led to urgent calls for better, more comprehensive and applicable approaches to data governance. One key driver of this is the use of data in machi... Read More about The Ethics of Data and Its Governance: A Discourse Theoretical Approach.

Network architecture of transcriptomic stress responses in zebrafish embryos (2025)
Journal Article
Beine, K., Feugere, L., Turner, A. P., & Wollenberg Valero, K. C. (2025). Network architecture of transcriptomic stress responses in zebrafish embryos. PLoS Computational Biology, 21(6), Article e1013164. https://doi.org/10.1371/journal.pcbi.1013164

Protein-protein interaction (PPI) network topology can contribute to explain fundamental 13 properties of genes, from expression levels to evolutionary constraints. Genes central to a network 14 are more likely to be both conserved and highly express... Read More about Network architecture of transcriptomic stress responses in zebrafish embryos.

Is Temporal Prompting All We Need For Limited Labeled Action Recognition? (2025)
Presentation / Conference Contribution
Gowda, S. N., Gao, B., Gu, X., & Jin, X. (2025, June). Is Temporal Prompting All We Need For Limited Labeled Action Recognition?. Presented at 2025 IEEE CVPR Workshop on Fair, Data-efficient, and Trusted Computer Vision, Nashville, TN, USA

Video understanding has shown remarkable improvements in recent years, largely dependent on the availability of large scaled labeled datasets. Recent advancements in visual-language models, especially based on contrastive pretraining, have shown rema... Read More about Is Temporal Prompting All We Need For Limited Labeled Action Recognition?.

Just-in-Time Informed Trees: Manipulability-Aware Asymptotically Optimized Motion Planning (2025)
Journal Article
Cai, K., Zhang, L., Su, X., Chen, K., Wang, C., Haddadin, S., Knoll, A., Ajoudani, A., & Figueredo, L. (2025). Just-in-Time Informed Trees: Manipulability-Aware Asymptotically Optimized Motion Planning. IEEE/ASME Transactions on Mechatronics, 1-12. https://doi.org/10.1109/tmech.2025.3570573

In high-dimensional robotic path planning, traditional sampling-based methods often struggle to efficiently identify both feasible and optimal paths in complex, multiobstacle environments. This challenge is intensified in robotic manipulators, where... Read More about Just-in-Time Informed Trees: Manipulability-Aware Asymptotically Optimized Motion Planning.

A Responsible Research and Innovation Approach to Assessing the Implications of Anti-Trafficking Technologies (2025)
Journal Article
Moyo, T., Albayaydh, W., Webb, H., Gunes, O., & Jirotka, M. (2025). A Responsible Research and Innovation Approach to Assessing the Implications of Anti-Trafficking Technologies. ACM Journal on Responsible Computing, https://doi.org/10.1145/3737883

Responsible Research and Innovation (RRI) is crucial to address the risks associated with emerging technologies with the aim of minimising negative consequences and promoting positive outcomes. This paper uses RRI principles and semi-structured inter... Read More about A Responsible Research and Innovation Approach to Assessing the Implications of Anti-Trafficking Technologies.

Incomplete Multi-view Data Learning via Adaptive Embedding and Partial l 2,1 Norm Constraints for Parkinson's Disease Diagnosis (2025)
Journal Article
Huang, Z., Wang, K., Chen, C., Chen, J., Wan, J., Yang, Z., Zhou, R., & Gan, H. (2025). Incomplete Multi-view Data Learning via Adaptive Embedding and Partial l 2,1 Norm Constraints for Parkinson's Disease Diagnosis. IEEE Journal of Biomedical and Health Informatics, 1-13. https://doi.org/10.1109/JBHI.2025.3576786

Parkinson's disease (PD) is a progressive neurodegenerative disorder characterized by mental abnormalities and motor dysfunction. Its early classification and prediction of clinical scores have been major concerns for researchers. Currently, multi-vi... Read More about Incomplete Multi-view Data Learning via Adaptive Embedding and Partial l 2,1 Norm Constraints for Parkinson's Disease Diagnosis.

Generative AI for Supporting Cultural Learning and Reflection: A Study on Technology User Acceptance (2025)
Journal Article
Iddamalgoda, C., Ng, K. H., & Koleva, B. (2025). Generative AI for Supporting Cultural Learning and Reflection: A Study on Technology User Acceptance. International Journal of Human-Computer Interaction, https://doi.org/10.1080/10447318.2025.2505777

This study examines user acceptance of generative AI in cultural heritage contexts through a Reflection Story Generator deployed at an interactive exhibition in Malacca, a UNESCO World Heritage site. Using the AI Technology Acceptance Model (AI-TAM),... Read More about Generative AI for Supporting Cultural Learning and Reflection: A Study on Technology User Acceptance.

Varanus: Runtime Verification for CSP (2025)
Presentation / Conference Contribution
Luckcuck, M., Ferrando, A., & Faruq, F. (2025, August). Varanus: Runtime Verification for CSP. Presented at Towards Autonomous Robotic Systems 26th TAROS Conference 2025, York, UK

Autonomous systems are often used in changeable and unknown environments, where traditional verification may not be suitable. Runtime Verification (RV) checks events performed by a system against a formal specification of its intended behaviour, maki... Read More about Varanus: Runtime Verification for CSP.

Personalization variables in digital mental health interventions for depression and anxiety in adolescents and youth: a scoping review (2025)
Journal Article
Wanniarachchi, V. U., Greenhalgh, C., Choi, A., & Warren, J. R. (2025). Personalization variables in digital mental health interventions for depression and anxiety in adolescents and youth: a scoping review. Frontiers in Digital Health, 7, Article 1500220. https://doi.org/10.3389/fdgth.2025.1500220

Introduction:

The impact of personalization on user engagement and adherence in digital mental health interventions (DMHIs) has been widely explored. However, there is a lack of clarity regarding the prevalence of its application, as well as the... Read More about Personalization variables in digital mental health interventions for depression and anxiety in adolescents and youth: a scoping review.

A survey of deep-learning-based radiology report generation using multimodal inputs (2025)
Journal Article
Wang, X., Figueredo, G., Li, R., Zhang, W. E., Chen, W., & Chen, X. (2025). A survey of deep-learning-based radiology report generation using multimodal inputs. Medical Image Analysis, 103, Article 103627. https://doi.org/10.1016/j.media.2025.103627

Automatic radiology report generation can alleviate the workload for physicians and minimize regional disparities in medical resources, therefore becoming an important topic in the medical image analysis field. It is a challenging task, as the comput... Read More about A survey of deep-learning-based radiology report generation using multimodal inputs.

Beyond the Ivory Tower: Public Engagement, Class, and Access in Research (2025)
Digital Artefact
(2025). Beyond the Ivory Tower: Public Engagement, Class, and Access in Research. [Podcast - Audio]

Dr Peter Winter and Dr Alan Chamberlain join Matimba Swana to explore elitism in research, the barriers to public engagement and why making research more inclusive and accessible is essential for meaningful community participation. Recorded 11 Oct 20... Read More about Beyond the Ivory Tower: Public Engagement, Class, and Access in Research.