Outputs (191)

Reconstructing cardiac electrical excitations from optical mapping recordings (2023)
Journal Article
Marcotte, C. D., Hoffman, M. J., Fenton, F. H., & Cherry, E. M. (2023). Reconstructing cardiac electrical excitations from optical mapping recordings. Chaos: An Interdisciplinary Journal of Nonlinear Science, 33(9), Article 093141. https://doi.org/10.1063/5.0156314

The reconstruction of electrical excitation patterns through the unobserved depth of the tissue is essential to realizing the potential of computational models in cardiac medicine. We have utilized experimental optical-mapping recordings of cardiac e... Read More about Reconstructing cardiac electrical excitations from optical mapping recordings.

Federated-ANN-Based Critical Path Analysis and Health Recommendations for MapReduce Workflows in Consumer Electronics Applications (2023)
Journal Article
Demirbaga, U., & Aujla, G. S. (2024). Federated-ANN-Based Critical Path Analysis and Health Recommendations for MapReduce Workflows in Consumer Electronics Applications. IEEE Transactions on Consumer Electronics, 70(1), 2639-2647. https://doi.org/10.1109/tce.2023.3318813

Although much research has been done to improve the performance of big data systems, predicting the performance degradation of these systems quickly and efficiently remains a significant challenge. Unfortunately, the complexity of big data systems is... Read More about Federated-ANN-Based Critical Path Analysis and Health Recommendations for MapReduce Workflows in Consumer Electronics Applications.

Deconfounding Causal Inference for Zero-shot Action Recognition (2023)
Journal Article
Wang, J., Jiang, Y., Long, Y., Sun, X., Pagnucco, M., & Song, Y. (2023). Deconfounding Causal Inference for Zero-shot Action Recognition. IEEE Transactions on Multimedia, 26, 3976 - 3986. https://doi.org/10.1109/tmm.2023.3318300

Zero-shot action recognition (ZSAR) aims to recognize unseen action categories in the test set without corresponding training examples. Most existing zero-shot methods follow the feature generation framework to transfer knowledge from seen action cat... Read More about Deconfounding Causal Inference for Zero-shot Action Recognition.

Fractional covers of hypergraphs with bounded multi-intersection (2023)
Journal Article
Gottlob, G., Lanzinger, M., Pichler, R., & Razgon, I. (2023). Fractional covers of hypergraphs with bounded multi-intersection. Theoretical Computer Science, 979, Article 114204. https://doi.org/10.1016/j.tcs.2023.114204

Fractional (hyper-)graph theory is concerned with the specific problems that arise when fractional analogues of otherwise integer-valued (hyper-)graph invariants are considered. The focus of this paper is on fractional edge covers of hypergraphs. Our... Read More about Fractional covers of hypergraphs with bounded multi-intersection.

Computing Subset Vertex Covers in H-Free Graphs (2023)
Presentation / Conference Contribution
Brettell, N., Oostveen, J. J., Pandey, S., Paulusma, D., & van Leeuwen, E. J. (2023, September). Computing Subset Vertex Covers in H-Free Graphs. Presented at FCT 2023: Fundamentals of Computation Theory, Trier, Germany

Race Bias Analysis of Bona Fide Errors in Face Anti-spoofing (2023)
Presentation / Conference Contribution
Abduh, L., & Ivrissimtzis, I. (2023, September). Race Bias Analysis of Bona Fide Errors in Face Anti-spoofing. Presented at CAIP 2023: The 20th International Conference on Computer Analysis of Images and Patterns, Limassol, Cyprus

The study of bias in Machine Learning is receiving a lot of attention in recent years, however, few only papers deal explicitly with the problem of race bias in face anti-spoofing. In this paper, we present a systematic study of race bias in face ant... Read More about Race Bias Analysis of Bona Fide Errors in Face Anti-spoofing.

Reinforcement learning-based aggregation for robot swarms (2023)
Journal Article
Sadeghi Amjadi, A., Bilaloğlu, C., Turgut, A. E., Na, S., Şahin, E., Krajník, T., & Arvin, F. (2024). Reinforcement learning-based aggregation for robot swarms. Adaptive Behavior, 32(3), 265-281. https://doi.org/10.1177/10597123231202593

Aggregation, the gathering of individuals into a single group as observed in animals such as birds, bees, and amoeba, is known to provide protection against predators or resistance to adverse environmental conditions for the whole. Cue-based aggregat... Read More about Reinforcement learning-based aggregation for robot swarms.

An end-to-end dynamic point cloud geometry compression in latent space (2023)
Journal Article
Jiang, Z., Wang, G., Tam, G. K. L., Song, C., Yang, B., & Li, F. W. B. (2023). An end-to-end dynamic point cloud geometry compression in latent space. Displays, 80, Article 102528. https://doi.org/10.1016/j.displa.2023.102528

Dynamic point clouds are widely used for 3D data representation in various applications such as immersive and mixed reality, robotics and autonomous driving. However, their irregularity and large scale make efficient compression and... Read More about An end-to-end dynamic point cloud geometry compression in latent space.

Reimagining AI Governance: a Response by AGENCY to the UK Government's White Paper AI Regulation (2023)
Report
Owens, R., Copilah-Ali, J., Kolomeets, M., Malviya, S., Markeviciute, K., Olabode, S., …Farrand, B. (2023). Reimagining AI Governance: a Response by AGENCY to the UK Government's White Paper AI Regulation. SSRN: AGENCY project

In March 29, 2023, the UK Government released a white paper outlining its plans to implement a pro-innovation approach to Artificial Intelligence (AI) regulation and strengthen the UK's position as a global leader in AI.

As part of the white paper... Read More about Reimagining AI Governance: a Response by AGENCY to the UK Government's White Paper AI Regulation.

AGENCY—written evidence (LLM0028) for House of Lords Communications and Digital Select Committee inquiry: Large language models (2023)
Report
Malviya, S., Owens, R., Copilah-Ali, J., Elliot, K., Farrand, B., Neesham, C., Shi, L., Vlachokyriakos, V., Katsigiannis, S., & van Moorsel, A. (2023). AGENCY—written evidence (LLM0028) for House of Lords Communications and Digital Select Committee inquiry: Large language models. House of Lords Communications and Digital Select Committee

AGENCY is a multidisciplinary research team of academics with expertise in computer science (natural language processing, cybersecurity, artificial intelligence, human-computer interaction), law, business, economics, social sciences and media studies... Read More about AGENCY—written evidence (LLM0028) for House of Lords Communications and Digital Select Committee inquiry: Large language models.