Outputs (102)

Soma design to enhance aircraft passenger comfort (2021)
Presentation / Conference Contribution
Sharafkhani, M., Tennent, P., Argyle, E., & Cobb, S. (2021, September). Soma design to enhance aircraft passenger comfort. Presented at Comfort Congress (ICC2021), Nottingham, UK

Aircraft passengers can become uncomfortable while seated because of the restricted physical space. This work aims to investigate a new strategy for designing interventions that can be used to encourage aircraft passengers to move more while seated a... Read More about Soma design to enhance aircraft passenger comfort.

Calculating dependently-typed compilers (functional pearl) (2021)
Journal Article
Pickard, M., & Hutton, G. (2021). Calculating dependently-typed compilers (functional pearl). Proceedings of the ACM on Programming Languages, 5(ICFP), 1-27. https://doi.org/10.1145/3473587

Compilers are difficult to write, and difficult to get right. Bahr and Hutton recently developed a new technique for calculating compilers directly from specifications of their correctness, which ensures that the resulting compilers are correct-by-co... Read More about Calculating dependently-typed compilers (functional pearl).

Covariance Pattern Search with Eigenvalue-determined Radii (2021)
Presentation / Conference Contribution
Neri, F., & Zhou, Y. (2021, June). Covariance Pattern Search with Eigenvalue-determined Radii. Presented at 2021 IEEE Congress on Evolutionary Computation (CEC 2021), Krakow, Poland (Virtual)

Effective implementations of Memetic Algorithms often integrate, within their design, problem-based pieces of information. When no information is known, an efficient MA can still be designed after a preliminary analysis of the problem. This approach... Read More about Covariance Pattern Search with Eigenvalue-determined Radii.

Intent-Aware Predictive Haptic Guidance and its Application to Shared Control Teleoperation (2021)
Presentation / Conference Contribution
Ly, K. T., Poozhiyil, M., Pandya, H., Neumann, G., & Kucukyilmaz, A. (2021, August). Intent-Aware Predictive Haptic Guidance and its Application to Shared Control Teleoperation. Presented at 2021 30th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2021, Vancouver, Canada (Online)

This paper presents a haptic shared control paradigm that modulates the level of robotic guidance, based on predictions of human motion intentions. The proposed method incorporates robot trajectories learned from human demonstrations and dynamically... Read More about Intent-Aware Predictive Haptic Guidance and its Application to Shared Control Teleoperation.

Generic stacks and application of composite rules for the detailed sizing of laminated structures (2021)
Journal Article
Ntourmas, G., Glock, F., Daoud, F., Schuhmacher, G., Chronopoulos, D., & Özcan, E. (2021). Generic stacks and application of composite rules for the detailed sizing of laminated structures. Composite Structures, 276, Article 114487. https://doi.org/10.1016/j.compstruct.2021.114487

Two-stage approaches are commonly applied to optimise the stacking sequence of large-scale composite structures. The two stages consist of a gradient and non-gradient based optimisation addressing the mixed nature of continuous and discrete constrain... Read More about Generic stacks and application of composite rules for the detailed sizing of laminated structures.

Do People Prefer to Give Interval-Valued or Point Estimates and Why? (2021)
Presentation / Conference Contribution
Ellerby, Z., & Wagner, C. (2021, July). Do People Prefer to Give Interval-Valued or Point Estimates and Why?. Presented at 2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Luxembourg (now virtual)

Capturing interval-valued, as opposed to more conventional point-valued data, offers a potentially efficient method of obtaining richer information in individual responses. In turn, interval-valued data provide a strong foundation for subsequent fuzz... Read More about Do People Prefer to Give Interval-Valued or Point Estimates and Why?.

FuzzyDCNN: Incorporating Fuzzy Integral Layers to Deep Convolutional Neural Networks for Image Segmentation (2021)
Presentation / Conference Contribution
Lin, Q., Chen, X., Chen, C., & Garibaldi, J. M. (2021, July). FuzzyDCNN: Incorporating Fuzzy Integral Layers to Deep Convolutional Neural Networks for Image Segmentation. Presented at IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2021), Luxembourg, Luxembourg

Convolutional neural networks (CNNs) have achieved the state-of-the-art performance in many application areas, due to the capability of automatically extracting and aggregating spatial and channel-wise features from images. Most recent studies have c... Read More about FuzzyDCNN: Incorporating Fuzzy Integral Layers to Deep Convolutional Neural Networks for Image Segmentation.

From computer ethics and the ethics of AI towards an ethics of digital ecosystems (2021)
Journal Article
Stahl, B. C. (2022). From computer ethics and the ethics of AI towards an ethics of digital ecosystems. AI and Ethics, 2(1), 65-77. https://doi.org/10.1007/s43681-021-00080-1

Ethical, social and human rights aspects of computing technologies have been discussed since the inception of these technologies. In the 1980s, this led to the development of a discourse often referred to as computer ethics. More recently, since the... Read More about From computer ethics and the ethics of AI towards an ethics of digital ecosystems.

A Multi-Objective Evolutionary Approach Based on Graph-in-Graph for Neural Architecture Search of Convolutional Neural Networks (2021)
Journal Article
Xue, Y., Jiang, P., Neri, F., & Liang, J. (2021). A Multi-Objective Evolutionary Approach Based on Graph-in-Graph for Neural Architecture Search of Convolutional Neural Networks. International Journal of Neural Systems, 31(09), Article 2150035. https://doi.org/10.1142/S0129065721500350

With the development of deep learning, the design of an appropriate network structure becomes fundamental. In recent years, the successful practice of Neural Architecture Search (NAS) has indicated that an automated design of the network structure ca... Read More about A Multi-Objective Evolutionary Approach Based on Graph-in-Graph for Neural Architecture Search of Convolutional Neural Networks.

Automated design of search algorithms: Learning on algorithmic components (2021)
Journal Article
Meng, W., & Qu, R. (2021). Automated design of search algorithms: Learning on algorithmic components. Expert Systems with Applications, 185, Article 115493. https://doi.org/10.1016/j.eswa.2021.115493

This paper proposes AutoGCOP, a new general framework for automated design of local search algorithms. In a recently established General Combinatorial Optimisation Problem (GCOP) model, the problem of algorithm design itself is defined as a combinato... Read More about Automated design of search algorithms: Learning on algorithmic components.