Outputs (15)

Hyper-parameter initialization of classification algorithms using dynamic time warping: A perspective on PCA meta-features (2022)
Presentation / Conference Contribution
Horváth, T., Mantovani, R. G., & de Carvalho, A. C. Hyper-parameter initialization of classification algorithms using dynamic time warping: A perspective on PCA meta-features

Meta-learning, a concept from the area of automated machine learning, aims at providing decision support for data scientists by recommending a suitable setting (a machine learning algorithm or its hyper-parameters) to be used for a given dataset. Suc... Read More about Hyper-parameter initialization of classification algorithms using dynamic time warping: A perspective on PCA meta-features.

Most NLG is Low-Resource: here's what we can do about it (2022)
Presentation / Conference Contribution
Howcroft, D. M., & Gkatzia, D. (2022, December). Most NLG is Low-Resource: here's what we can do about it. Presented at Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), Abu Dhabi, UAE

Many domains and tasks in natural language generation (NLG) are inherently 'low-resource', where training data, tools and linguistic analyses are scarce. This poses a particular challenge to researchers and system developers in the era of machine-lea... Read More about Most NLG is Low-Resource: here's what we can do about it.

Accelerating neural network architecture search using multi-GPU high-performance computing (2022)
Journal Article
Lupión, M., Cruz, N. C., Sanjuan, J. F., Paechter, B., & Ortigosa, P. M. (2023). Accelerating neural network architecture search using multi-GPU high-performance computing. Journal of Supercomputing, 79, 7609-7625. https://doi.org/10.1007/s11227-022-04960-z

Neural networks stand out from artificial intelligence because they can complete challenging tasks, such as image classification. However, designing a neural network for a particular problem requires experience and tedious trial and error. Automating... Read More about Accelerating neural network architecture search using multi-GPU high-performance computing.

Universally Hard Hamiltonian Cycle Problem Instances (2022)
Presentation / Conference Contribution
Sleegers, J., Thomson, S. L., & van den Berg, D. (2022, November). Universally Hard Hamiltonian Cycle Problem Instances. Presented at ECTA 2022 : 14th International Conference on Evolutionary Computation Theory and Applications, Valletta, Malta

In 2021, evolutionary algorithms found the hardest-known yes and no instances for the Hamiltonian cycle problem. These instances, which show regularity patterns, require a very high number of recursions for the best exact backtracking algorithm (Vand... Read More about Universally Hard Hamiltonian Cycle Problem Instances.

Multi-Agent Modelling Notation (MAMN): A multi-layered graphical modelling notation for agent-based simulations (2022)
Presentation / Conference Contribution
Nguyen, J., Powers, S., Urquhart, N., Farrenkopf, T., & Guckert, M. (2022, November). Multi-Agent Modelling Notation (MAMN): A multi-layered graphical modelling notation for agent-based simulations. Presented at 24th International Conference on Principles and Practice of Multi-Agent Systems, Valencia, Spain

Cause-effect graphs have been applied in non agent-based simulations, where they are used to model chained causal relations between input parameters and system behaviour measured by appropriate indicators. This can be useful for the analysis and inte... Read More about Multi-Agent Modelling Notation (MAMN): A multi-layered graphical modelling notation for agent-based simulations.

Object Detection Using Sim2Real Domain Randomization for Robotic Applications (2022)
Journal Article
Horváth, D., Erdős, G., Istenes, Z., Horváth, T., & Földi, S. (2023). Object Detection Using Sim2Real Domain Randomization for Robotic Applications. IEEE Transactions on Robotics, 39(2), 1225-1243. https://doi.org/10.1109/tro.2022.3207619

Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific labeled data for different ind... Read More about Object Detection Using Sim2Real Domain Randomization for Robotic Applications.

Structural Complexity and Performance of Support Vector Machines (2022)
Presentation / Conference Contribution
Olorisade, B. K., Brereton, P., & Andras, P. (2022, July). Structural Complexity and Performance of Support Vector Machines. Presented at 2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy

Support vector machines (SVM) are often applied in the context of machine learning analysis of various data. Given the nature of SVMs, these operate always in the sub-interpolation range as a machine learning method. Here we explore the impact of str... Read More about Structural Complexity and Performance of Support Vector Machines.

Dense reconstruction for narrow baseline motion observations (2022)
Patent
Mitchell, K., Dumbgen, F., & Liu, S. (2022). Dense reconstruction for narrow baseline motion observations. USPTO

Techniques for constructing a three-dimensional model of facial geometry are disclosed. A first three-dimensional model of an object is generated, based on a plurality of captured images of the object. A projected three-dimensional model of the objec... Read More about Dense reconstruction for narrow baseline motion observations.

Dynamic noise filtering for multi-class classification of beehive audio data (2022)
Journal Article
Várkonyi, D. T., Seixas Junior, J. L., & Horváth, T. (2023). Dynamic noise filtering for multi-class classification of beehive audio data. Expert Systems with Applications, 213(Part A), Article 118850. https://doi.org/10.1016/j.eswa.2022.118850

Honeybees are the most specialized insect pollinators and are critical not only for honey production but, also, for keeping the environmental balance by pollinating the flowers of a wide variety of crops.

Recording and analyzing bee sounds became... Read More about Dynamic noise filtering for multi-class classification of beehive audio data.

Federated Learning for Short-term Residential Load Forecasting (2022)
Journal Article
Briggs, C., Fan, Z., & Andras, P. (2022). Federated Learning for Short-term Residential Load Forecasting. IEEE Open Access Journal of Power and Energy, 9, 573-583. https://doi.org/10.1109/oajpe.2022.3206220

Load forecasting is an essential task performed within the energy industry to help balance supply with demand and maintain a stable load on the electricity grid. As supply transitions towards less reliable renewable energy generation, smart meters wi... Read More about Federated Learning for Short-term Residential Load Forecasting.

Fractal Dimension and Perturbation Strength: A Local Optima Networks View (2022)
Presentation / Conference Contribution
Thomson, S. L., Ochoa, G., & Verel, S. (2022, September). Fractal Dimension and Perturbation Strength: A Local Optima Networks View

We study the effect of varying perturbation strength on the fractal dimensions of Quadratic Assignment Problem (QAP) fitness landscapes induced by iterated local search (ILS). Fitness landscapes are represented as Local Optima Networks (LONs), which... Read More about Fractal Dimension and Perturbation Strength: A Local Optima Networks View.

On funnel depths and acceptance criteria in stochastic local search (2022)
Presentation / Conference Contribution
Thomson, S. L., & Ochoa, G. (2022, July). On funnel depths and acceptance criteria in stochastic local search. Presented at GECCO '22: Genetic and Evolutionary Computation Conference, Boston Massachusetts

We propose looking at the phenomenon of fitness landscape funnels in terms of their depth. In particular, we examine how the depth of funnels in Local Optima Networks (LONs) of benchmark Quadratic Assignment Problem instances relate to metaheuristic... Read More about On funnel depths and acceptance criteria in stochastic local search.

Real-time feature preserving rendering of visual effects on an image of a face (2022)
Patent
Mitchell, K. J., Cambra, L. C., & Li, Y. (2022). Real-time feature preserving rendering of visual effects on an image of a face

Embodiments provide techniques for rendering augmented reality effects on an image of a user's face in real time. The method generally includes receiving an image of a face of a user. A global facial depth map and a luminance map are generated based... Read More about Real-time feature preserving rendering of visual effects on an image of a face.

Tracing the Local Breeds in an Outdoor System – A Hungarian Example with Mangalica Pig Breed (2022)
Book Chapter
Alexy, M., & Horváth, T. Tracing the Local Breeds in an Outdoor System – A Hungarian Example with Mangalica Pig Breed. In Tracing the Domestic Pig. IntechOpen. https://doi.org/10.5772/intechopen.101615

Pig farming is largely characterized by closed, large-scale housing technology. These systems are driven by resource efficiency. In intensive technologies, humans control almost completely. However, there are pig farming systems where humans have jus... Read More about Tracing the Local Breeds in an Outdoor System – A Hungarian Example with Mangalica Pig Breed.

Scalability resilience framework using application-level fault injection for cloud-based software services (2022)
Journal Article
Al-Said Ahmad, A., & Andras, P. (2022). Scalability resilience framework using application-level fault injection for cloud-based software services. Journal of cloud computing: advances, systems and applications, 11(1), Article 1. https://doi.org/10.1186/s13677-021-00277-z

This paper presents an investigation into the effect of faults on the scalability resilience of cloud-based software services. The study introduces an experimental framework using the Application-Level Fault Injection (ALFI) to investigate how the fa... Read More about Scalability resilience framework using application-level fault injection for cloud-based software services.