Outputs (47)

Machine Learning Pipeline for Energy and Environmental Prediction in Cold Storage Facilities (2024)
Journal Article
Alkhulaifi, N., Bowler, A. L., Pekaslan, D., Serdaroglu, G., Closs, S., Watson, N. J., & Triguero, I. (2024). Machine Learning Pipeline for Energy and Environmental Prediction in Cold Storage Facilities. IEEE Access, 12, 153935-153951. https://doi.org/10.1109/access.2024.3482572

As energy demands and costs rise, enhancing energy efficiency in Food and Drink Cold Storage (FDCS) rooms is important for reducing expenses and achieving environmental sustainability ambitions. Forecasting electricity use in FDCSs can help optimise... Read More about Machine Learning Pipeline for Energy and Environmental Prediction in Cold Storage Facilities.

SEGAL time series classification — Stable explanations using a generative model and an adaptive weighting method for LIME (2024)
Journal Article
Meng, H., Wagner, C., & Triguero, I. (2024). SEGAL time series classification — Stable explanations using a generative model and an adaptive weighting method for LIME. Neural Networks, 176, Article 106345. https://doi.org/10.1016/j.neunet.2024.106345

Local Interpretability Model-agnostic Explanations (LIME) is a well-known post-hoc technique for explaining black-box models. While very useful, recent research highlights challenges around the explanations generated. In particular, there is a potent... Read More about SEGAL time series classification — Stable explanations using a generative model and an adaptive weighting method for LIME.

Local-global methods for generalised solar irradiance forecasting (2024)
Journal Article
Cargan, T. R., Landa-Silva, D., & Triguero, I. (2024). Local-global methods for generalised solar irradiance forecasting. Applied Intelligence, 54(2), 2225-2247. https://doi.org/10.1007/s10489-024-05273-9

For efficient operation, solar power operators often require generation forecasts for multiple sites with varying data availability. Many proposed methods for forecasting solar irradiance / solar power production formulate the problem as a time-serie... Read More about Local-global methods for generalised solar irradiance forecasting.

General Purpose Artificial Intelligence Systems (GPAIS): Properties, definition, taxonomy, societal implications and responsible governance (2023)
Journal Article
Triguero, I., Molina, D., Poyatos, J., Del Ser, J., & Herrera, F. (2024). General Purpose Artificial Intelligence Systems (GPAIS): Properties, definition, taxonomy, societal implications and responsible governance. Information Fusion, 103, Article 102135. https://doi.org/10.1016/j.inffus.2023.102135

Most applications of Artificial Intelligence (AI) are designed for a confined and specific task. However, there are many scenarios that call for a more general AI, capable of solving a wide array of tasks without being specifically designed for them.... Read More about General Purpose Artificial Intelligence Systems (GPAIS): Properties, definition, taxonomy, societal implications and responsible governance.

Hyper-Stacked: Scalable and Distributed Approach to AutoML for Big Data (2023)
Presentation / Conference Contribution
Dave, R., Angarita-Zapata, J. S., & Triguero, I. (2023, August). Hyper-Stacked: Scalable and Distributed Approach to AutoML for Big Data. Presented at 7th IFIP TC 5, TC 12, WG 8.4, WG 8.9, WG 12.9 International Cross-Domain Conference, CD-MAKE 2023, Benevento, Italy

The emergence of Machine Learning (ML) has altered how researchers and business professionals value data. Applicable to almost every industry, considerable amounts of time are wasted creating bespoke applications and repetitively hand-tuning models t... Read More about Hyper-Stacked: Scalable and Distributed Approach to AutoML for Big Data.

Explaining time series classifiers through meaningful perturbation and optimisation (2023)
Journal Article
Meng, H., Wagner, C., & Triguero, I. (2023). Explaining time series classifiers through meaningful perturbation and optimisation. Information Sciences, 645, Article 119334. https://doi.org/10.1016/j.ins.2023.119334

Machine learning approaches have enabled increasingly powerful time series classifiers. While performance has improved drastically, the resulting classifiers generally suffer from poor explainability, limiting their applicability in critical areas. S... Read More about Explaining time series classifiers through meaningful perturbation and optimisation.

Identifying bird species by their calls in Soundscapes (2023)
Journal Article
Maclean, K., & Triguero, I. (2023). Identifying bird species by their calls in Soundscapes. Applied Intelligence, 53, 21485-21499. https://doi.org/10.1007/s10489-023-04486-8

In many real data science problems, it is common to encounter a domain mismatch between the training and testing datasets, which means that solutions designed for one may not transfer well to the other due to their differences. An example of such was... Read More about Identifying bird species by their calls in Soundscapes.

Feature Importance Identification for Time Series Classifiers (2022)
Presentation / Conference Contribution
Meng, H., Wagner, C., & Triguero, I. (2022, October). Feature Importance Identification for Time Series Classifiers. Presented at 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Prague, Czech Republic

Time series classification is a challenging research area where machine learning techniques such as deep learning perform well, yet lack interpretability. Identifying the most important features for such classifiers provides a pathway to improving th... Read More about Feature Importance Identification for Time Series Classifiers.

Accelerated pattern search with variable solution size for simultaneous instance selection and generation (2022)
Presentation / Conference Contribution
Le, H. L., Neri, F., Landa-Silva, D., & Triguero, I. (2022, July). Accelerated pattern search with variable solution size for simultaneous instance selection and generation. Poster presented at Genetic and Evolutionary Computation Conference Companion (GECCO 2022), Boston, USA and online

The search for the optimum in a mixed continuous-combinatorial space is a challenging task since it requires operators that handle both natures of the search domain. Instance reduction (IR), an important pre-processing technique in data science, is o... Read More about Accelerated pattern search with variable solution size for simultaneous instance selection and generation.

A fusion spatial attention approach for few-shot learning (2021)
Journal Article
Song, H., Deng, B., Pound, M., Özcan, E., & Triguero, I. (2022). A fusion spatial attention approach for few-shot learning. Information Fusion, 81, 187-202. https://doi.org/10.1016/j.inffus.2021.11.019

Few-shot learning is a challenging problem in computer vision that aims to learn a new visual concept from very limited data. A core issue is that there is a large amount of uncertainty introduced by the small training set. For example, the few image... Read More about A fusion spatial attention approach for few-shot learning.