Skip to main content

Research Repository

Advanced Search

All Outputs (55)

Object landmark discovery through unsupervised adaptation (2019)
Journal Article
Sanchez, E., & Tzimiropoulos, G. (2019). Object landmark discovery through unsupervised adaptation. Advances in Neural Information Processing Systems, 32,

This paper proposes a method to ease the unsupervised learning of object landmark detectors. Similarly to previous methods, our approach is fully unsupervised in a sense that it does not require or make any use of annotated landmarks for the target o... Read More about Object landmark discovery through unsupervised adaptation.

The Effect of Light Intensity, Sensor Height, and Spectral Pre-Processing Methods When Using NIR Spectroscopy to Identify Different Allergen-Containing Powdered Foods (2019)
Journal Article
Rady, A., Fischer, J., Reeves, S., Logan, B., & James Watson, N. (2020). The Effect of Light Intensity, Sensor Height, and Spectral Pre-Processing Methods When Using NIR Spectroscopy to Identify Different Allergen-Containing Powdered Foods. Sensors, 20(1), Article 230. https://doi.org/10.3390/s20010230

Food allergens present a significant health risk to the human population, so their presence must be monitored and controlled within food production environments. This is especially important for powdered food, which can contain nearly all known food... Read More about The Effect of Light Intensity, Sensor Height, and Spectral Pre-Processing Methods When Using NIR Spectroscopy to Identify Different Allergen-Containing Powdered Foods.

Conceptual modelling: Towards detecting modelling errors in engineering applications (2019)
Journal Article
Gürlebeck, K., Legatiuk, D., Nilsson, H., & Smarsly, K. (2020). Conceptual modelling: Towards detecting modelling errors in engineering applications. Mathematical Methods in the Applied Sciences, 43(3), 1243-1252. https://doi.org/10.1002/mma.5934

Rapid advancements of modern technologies put high demands on mathematical modelling of engineering systems. Typically, systems are no longer “simple” objects, but rather coupled systems involving multiphysics phenomena, the modelling of which involv... Read More about Conceptual modelling: Towards detecting modelling errors in engineering applications.

A hybrid combinatorial approach to a two-stage stochastic portfolio optimization model with uncertain asset prices (2019)
Journal Article
Cui, T., Bai, R., Ding, S., Parkes, A. J., Qu, R., He, F., & Li, J. (2020). A hybrid combinatorial approach to a two-stage stochastic portfolio optimization model with uncertain asset prices. Soft Computing, 24, 2809–2831. https://doi.org/10.1007/s00500-019-04517-y

© 2019, Springer-Verlag GmbH Germany, part of Springer Nature. Portfolio optimization is one of the most important problems in the finance field. The traditional Markowitz mean-variance model is often unrealistic since it relies on the perfect market... Read More about A hybrid combinatorial approach to a two-stage stochastic portfolio optimization model with uncertain asset prices.

End-of-life vehicle management: a comprehensive review (2019)
Journal Article
Karagoz, S., Aydin, N., & Simic, V. (2020). End-of-life vehicle management: a comprehensive review. Journal of Material Cycles and Waste Management, 22, 416–442. https://doi.org/10.1007/s10163-019-00945-y

Waste management is gaining very high importance in recent years. As automotive is one of the most critical sectors worldwide, which is rapidly increasing, the management of end-of-life vehicles (ELVs) gains importance day by day. Due to legislation... Read More about End-of-life vehicle management: a comprehensive review.

RootNav 2.0: Deep learning for automatic navigation of complex plant root architectures (2019)
Journal Article
Yasrab, R., Atkinson, J. A., Wells, D. M., French, A. P., Pridmore, T. P., & Pound, M. P. (2019). RootNav 2.0: Deep learning for automatic navigation of complex plant root architectures. GigaScience, 8(11), https://doi.org/10.1093/gigascience/giz123

© The Author(s) 2019. Published by Oxford University Press. BACKGROUND: In recent years quantitative analysis of root growth has become increasingly important as a way to explore the influence of abiotic stress such as high temperature and drought on... Read More about RootNav 2.0: Deep learning for automatic navigation of complex plant root architectures.

Editorial of the special issue on differential evolution (2019)
Journal Article
Brest, J., & Neri, F. (2019). Editorial of the special issue on differential evolution. Swarm and Evolutionary Computation, 50, Article 100583. https://doi.org/10.1016/j.swevo.2019.100583

Differential Evolution (DE) is a population-based metaheuristic for addressing optimization problems [[1], [2], [3]]. The algorithm processes a population of candidate solutions by performing two operations. The first operation, namely mutation, is t... Read More about Editorial of the special issue on differential evolution.

Shallow Embedding of Type Theory is Morally Correct (2019)
Journal Article
Kaposi, A., Kovács, A., & Kraus, N. (2019). Shallow Embedding of Type Theory is Morally Correct. Lecture Notes in Artificial Intelligence, 11825 LNCS, 329-365. https://doi.org/10.1007/978-3-030-33636-3_12

© 2019, Springer Nature Switzerland AG. There are multiple ways to formalise the metatheory of type theory. For some purposes, it is enough to consider specific models of a type theory, but sometimes it is necessary to refer to the syntax, for exampl... Read More about Shallow Embedding of Type Theory is Morally Correct.

Sex-specific hippocampal metabolic signatures at the onset of systemic inflammation with lipopolysaccharide in the APPswe/PS1dE9 mouse model of Alzheimer's disease (2019)
Journal Article
Agostini, A., Yuchun, D., Li, B., Kendall, D. A., & Pardon, M. (2020). Sex-specific hippocampal metabolic signatures at the onset of systemic inflammation with lipopolysaccharide in the APPswe/PS1dE9 mouse model of Alzheimer's disease. Brain, Behavior, and Immunity, 83, 87-111. https://doi.org/10.1016/j.bbi.2019.09.019

Systemic inflammation enhances the risk and progression of Alzheimer's disease (AD). Lipopolysaccharide (LPS), a potent pro-inflammatory endotoxin produced by the gut, is found in excess levels in AD where it associates with neurological hallmarks of... Read More about Sex-specific hippocampal metabolic signatures at the onset of systemic inflammation with lipopolysaccharide in the APPswe/PS1dE9 mouse model of Alzheimer's disease.

Using agent-based modelling for investigating modal shift: The case of university travel (2019)
Journal Article
Olusola, F. T., Siebers, P., Faboya, O., Ryan, B., & Figueredo, G. P. (2020). Using agent-based modelling for investigating modal shift: The case of university travel. Computers and Industrial Engineering, 139, https://doi.org/10.1016/j.cie.2019.106077

© 2019 Travel mode choices are a result of several factors and how they affect individual travellers. This paper examines those factors influencing travellers’ mode choices commuting to and from a university. Furthermore, we investigate how a shift t... Read More about Using agent-based modelling for investigating modal shift: The case of university travel.

On the Choice of Similarity Measures for Type-2 Fuzzy Sets (2019)
Journal Article
McCulloch, J., & Wagner, C. (2020). On the Choice of Similarity Measures for Type-2 Fuzzy Sets. Information Sciences, 510, 135-154. https://doi.org/10.1016/j.ins.2019.09.027

Similarity measures are among the most common methods of comparing type-2 fuzzy sets and have been used in numerous applications. However, deciding how to measure similarity and choosing which existing measure to use can be difficult. Whilst some mea... Read More about On the Choice of Similarity Measures for Type-2 Fuzzy Sets.

Dual memory network model for sentiment analysis of review text (2019)
Journal Article
Shen, J., Ma, M. D., Xiang, R., Lu, Q., Vallejos, E. P., Xu, G., …Huang, C. (2019). Dual memory network model for sentiment analysis of review text. Knowledge-Based Systems, 188, Article 105004. https://doi.org/10.1016/j.knosys.2019.105004

In sentiment analysis of product reviews, both user and product information are proven to be useful. Current works handle user profile and product information in a unified model which may not be able to learn salient features of users and products ef... Read More about Dual memory network model for sentiment analysis of review text.

Pattern-Based Approach to the Workflow Satisfiability Problem with User-Independent Constraints (2019)
Journal Article
Karapetyan, D., J. Parkes, A., Gutin, G., & Gagarin, A. (2019). Pattern-Based Approach to the Workflow Satisfiability Problem with User-Independent Constraints. Journal of Artificial Intelligence Research, 66, 85-122. https://doi.org/10.1613/jair.1.11339

The fixed parameter tractable (FPT) approach is a powerful tool in tackling computationally hard problems. In this paper, we link FPT results to classic artificial intelligence (AI) techniques to show how they complement each other. Specifically, we... Read More about Pattern-Based Approach to the Workflow Satisfiability Problem with User-Independent Constraints.

Accelerated genetic algorithm based on search-space decomposition for change detection in remote sensing images (2019)
Journal Article
Mu, C., Li, C., Liu, Y., Qu, R., & Jiao, L. (2019). Accelerated genetic algorithm based on search-space decomposition for change detection in remote sensing images. Applied Soft Computing, 84, Article 105727. https://doi.org/10.1016/j.asoc.2019.105727

Detecting change areas among two or more remote sensing images is a key technique in remote sensing. It usually consists of generating and analyzing a difference image thus to produce a change map. Analyzing the difference image to obtain the change... Read More about Accelerated genetic algorithm based on search-space decomposition for change detection in remote sensing images.

Call-by-need is clairvoyant call-by-value (2019)
Journal Article
Hackett, J., & Hutton, G. (2019). Call-by-need is clairvoyant call-by-value. Proceedings of the ACM on Programming Languages, 3(ICFP), 1-21. https://doi.org/10.1145/3341718

Call-by-need evaluation, also known as lazy evaluation, provides two key benefits: compositional programming and infinite data. The standard semantics for laziness is Launchbury’s natural semantics, which uses a heap to memoise the results of delayed... Read More about Call-by-need is clairvoyant call-by-value.

Deep Fuzzy Tree for Large-Scale Hierarchical Visual Classification (2019)
Journal Article
Wang, Y., Hu, Q., Zhu, P., Li, L., Lu, B., Garibaldi, J. M., & Li, X. (2020). Deep Fuzzy Tree for Large-Scale Hierarchical Visual Classification. IEEE Transactions on Fuzzy Systems, 28(7), 1395-1406. https://doi.org/10.1109/tfuzz.2019.2936801

Deep learning models often use a flat softmax layer to classify samples after feature extraction in visual classification tasks. However, it is hard to make a single decision of finding the true label from massive classes. In this scenario, hierarchi... Read More about Deep Fuzzy Tree for Large-Scale Hierarchical Visual Classification.

Recent advances in selection hyper-heuristics (2019)
Journal Article
Drake, J. H., Kheiri, A., Özcan, E., & Burke, E. K. (2020). Recent advances in selection hyper-heuristics. European Journal of Operational Research, 285(2), 405-428. https://doi.org/10.1016/j.ejor.2019.07.073

Hyper-heuristics have emerged as a way to raise the level of generality of search techniques for computational search problems. This is in contrast to many approaches, which represent customised methods for a single problem domain or a narrow class o... Read More about Recent advances in selection hyper-heuristics.

Comparing Performance Potentials of Classical and Intuitionistic Fuzzy Systems in Terms of Sculpting the State Space (2019)
Journal Article
Mendel, J. M., Eyoh, I., & John, R. (2020). Comparing Performance Potentials of Classical and Intuitionistic Fuzzy Systems in Terms of Sculpting the State Space. IEEE Transactions on Fuzzy Systems, 28(9), 2244-2254. https://doi.org/10.1109/TFUZZ.2019.2933786

This paper provides new application-independent perspectives about the performance potential of an intuitionistic (I-) fuzzy system over a (classical) TSK fuzzy system. It does this by extending sculpting the state space works from a TSK fuzzy system... Read More about Comparing Performance Potentials of Classical and Intuitionistic Fuzzy Systems in Terms of Sculpting the State Space.

ADONiS - Adaptive Online Non-Singleton Fuzzy Logic Systems (2019)
Journal Article
Pekaslan, D., Wagner, C., & Garibaldi, J. M. (2020). ADONiS - Adaptive Online Non-Singleton Fuzzy Logic Systems. IEEE Transactions on Fuzzy Systems, 28(10), 2302-2312. https://doi.org/10.1109/tfuzz.2019.2933787

Non-Singleton Fuzzy Logic Systems (NSFLSs) have the potential to capture and handle input noise within the design of input fuzzy sets. In this paper, we propose an online learning method which utilises a sequence of observations to continuously updat... Read More about ADONiS - Adaptive Online Non-Singleton Fuzzy Logic Systems.