Tecnalia Research & Innovation

Ali S., Abuhmed T., El-Sappagh S., Muhammad K., Alonso-Moral J.M., Confalonieri R., Guidotti R., Ser J.D., Díaz-Rodríguez N., Herrera F.

Artificial intelligence (AI) is currently being utilized in a wide range of sophisticated applications, but the outcomes of many AI models are challenging to comprehend and trust due to their black-box nature. Usually, it is essential to understand the reasoning behind an AI model’s decision-making. Thus, the need for eXplainable AI (XAI) methods for improving trust in AI models has arisen. XAI has become a popular research subject within the AI field in recent years. Existing survey papers have tackled the concepts of XAI, its general terms, and post-hoc explainability methods but there have not been any reviews that have looked at the assessment methods, available tools, XAI datasets, and other related aspects. Therefore, in this comprehensive study, we provide readers with an overview of the current research and trends in this rapidly emerging area with a case study example. The study starts by explaining the background of XAI, common definitions, and summarizing recently proposed techniques in XAI for supervised machine learning. The review divides XAI techniques into four axes using a hierarchical categorization system: (i) data explainability, (ii) model explainability, (iii) post-hoc explainability, and (iv) assessment of explanations. We also introduce available evaluation metrics as well as open-source packages and datasets with future research directions. Then, the significance of explainability in terms of legal demands, user viewpoints, and application orientation is outlined, termed as XAI concerns. This paper advocates for tailoring explanation content to specific user types. An examination of XAI techniques and evaluation was conducted by looking at 410 critical articles, published between January 2016 and October 2022, in reputed journals and using a wide range of research databases as a source of information. The article is aimed at XAI researchers who are interested in making their AI models more trustworthy, as well as towards researchers from other disciplines who are looking for effective XAI methods to complete tasks with confidence while communicating meaning from data.

Salvia M., Reckien D., Pietrapertosa F., Eckersley P., Spyridaki N., Krook-Riekkola A., Olazabal M., De Gregorio Hurtado S., Simoes S.G., Geneletti D., Viguié V., Fokaides P.A., Ioannou B.I., Flamos A., Csete M.S., et. al.

Cities across the globe recognise their role in climate mitigation and are acting to reduce carbon emissions. Knowing whether cities set ambitious climate and energy targets is critical for determining their contribution towards the global 1.5 °C target, partly because it helps to identify areas where further action is necessary. This paper presents a comparative analysis of the mitigation targets of 327 European cities, as declared in their local climate plans. The sample encompasses over 25% of the EU population and includes cities of all sizes across all Member States, plus the UK. The study analyses whether the type of plan, city size, membership of climate networks, and its regional location are associated with different levels of mitigation ambition. Results reveal that 78% of the cities have a GHG emissions reduction target. However, with an average target of 47%, European cities are not on track to reach the Paris Agreement: they need to roughly double their ambitions and efforts. Some cities are ambitious, e.g. 25% of our sample (81) aim to reach carbon neutrality, with the earliest target date being 2020.90% of these cities are members of the Climate Alliance and 75% of the Covenant of Mayors. City size is the strongest predictor for carbon neutrality, whilst climate network(s) membership, combining adaptation and mitigation into a single strategy, and local motivation also play a role. The methods, data, results and analysis of this study can serve as a reference and baseline for tracking climate mitigation ambitions across European and global cities.

Muhammad K., Ullah A., Lloret J., Ser J.D., de Albuquerque V.H.

Advances in information and signal processing technologies have a significant impact on autonomous driving (AD), improving driving safety while minimizing the efforts of human drivers with the help of advanced artificial intelligence (AI) techniques. Recently, deep learning (DL) approaches have solved several real-world problems of complex nature. However, their strengths in terms of control processes for AD have not been deeply investigated and highlighted yet. This survey highlights the power of DL architectures in terms of reliability and efficient real-time performance and overviews state-of-the-art strategies for safe AD, with their major achievements and limitations. Furthermore, it covers major embodiments of DL along the AD pipeline including measurement, analysis, and execution, with a focus on road, lane, vehicle, pedestrian, drowsiness detection, collision avoidance, and traffic sign detection through sensing and vision-based DL methods. In addition, we discuss on the performance of several reviewed methods by using different evaluation metrics, with critics on their pros and cons. Finally, this survey highlights the current issues of safe DL-based AD with a prospect of recommendations for future research, rounding up a reference material for newcomers and researchers willing to join this vibrant area of Intelligent Transportation Systems.

Muhammad K., Khan S., Ser J.D., Albuquerque V.H.

Brain tumor is one of the most dangerous cancers in people of all ages, and its grade recognition is a challenging problem for radiologists in health monitoring and automated diagnosis. Recently, numerous methods based on deep learning have been presented in the literature for brain tumor classification (BTC) in order to assist radiologists for a better diagnostic analysis. In this overview, we present an in-depth review of the surveys published so far and recent deep learning-based methods for BTC. Our survey covers the main steps of deep learning-based BTC methods, including preprocessing, features extraction, and classification, along with their achievements and limitations. We also investigate the state-of-the-art convolutional neural network models for BTC by performing extensive experiments using transfer learning with and without data augmentation. Furthermore, this overview describes available benchmark data sets used for the evaluation of BTC. Finally, this survey does not only look into the past literature on the topic but also steps on it to delve into the future of this area and enumerates some research directions that should be followed in the future, especially for personalized and smart healthcare.

Argüeso D., Picon A., Irusta U., Medela A., San-Emeterio M.G., Bereciartua A., Alvarez-Gila A.

Prompt plant disease detection is critical to prevent plagues and to mitigate their effects on crops. The most accurate automatic algorithms for plant disease identification using plant field images are based on deep learning. These methods require the acquisition and annotation of large image datasets, which is frequently technically or economically unfeasible. This study introduces Few-Shot Learning (FSL) algorithms for plant leaf classification using deep learning with small datasets. For the study 54,303 labeled images from the PlantVillage dataset were used, comprising 38 plant leaf and/or disease types (classes). The data was split into a source (32 classes) and a target (6 classes) domain. The Inception V3 network was fine-tuned in the source domain to learn general plant leaf characteristics. This knowledge was transferred to the target domain to learn new leaf types from few images. FSL using Siamese networks and Triplet loss was used and compared to classical fine-tuning transfer learning. The source and target domain sets were split into a training set (80%) to develop the methods and a test set (20%) to obtain the results. Algorithm performance was evaluated using the total accuracy, and the precision and recall per class. For the FSL experiments the algorithms were trained with different numbers of images per class and the experiments were repeated 20 times to statistically characterize the results. The accuracy in the source domain was 91.4% (32 classes), with a median precision/recall per class of 93.8%/92.6%. The accuracy in the target domain was 94.0% (6 classes) learning from all the training data, and the median accuracy (90% confidence interval) learning from 1 image per class was 55.5 (46.0–61.7)%. Median accuracies of 80.0 (76.4–86.5)% and 90.0 (86.1–94.2)% were reached for 15 and 80 images per class, yielding a reduction of 89.1% (80 images/class) in the training dataset with only a 4-point loss in accuracy. The FSL method outperformed the classical fine tuning transfer learning which had accuracies of 18.0 (16.0–24.0)% and 72.0 (68.0–77.3)% for 1 and 80 images per class, respectively. It is possible to learn new plant leaf and disease types with very small datasets using deep learning Siamese networks with Triplet loss, achieving almost a 90% reduction in training data needs and outperforming classical learning techniques for small training sets.

Osaba E., Villar-Rodriguez E., Del Ser J., Nebro A.J., Molina D., LaTorre A., Suganthan P.N., Coello Coello C.A., Herrera F.

In the last few years, the formulation of real-world optimization problems and their efficient solution via metaheuristic algorithms has been a catalyst for a myriad of research studies. In spite of decades of historical advancements on the design and use of metaheuristics, large difficulties still remain in regards to the understandability, algorithmic design uprightness, and performance verifiability of new technical achievements. A clear example stems from the scarce replicability of works dealing with metaheuristics used for optimization, which is often infeasible due to ambiguity and lack of detail in the presentation of the methods to be reproduced. Additionally, in many cases, there is a questionable statistical significance of their reported results. This work aims at providing the audience with a proposal of good practices which should be embraced when conducting studies about metaheuristics methods used for optimization in order to provide scientific rigor, value and transparency. To this end, we introduce a step by step methodology covering every research phase that should be followed when addressing this scientific field. Specifically, frequently overlooked yet crucial aspects and useful recommendations will be discussed in regards to the formulation of the problem, solution encoding, implementation of search operators, evaluation metrics, design of experiments, and considerations for real-world performance, among others. Finally, we will outline important considerations, challenges, and research directions for the success of newly developed optimization metaheuristics in their deployment and operation over real-world application environments.

Mendibil U., Ruiz-Hernandez R., Retegi-Carrion S., Garcia-Urquia N., Olalde-Graells B., Abarrategi A.

The extracellular matrix (ECM) is a complex network with multiple functions, including specific functions during tissue regeneration. Precisely, the properties of the ECM have been thoroughly used in tissue engineering and regenerative medicine research, aiming to restore the function of damaged or dysfunctional tissues. Tissue decellularization is gaining momentum as a technique to obtain potentially implantable decellularized extracellular matrix (dECM) with well-preserved key components. Interestingly, the tissue-specific dECM is becoming a feasible option to carry out regenerative medicine research, with multiple advantages compared to other approaches. This review provides an overview of the most common methods used to obtain the dECM and summarizes the strategies adopted to decellularize specific tissues, aiming to provide a helpful guide for future research development.

Lobo J.L., Del Ser J., Bifet A., Kasabov N.

Applications that generate huge amounts of data in the form of fast streams are becoming increasingly prevalent, being therefore necessary to learn in an online manner. These conditions usually impose memory and processing time restrictions, and they often turn into evolving environments where a change may affect the input data distribution. Such a change causes that predictive models trained over these stream data become obsolete and do not adapt suitably to new distributions. Specially in these non-stationary scenarios, there is a pressing need for new algorithms that adapt to these changes as fast as possible, while maintaining good performance scores. Unfortunately, most off-the-shelf classification models need to be retrained if they are used in changing environments, and fail to scale properly. Spiking Neural Networks have revealed themselves as one of the most successful approaches to model the behavior and learning potential of the brain, and exploit them to undertake practical online learning tasks. Besides, some specific flavors of Spiking Neural Networks can overcome the necessity of retraining after a drift occurs. This work intends to merge both fields by serving as a comprehensive overview, motivating further developments that embrace Spiking Neural Networks for online learning scenarios, and being a friendly entry point for non-experts.

Benítez-Hidalgo A., Nebro A.J., García-Nieto J., Oregi I., Del Ser J.

This paper describes jMetalPy, an object-oriented Python-based framework for multi-objective optimization with metaheuristic techniques. Building upon our experiences with the well-known jMetal framework, we have developed a new multi-objective optimization software platform aiming not only at replicating the former one in a different programming language, but also at taking advantage of the full feature set of Python, including its facilities for fast prototyping and the large amount of available libraries for data processing, data analysis, data visualization, and high-performance computing. As a result, jMetalPy provides an environment for solving multi-objective optimization problems focused not only on traditional metaheuristics, but also on techniques supporting preference articulation, constrained and dynamic problems, along with a rich set of features related to the automatic generation of statistical data from the results generated, as well as the real-time and interactive visualization of the Pareto front approximations produced by the algorithms. jMetalPy offers additionally support for parallel computing in multicore and cluster systems. We include some use cases to explore the main features of jMetalPy and to illustrate how to work with it.

Diez-Gutiérrez L., San Vicente L., R. Barrón L.J., Villarán M.D., Chávarri M.

Probiotics have attracted growing interest in recent decades due to their multiple health benefits. The synergistic relationship between probiotics and prebiotics can enhance the production of metabolites called postbiotics, which are gaining increasing importance because of their beneficial functions in the gastrointestinal tract and their influence on different organs and tissues. Notable among the postbiotics is gamma-aminobutyric acid, which plays an essential role in the prevention of neural disease, type 1 diabetes, cancer, immunological disorders and asthma. Generally, gamma-aminobutyric acid is produced by lactic acid bacteria, which under certain conditions can produce a high amount of this amino acid. The food industry has leveraged this capacity to develop functional foods enriched with gamma-aminobutyric acid.