Robustness is a pivotal attribute of trustworthy explainable artificial intelligence, ensuring that explanations remain consistent when inputs are perturbed slightly. Although numerous metrics have been proposed to quantify this robustness, their reliability remains largely unverified. This study introduces a novel meta-evaluation framework for robustness metrics, grounded in controlled, verifiable experimental setups. We propose three sanity tests: perfect explanation, normal explanation, and random output. These tests facilitate the systematic assessment of the validity of robustness metrics using transparent models. By evaluating seven state-of-the-art robustness metrics across four benchmark datasets, our results reveal significant shortcomings: no single metric consistently achieves the expected outcomes across all tests. These findings underscore fundamental flaws in robustness metrics and emphasise the necessity for improved evaluation frameworks. Our methodology provides a reproducible, assumption-light benchmark for identifying unreliable metrics before deployment in critical applications.

The growing integration of Artificial intelligence (AI) into financial markets offers unprecedented opportunities for advanced forecasting, automated decision-making, and strategic trading. However, despite notable progress, current systems often fail to balance predictive performance with critical requirements such as explainability, dynamic risk management, and regulatory alignment, especially in institutional contexts. This paper introduces the Explainable Deep Trading Approach (EDTA), a novel modular framework that combines Large Language Models (LLMs), multi-agent architectures, explainable AI (XAI) techniques, and adaptive risk management into a unified, transparent trading system. Unlike prior models focused solely on accuracy, EDTA embeds explainability and risk differentiation directly within its decision-making process, ensuring outputs that are both high-performing and regulatorily compliant under frameworks such as MiFID II. We conduct extensive empirical evaluations across diverse financial assets and temporal resolutions, demonstrating that EDTA achieves a Mean Directional Accuracy (MDA) of 72.4%, with an F1-score of 0.71, outperforming established benchmarks such as FinGPT, FinBERT, and DeepScalper. Furthermore, a domain expert panel rated EDTA’s generated explanations highly, with average scores of 4.6/5 for clarity, 4.4/5 for regulatory alignment, and 4.5/5 for practical relevance. These results highlight EDTA as a robust, next-generation framework that addresses both technological and regulatory demands, paving the way for more trustworthy, explainable, and effective AI-driven financial systems.

This work presents a novel approach for selecting the optimal ensemble-based classification method and features with a primarly focus on achieving generalization, based on the state-of-the-art, to provide diagnostic support for Sickle Cell Disease using peripheral blood smear images of red blood cells. We pre-processed and segmented the microscopic images to ensure the extraction of high-quality features. To ensure the reliability of our proposed system, we conducted an in-depth analysis of interpretability. Leveraging techniques established in the literature, we extracted features from blood cells and employed ensemble machine learning methods to classify their morphology. Furthermore, we have devised a methodology to identify the most critical features for classification, aimed at reducing complexity and training time and enhancing interpretability in opaque models. Lastly, we validated our results using a new dataset, where our model overperformed state-of-the-art models in terms of generalization. The results of classifier ensembled of Random Forest and Extra Trees classifier achieved an harmonic mean of precision and recall (F1-score) of 90.71% and a Sickle Cell Disease diagnosis support score (SDS-score) of 93.33%. These results demonstrate notable enhancement from previous ones with Gradient Boosting classifier (F1-score 87.32% and SDS-score 89.51%). To foster scientific progress, we have made available the parameters for each model, the implemented code library, and the confusion matrices with the raw data.

The use of eXplainable Artificial Intelligence (XAI) systems has introduced a set of challenges that need resolution. Herein, we focus on how to correctly select an XAI method, an open questions within the field. The inherent difficulty of this task is due to the lack of a ground truth. Several authors have proposed metrics to approximate the fidelity of different XAI methods. These metrics lack verification and have concerning disagreements. In this study, we proposed a novel methodology to verify fidelity metrics, using transparent models. These models allowed us to obtain explanations with perfect fidelity. Our proposal constitutes the first objective benchmark for these metrics, facilitating a comparison of existing proposals, and surpassing existing methods. We applied our benchmark to assess the existing fidelity metrics in two different experiments, each using public datasets comprising 52,000 images. The images from these datasets had a size a 128 by 128 pixels and were synthetic data that simplified the training process. We identified that two fidelity metrics, Faithfulness Estimate and Faithfulness Correlation, obtained the expected perfect results for linear models, showing their ability to approximate fidelity for this kind of methods. However, when present with non-linear models, as the ones most used in the state-of-the-art,all metric values, indicated a lack of fidelity, with the best one showing a 30% deviation from the expected values for perfect explanation. Our experimentation led us to conclude that the current fidelity metrics are not reliable enough to be used in real scenarios. From this finding, we deemed it necessary to development new metrics, to avoid the detected problems, and we recommend the usage of our proposal as a benchmark within the scientific community to address these limitations. • Usage of XAI methods lacks an objective evaluation of the fidelity between the explanation and the real cause learned by the model. • The fidelity metrics proposed in the state-of-the-art lack a strong validation of their results. • Fidelity metrics can be used alongside transparent models to validate their correctness. • The existing fidelity metrics are not reliable enough to be used in a real scenario.

The evaluation of the fidelity of eXplainable Artificial Intelligence (XAI) methods to their underlying models is a challenging task, primarily due to the absence of a ground truth for explanations. However, assessing fidelity is a necessary step for ensuring a correct XAI methodology. In this study, we conduct a fair and objective comparison of the current state-of-the-art XAI methods by introducing three novel image datasets with reliable ground truth for explanations. The primary objective of this comparison is to identify methods with low fidelity and eliminate them from further research, thereby promoting the development of more trustworthy and effective XAI techniques. Our results demonstrate that XAI methods based on the direct gradient calculation and the backpropagation of output information to input yield higher accuracy and reliability compared to methods relying on perturbation based or Class Activation Maps (CAM). However, these methods tend to generate more noisy saliency maps. These findings have significant implications for the advancement of XAI methods, enabling the elimination of erroneous explanations and fostering the development of more robust and reliable XAI.

Abstract This study presents a method to improve state-of-the-art concave point detection methods as the first step towards effectively segmenting overlapping objects in images. The approach relies on analysing the curvature of the object contour. This method comprises three main steps. First, the original image is preprocessed to obtain the curvature value at each contour point. Second, the regions with higher curvatures are selected and a recursive algorithm is applied to refine previously selected regions. Finally, a concave point is obtained for each region by analysing the relative position of their neighbourhood. Furthermore, the experimental results indicate that improving the detection of concave points leads to better division of clusters. To evaluate the quality of the concave point detection algorithm, a synthetic dataset was constructed to simulate the presence of overlapping objects. This dataset includes the precise location of concave points, which serve as the ground truth for evaluation. As a case study, the performance of a well-known application, such as the splitting of overlapping cells in images of peripheral blood smears samples from patients with sickle cell anaemia, was evaluated. We used the proposed method to detect concave points in cell clusters and then separated these clusters by ellipse fitting.

Abstract A robust segmentation method that can be used to perform measurements on toenails is presented. The proposed method is used as the first step in a clinical trial to objectively quantify the incidence of a particular pathology. For such an assessment, it is necessary to distinguish a nail, which locally appears to be similar to the skin. Many algorithms have been used, each of which leverages different aspects of toenail appearance. We used the Hough transform to locate the tip of the toe and estimate the nail location and size. Subsequently, we classified the super-pixels of the image based on their geometric and photometric information. Thereafter, the watershed transform delineated the border of the nail. The method was validated using a 348-image medical dataset, achieving an accuracy of 0.993 and an F-measure of 0.925. The proposed method is considerably robust across samples, with respect to factors such as nail shape, skin pigmentation, illumination conditions, and appearance of large regions affected by a medical condition.

The study of cell morphology is an important aspect of the diagnosis of some diseases, such as sickle cell disease, because red blood cell deformation is caused by these diseases. Due to the elongated shape of the erythrocyte, ellipse adjustment and concave point detection are applied widely to images of peripheral blood samples, including during the detection of cells that are partially occluded in the clusters generated by the sample preparation process. In the present study, we propose a method for the analysis of the shape of erythrocytes in peripheral blood smear samples of sickle cell disease, which uses ellipse adjustments and a new algorithm for detecting notable points. Furthermore, we apply a set of constraints that allow the elimination of significant image preprocessing steps proposed in previous studies. We used three types of images to validate our method: artificial images, which were automatically generated in a random manner using a computer code; real images from peripheral blood smear sample images that contained normal and elongated erythrocytes; and synthetic images generated from real isolated cells. Using the proposed method, the efficiency of detecting the two types of objects in the three image types exceeded 99.00%, 98.00%, and 99.35%, respectively. These efficiency levels were superior to the results obtained with previously proposed methods using the same database, which is available at http://erythrocytesidb.uib.es/. This method can be extended to clusters of several cells and it requires no user inputs.

Research studies show that serious games help to motivate users in rehabilitation and therapy is better when users are motivated. In this work we experiment with serious games for cerebral palsy patients, who rarely show capacity increases with therapy which causes them demotivation. For this reason, we have implemented balance rehabilitation video games for this group of patients. The video games were developed using the prototype development paradigm, respecting the requirements indicated by physiotherapists and including desirable features for rehabilitation serious games presented in the literature. A set of patients who abandoned therapy last year due to loss of motivation, has tested the video game for a period of 6 months. Whilst using the video game no patients have abandoned therapy, showing the appropriateness of games for this kind of patients.

In most of the existing human–computer interfaces, enactive knowledge as new natural interaction paradigm has not been fully exploited yet. Recent technological advances have created the possibility to enhance naturally and significantly the interface perception by means of visual inputs, the so-called Vision-Based Interfaces (VBI). In the present paper, we explore the recovery of the user’s body posture by means of combining robust computer vision techniques and a well known inverse kinematics algorithm in real-time. Specifically, we focus on recognizing the user’s motions with a particular mean, that is, a body gesture. Defining an appropriate representation of the user’s body posture based on a temporal parameterization, we apply non-parametric techniques to learn and recognize the user’s body gestures. This scheme of recognition has been applied to control a computer videogame in real-time to show the viability of the presented approach.