Explore the vast range of titles available.

Artificial intelligence (AI) has become an essential tool for manufacturers seeking to optimize their production processes, reduce costs, and improve product quality. However, the complexity of the underlying mechanisms of AI systems can render it difficult for humans to understand and trust AI-driven decisions. Explainable AI (XAI) is a rapidly evolving field that addresses this challenge, providing human-understandable explanations of AI decisions. Based on a systematic literature survey, We explore the latest techniques and approaches that are helping manufacturers gain transparency in the decision-making processes of their AI systems. In this survey, we focus on two of the most exciting areas of XAI: ontology-based and semantic-based XAI (O-XAI, S-XAI, respectively), which provide human-readable explanations of AI decisions by exploiting semantic information. These latter types of explanations are presented in natural language and are designed to be easily understood by non-experts. Translating the decision paths taken by AI algorithms to meaningful explanations through semantics, O-XAI, and S-XAI enables humans to identify various cross-cutting concerns that influence the decisions made by the AI system. This information can be used to improve the performance of the AI system, identify potential biases in the system, and ensure that the decisions are aligned with the goals and values of the manufacturing organization. Additionally, we highlight the benefits and challenges of using O-XAI and S-XAI in manufacturing and discuss the potential for future research, aiming to provide valuable guidance for researchers and practitioners looking to leverage the power of ontologies and general semantics for XAI.

Background We focus on the importance of interpreting the quality of the labeling used as the input of predictive models to understand the reliability of their output in support of human decision-making, especially in critical domains, such as medicine. Methods Accordingly, we propose a framework distinguishing the reference labeling (or Gold Standard) from the set of annotations from which it is usually derived (the Diamond Standard). We define a set of quality dimensions and related metrics: representativeness (are the available data representative of its reference population?); reliability (do the raters agree with each other in their ratings?); and accuracy (are the raters’ annotations a true representation?). The metrics for these dimensions are, respectively, the degree of correspondence , Ψ , the degree of weighted concordance ϱ , and the degree of fineness , Φ . We apply and evaluate these metrics in a diagnostic user study involving 13 radiologists. Results We evaluate Ψ against hypothesis-testing techniques, highlighting that our metrics can better evaluate distribution similarity in high-dimensional spaces. We discuss how Ψ could be used to assess the reliability of new predictions or for train-test selection. We report the value of ϱ for our case study and compare it with traditional reliability metrics, highlighting both their theoretical properties and the reasons that they differ. Then, we report the degree of fineness as an estimate of the accuracy of the collected annotations and discuss the relationship between this latter degree and the degree of weighted concordance , which we find to be moderately but significantly correlated. Finally, we discuss the implications of the proposed dimensions and metrics with respect to the context of Explainable Artificial Intelligence (XAI). Conclusion We propose different dimensions and related metrics to assess the quality of the datasets used to build predictive models and Medical Artificial Intelligence (MAI). We argue that the proposed metrics are feasible for application in real-world settings for the continuous development of trustable and interpretable MAI systems.

Research into conversationally explainable artificial intelligence (CXAI) aims to emulate the interactive and co-constructive nature of explanations. From the perspective of human-centredness, previous work has shown that AI users prefer conversational explanations over static ones. Various approaches for modelling and implementing CXAI solutions have also been proposed. However, as for concrete dialogue capabilities possessed by such systems, previous approaches have not been properly grounded in analogous dialogue patterns in human–human interaction. The present study bridges this gap in previous work by experimentally collecting human dialogues revolving around AI predictions concerning personality estimation. By distilling the collected interactions into the kind of interactions that would occur if the explainer was a dialogue system, the study identifies dialogue strategies which might be important for CXAI to support. The study reveals that some of the observed strategies—explaining predictions with reference to general rules or patterns and signalling presupposition violations in questions raised by explainees—have received very limited attention in previous work on CXAI. Overall, the study contributes a methodology for empirically identifying CXAI desiderata in human dialogues as well as concrete results with implications for future work.

This comprehensive literature review explores the latest advancements in explainable artificial intelligence (XAI) techniques within the field of medical imaging (MI). Over the past decade, machine learning (ML) and deep learning (DL) technologies have made significant strides in healthcare, enabling advancements in tasks such as disease diagnosis, medical image segmentation, and the detection of various medical conditions. However, despite these successes, the widespread adoption of AI-driven tools in clinical practice remains slow, primarily due to the “black-box” nature of many AI models. These models make decisions without transparent reasoning, which poses significant barriers in critical medical and legal environments, where accountability and trust are paramount. This review investigates various XAI methods, focusing on both intrinsic and post-hoc techniques, to evaluate their potential in addressing these challenges. The paper examines how XAI can enhance the transparency of healthcare algorithms, thereby fostering greater trust and confidence among clinicians, patients, and regulators. Key challenges faced by XAI in healthcare, such as limited interpretability, computational complexity, and the absence of standardized evaluation frameworks, are discussed in detail. Furthermore, this work highlights existing gaps in the literature, including the lack of detailed comparative analyses of specific XAI techniques, especially in terms of their mathematical foundations and applicability across diverse medical imaging contexts. In response to these gaps, the paper introduces a new set of standardized evaluation metrics aimed at assessing XAI performance across various medical imaging tasks, such as image segmentation, classification, and diagnosis. The review proposes actionable recommendations for enhancing the effectiveness of XAI in healthcare, with a focus on real-world clinical applications. Unlike previous studies that focus on broader overviews or limited subsets of methods, this work provides a comprehensive comparative analysis of over 18 XAI techniques, emphasizing their strengths, weaknesses, and practical implications. By offering a detailed understanding of how XAI methods can be integrated into clinical workflows, this paper aims to bridge the gap between cutting-edge AI technologies and their practical use in medical settings. Ultimately, the insights provided are valuable for researchers, clinicians, and industry professionals, encouraging the adoption and standardization of XAI practices in clinical environments, thus ensuring the successful integration of transparent, interpretable, and reliable AI systems into healthcare.

Solving the challenge of occupancy prediction is crucial in order to design efficient and sustainable office spaces and automate lighting, heating, and air circulation in these facilities. In office spaces where large areas need to be observed, multiple sensors must be used for full coverage. In these cases, it is normally important to keep the costs low, but also to make sure that the privacy of the people who use such environments are preserved. Low-cost and low-resolution heat (thermal) sensors can be very useful to build solutions that address these concerns. However, they are extremely sensitive to noise artifacts which might be caused by heat prints of the people who left the space or by other objects, which are either using electricity or exposed to sunlight. There are some earlier solutions for occupancy prediction that employ low-resolution heat sensors; however, they have not addressed nor compensated for such heat artifacts. Therefore, in this paper, we presented a low-cost and low-energy consuming smart space implementation to predict the number of people in the environment based on whether their activity is static or dynamic in time. We used a low-resolution (8×8) and non-intrusive heat sensor to collect data from an actual meeting room. We proposed two novel workflows to predict the occupancy; one that is based on computer vision and one based on machine learning. Besides comparing the advantages and disadvantages of these different workflows, we used several state-of-the-art explainability methods in order to provide a detailed analysis of the algorithm parameters and how the image properties influence the resulting performance. Furthermore, we analyzed noise resources that affect the heat sensor data. The experiments show that the feature classification based method gives high accuracy when the data are clean from noise artifacts. However, when there are noise artifacts, the computer vision based method can compensate for those artifacts providing robust results. Because the computer vision based method requires an empty room recording, the feature classification based method should be chosen either when there is no expectancy of seeing noise artifacts in the data or when there is no empty recording available. We hope that our analysis brings light into understanding how to handle very low-resolution heat images in these environments. The presented workflows could be used in various domains and applications other than smart offices, where occupancy prediction is essential, e.g., for elderly care.

Medical imaging has evolved from conventional x-rays to advanced digital modalities, with artificial intelligence (AI), particularly deep learning, showing an increasingly central role in diagnostic support. This study presents a systematic literature review (SLR) of AI-driven medical imaging research focusing on classification-based models and explainability approaches in pneumonia detection. Using predefined inclusion criteria and PRISMA-guided screening, 95 studies were synthesized to identify dominant architectures, dataset trends, performance patterns, and persistent challenges. The analysis shows that convolutional neural networks (CNNs) and their variants remain the most frequently adopted models, accounting for the largest proportion of applications across x-ray, computed tomography scan (CT scan), and magnetic resonance imaging (MRI). Reported diagnostic performance across reviewed studies commonly exceeded 90% in accuracy and AUC, with models such as DeepMediX, XNet, Wavelet-CNN, and RadCLIP demonstrating strong predictive capability in their respective experimental settings. However, the review identifies significant gaps in explainability, clinical workflow integration, ethical compliance, and trust evaluation. Thus, this paper proposes a clinician-centric explainable artificial intelligence (CC-XAI) framework derived from literature synthesis. The framework integrates multilevel explainability, contextual clinical alignment, and human-in-the-loop feedback mechanisms to bridge the gap between black-box AI systems and real-world clinical practice. Rather than introducing a new predictive model, the framework provides a structured design blueprint for embedding explainability into medical imaging diagnostics. The findings highlight the continued dominance of deep learning in medical imaging while emphasizing the urgent need for clinician-oriented XAI frameworks to support transparency, trust, and responsible AI deployment in healthcare.

Power system imbalances pose significant challenges to maintaining grid stability and ensuring efficient market performance, particularly in the context of the Japanese electricity market. The primary drivers of these imbalances are identified as the nonlinear responses of power generation and consumer electricity demand to uncertain variables such as temperature and solar radiation, in addition to complex factors such as planned generator outages and operational constraints. Consequently, the prediction of imbalance signals using linear models is inherently challenging and requires the adaptation of more advanced methods in practice. This study comprehensively analyzes imbalance signal dynamics and develops practical forecasting tools using Machine Learning (ML) techniques. By incorporating a diverse range of features—including lagged imbalance data, weather forecast errors specific to Japan, and temporal patterns—we demonstrate that the prediction accuracy of imbalance signals is significantly improved compared to a baseline reflecting random forecasts based on class distribution observed during the initial training period. Furthermore, the proposed approach identifies the key drivers of hourly imbalance signals, while leveraging out-of-sample forecasting models. Based on these findings, we conclude that the use of multiple predictive models enhances the robustness and reliability of our forecasts, offering actionable tools for improving forecasting accuracy in real-world operations and contributing to a more stable and efficient electricity market.

Background Adverse drug reactions (ADRs) are statistically characterized within randomized clinical trials and postmarketing pharmacovigilance, but their molecular mechanism remains unknown in most cases. This is true even for hepatic or skin toxicities, which are classically monitored during drug design. Aside from clinical trials, many elements of knowledge about drug ingredients are available in open-access knowledge graphs, such as their properties, interactions, or involvements in pathways. In addition, drug classifications that label drugs as either causative or not for several ADRs, have been established. Methods We propose in this paper to mine knowledge graphs for identifying biomolecular features that may enable automatically reproducing expert classifications that distinguish drugs causative or not for a given type of ADR. In an Explainable AI perspective, we explore simple classification techniques such as Decision Trees and Classification Rules because they provide human-readable models, which explain the classification itself, but may also provide elements of explanation for molecular mechanisms behind ADRs. In summary, (1) we mine a knowledge graph for features; (2) we train classifiers at distinguishing, on the basis of extracted features, drugs associated or not with two commonly monitored ADRs: drug-induced liver injuries (DILI) and severe cutaneous adverse reactions (SCAR); (3) we isolate features that are both efficient in reproducing expert classifications and interpretable by experts (i.e., Gene Ontology terms, drug targets, or pathway names); and (4) we manually evaluate in a mini-study how they may be explanatory. Results Extracted features reproduce with a good fidelity classifications of drugs causative or not for DILI and SCAR (Accuracy =  0 .74 and 0 .81 , respectively). Experts fully agreed that 7 3 % and 3 8 % of the most discriminative features are possibly explanatory for DILI and SCAR, respectively; and partially agreed (2/3) for 9 0 % and 7 7 % of them. Conclusion Knowledge graphs provide sufficiently diverse features to enable simple and explainable models to distinguish between drugs that are causative or not for ADRs. In addition to explaining classifications, most discriminative features appear to be good candidates for investigating ADR mechanisms further.

Deep Reinforcement Learning (DRL) policies often exhibit fragility in unseen environments, limiting their deployment in safety-critical applications. While Robust Markov Decision Processes (R-MDPs) enhance control performance by optimizing against worst-case disturbances, the resulting conservative behaviors are difficult to interpret using standard Explainable RL (XRL) methods, which typically ignore adversarial disturbances. To bridge this gap, this paper proposes RAISE (Robust and Adversarially Informed Safe Explanations), a novel framework designed for the Noisy Action Robust MDP (NR-MDP) setting. We first introduce the Decomposed Reward NR-MDP (DRNR-MDP) and the DRNR-Deep Deterministic Policy Gradient (DRNR-DDPG) algorithm to learn robust policies and a vector-valued value function. RAISE utilizes this vectorized value function to generate contrastive explanations (“Why action a instead of b?”), explicitly highlighting the reward components such as safety or energy efficiency prioritized under worst-case attacks. Experiments on a continuous Cliffworld benchmark and the MuJoCo Hopper task demonstrate that the proposed method preserves robust performance under dynamics variations and produces meaningful, component-level explanations that align with intuitive safety and performance trade-offs. Ablation results further show that ignoring worst-case disturbances can substantially alter or invalidate explanations, underscoring the importance of adversarial awareness for reliable interpretability in robust RL.

Recently, breast types were categorized into four types based on the Breast Imaging Reporting and Data System (BI-RADS) atlas, and evaluating them is vital in clinical practice. A Japanese guideline, called breast composition, was developed for the breast types based on BI-RADS. The guideline is characterized using a continuous value called the mammary gland content ratio calculated to determine the breast composition, therefore allowing a more objective and visual evaluation. Although a discriminative deep convolutional neural network (DCNN) has been developed conventionally to classify the breast composition, it could encounter two-step errors or more. Hence, we propose an alternative regression DCNN based on mammary gland content ratio. We used 1476 images, evaluated by an expert physician. Our regression DCNN contained four convolution layers and three fully connected layers. Consequently, we obtained a high correlation of 0.93 (p < 0.01). Furthermore, to scrutinize the effectiveness of the regression DCNN, we categorized breast composition using the estimated ratio obtained by the regression DCNN. The agreement rates are high at 84.8%, suggesting that the breast composition can be calculated using regression DCNN with high accuracy. Moreover, the occurrence of two-step errors or more is unlikely, and the proposed method can intuitively understand the estimated results.