The most successful Machine Learning (ML) systems remain complex black boxes to end-users, and even experts are often unable to understand the rationale behind their decisions. The lack of transparency of such systems can have severe consequences or...
The widespread use of machine and deep learning algorithms for anomaly detection has created a critical need for robust explanations that can identify the features contributing to anomalies. However, effective evaluation methodologies for anomaly exp...
Explainable Artificial Intelligence (XAI) evaluation has grown significantly due to its extensive adoption, and the catastrophic consequence of misinterpreting sensitive data, especially in the medical field. However, the multidisciplinary nature of...
Assessing the quality of multimodal posts is a challenging task that involves using multimodal data to evaluate the quality of posts’ responses to discussion topics. Providing evaluations and explanations plays a crucial role in promoting stude...
Decision support systems are being increasingly applied in critical decision-making domains such as healthcare and criminal justice. Trust in these systems requires transparency and explainability. Among the forms of explanation, globally consistent...
In this study, a structured and methodological evaluation approach for eXplainable Artificial Intelligence (XAI) methods in medical image classification is proposed and implemented using LIME and SHAP explanations for chest X-ray interpretations. The...
Unmanned autonomous systems (UASs), including drones and robotics, are widely employed across various fields. Despite significant advances in AI-enhanced intelligent systems, there remains a notable deficiency in the interpretability and comprehensiv...
The widespread adoption of Artificial Intelligence (AI) in critical domains, such as healthcare, finance, law, and autonomous systems, has brought unprecedented societal benefits. Its black-box (sub-symbolic) nature allows AI to compute prediction wi...
In within-visual-range (WVR) air combat, basic fighter maneuvers (BFMs) are widely used. Air combat engagement database (ACED) is a dedicated database for researching WVR air combat. Utilizing the data in ACED, a Transformer-based BFM decision suppor...
This research introduces the self-explanation-based automated feedback (SEAF) system, aimed at alleviating the teaching burden through real-time, automated feedback while aligning with SDG 4’s sustainability goals for quality education. The sys...
In Crohn’s disease (CD) and ulcerative colitis (UC), the major inflammatory bowel diseases (IBD) in human beings, the tissue-damaging inflammatory response is characterized by elevated levels of Suppressor of Mothers Against Decapentaplegic (Sm...
The rapid growth of research in explainable artificial intelligence (XAI) follows on two substantial developments. First, the enormous application success of modern machine learning methods, especially deep and reinforcement learning, have created hi...
Epilepsy is a neurological disease with one of the highest rates of incidence worldwide. Although EEG is a crucial tool for its diagnosis, the manual detection of epileptic seizures is time consuming. Automated methods are needed to streamline this p...
The scientific literature and decision makers debate and explore education’s influence on regional development. However, differences among EU regions remain to be explained. The present article proposes to measure these disparites in terms of t...
In recent times two or more desalination processes have been combined to form integrated systems that have been widely used to resolve the limitations of individual processes as well as producing high performance systems. In this regard, a simple int...
The growing use of deep neural networks in critical applications is making interpretability urgently to be solved. Local interpretation methods are the most prevalent and accepted approach for understanding and interpreting deep neural networks. How...
In this paper, we propose an application of critical thinking (CT) to real-world problems, taking into account personal well-being (PB) and lifelong formation (FO). First, we raise a substantial problem with CT, which is that causal explanation is of...
To determine the effects of measures on flood risk, the International Commission for the Protection of the Rhine (ICPR), supported by the engineering consultant HKV has developed a method and a GIS-tool named “ICPR FloRiAn (Flood Risk Analysis)...
Postural deficits such as hyperlordosis (hollow back) or hyperkyphosis (hunchback) are relevant health issues. Diagnoses depend on the experience of the examiner and are, therefore, often subjective and prone to errors. Machine learning (ML) methods...
Recently, artificial intelligence (AI) approaches have gained the attention of researchers in the civil engineering field for estimating the mechanical characteristics of concrete to save the effort, time, and cost of researchers. Consequently, the c...
This research employed machine learning (ML) and SHapley Additive ExPlanations (SHAP) methods to assess the strength and impact of raw ingredients of cement mortar (CM) incorporated with waste glass powder (WGP). The data required for this study were...
Explainability features are intended to provide insight into the internal mechanisms of an Artificial Intelligence (AI) device, but there is a lack of evaluation techniques for assessing the quality of provided explanations. We propose a framework to...
All professional decisions prepared for a specific stakeholder can and must be explained. The primary role of explanation is to defend and reinforce the proposed decision, supporting stakeholder confidence in the validity of the decision. In this pap...
This study aimed to observe the impact of eight explainable AI (XAI) explanation techniques on user trust and satisfaction in the context of XAI-enhanced learning analytics while comparing two groups of STEM college students based on their Bologna st...
In the realm of mathematics education, self-explanation stands as a crucial learning mechanism, allowing learners to articulate their comprehension of intricate mathematical concepts and strategies. As digital learning platforms grow in prominence, t...
Robert Nola has recently defended an argument against the existence of God on the basis of naturalistic explanations of religious belief. I will critically evaluate his argument in this paper. Nola’s argument takes the form of an inference to t...
With the rise of DDoS attacks, several machine learning-based attack detection models have been used to mitigate malicious behavioral attacks. Understanding how machine learning models work is not trivial. This is particularly true for complex and no...
With the growing prevalence of Explainable AI (XAI), the effectiveness, transparency, usefulness, and trustworthiness of explanations have come into focus. However, recent work in XAI often still falls short in terms of integrating human knowledge an...
This study surveys and evaluates previous attempts to use game theory to explain the strategic dynamic of the Cuban missile crisis, including, but not limited to, explanations developed in the style of Thomas Schelling, Nigel Howard and Steven Brams....
Modern network intrusion detection systems (NIDSs) rely on complex deep learning models. However, the “black-box” nature of deep learning methods hinders transparency and trust in predictions, preventing the timely implementation of count...
19 September 2021
In this paper, we present the potential of Explainable Artificial Intelligence methods for decision support in medical image analysis scenarios. Using three types of explainable methods applied to the same medical image data set, we aimed to improve...
Decision support systems based on machine learning models should be able to help users identify opportunities and threats. Popular model-agnostic explanation models can identify factors that support various predictions, answering questions such as &l...
In our daily lives, we are often faced with the need to explain various phenomena, but we do not always select the most accurate explanation. For example, let us consider a “toxic” relationship with physical and psychological abuse, where...
Explainable Artificial Intelligence is a key component of artificially intelligent systems that aim to explain the classification results. The classification results explanation is essential for automatic disease diagnosis in healthcare. The human re...
Explainable artificial intelligence (XAI) methods aim to explain to the user on what basis the model makes decisions. Unfortunately, general-purpose approaches that are independent of the types of data, model used and the level of sophistication of t...
Deep Reinforcement Learning (RL) is a black-box method and is hard to understand because the agent employs a neural network (NN). To explain the behavior and decisions made by the agent, different eXplainable RL (XRL) methods are developed; for examp...
Explainable artificial intelligence provides tools to better understand predictive models and their decisions, but many such methods are limited to producing insights with respect to a single class. When generating explanations for several classes, r...
Explainable Artificial Intelligence (XAI) has primarily focused on explaining model predictions, yet a critical gap remains in explaining semantic structure discovery within knowledge graphs derived from concept maps (CMs). This study extends the OBO...
Automated vehicles (AVs) are recognized as one of the most effective measures to realize sustainable transport. These vehicles can reduce emissions and environmental pollution, enhance accessibility, improve safety, and produce economic benefits thro...
Socially-relevant and controversial topics, such as water issues, are subject to differences in the explanations that scientists and the public (herein, students) find plausible. Students need to be more evaluative of the validity of explanations (e....
Understanding the function learned by a neural network is crucial in many domains, e.g., to detect a model’s adaption to concept drift in online learning. Existing global surrogate model approaches generate explanations by maximizing the fideli...
Large Language Models (LLMs) are increasingly used in industrial monitoring and decision support, yet they remain prone to process-control hallucinations—diagnoses and explanations that sound plausible but conflict with physical constraints, se...
Explanations for static-analysis warnings assist developers in understanding potential code issues. An end-to-end pipeline was implemented to generate natural-language explanations, evaluated on 5183 warning–explanation pairs from Java reposito...
Nowadays, Artificial Intelligence systems have expanded their competence field from research to industry and daily life, so understanding how they make decisions is becoming fundamental to reducing the lack of trust between users and machines and inc...
The lack of interpretability in AI-based intrusion detection systems poses a critical barrier to their adoption in forensic cybersecurity, which demands high levels of reliability and verifiable evidence. To address this challenge, the integration of...
In the digital marketplaces, businesses can micro-monitor sales worldwide and in real-time. Due to the vast amounts of data, there is a pressing need for tools that automatically highlight changing trends and anomalous (outlier) behavior that is pote...
This paper deals with Generative Adversarial Networks (GANs) applied to face aging. An explainable face aging framework is proposed that builds on a well-known face aging approach, namely the Conditional Adversarial Autoencoder (CAAE). The proposed f...
Convolutional neural networks (CNNs) have achieved remarkable progress in recent years, largely driven by advances in computational hardware. However, their increasingly complex architectures continue to pose significant challenges for interpretabili...
A brief review and classification of technology in general begins the paper, followed by an application of the classification to two specific marathon case studies: the 2018 Boston marathon and the 2017 Nike Breaking2 Project marathon. Then concepts...
This paper focuses on explaining changes over time in globally sourced annual temporal data with the specific objective of identifying features in black-box models that contribute to these temporal shifts. Leveraging local explanations, a part of exp...
of 32