Explainable and Trustworthy AI through Fuzzy Logic

Dear Colleagues,

In recent years, artificial intelligence has achieved remarkable performance across various domains, from image recognition and natural language processing to autonomous vehicles and financial forecasting; however, its “black‐box” nature often leaves users, developers, and regulators uncertain about how decisions are made. Fuzzy logic, with its human‐centric rule‐based reasoning and inherent ability to model uncertainty, offers an important bridge between raw data-driven models and the interpretability that real-world applications demand. By embedding linguistic variables (“high,” “medium,” “low”) and expert knowledge into adaptive inference engines, fuzzy systems render AI decisions transparent, traceable, and aligned with human intuition.

We aim to gather cutting-edge research that advances both theory and practice at this intersection. We invite contributions that achieve the following:

• Innovate hybrid architectures, combining fuzzy rule systems with deep learning, reinforcement learning, or probabilistic models to deliver interpretable yet high-accuracy solutions.
• Develop new XAI methods grounded in fuzzy sets, e.g., fuzzy clustering for feature attribution, type-2 fuzzy explanations for second-order uncertainty, or neuro-fuzzy additive models for transparent prediction.
• Demonstrate real-world impact in high-stakes areas such as healthcare diagnostics, financial risk assessment, autonomous control, and critical infrastructure, showcasing how fuzzy-enhanced explainability can improve trust, compliance, and human-in-the-loop collaboration.
• Evaluate trustworthiness metrics tailored to fuzzy-logic frameworks, including robustness under noisy inputs, consistency of rule-based justifications, and measures of user comprehension and acceptance.
• Explore regulatory and ethical dimensions, addressing how fuzzy‐based XAI can satisfy emerging standards for accountability, fairness, and transparency in AI deployment.

By bringing together interdisciplinary advances, from algorithmic innovations to user-centric evaluations, this collection will chart the future of AI systems that users can both trust and understand. We welcome original research articles, comprehensive reviews, and application case studies that not only push the boundaries of fuzzy logic and explainable AI but also demonstrate tangible benefits in real-world settings. Scholars, practitioners, and industry experts are encouraged to share insights, methodologies, and best practices that will shape a new generation of transparent, reliable, and socially responsible intelligent systems.

Dr. Namal Rathnayake
Prof. Dr. Yukinobu Hoshino
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• explainable AI (XAI)
• fuzzy rule-based systems
• trustworthy AI
• neuro-fuzzy models
• uncertainty quantification
• human-in-the-loop reasoning
• AI transparency metrics