Explainable Artificial Intelligence: Concepts, Techniques, Analytics and Applications
A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".
Deadline for manuscript submissions: 31 March 2025 | Viewed by 48
Special Issue Editors
Interests: computer vision; machine learning; deep learning; wireless sensor networks; IoT
Special Issues, Collections and Topics in MDPI journals
Interests: neuro-fuzzy technologies; fuzzy logic approaches; adaptive fuzzy
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Explainable Artificial Intelligence (XAI) has emerged as a crucial field addressing the need for transparency and understanding in AI systems to foster trust and accountability. XAI aims to make AI decision-making processes comprehensible to humans by developing methodologies that clarify how AI systems arrive at their decisions, encompassing both final outputs and intermediate processes. Techniques to enhance explainability include creating inherently interpretable models like decision trees, applying post hoc methods such as LIME and SHAP to existing models, and using visualization tools like feature importance plots and heatmaps. Analytical frameworks in XAI evaluate the accuracy, comprehensibility, and actionability of explanations to ensure they are useful to end-users. XAI applications span healthcare, finance, autonomous systems, legal contexts, agriculture, and transportation, where transparency enhances trust, safety, regulatory compliance, and operational efficiency. This Special Issue explores the latest advancements in XAI, fostering collaboration and innovation in developing more explainable and reliable AI systems.
Topics of Interest:
- Bio-inspired methods, deep learning, convolutional neural networks, hybrid architectures, etc.
- Time series analysis, fractional-order controllers, gradient field methods, surface reconstruction, and other mathematical models for intelligent feature detection, extraction, and recognition.
- Embedded intelligent computer vision algorithms.
- Human, nature, technology, and various object activity recognition models.
- Hyper-parameter learning and tuning, automatic calibration, and hybrid and surrogate learning for computational intelligence in vision systems.
- Intelligent video and image acquisition techniques.
Dr. Mohit Mittal
Prof. Dr. Valentina E. Balas
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. Electronics is an international peer-reviewed open access semimonthly 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 2400 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.
Keywords
- explainable AI
- computer vision algorithms
- embedded AI
- AI approaches
