Advancing Information Systems through Artificial Intelligence: Innovative Approaches and Applications

Dear Colleagues,

The MDPI journal Information invites submissions to a Special Issue on “Advancing Information Systems through Artificial Intelligence: Innovative Approaches and Applications”.

In continuous rapid technological evolution, artificial intelligence (AI) has been integrated into the development and advancement of information systems (ISs). The objective of this Special Issue is to explore the synergies between AI and ISs, with a special emphasis on how AI-driven innovations become the transformative factors of basic aspects of ISs, such as information management, decision making, and overall IS functionality.

AI techniques and methodologies such as machine learning, large language models, neuro-fuzzy systems, and intelligent data analysis have been the vaulting horses of the radical changes in data management, data interpretation, and data utilization. The integration of AI into ISs enables advanced data processing, predictive analytics, and efficient system interoperability, leading to smarter and more responsive systems.

This Special Issue seeks novel research contributions showcasing the utilization of AI as a transformative factor of ISs, demonstrating important insights and boosting innovation in the AI–IS blending field. Towards this direction, we invite the research community to contribute original research, case studies, and reviews that highlight the impact of AI on ISs.

Topics of interest include, but are not limited to, the following:

• AI-driven data management.
• AI-driven decision support systems.
• Applications of neuro-fuzzy systems in ISs.
• Intelligent data analysis and knowledge extraction.
• Utilization of AI in e-governance and enterprise systems.
• AI-driven information retrieval and processing.
• Case studies on the practical implementation of AI in ISs.

Dr. Konstantinos Giotopoulos
Prof. Dr. Spyros Sioutas
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 1600 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.

• artificial intelligence
• information systems
• data management
• decision support systems
• neuro-fuzzy systems
• intelligent data analysis
• e-governance
• enterprise systems

Title: XCiT-lite: A Lightweight Vision Transformer for Real-time Driver Gaze Estimation with Uncertainty Quantification
Authors: Massimo Salvi
Affiliation: PolitoBIOMed Lab, Biolab - Department of Electronics and Telecommunications Politecnico di Torino Corso Duca degli Abruzzi 24, 10129 Torino, Italy
Abstract: Driver gaze estimation is crucial for evaluating attention, situational awareness, and readiness in both manual and automated driving scenarios. This paper presents a novel approach to gaze zone estimation using a lightweight vision transformer and uncertainty quantification. We introduce XCiT-lite, a modified Cross-Covariance Image Transformer architecture optimized for efficient inference on embedded automotive hardware. Our framework integrates Mediapipe for fast face detection and incorporates uncertainty quantification through Monte Carlo dropout. To our knowledge, this is the first study to include model uncertainty in driver gaze estimation, significantly enhancing prediction reliability. We validate our approach on a custom dataset of 10,800 annotated frames from 30 diverse subjects. Experimental results show that XCiT-lite outperforms state-of-the-art techniques, achieving 94.0% accuracy across 9 gaze zones, further improving to 96.5% with uncertainty quantification. We also employ Score-CAM for model explainability, revealing adaptive feature selection across the entire face. The system maintains real-time performance, processing frames in 6.9ms (47.7ms with uncertainty quantification). By combining accuracy, efficiency, and reliability, this work advances driver gaze estimation and paves the way for more robust and interpretable driver monitoring systems in automotive safety applications.