Talhe Ghodousiyan, Mehdi Razani, Amir Hossein Mehdikhani, Arash Keshtkar, Ali Kh Mirzaie, Alireza Mansouri, Ali Akbar Kiaei , Hossein Shirazi , Mustafa Dehpahlavan, Abdolbasir Hosseinbor,
Volume 7, Issue 3 (11-2024)
Abstract
Artificial intelligence (AI) and machine learning (ML) have emerged as transformative tools in preserving, analyzing, and representing cultural heritage and arts. This article provides a systematic and comprehensive review of AI applications in this domain, exploring their potential to address longstanding challenges such as natural degradation, limited accessibility, and complex documentation. By integrating classical and advanced ML algorithms, we examine case studies including the Time Machine Europe project, the Ithaca model for ancient Greek texts, and metaverse-based heritage digitization. These initiatives demonstrate AI’s capacity to enhance precision, speed, and interactivity in heritage tasks, from virtual reconstruction to multimodal data analysis. However, limitations such as data quality, ethical concerns, and computational complexity pose significant barriers to widespread adoption. Emerging technologies like non-fungible tokens (NFTs), prompt engineering, and quantum AI are highlighted as future directions that promise further innovation. This study underscores the need for interdisciplinary collaboration and ethical frameworks to ensure sustainable advancements, offering a roadmap for researchers and policymakers in the digital era.
Mohammadali Ashraf Ganjouei, Elham Shabaninia ,
Volume 8, Issue 2 (9-2025)
Abstract
Artificial intelligence is rapidly transforming the landscape of education, yet its potential in restoration education has remained largely unexplored.
This research investigates how various artificial intelligence tools intersect with the teaching and learning of restoration at the university level.
Drawing on three major learning theories—experiential, constructivist, and connectivist—the study analyzes research from recent years to determine where AI aligns with or departs from effective pedagogical practices. The findings show that AI-driven technologies can significantly
strengthen concrete experience, active learning, social interaction, and prior knowledge integration which are associated with experiential and
constructivist learning, and also lifelong learning, technological facilitation, networking and communication, cognitive skills, and digital collaboration in connectivist. However, certain aspects, particularly those requiring in-depth contextual and textual understanding specific to heritage sites, present ongoing challenges for AI tools. These results provide valuable insights for educators and researchers seeking to implement AI solutions in restoration-related courses.
