Exploring Biomedical Video Source Identification: Transitioning from Fuzzy-Based Systems to Machine Learning Models

In recent years, the field of biomedical video source identification has witnessed a significant evolution driven by advances in both fuzzy-based systems and machine learning models. This paper presents a comprehensive survey of the current state of the art in this domain, highlighting the transition from traditional fuzzy-based approaches to the emerging dominance of machine learning techniques. Biomedical videos have become integral in various aspects of healthcare, from medical imaging and diagnostics to surgical procedures and patient monitoring. The accurate identification of the sources of these videos is of paramount importance for quality control, accountability, and ensuring the integrity of medical data. In this context, source identification plays a critical role in establishing the authenticity and origin of biomedical videos. This survey delves into the evolution of source identification methods, covering the foundational principles of fuzzy-based systems and their applications in the biomedical context. It explores how linguistic variables and expert knowledge were employed to model video sources, and discusses the strengths and limitations of these early approaches. By surveying existing methodologies and databases, this paper contributes to a broader understanding of the field's progress and challenges.