Solving Data Mining Challenges in Neutrosophic Environments Using Bio-Inspired Optimization Techniques

Abstract

Big data refers to large, diverse, and intricate data sets that are challenging to store, handle, and visualize for use in subsequent procedures or outcomes. The practice of analyzing and assessing vast amounts of data in order to find significant trends and principles is known as data mining. Data mining is crucial to many human endeavors because it can uncover valuable patterns that were previously undiscovered. Numerous machine learning algorithms are frequently employed in this context. Neutrosophic set theory (NS) is currently acknowledged as one of the most successful methods for resolving the aforementioned issues when paired with nature inspired metaheuristic algorithms and machine learning techniques. Neutrosophic set theory (NS), which is a generalization of interval fuzzy sets, has attracted a lot of interest in the data mining and machine learning fields during the last ten years because of its many uses. In order to remove ambiguity from data, add more precise data values, and increase the accuracy and efficiency of mining techniques, researchers have been inspired to integrate neutrosophic group theory (NS), which addresses natural ambiguity, into machine learning algorithms and nature-inspired metaheuristic algorithms. Numerous studies on the combination of machine learning methods and neutrosophic set theory (NS) have been submitted for publication. This has inspired us to provide an overview of the research on using NS in conjunction with metaheuristic and machine learning techniques to tackle data mining problems between 2020 and 2025.