An Interval Intuitionistic Fuzzy Characterization Method Based on Heterogeneous Big Data and Its Application in Forest Land Quality Assessment

Abstract

With the rapid advancement and ongoing evolution of data information technology, the methods and approaches for data collection have become increasingly varied. The synthesis of heterogeneous big data to minimize information loss during the aggregation process poses a significant challenge. In practical applications, fuzzy dimensionality reduction characterization has proven to be an effective approach for handling heterogeneous big data. In this study, a novel approach is proposed for characterizing and evaluating heterogeneous big data using an interval intuitionistic fuzzy framework. We establish the interval intuitionistic fuzzy transformation method for large-scale quantitative data by defining satisfaction intervals, dissatisfaction intervals, and hesitation intervals. To integrate calculation and processing for linguistic evaluation information with different granularities, a transformation formula that handles multi-granularity uncertain linguistic information and interval intuitionistic fuzzy numbers is introduced. The proposed formula aggregates heterogeneous attribute values into interval intuitionistic fuzzy numbers. We employ interval intuitionistic fuzzy entropy to determine the objective weight of each evaluation indicator. Subsequently, the interval intuitionistic fuzzy comprehensive evaluation information for each alternative scheme, enabling effective ranking based on the information, is derived. Finally, the applicability of our proposed method is verified through a case study conducted on forest land in the county area of Fujian province. This case study comprehensively assesses and ranks the forest land quality in 16 sample plots. The evaluation serves as a theoretical framework for advancing sustainable development and conservation initiatives about forest land within the county.