Prediction and Decision-Making Process of Cultural Trends using Big Data: Enhanced Social Analysis Through an Artificial Intelligence-Based Fuzzy System
Abstract
Cultural trends are growing more popular in the tourist industry. The objective of this research is to enhance the prediction and decision-making process for cultural tourist attractions using deep learning (DL) methods and Internet of Things (IoT) technologies. The primary focus is on detecting and extracting features from Mongolian decoration trends, which will provide novel perspectives into the broad utilization of cultural tradition and visual architecture. This research proposes that fuzzy decision-making enables more precise assessments in a setting of unpredictability. The investigation creates a multiple impact through the use of a smart decision-making platform. This multiplier impact is apparent in the framework's ability to handle big databases and provide timely, accurate decision assistance, making it critical for tourist asset administration and scheduling. The outcomes of this research show that improving smart growth technologies for local tourism using IoT can improve the performance of smart approaches. In regard to pattern identification performance, VGGNet, AlexNet, and ResNet reach accuracy scores of 94.6%, 90.9%, and 97.0%, respectively, whereas the suggested fusion-based fuzzy approach achieves 98.9%. These findings provide practical data for remote tourist image development and highlight the value of using fuzzy decision algorithms in city visual and tourism development. Furthermore, the study's findings have important practical consequences for the growth of Mongolian cultural tourist attractions, as well as critical insights for investigating new approaches in image evaluation and pattern identification. This investigation provides valuable information for future study projects in relevant fields.