Tourism Resource Management and Optimization Based on Internet of Things Edge Computing

Abstract

Tourism is a significant driver of economic growth, contributing to local economies while fostering cultural exchange and promoting environmental awareness. Effective tourism resource management is essential for optimizing both the efficiency and sustainability of tourism destinations. The increasing number of tourists has raised concerns about the need to monitor the natural environment in real-time. To address these challenges, this research integrates the Internet of Things (IoT) and edge computing to enhance resource management in tourism hotspots. By leveraging IoT devices and sensors, real-time data on visitor flow, resource utilization and environmental factors are collected and processed locally via edge computing. Data cleaning and filtering techniques are applied to ensure the integrity of the collected data, removing noise and inconsistencies. Additionally, t-distributed stochastic neighbor embedding (t-SNE) is used for dimensionality reduction, simplifying complex data and enabling effective visualization for decision-making. The research further proposes the use of an enhanced hippopotamus optimized deep convolutional neural network (EHO-DCNN) to model and predict optimal resource allocation strategies. The proposed method outperforms existing models, achieving accuracy (91.5%), recall (91.7%), precision (92.3%), and F1 score (93.1%). These results demonstrate the method's effectiveness in real-time monitoring and predictive analytics. This integrated approach enables efficient resource management, contributing to both enhanced visitor experiences and the sustainable development of tourism practices.