Scholarlink

The study on the behavior of on-campus individuals provides valuable insights for campus management, resource allocation, and planning layout. The application of multi-source data offers more objective and in-depth opportunities for exploring behavioral phenomena. Focusing on the Wuxi campus of Southeast University, this research utilized Wi-Fi probe positioning technology combined with a physical environment sensor system to comprehensively collect 28.87 million positioning data points and 340,000 environmental data points over a period of 14 days. After cleaning redundant, missing, abnormal, drifting, and ping-pong data, both types of data underwent visual analysis, and their correlations were studied. Additionally, trajectory feature extraction was conducted using a convolutional autoencoder neural network. The study revealed the temporal distribution of pedestrian flow, the spatial distribution of stopover behavior, and the spatiotemporal characteristics of pedestrian trajectories. This provides a reliable basis for guiding crowd behavior by improving specific campus areas and the physical environment.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Analysis of Campus Crowd Behavior Based on Location Data and Physical Environment Data: A Case Study of Southeast University Wuxi Campus

  • 会议论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年

查看全文
  • Ye Tang,
  • Junqiang Sun,
  • Guangjin Wang,
  • Wenjin Hong,
  • Li Li

摘要

The study on the behavior of on-campus individuals provides valuable insights for campus management, resource allocation, and planning layout. The application of multi-source data offers more objective and in-depth opportunities for exploring behavioral phenomena. Focusing on the Wuxi campus of Southeast University, this research utilized Wi-Fi probe positioning technology combined with a physical environment sensor system to comprehensively collect 28.87 million positioning data points and 340,000 environmental data points over a period of 14 days. After cleaning redundant, missing, abnormal, drifting, and ping-pong data, both types of data underwent visual analysis, and their correlations were studied. Additionally, trajectory feature extraction was conducted using a convolutional autoencoder neural network. The study revealed the temporal distribution of pedestrian flow, the spatial distribution of stopover behavior, and the spatiotemporal characteristics of pedestrian trajectories. This provides a reliable basis for guiding crowd behavior by improving specific campus areas and the physical environment.