Scholarlink

In the ever-increasing need to optimize healthcare systems, an effective tool for hospital queue management is imperative for enhancing patient satisfaction and optimizing resource utilization. Pre-existing queue management tools and methods often struggle to handle the fluctuating patient flow, which in turn leads to an extended waiting time for patients. This paper introduces a Hospital Queue Management System that leverages the YOLOv8-seg model for real-time person detection, SORT algorithm for patient tracking, and IoT devices for queue status monitoring. The evaluation of this tool is performed through key performance metrics, which include detection accuracy, average wait times, and processing speed. Experimental results show that this technique reduces average wait times, achieving an Average Precision of 0.557 and Recall ratings of 0.598, 0.782, and 0.847 for small, medium, and large-scale detection, respectively. The system maintains real-time performance at 15 fps (FPS) across various patient densities and hospital environments. This approach toward hospital queue management has exhibited crucial advancements in reducing of waiting times and improving patient flow as compared to conventional systems and hence proves to be a scalable and ideal solution for modern hospital infrastructure.

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

Real-Time Hospital Queue Management Tool: Integrating YOLO and SORT Algorithms with IoT for Patient Flow Optimization

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Swati Sharma,
  • Vanshikaa Jindal,
  • Riya Sistu,
  • Suniti Gupta

摘要

In the ever-increasing need to optimize healthcare systems, an effective tool for hospital queue management is imperative for enhancing patient satisfaction and optimizing resource utilization. Pre-existing queue management tools and methods often struggle to handle the fluctuating patient flow, which in turn leads to an extended waiting time for patients. This paper introduces a Hospital Queue Management System that leverages the YOLOv8-seg model for real-time person detection, SORT algorithm for patient tracking, and IoT devices for queue status monitoring. The evaluation of this tool is performed through key performance metrics, which include detection accuracy, average wait times, and processing speed. Experimental results show that this technique reduces average wait times, achieving an Average Precision of 0.557 and Recall ratings of 0.598, 0.782, and 0.847 for small, medium, and large-scale detection, respectively. The system maintains real-time performance at 15 fps (FPS) across various patient densities and hospital environments. This approach toward hospital queue management has exhibited crucial advancements in reducing of waiting times and improving patient flow as compared to conventional systems and hence proves to be a scalable and ideal solution for modern hospital infrastructure.