ML-Based Smart Queue Management System for Public Services

@article{1717976,
      author = {Dr. Balamurugan S, Dhanush S},
      title = {ML-Based Smart Queue Management System for Public Services},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {11},
      pages = {2662-2673},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1717976.pdf},
      abstract = {Public-service queue systems in hospitals, banks, and citizen-service centers still face long waits, weak transparency, and inefficient use of counters. Recent studies show that machine learning and lightweight sensing can improve waiting-time estimation and queue visibility, but the most directly relevant evidence is concentrated in healthcare, banking, and service-center applications. This paper reviews ten highly relevant queue studies and uses them to propose an ML-based smart queue management framework for public-service delivery. The review identifies queue length, arrival rate, service duration, and real-time queue-state signals as the most useful predictive inputs, while the main unresolved gaps are cross-domain generalization, prediction-allocation integration, infrastructure-light deployment, and balanced evaluation of service outcomes. Based on these findings, the paper proposes a framework that combines event capture, preprocessing, feature engineering, waiting-time prediction, dynamic counter allocation, monitoring, and HOT-Fit evaluation. The framework is intended to improve transparency, reduce congestion, and support practical queue modernization in public-service settings.},
      keywords = {Smart Queue Management System, Waiting-Time Prediction, Machine Learning, Dynamic Counter Allocation, Public Service Delivery, HOT-Fit Evaluation},
      month = {May},
      doi = {https://doi.org/10.64388/IREV9I11-1717976}
  }