Scholarlink

<p>A cloud-native distributed pipeline integrating statistical synthetic data generation with adaptive routing and infrastructure optimisation is proposed for unmanned aerial vehicle (UAV)-based emergency medical logistics in data-sparse rural environments. The synthetic data generation component employs a kernel density estimation (KDE)-based statistical model that learns mission attribute distributions from real operational data without requiring neural generative architectures, making it well-suited for data-sparse deployment contexts. The framework combines a three-layer edge-cloud architecture with stochastic demand augmentation, enabling scalable mission orchestration and real-time reconfiguration across distributed UAV networks. A dataset of 611 real-world missions was expanded to 3,055 simulated events through synthetic generation achieving a distributional deviation of 0.0093. Evaluated in simulation across 3,000 routing instances, the framework achieves a mission success rate of 98.47%, a mean reroute delay of 0.91 minutes (an 88% reduction relative to the best published real-world benchmark), and near-optimal routing within 1.2% of the shortest-path optimum. Shortest-path solvers (Dijkstra, A<InlineEquation ID="IEq1"><EquationSource Format="TEX">\({}^{*}\)</EquationSource></InlineEquation>) are reported as idealised static-graph reference bounds rather than as competing methods, since they are not subject to the disruptions and demand surges of the stochastic mission space. Infrastructure optimisation reduces base requirements by 50% while maintaining 100% demand coverage. Stress testing across weather escalation, terrain scaling, data scarcity, and demand surge indicates stable performance above 93% under the most severe conditions tested. Ablation analysis indicates that performance gains emerge from the integrated architecture rather than any single module. The operational and energetic characteristics are additionally corroborated against an independent real-flight dataset. The framework is evaluated in simulation, grounded in real mission data and a range of validated synthetic scenarios and stress conditions, with live field deployment the natural next step.</p>

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

Cloud-native optimisation of UAV logistics for rural emergency healthcare under data scarcity

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月23日

查看全文
  • Amr Adel,
  • Mohammad Al-Rawi,
  • Anna Shillabeer,
  • Fei Dai,
  • Bhagwan Das,
  • Emre Erturk,
  • Farhad Mehdipour,
  • Anastasia Mozhaeva,
  • Jinting Zhu,
  • Mahsa Boroushaki,
  • Akbar Hossain,
  • Patrick Shearman,
  • Syed Shahid,
  • Syeda Fouzia,
  • Mohamed El-Sayyad,
  • Jyothi Kunchala,
  • Tony Jan

摘要

A cloud-native distributed pipeline integrating statistical synthetic data generation with adaptive routing and infrastructure optimisation is proposed for unmanned aerial vehicle (UAV)-based emergency medical logistics in data-sparse rural environments. The synthetic data generation component employs a kernel density estimation (KDE)-based statistical model that learns mission attribute distributions from real operational data without requiring neural generative architectures, making it well-suited for data-sparse deployment contexts. The framework combines a three-layer edge-cloud architecture with stochastic demand augmentation, enabling scalable mission orchestration and real-time reconfiguration across distributed UAV networks. A dataset of 611 real-world missions was expanded to 3,055 simulated events through synthetic generation achieving a distributional deviation of 0.0093. Evaluated in simulation across 3,000 routing instances, the framework achieves a mission success rate of 98.47%, a mean reroute delay of 0.91 minutes (an 88% reduction relative to the best published real-world benchmark), and near-optimal routing within 1.2% of the shortest-path optimum. Shortest-path solvers (Dijkstra, A\({}^{*}\)) are reported as idealised static-graph reference bounds rather than as competing methods, since they are not subject to the disruptions and demand surges of the stochastic mission space. Infrastructure optimisation reduces base requirements by 50% while maintaining 100% demand coverage. Stress testing across weather escalation, terrain scaling, data scarcity, and demand surge indicates stable performance above 93% under the most severe conditions tested. Ablation analysis indicates that performance gains emerge from the integrated architecture rather than any single module. The operational and energetic characteristics are additionally corroborated against an independent real-flight dataset. The framework is evaluated in simulation, grounded in real mission data and a range of validated synthetic scenarios and stress conditions, with live field deployment the natural next step.