Scholarlink

<p>Urban areas worldwide grapple with the persistent issue of traffic management. Various intelligent techniques has emerged to tackle this problem, but they often rely on costly traffic lights and struggle with emergency situations. This research introduces three innovative: (i) Deep Mutual Exclusion Algorithm based on Single Instruction (D-MEASIR), (ii) D-Mutual Exclusion Algorithm based on optimal path (D-MEAPRI), and (iii) Deep Mutual Exclusion Algorithm based on Multi-Agent Systems (D-MEAMAS). These algorithms facilitate management within a group through a queue structure using traffic prediction dataset, employing external elements like routers for internal communication. Beyond presenting experimental and simulation outcomes, the article conducts a comprehensive statistical analysis, comparing the efficiency of D-MEASIR, D-MEAPRI, and D-MEAMAS with existing alternatives. Finally, these algorithms demonstrate remarkable efficiency while maintaining a CC of O(n) for accessing critical sections.</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

Revolutionizing Urban Traffic Management: IoT-Driven Algorithms for Intelligent Transportation Systems

  • 期刊论文

  • 发表日期：

    2025年3月13日

查看全文
  • M. Sreelekha,
  • Midhunchakkaravarthy

摘要

Urban areas worldwide grapple with the persistent issue of traffic management. Various intelligent techniques has emerged to tackle this problem, but they often rely on costly traffic lights and struggle with emergency situations. This research introduces three innovative: (i) Deep Mutual Exclusion Algorithm based on Single Instruction (D-MEASIR), (ii) D-Mutual Exclusion Algorithm based on optimal path (D-MEAPRI), and (iii) Deep Mutual Exclusion Algorithm based on Multi-Agent Systems (D-MEAMAS). These algorithms facilitate management within a group through a queue structure using traffic prediction dataset, employing external elements like routers for internal communication. Beyond presenting experimental and simulation outcomes, the article conducts a comprehensive statistical analysis, comparing the efficiency of D-MEASIR, D-MEAPRI, and D-MEAMAS with existing alternatives. Finally, these algorithms demonstrate remarkable efficiency while maintaining a CC of O(n) for accessing critical sections.