Scholarlink

<p>Realtime object identification and examination, driven by Artificial Intelligence (AI), have garnered tremendous importance across diverse applications in the digital era. The successful implementation of Industry 4.0 relies heavily on the integration of digital informatics and decision-making, which is crucial for smart manufacturing, Logistics 4.0, and the digitization of the supply chain. Nevertheless, a significant portion of digital content lacks interconnectedness. Therefore, the introduction of the Zebra-based Modular Digital Twin Model (ZbMDTM) presents a novel optimization algorithm. This suggested model aims to avoid potential malfunctions of machines. The ZbMDTM process was implemented to enhance the support for predictive maintenance tasks through the execution of a task allocation process focused on material recognition and maintenance. Finally, the performance measures were assessed and accorded a comparable emphasis as in prior studies. The other models were surpassed by it, attaining an F1 score of 97.6%. The evaluation of the optimized parameters was subsequently assessed in terms of F1 score, computation time, life span, and Latency. The performance of this method was validated on several existing models to showcase the enhancement. The delay value achieved by the proposed ZbMDTM method is 9%, which is less than that of any other method.</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

Task support and collaborative capabilities enhancement an mixed reality and digital twin environment using an optimized network

  • 期刊论文

  • 发表日期：

    2025年10月6日

查看全文
  • Anurag Tiwari,
  • Nileshkumar Patel,
  • Shishir Kumar

摘要

Realtime object identification and examination, driven by Artificial Intelligence (AI), have garnered tremendous importance across diverse applications in the digital era. The successful implementation of Industry 4.0 relies heavily on the integration of digital informatics and decision-making, which is crucial for smart manufacturing, Logistics 4.0, and the digitization of the supply chain. Nevertheless, a significant portion of digital content lacks interconnectedness. Therefore, the introduction of the Zebra-based Modular Digital Twin Model (ZbMDTM) presents a novel optimization algorithm. This suggested model aims to avoid potential malfunctions of machines. The ZbMDTM process was implemented to enhance the support for predictive maintenance tasks through the execution of a task allocation process focused on material recognition and maintenance. Finally, the performance measures were assessed and accorded a comparable emphasis as in prior studies. The other models were surpassed by it, attaining an F1 score of 97.6%. The evaluation of the optimized parameters was subsequently assessed in terms of F1 score, computation time, life span, and Latency. The performance of this method was validated on several existing models to showcase the enhancement. The delay value achieved by the proposed ZbMDTM method is 9%, which is less than that of any other method.