Scholarlink

<p>The integration of sixth-generation (6G) networks with the Internet of Things (IoT) is transforming smart healthcare by enabling ultra-low latency, high bandwidth, and intelligent connectivity across medical systems. Despite these advancements, existing healthcare IoT frameworks face three critical limitations: real-time resource allocation, secure data handling, and scalable infrastructure deployment. To address these challenges, we present a unified AI-powered 6G-IoT healthcare framework comprising three tightly integrated components: adaptive medical resource allocation, privacy-preserving anomaly detection, and scalable network optimisation. Our allocation module utilizes eXtreme Gradient Boosting (XGBoost) for predicting resource efficiency, achieving an <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(R^{2}\)</EquationSource> </InlineEquation> score of 0.988. It also incorporates a Long Short-Term Memory (LSTM)-based network reliability forecasting model refined using the Hungarian algorithm, which achieves a latency of under 50 ms. To safeguard patient data, we incorporate federated autoencoders and differential privacy within a blockchain-enabled trust architecture, delivering decentralised anomaly detection and a secure throughput of 1.5 KB/sec. For deployment at scale, the system supports over 240 concurrent sensors while maintaining energy consumption at just 41 W/hr through dynamic spectrum allocation and intelligent power cycling. Experimental results highlight the framework’s ability to deliver responsive, secure, and energy-efficient healthcare services, paving the way for next-generation smart hospital environments.</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

An AI and 6G-IoT enabled computational framework for intelligent medical resource allocation and adaptive personalized healthcare

  • 期刊论文

  • 发表日期：

    2025年11月28日

查看全文
  • Ahmad Almadhor,
  • Mohamed Ayari,
  • Abdullah Alqahtani,
  • Abdullah Al Hejaili,
  • Belgacem Bouallegue,
  • Roben A. Juanatas,
  • Gabriel Avelino Sampedro

摘要

The integration of sixth-generation (6G) networks with the Internet of Things (IoT) is transforming smart healthcare by enabling ultra-low latency, high bandwidth, and intelligent connectivity across medical systems. Despite these advancements, existing healthcare IoT frameworks face three critical limitations: real-time resource allocation, secure data handling, and scalable infrastructure deployment. To address these challenges, we present a unified AI-powered 6G-IoT healthcare framework comprising three tightly integrated components: adaptive medical resource allocation, privacy-preserving anomaly detection, and scalable network optimisation. Our allocation module utilizes eXtreme Gradient Boosting (XGBoost) for predicting resource efficiency, achieving an \(R^{2}\) score of 0.988. It also incorporates a Long Short-Term Memory (LSTM)-based network reliability forecasting model refined using the Hungarian algorithm, which achieves a latency of under 50 ms. To safeguard patient data, we incorporate federated autoencoders and differential privacy within a blockchain-enabled trust architecture, delivering decentralised anomaly detection and a secure throughput of 1.5 KB/sec. For deployment at scale, the system supports over 240 concurrent sensors while maintaining energy consumption at just 41 W/hr through dynamic spectrum allocation and intelligent power cycling. Experimental results highlight the framework’s ability to deliver responsive, secure, and energy-efficient healthcare services, paving the way for next-generation smart hospital environments.