Scholarlink

<p>The rapid integration of Internet of Things (IoT) devices in healthcare demands a robust framework to ensure secure patient monitoring and timely attack detection. This study proposes a Secure Healthcare Monitoring and Attack Detection Framework (SHMADF) designed to safeguard IoT-enabled healthcare environments by leveraging advanced data processing and security techniques. The framework initiates with comprehensive data collection from IoT sensors and network traffic within healthcare settings. Preprocessing steps—including removal of duplicates, handling missing data, and Z-score normalization—prepare the data for efficient analysis. Feature extraction targets low-level and protocol-specific features, Session-Level and Statistical Features. Thus, the extracted features were fused by Weighted Feature Concatenation (WFC). To optimize feature selection, a novel hybrid metaheuristic—Cuckoo-Bat Echolocation Search (CBES)—combines the strengths of Cuckoo Search and Bat Algorithm, enhancing detection accuracy. Data confidentiality during transmission is ensured through a Chaotic Map-Based Stream Cipher Encryption (CMSCE), tailored for resource-constrained IoT devices. Moreover, the encrypted data are stored in cloud and it support real-time data aggregation and low-latency decision-making. The core detection engine employs a hybrid ConvGRU-Net model, merging Convolutional Neural Networks with Gated Recurrent Units for spatial–temporal pattern recognition of cyber-attacks. Additionally, an interactive alert and feedback system offers real-time visualization and adaptive model refinement, enabling proactive healthcare management. The proposed framework demonstrates potential for comprehensive, efficient, and secure IoT healthcare monitoring. The proposed SHMADF model achieved superior performance with 99.35% accuracy, 99.3% precision, 99.4% recall, and 99.35% F1-score. It demonstrated low FPR (1.0%) and FNR (0.6%), with fast encryption (10.2&#xa0;ms), decryption (9.8&#xa0;ms), and key generation (2.6&#xa0;ms), ensuring secure, real-time IoT healthcare monitoring and attack detection.</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

SHMADF: A Secure and Intelligent Framework for IoT-Enabled Healthcare Monitoring and Attack Detection

  • 期刊论文

  • 发表日期：

    2025年10月28日

查看全文
  • Renuka Sagar,
  • N. V. Sanjay Kumar,
  • Anitha S. Sastry,
  • Nanditha Krishna,
  • Reshma S

摘要

The rapid integration of Internet of Things (IoT) devices in healthcare demands a robust framework to ensure secure patient monitoring and timely attack detection. This study proposes a Secure Healthcare Monitoring and Attack Detection Framework (SHMADF) designed to safeguard IoT-enabled healthcare environments by leveraging advanced data processing and security techniques. The framework initiates with comprehensive data collection from IoT sensors and network traffic within healthcare settings. Preprocessing steps—including removal of duplicates, handling missing data, and Z-score normalization—prepare the data for efficient analysis. Feature extraction targets low-level and protocol-specific features, Session-Level and Statistical Features. Thus, the extracted features were fused by Weighted Feature Concatenation (WFC). To optimize feature selection, a novel hybrid metaheuristic—Cuckoo-Bat Echolocation Search (CBES)—combines the strengths of Cuckoo Search and Bat Algorithm, enhancing detection accuracy. Data confidentiality during transmission is ensured through a Chaotic Map-Based Stream Cipher Encryption (CMSCE), tailored for resource-constrained IoT devices. Moreover, the encrypted data are stored in cloud and it support real-time data aggregation and low-latency decision-making. The core detection engine employs a hybrid ConvGRU-Net model, merging Convolutional Neural Networks with Gated Recurrent Units for spatial–temporal pattern recognition of cyber-attacks. Additionally, an interactive alert and feedback system offers real-time visualization and adaptive model refinement, enabling proactive healthcare management. The proposed framework demonstrates potential for comprehensive, efficient, and secure IoT healthcare monitoring. The proposed SHMADF model achieved superior performance with 99.35% accuracy, 99.3% precision, 99.4% recall, and 99.35% F1-score. It demonstrated low FPR (1.0%) and FNR (0.6%), with fast encryption (10.2 ms), decryption (9.8 ms), and key generation (2.6 ms), ensuring secure, real-time IoT healthcare monitoring and attack detection.