Scholarlink

<p>For automated services, a wide range of Internet of Things (IOT) related technologies are currently in use. The deployment of IoT services in real-time environments has been limited by a number of concerns, including security, dependability, and fault tolerance. Additionally, the sent data is vulnerable to a variety of assaults. As a result, secure data transfer is required, and various attack types need to be categorized. In this manuscript, Blockchain with Improved Deep Residual Shrinking Network for Ensuring Cybersecurity in Iot-Driven Healthcare Systems (BC-IDRSN-IOT-HS) is proposed. The input data is first hashed using the Composite Logistic Sine Map approach, then encrypted using Martino homomorphic encryption (MHE), and finally assembled in a blockchain framework called the FileDAG. Decryption is then performed to retrieve the original data, and the cyber security attacks are categorized using Improved Deep Residual Shrinking Network (IDRSN). To improve the accuracy of IDRSN, boosted sooty tern optimization algorithm (BSTOA) is proposed. Here, Python is used for the experimentation, and two public dataset (CICIDS-2017 and ToN-IoT) are evaluated to determine the effectiveness of the proposed model. Performance parameters such as accuracy, precision, recall, F-measure, encryption time and decryption time are examined. The BC-IDRSN-IOT-HS technique reaches in the range of 5.31%, 2.75% and 4.37% higher accuracy, 3.24%, 5.39% and 2.57% higher precision when compared with existing techniques such as secret elliptic curve based bidirectional gated unit assisted residual network for enabling secure IoT data transmission and categorization using blockchain (SEC-BGARN-IOT-BC), a blockchain-orchestrated deep learning approach for secure data transmission in IoT-enabled healthcare system (BC-DL-IOT-HS) and a blockchain based federated deep learning model for secured transmission in healthcare IoT networks (BC-FDL-IOT-HS) respectively.</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

Blockchain with improved deep residual shrinking network for ensuring cybersecurity in IoT-driven healthcare systems

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月3日

查看全文
  • Mohammed Alshehri

摘要

For automated services, a wide range of Internet of Things (IOT) related technologies are currently in use. The deployment of IoT services in real-time environments has been limited by a number of concerns, including security, dependability, and fault tolerance. Additionally, the sent data is vulnerable to a variety of assaults. As a result, secure data transfer is required, and various attack types need to be categorized. In this manuscript, Blockchain with Improved Deep Residual Shrinking Network for Ensuring Cybersecurity in Iot-Driven Healthcare Systems (BC-IDRSN-IOT-HS) is proposed. The input data is first hashed using the Composite Logistic Sine Map approach, then encrypted using Martino homomorphic encryption (MHE), and finally assembled in a blockchain framework called the FileDAG. Decryption is then performed to retrieve the original data, and the cyber security attacks are categorized using Improved Deep Residual Shrinking Network (IDRSN). To improve the accuracy of IDRSN, boosted sooty tern optimization algorithm (BSTOA) is proposed. Here, Python is used for the experimentation, and two public dataset (CICIDS-2017 and ToN-IoT) are evaluated to determine the effectiveness of the proposed model. Performance parameters such as accuracy, precision, recall, F-measure, encryption time and decryption time are examined. The BC-IDRSN-IOT-HS technique reaches in the range of 5.31%, 2.75% and 4.37% higher accuracy, 3.24%, 5.39% and 2.57% higher precision when compared with existing techniques such as secret elliptic curve based bidirectional gated unit assisted residual network for enabling secure IoT data transmission and categorization using blockchain (SEC-BGARN-IOT-BC), a blockchain-orchestrated deep learning approach for secure data transmission in IoT-enabled healthcare system (BC-DL-IOT-HS) and a blockchain based federated deep learning model for secured transmission in healthcare IoT networks (BC-FDL-IOT-HS) respectively.