ZTCloudGuard: Zero Trust Context-Aware Access Management Framework to Avoid Medical Errors in the Era of Generative AI and Cloud-Based Health Information Ecosystems DOI Creative Commons
Khalid Al-hammuri, Fayez Gebali, Awos Kanan

et al.

AI, Journal Year: 2024, Volume and Issue: 5(3), P. 1111 - 1131

Published: July 8, 2024

Managing access between large numbers of distributed medical devices has become a crucial aspect modern healthcare systems, enabling the establishment smart hospitals and telehealth infrastructure. However, as technology continues to evolve Internet Things (IoT) more widely used, they are also increasingly exposed various types vulnerabilities errors. In information about 90% emerge from error human error. As result, there is need for additional research development security tools prevent such attacks. This article proposes zero-trust-based context-aware framework managing main components cloud ecosystem, including users, devices, output data. The goal benefit proposed build scoring system or alleviate errors while using in cloud-based systems. two criteria maintain chain trust. First, it critical trust score based on cloud-native microservices authentication, encryption, logging, authorizations. Second, bond created assess real-time semantic syntactic analysis attributes stored system. pre-trained machine learning model that generates scores. takes into account regulatory compliance user consent creation advantage this method applies any language adapts all attributes, relies model, not just set predefined limited attributes. results show high F1 93.5%, which proves valid detecting

Language: Английский

Hybrid deep learning-based cyberthreat detection and IoMT data authentication model in smart healthcare DOI
Manish Kumar, Sushil Kumar Singh, Sunggon Kim

et al.

Future Generation Computer Systems, Journal Year: 2025, Volume and Issue: unknown, P. 107711 - 107711

Published: Jan. 1, 2025

Language: Английский

Citations

1
Navigating Challenges and Harnessing Opportunities: Deep Learning Applications in Internet of Medical Things DOI Creative Commons

John Mulo,

Hengshuo Liang, Mian Qian

et al.

Future Internet, Journal Year: 2025, Volume and Issue: 17(3), P. 107 - 107

Published: March 1, 2025

Integrating deep learning (DL) with the Internet of Medical Things (IoMT) is a paradigm shift in modern healthcare, offering enormous opportunities for patient care, diagnostics, and treatment. Implementing DL IoMT has potential to deliver better diagnosis, treatment, management. However, practical implementation challenges, including data quality, privacy, interoperability, limited computational resources. This survey article provides conceptual framework synthesizes identifies state-of-the-art solutions that tackle challenges current applications DL, analyzes existing limitations future developments. Through an analysis case studies real-world implementations, this work insights into best practices lessons learned, importance robust preprocessing, integration legacy systems, human-centric design. Finally, we outline research directions, emphasizing development transparent, scalable, privacy-preserving models realize full healthcare. aims serve as foundational reference researchers practitioners seeking navigate harness rapidly evolving field.

Language: Английский

Citations

0
Enhanced Light‐Gradient Boosting Machine (GBM)‐Based Artificial Intelligence‐Blockchain‐Based Telesurgery in Sixth Generation Communication Using Optimization Concept DOI Creative Commons

S. Punitha,

K. S. Preetha

Journal of Electrical and Computer Engineering, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

Telesurgery and robotic surgery are two real‐time mission‐critical applications where Artificial Intelligence (AI) has a lot of perspective. In this work, blockchain‐ AI‐powered telesurgery system for 6 G communication is suggested, which describes transparent, safe, self‐managing, trustworthy structure having massive Ultra‐Reliable Low‐Latency Communication (mURLLC). The condition categorized using AI methods like Enhanced Light GBM, whose criticality scores range from 0 to 1 (after the predicted output, score corresponding disease divided into high critical, medium low critical on basis that 1). Here, parameter tuning in light GBM performed Tasmanian Devil Optimization (TDO) with consideration attaining fitness function thus referred as GBM. This proposed novel predicts final output based scores. future, recent deep learning algorithms can be considered drone‐assisted framework together hybrid optimization algorithms. GBM‐TDO model drone‐oriented respect prediction accuracy 3.22%, 3.11%, 1.84%, 3.40%, 2.26%, 1.15% advanced than Aayush, Habits, BATS, CSIMH, MGA, heuristic approach, respectively.

Language: Английский

Citations

0
Optimized Deep learning Frameworks for the Medical Image Transmission in IoMT Environment DOI
Rashmi Priya,

R. Gomathi

Journal of Smart Internet of Things, Journal Year: 2024, Volume and Issue: 2024(2), P. 148 - 165

Published: Dec. 1, 2024

Abstract The Internet of Medical Things (IoMT) is reforming healthcare by enabling interconnected medical devices and systems to facilitate efficient data collection, transmission, analysis. While IoMT has significantly improved real-time monitoring personalized care, the transmission high-resolution images remains a challenge due bandwidth constraints, latency issues, loss, computational overhead. Efficient secure image critical ensuring reliable diagnostics timely patient care in this ecosystem. This research presents an optimized Deep Learning (DL) architecture developed overcome limitations environments. proposed solution incorporates Convolutional Neural Networks (CNNs) for spatial feature extraction dimensionality reduction while preserving diagnostic-critical information, Long Short-Term Memory (LSTM) networks manage sequential mitigate issues such as packet loss latency. framework robust encryption mechanisms ensure security without increasing Once predictions are made, securely transferred cloud further analysis storage. Furthermore, Hippopotamus Optimization utilised enhance model's performance fine-tune hyperparameters, improving both efficiency accuracy. Performance evaluations were conducted using real-world datasets under varying network conditions. results demonstrate that CNN-LSTM delivers superior across key metrics, like Peak Signal-to-Noise Ratio (PSNR), accuracy, F1 score, specificity, sensitivity. Additionally, optimizes decryption times reduces consumption, transmission. approach showcases significant advancement IoMT-based imaging, paving way enhanced reliability delivery systems.

Language: Английский

Citations

0
ZTCloudGuard: Zero Trust Context-Aware Access Management Framework to Avoid Medical Errors in the Era of Generative AI and Cloud-Based Health Information Ecosystems DOI Creative Commons
Khalid Al-hammuri, Fayez Gebali, Awos Kanan

et al.

AI, Journal Year: 2024, Volume and Issue: 5(3), P. 1111 - 1131

Published: July 8, 2024

Managing access between large numbers of distributed medical devices has become a crucial aspect modern healthcare systems, enabling the establishment smart hospitals and telehealth infrastructure. However, as technology continues to evolve Internet Things (IoT) more widely used, they are also increasingly exposed various types vulnerabilities errors. In information about 90% emerge from error human error. As result, there is need for additional research development security tools prevent such attacks. This article proposes zero-trust-based context-aware framework managing main components cloud ecosystem, including users, devices, output data. The goal benefit proposed build scoring system or alleviate errors while using in cloud-based systems. two criteria maintain chain trust. First, it critical trust score based on cloud-native microservices authentication, encryption, logging, authorizations. Second, bond created assess real-time semantic syntactic analysis attributes stored system. pre-trained machine learning model that generates scores. takes into account regulatory compliance user consent creation advantage this method applies any language adapts all attributes, relies model, not just set predefined limited attributes. results show high F1 93.5%, which proves valid detecting

Language: Английский

Citations

0