A Memetic-Enhanced Glowworm Swarm Optimization Algorithm with Adaptive Particle Refinement for secure and privacy-aware medical cloud computing

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Cloud computing has become an influential paradigm for facilitating effective storage, access, and sharing of medical information. Despite its merits, issues related to data security and privacy have remained central limitations to its large-scale adoption in the healthcare industry. In a bid to overcome such challenges, this article suggests a privacy-preserving framework to improve the privacy of healthcare data as well as for securing data sanitization and restoration based on a new hybrid algorithm called Memetic-Enhanced Glowworm Swarm Optimization with Adaptive Particle Refinement (ME-GSO-APR).The algorithm proposed combines Glowworm Swarm Optimization (GSO) for multimodal exploration in continuous domains, Dynamic Particle Swarm Optimization (DPSO) for faster convergence in discrete optimization, Memetic Algorithms (MA) for optimized local utilization, and Simulated Annealing (SA) to break free from optima, Memetic Algorithms (MA) for optimized local utilization, and Simulated Annealing (SA) to break free from optima. Altogether the algorithms are used to secure peak performance in data hiding as well as recovery operations. ME-GSO-APR has adaptive neighborhood scaling and improved key extraction methods that maintain data integrity without losing too much information. The proposed model was validated on three independent UCI healthcare datasets (Heart Disease, Breast Cancer Wisconsin, and Pima Indians Diabetes) and compared against benchmark optimization techniques including Artificial Bee Colony (ABC), Firefly Algorithm (FF), Glowworm Swarm Optimization (GSO), Genetically Modified Glowworm Swarm Optimization (GMGW), and the more recent Hunter-Prey Optimization (HPO, 2022) algorithm. A full ablation study, paired statistical significance testing, and a computational complexity analysis are also reported. Comparative study shows that ME-GSO-APR achieves statistically significant improvements in sanitization accuracy and restoration fidelity on higher-dimensional data, and is competitive with the strongest baseline on lower-dimensional data, in terms of sanitization accuracy, restoration fidelity, convergence rate, and robustness to significant sensitivity variations between 10% to 70% as well as in the radar chart showing multi-metric performance. Made to address the rigorous demands of privacy maintenance in cloud environments of healthcare, the superiority of the developed model is established. Clinical trial number Not applicable.