Thermal damage to ocular tissues is a critical medical concern because even small temperature elevations can impair corneal endothelial function, accelerate cataract formation, and disrupt retinal metabolism. This issue is particularly relevant in regions with intense thermal environments, such as Saudi Arabia, where preventive health care and advanced biomedical facilities are required. This study develops a predictive framework for estimating temperature distributions within the human eye under external heat exposure. A dual-phase-lag (DPL) bioheat transfer model incorporating two thermal relaxation times is formulated to capture finite speed thermal wave propagation in the multilayer structure of the eye, and closed-form analytical solutions are obtained using a normal mode approach. A mechanics-informed machine learning surrogate model is then constructed using data generated from the analytical DPL solutions, enabling rapid prediction of intraocular temperature across the parameter space. Parametric investigations examine the effects of ambient temperature, evaporation rate, tissue porosity, and blood perfusion on the thermal response of the six ocular layers. Comparisons with the Lord–Shulman and classical Fourier models reveal important differences in predicted temperature behavior under non-Fourier heat transfer. Additional analyses—including thermal safety mapping, sensitivity assessment, and response surface visualization—provide further insight into the combined influence of environmental and physiological parameters. The results show that non-Fourier thermal effects significantly influence peak intraocular temperature, while ambient temperature and evaporation dominate anterior eye heating and perfusion primarily affects deeper tissues. The present model assumes axisymmetric geometry and temperature-independent material properties, which may be extended in future studies using three-dimensional or patient-specific models. Overall, the proposed hybrid analytical–machine learning framework provides an efficient tool for ocular thermal risk assessment and supports the development of preventive strategies for populations exposed to extreme thermal environments.
This paper presents a novel metaheuristic methodology for Transmission Network Expansion Planning (TNEP) that incorporates demand uncertainty and N-1 security constraints using Quadratic Unconstrained Binary Optimization (QUBO) in combination with Monte Carlo Simulations (MCS). As power systems become increasingly complex, there is a growing need for planning techniques that ensure reliability and cost-effectiveness under uncertain conditions. The proposed method reformulates the constrained TNEP problem into an unconstrained binary optimization model, allowing for efficient decision-making through the use of binary variables. The Monte Carlo simulation is employed to evaluate system performance for varied demand conditions. The method is applied to the IEEE 14-Bus system under normal operation and with a 20
Nanorobots have been used in smart health to collect time series data such as electrocardiograms and electroencephalograms. Real-time classification of dynamic time series signals in nanorobots is a challenging task. Nanorobots in the nanoscale range require a classification algorithm with low computational complexity. First, the classification algorithm should be able to dynamically analyze time series signals and update itself to process the concept drifts (CD). Second, the classification algorithm should have the ability to handle catastrophic forgetting (CF) and classify historical data. Most importantly, the classification algorithm should be energy-efficient to use less computing power and memory to classify signals in real-time on a smart nanorobot. To solve these challenges, we design an algorithm that can Prevent Concept Drift in Online continual Learning for time series classification (PCDOL). The prototype suppression item in PCDOL can reduce the impact caused by CD. It also solves the CF problem through the replay feature. The computation per second and the memory consumed by PCDOL are only 3.572M and 1KB, respectively. The experimental results show that PCDOL is better than several state-of-the-art methods for dealing with CD and CF in energy-efficient nanorobots.
Smart healthcare aims to revolutionize medical services by integrating artificial intelligence (AI). The limitations of classical machine learning include privacy concerns that prevent direct data sharing among medical institutions, untimely updates, and long training times. To address these issues, this study proposes a digital twin-assisted quantum federated learning algorithm (DTQFL). By leveraging the 5G mobile network, digital twins (DT) of patients can be created instantly using data from various Internet of Medical Things (IoMT) devices and simultaneously reduce communication time in federated learning (FL) at the same time. DTQFL generates DT for patients with specific diseases, allowing for synchronous training and updating of the variational quantum neural network (VQNN) without disrupting the VQNN in the real world. This study utilized DTQFL to train its own personalized VQNN for each hospital, considering privacy security and training speed. Simultaneously, the personalized VQNN of each hospital was obtained through further local iterations of the final global parameters. The results indicate that DTQFL can train a good VQNN without collecting local data while achieving accuracy comparable to that of data-centralized algorithms. In addition, after personalized training, the VQNN can achieve higher accuracy than that without personalized training.
