Journal Articles
Permanent URI for this collection
Browse
Recent Submissions
1 - 2 of 2
-
PublicationElectrically small spiral PIFA for deep implantable devices(IEEE, 2020)n this paper, a miniaturized implantable circularly polarized spiral Planar Inverted-F Antenna (SPIFA) in the UHF (600-800 MHz) band is presented. This antenna is intended for deep implantable devices such as leadless pacemakers and deep brain stimulation (DBS), which facilitates the reception of RF power from an external transmitter. The antenna is electrically small, with a volume of π× 5 mm × 5 mm × 3.2 mm and a diameter of 0.022λ. The performance of the proposed antenna in terms of reflection coefficient, realized gain and axial ratio are assessed when accounting for the effects of operating in different types of human body tissues, different biocompatible materials and different thicknesses and depths of the implanted antenna. Finally, the antenna is prototyped and measured in free space, a phantom model, in a cow’s fat and muscle tissues to validate the simulation results, indicating good agreements. A realized gain around −20 dBm is achieved when operating in 50 mm depth in cow’s muscle tissue while having electrically very small dimensions compared to implantable antennas reported in the literature.
-
PublicationAnalysis of the effectiveness of Metaheuristic methods on Bayesian optimization in the classification of visual field defects(MDPI, 2023)Bayesian optimization (BO) is commonly used to optimize the hyperparameters of transfer learning models to improve the model’s performance significantly. In BO, the acquisition functions direct the hyperparameter space exploration during the optimization. However, the computational cost of evaluating the acquisition function and updating the surrogate model can become prohibitively expensive due to increasing dimensionality, making it more challenging to achieve the global optimum, particularly in image classification tasks. Therefore, this study investigates and analyses the effect of incorporating metaheuristic methods into BO to improve the performance of acquisition functions in transfer learning. By incorporating four different metaheuristic methods, namely Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC) Optimization, Harris Hawks Optimization, and Sailfish Optimization (SFO), the performance of acquisition function, Expected Improvement (EI), was observed in the VGGNet models for visual field defect multi-class classification. Other than EI, comparative observations were also conducted using different acquisition functions, such as Probability Improvement (PI), Upper Confidence Bound (UCB), and Lower Confidence Bound (LCB). The analysis demonstrates that SFO significantly enhanced BO optimization by increasing mean accuracy by 9.6% for VGG-16 and 27.54% for VGG-19. As a result, the best validation accuracy obtained for VGG-16 and VGG-19 is 98.6% and 98.34%, respectively.
2 25