Search

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. [ABSTRACT FROM AUTHOR]

Nowadays, most people rely on the electronic devices for work, communicating with friends and family, school and personal enjoyment. As a result, more new equipment or devices operates in higher frequency were rapidly developed to accommodate the consumers need. However, the demand of using wireless technology and higher frequency in new devices also brings the need to shield the unwanted electromagnetic signals from those devices for both proper operation and human health concerns. This paper highlights the potential of nanocellulose for electromagnetic shielding using the organic environmental nanocellulose composite materials. In addition, the theory of electromagnetic shielding and recent development of green and organic material in electromagnetic shielding application has also been reviewed in this paper. The use of the natural fibers which is nanocelllose instead of traditional reinforcement materials provides several advantages including the natural fibers are renewable, abundant and low cost. Furthermore, added with other advantages such as lightweight and high electromagnetic shielding ability, nanocellulose has a great potential as an alternative material for electromagnetic shielding application.