Your browser doesn't support javascript.
loading
Analysis of the Effectiveness of Metaheuristic Methods on Bayesian Optimization in the Classification of Visual Field Defects.
Abu, Masyitah; Zahri, Nik Adilah Hanin; Amir, Amiza; Ismail, Muhammad Izham; Yaakub, Azhany; Fukumoto, Fumiyo; Suzuki, Yoshimi.
Afiliação
  • Abu M; Center of Excellence for Advance Computing, Faculty of Electronic Engineering & Technology, Universiti Malaysia Perlis, Kangar 01000, Malaysia.
  • Zahri NAH; Center of Excellence for Advance Computing, Faculty of Electronic Engineering & Technology, Universiti Malaysia Perlis, Kangar 01000, Malaysia.
  • Amir A; Center of Excellence for Advance Computing, Faculty of Electronic Engineering & Technology, Universiti Malaysia Perlis, Kangar 01000, Malaysia.
  • Ismail MI; Institute of Engineering Mathematics, Faculty of Applied and Human Sciences, Universiti Malaysia Perlis, Arau 02600, Malaysia.
  • Yaakub A; Department of Ophthalmology & Visual Science, Universiti Sains Malaysia, Kubang Kerian 16150, Malaysia.
  • Fukumoto F; Graduate Faculty of Interdisciplinary Research, University of Yamanashi, Kofu 400-0016, Japan.
  • Suzuki Y; Graduate Faculty of Interdisciplinary Research, University of Yamanashi, Kofu 400-0016, Japan.
Diagnostics (Basel) ; 13(11)2023 Jun 02.
Article em En | MEDLINE | ID: mdl-37296798
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.
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Idioma: En Revista: Diagnostics (Basel) Ano de publicação: 2023 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Idioma: En Revista: Diagnostics (Basel) Ano de publicação: 2023 Tipo de documento: Article