Enhanced Grey Wolf Optimization based Hyper-parameter optimized Convolution Neural Network for Kidney Image Classification

Over the last few years, Convolution Neural Networks (CNN) have shown dominant performance over real world applications due to their ability find good solutions and deal with image data. However is highly dependent on network architecture methods for optimizing hyper parameters especially number size of filters. Designing a CNN requires human expertise domain knowledge. So, it difficult in sufficient filters classification problems. The standard GWO algorithm used any optimization purpose suffers from some issues such as slow convergence speed, trapping local minima unable maintain balance between exploration exploitation. In order proper these phases, two modifications are introduced this paper. A technique finding optimum using based Enhanced Grey Wolf Optimization (E-GWO) proposed. paper presents (numbers convolution layer) E-GWO improve model. Kidney ultrasound images dataset collected centre evaluate proposed algorithm. Experimental results showed that outperformed optimized traditional GA, PSO conventional yielding 97.01% accuracy. At last, obtained statistically validated t-test.