计算机科学
人工智能
超参数
人工神经网络
数据挖掘
网络体系结构
互联网
图像检索
深度学习
差异进化
机器学习
模式识别(心理学)
图像(数学)
计算机网络
万维网
作者
Arti Tiwari,Millie Pant
摘要
In this paper, a brownfield Internet of Medical Things network is introduced for imaging data that can be easily scaled out depending on the objectives, functional requirements, and the number of facilities and devices connected to it. This is further used to develop a novel Content-based Medical Image Retrieval framework. The developed framework uses DenseNet-201 architecture for generating the image descriptors. Then for classification, the optimized Deep Neural Network model has been configured through a population-based metaheuristic Differential Evolution. Differential Evolution iteratively performs the joint optimization of hyperparameters and architecture of Deep Neural Networks. The competence of the proposed model is validated on three publicly available datasets: Brain Tumor MRI dataset, Covid-19 Radiography database, and Breast Cancer MRI dataset, and by comparing it with selected models over different aspects of performance evaluation. Results show that the convergence rate of the proposed framework is very fast, and it achieves at least 97.28% accuracy across all the models.
科研通智能强力驱动
Strongly Powered by AbleSci AI