Abstract
Due to the wide variety of medical images and the complexity of the human body structure, the characteristics of manual extraction of medical images are difficult, the adaptive ability is poor, and the classification effect needs to be improved. Aiming at the shortcomings of traditional medical image recognition methods, this paper proposes an adaptive convolutional neural network model CNN-BN-PReLU based on the convolutional neural network method. The model first performs batch normalization (BN) processing on the input of each feature map of each layer of network, and then adaptively adjusts the parameters by using Parametric Rectified Linear Unit (PReLU) to compare the BN algorithm. Based on the performance before and after the activation function, an adaptive convolutional neural network model is constructed. The experimental results show that the model can abstract the image features without artificial intervention, speed up the network convergence speed and shorten the training time, and significantly improve the image recognition rate and reduce the misdiagnosis rate and missed diagnosis rate of the disease.
Highlights
Every aspect of human life contains shadows of images
IoT technology is used to design a collection device based on Internet of Things technology, and medical images are collected as a research database
The classification method based on convolutional neural network it can be simpler, more convenient, and has a strong self-learning ability, but the accuracy during training, this paper proposes to use the batch normalization algorithm and the parametric linear correction unit Parametric Rectified Linear Unit (PReLU) to improve it, and prove that the combination of the two can effectively shorten the training time and improve the network
Summary
Every aspect of human life contains shadows of images. With the continuous development of science and technology, many researchers have done a lot of research on digital images, and applied them to actual production and life, and constantly improve people’s lives. Aiming at the cumbersome process of traditional brain image recognition algorithm and difficulty in feature extraction, this chapter proposes an adaptive convolutional neural network model. Convolutional neural network uses multi-layer nonlinear information processing to achieve supervised or unsupervised feature extraction and transformation, pattern analysis and classification to explain data such as images, sounds, and text. Three important reasons for the popularity of convolutional neural network are: first, the processing power of the chip has been greatly improved, for example, the emergence of general-purpose graphics processing units, and secondly, the cost of hardware computing is significantly reduced, and third, machine learning and signal/information processing in research These advances have enabled convolutional neural network methods to efficiently utilize complex, integrated nonlinear functions to learn distributed and hierarchical feature representations and to make efficient use of tagged and unlabeled data.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
