scholarly journals BBNet: A Novel Convolutional Neural Network Structure in Edge-Cloud Collaborative Inference

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4494
Author(s):  
Hongbo Zhou ◽  
Weiwei Zhang ◽  
Chengwei Wang ◽  
Xin Ma ◽  
Haoran Yu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Structure ◽  
Original Data ◽  
Compression Rate ◽  
Original Network ◽  
Intermediate Data ◽  
Communication Time ◽  
Neural Network Structure ◽  
End To End

Edge-cloud collaborative inference can significantly reduce the delay of a deep neural network (DNN) by dividing the network between mobile edge and cloud. However, the in-layer data size of DNN is usually larger than the original data, so the communication time to send intermediate data to the cloud will also increase end-to-end latency. To cope with these challenges, this paper proposes a novel convolutional neural network structure—BBNet—that accelerates collaborative inference from two levels: (1) through channel-pruning: reducing the number of calculations and parameters of the original network; (2) through compressing the feature map at the split point to further reduce the size of the data transmitted. In addition, This paper implemented the BBNet structure based on NVIDIA Nano and the server. Compared with the original network, BBNet’s FLOPs and parameter achieve up to 5.67× and 11.57× on the compression rate, respectively. In the best case, the feature compression layer can reach a bit-compression rate of 512×. Compared with the better bandwidth conditions, BBNet has a more obvious inference delay when the network conditions are poor. For example, when the upload bandwidth is only 20 kb/s, the end-to-end latency of BBNet is increased by 38.89× compared with the cloud-only approach.

Application of convolution neural network in medical image processing

2020 ◽  
pp. 1-11
Author(s):  
Jie Liu ◽  
Hongbo Zhao
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Structure ◽  
Medical Image ◽  
Sampling Methods ◽  
Medical Image Processing ◽  
Convolution Neural Network ◽  
Data Set ◽  
Convolution Kernels ◽  
Neural Network Structure

BACKGROUND: Convolution neural network is often superior to other similar algorithms in image classification. Convolution layer and sub-sampling layer have the function of extracting sample features, and the feature of sharing weights greatly reduces the training parameters of the network. OBJECTIVE: This paper describes the improved convolution neural network structure, including convolution layer, sub-sampling layer and full connection layer. This paper also introduces five kinds of diseases and normal eye images reflected by the blood filament of the eyeball “yan.mat” data set, convenient to use MATLAB software for calculation. METHODSL: In this paper, we improve the structure of the classical LeNet-5 convolutional neural network, and design a network structure with different convolution kernels, different sub-sampling methods and different classifiers, and use this structure to solve the problem of ocular bloodstream disease recognition. RESULTS: The experimental results show that the improved convolutional neural network structure is ideal for the recognition of eye blood silk data set, which shows that the convolution neural network has the characteristics of strong classification and strong robustness. The improved structure can classify the diseases reflected by eyeball bloodstain well.

scholarly journals Forecast Model of TV Show Rating Based on Convolutional Neural Network

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Lingfeng Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Prediction Model ◽  
Convolutional Neural Network ◽  
Network Structure ◽  
Rating Data ◽  
Tv Program ◽  
Neural Network Structure ◽  
Rating Prediction ◽  
Tv Show

The TV show rating analysis and prediction system can collect and transmit information more quickly and quickly upload the information to the database. The convolutional neural network is a multilayer neural network structure that simulates the operating mechanism of biological vision systems. It is a neural network composed of multiple convolutional layers and downsampling layers sequentially connected. It can obtain useful feature descriptions from original data and is an effective method to extract features from data. At present, convolutional neural networks have become a research hotspot in speech recognition, image recognition and classification, natural language processing, and other fields and have been widely and successfully applied in these fields. Therefore, this paper introduces the convolutional neural network structure to predict the TV program rating data. First, it briefly introduces artificial neural networks and deep learning methods and focuses on the algorithm principles of convolutional neural networks and support vector machines. Then, we improve the convolutional neural network to fit the TV program rating data and finally apply the two prediction models to the TV program rating data prediction. We improve the convolutional neural network TV program rating prediction model and combine the advantages of the convolutional neural network to extract effective features and good classification and prediction capabilities to improve the prediction accuracy. Through simulation comparison, we verify the feasibility and effectiveness of the TV program rating prediction model given in this article.

scholarly journals Research and Verification of Convolutional Neural Network Lightweight in BCI

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Shipu Xu ◽  
Runlong Li ◽  
Yunsheng Wang ◽  
Yong Liu ◽  
Wenwen Hu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Structure ◽  
Classification Accuracy ◽  
Original Network ◽  
Network Parameter ◽  
Network Parameters ◽  
Network Operation ◽  
Depth And Complexity ◽  
Convergence Stability

With the increasing of depth and complexity of the convolutional neural network, parameter dimensionality and volume of computing have greatly restricted its applications. Based on the SqueezeNet network structure, this study introduces a block convolution and uses channel shuffle between blocks to alleviate the information jam. The method is aimed at reducing the dimensionality of parameters of in an original network structure and improving the efficiency of network operation. The verification performance of the ORL dataset shows that the classification accuracy and convergence efficiency are not reduced or even slightly improved when the network parameters are reduced, which supports the validity of block convolution in structure lightweight. Moreover, using a classic CIFAR-10 dataset, this network decreases parameter dimensionality while accelerating computational processing, with excellent convergence stability and efficiency when the network accuracy is only reduced by 1.3%.

Sign in / Sign up

Export Citation Format

Share Document