A reconstruction method of detonation wave surface based on convolutional neural network

Fuel ◽  
2022 ◽  
Vol 315 ◽  
pp. 123068
Author(s):  
Jing Bian ◽  
Lin Zhou ◽  
Pengfei Yang ◽  
Honghui Teng ◽  
Hoi Dick Ng
Keyword(s):  
Neural Network ◽  
Detonation Wave ◽  
Convolutional Neural Network ◽  
Reconstruction Method ◽  
Wave Surface

scholarly journals 3D particle field reconstruction method based on convolutional neural network for SAPIV

2019 ◽  
Vol 27 (8) ◽  
pp. 11413 ◽  
Author(s):  
Xiangju Qu ◽  
Yang Song ◽  
Ying Jin ◽  
Zhenyan Guo ◽  
Zhenhua Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Reconstruction Method ◽  
Particle Field ◽  
Field Reconstruction

scholarly journals Superresolution Reconstruction of Video Based on Efficient Subpixel Convolutional Neural Network for Urban Computing

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Jie Shen ◽  
Mengxi Xu ◽  
Xinyu Du ◽  
Yunbo Xiong
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Optical Flow ◽  
Video Surveillance ◽  
Reconstruction Method ◽  
Motion Information ◽  
Learning Networks ◽  
Urban Computing ◽  
Deep Convolution Network

Video surveillance is an important data source of urban computing and intelligence. The low resolution of many existing video surveillance devices affects the efficiency of urban computing and intelligence. Therefore, improving the resolution of video surveillance is one of the important tasks of urban computing and intelligence. In this paper, the resolution of video is improved by superresolution reconstruction based on a learning method. Different from the superresolution reconstruction of static images, the superresolution reconstruction of video is characterized by the application of motion information. However, there are few studies in this area so far. Aimed at fully exploring motion information to improve the superresolution of video, this paper proposes a superresolution reconstruction method based on an efficient subpixel convolutional neural network, where the optical flow is introduced in the deep learning network. Fusing the optical flow features between successive frames can compensate for information in frames and generate high-quality superresolution results. In addition, in order to improve the superresolution, a superpixel convolution layer is added after the deep convolution network. Finally, experimental evaluations demonstrate the satisfying performance of our method compared with previous methods and other deep learning networks; our method is more efficient.

scholarly journals Super-resolution reconstruction of seismic section image via multi-scale convolution neural network

2021 ◽  
Vol 303 ◽  
pp. 01058
Author(s):  
Meng-Di Deng ◽  
Rui-Sheng Jia ◽  
Hong-Mei Sun ◽  
Xing-Li Zhang
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Convolutional Neural Network ◽  
Super Resolution ◽  
Image Features ◽  
Image Feature ◽  
Reconstruction Method ◽  
Low Resolution ◽  
Seismic Section ◽  
Multi Scale

The resolution of seismic section images can directly affect the subsequent interpretation of seismic data. In order to improve the spatial resolution of low-resolution seismic section images, a super-resolution reconstruction method based on multi-scale convolution is proposed. This method designs a multi-scale convolutional neural network to learn high-low resolution image feature pairs, and realizes mapping learning from low-resolution seismic section images to high-resolution seismic section images. This multi-scale convolutional neural network model consists of four convolutional layers and a sub-pixel convolutional layer. Convolution operations are used to learn abundant seismic section image features, and sub-pixel convolution layer is used to reconstruct high-resolution seismic section image. The experimental results show that the proposed method is superior to the comparison method in peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). In the total training time and reconstruction time, our method is about 22% less than the FSRCNN method and about 18% less than the ESPCN method.

scholarly journals ECT Image Reconstruction Algorithm Based on Multiscale Dual-Channel Convolutional Neural Network

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Lili Wang ◽  
Xiao Liu ◽  
Deyun Chen ◽  
Hailu Yang ◽  
Chengdong Wang
Keyword(s):  
Neural Network ◽  
Image Reconstruction ◽  
Convolutional Neural Network ◽  
Middle Layer ◽  
Input Image ◽  
Local Optimum ◽  
Reconstruction Method ◽  
Reconstruction Algorithms ◽  
Feature Maps ◽  
Dual Channel

For the problems of missing edges and obvious artifacts in Electrical Capacitance Tomography (ECT) reconstruction algorithms, an image reconstruction method based on a multiscale dual-channel convolutional neural network is proposed. Firstly, the image reconstructed by Landweber algorithm is input into the convolutional neural network, and four scales are selected for feature extraction. Feature unions are used across the scales to fuse the information of the output layer with feature maps. To improve the imaging accuracy, two frequency channels are designed for the input image. The middle layer of the network consists of two fully convolutional structures. Convolutional layers and jump connections are designed separately for different channels, which greatly improves the network’s ability to extract feature information and reduces the number of feature maps required for each layer. The number of network layers is shallow, which can speed up the network training, prevent the network from falling into local optimum, and ensure the effective transmission of image details. Simulation experiments are carried out for four typical dual media distributions. The edges of the reconstructed image are smoother and the image error is smaller. It effectively resolves the lack of edges in the reconstruction image and reduces the image edge artifacts in the ECT system.

scholarly journals Magnetic Resonance Imaging Feature Analysis and Evaluation of Tubal Patency under Convolutional Neural Network in the Diagnosis of Infertility

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Na Liu ◽  
Qingling Ren
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Clinical Diagnosis ◽  
Fallopian Tube ◽  
The Other ◽  
Reconstruction Method ◽  
Inspection Method ◽  
Reconstruction Methods ◽  
Imaging Results ◽  
Imaging Artifacts

To explore the diagnostic value of MRI image features based on convolutional neural network for tubal unobstructed infertility, 30 infertile female patients were first selected as the research objects, who admitted to the hospital from May 2018 to January 2020. They all underwent routine MRI examinations and CNN-based MR-hysteron-salpingography (HSG) examinations, in order to discuss the diagnostic accuracy of the two examinations. In the research, it was necessary to observe the patients’ imaging results, calculate the diagnosis rate of the two examination results, and analyze the application effect of the CNN algorithm, thereby selecting the best reconstruction method. In this study, the analysis was conducted on the basis of no statistical difference in the baseline data of the included patients. The results of undersampling reconstruction at 2-fold, 4-fold, and 6-fold showed that CNN for data consistency layer (CNN_DC) had a better effect, and its peak signal-to-noise ratio (PSNR) was lower sharply than that of the other two reconstruction methods, while the normalized mean square error (NMSE) and structural similarity index measure (SSIM) were higher markedly than the values of the other two reconstruction methods. The diagnostic rate of routine MRI examination of the fallopian tube and other parts of the uterus was lower than or equal to that of MR-HSG examination by CNN. Routine MRI examinations of fallopian tube imaging artifacts were large, and the definition was reduced, which increased the difficulty of identification. However, MR-HSG examination by CNN indicated that the imaging artifacts were low, the clarity was high, and the influence of noise was small, which was conducive to clinical diagnosis and identification. For endometriosis, the accuracy of MR-HSG was 33.33% and the accuracy of MRI was 46.67%. CNN MR-HSG inspection method was significantly better than the conventional MRI inspection method P < 0.05 . Therefore, the results of this study revealed that MR-HSG examination by CNN had a clear imaging effect and obvious inhibition effect on background signals and rapid image generation without the need for reconstruction with the same spatial resolution, which improved the imaging quality and could provide a reference value for clinical diagnosis and subsequent related studies.

CONVOLUTIONAL NEURAL NETWORK BASED ALGORITHM FOR CECUM ACHIEVEMENT CONFIRMATION

2020 ◽  
Author(s):  
S Kashin ◽  
D Zavyalov ◽  
A Rusakov ◽  
V Khryashchev ◽  
A Lebedev
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network
Sign in / Sign up

Export Citation Format

Share Document