Yukuan Sun
Tianjin Polytechnic University
32 Papers
18 Citations
Yukuan Sun is an academic researcher from Tianjin Polytechnic University. The author has contributed to research in topics: Computer science & Electrical impedance tomography. The author has an hindex of 5, co-authored 14 publications.
Chat about Author
Papers
One-dimensional convolutional neural network (1D-CNN) image reconstruction for electrical impedance tomography
TL;DR: The average image correlation coefficient of the new network increases 0.0320 and 0.0616 compared with the DNN and 2D-CNN, which demonstrates that the proposed method could give better reconstruction results, especially for the distribution of complex geometries.
46
An image reconstruction framework based on deep neural network for electrical impedance tomography
Xiuyan Li,Yang Lu,Jianming Wang,Xin Dang,Qi Wang,Xiaojie Duan,Yukuan Sun +6 more
- 15 Sep 2017
TL;DR: A new framework based on deep neural network (DNN) model is presented that applies the stacked autoencoder (SAE) and a logistic regression layer to constitute a 4-layer DNN model and shows the effectiveness of the proposed framework in improving the quality of reconstructed images.
31
Residual convolutional graph neural network with subgraph attention pooling
TL;DR: Zhang et al. as mentioned in this paper proposed a residual convolutional graph neural network (RCNN) to tackle the problem of key classification features losing in graph classification by feeding discarded features back into the network architecture to reduce the probability of losing critical features for graph classification.
21
Circle Marker Based Distance Measurement Using a Single Camera
Yu-Tao Cao,Jian-Ming Wang,Yukuan Sun,Xiaojie Duan +3 more
- 01 Jan 2013
TL;DR: In this article, a single camera and a circle marker is used to measure the distance between a single image and a pinhole camera using the idea that the circle marker at a longer distance forms a smaller image when the parameters of the imaging system remain unchanged.
Electrical-impedance-tomography imaging based on a new three-dimensional thorax model for assessing the extent of lung injury
TL;DR: A true 3D thorax model is established and a method for calculating the global inhomogeneity index (GI) based on 3D EIT reconstruction images to evaluate lung injury is proposed, revealing that this method can accurately reflect the disease state of lung injury compared with the 2D GI calculation method, and even mild damage of Lung injury can be adequately detected.