Search

Your search keyword '"Wang, Hong-Jie"' showing total 416 results
Start Over Author "Wang, Hong-Jie"
416 results on '"Wang, Hong-Jie"'

9. Study on the potential mechanism of Qingxin Lianzi Yin Decoction on renoprotection in db/db mice via network pharmacology and metabolomics

Author

Gao, Wen-ya, primary, Tian, Meng-yao, additional, Li, Ming-li, additional, Gao, Shuang-rong, additional, Wei, Xiao-lu, additional, Gao, Chang, additional, Zhou, Yan-yan, additional, Li, Tao, additional, Wang, Hong-jie, additional, Bian, Bao-lin, additional, Si, Nan, additional, Zhao, Wei, additional, and Zhao, Hai-yu, additional

Published
2023
Full Text
View/download PDF

11. Representative-Based Active Learning with Max-Min Distance

Author

Liu, Fu-Lun, Min, Fan, Wen, Liu-Ying, Wang, Hong-Jie, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Flores, Víctor, editor, Gomide, Fernando, editor, Janusz, Andrzej, editor, Meneses, Claudio, editor, Miao, Duoqian, editor, Peters, Georg, editor, Ślęzak, Dominik, editor, Wang, Guoyin, editor, Weber, Richard, editor, and Yao, Yiyu, editor

Published
2016
Full Text
View/download PDF

13. Advanced Nitrogen Removal from Low C/N Actual Domestic Sewage in a Continuous Plug Flow Anaerobic/Oxic/Anoxic System: Driven by Endogenous Denitrification

Author

Liu, Huaguang, primary, Dong, Wenyi, additional, Zhao, Zilong, additional, Wang, Hong jie, additional, Hou, Zilong, additional, Li, Yanchen, additional, Zeng, Zhiwei, additional, Xie, Jin, additional, Wang, Fupeng, additional, Liu, Xueyon, additional, Yan, Yu, additional, and Qu, Yanhui, additional

Published
2023
Full Text
View/download PDF

32. Detection of Ears of Rice in field Based on SSD

Author

Yu Haoyang, Wang Hong-jie, Mu Jiong, Yang jie, and Shu Baiyi

Subjects
Hardware_MEMORYSTRUCTURES, Artificial neural network, Computer science, business.industry, Deep learning, food and beverages, Data_CODINGANDINFORMATIONTHEORY, Agricultural engineering, GeneralLiterature_MISCELLANEOUS, Field (computer science), Object detection, Test set, Field based, Artificial intelligence, Software_PROGRAMMINGLANGUAGES, business
Abstract

In order to improve the yield and quality of rice production, monitoring during rice development is particularly important. At present, rice pictures are recognized manually or by using traditional machine learning methods, but the efficiency is not high, and it is not possible to quickly identify rice in a wide range. Therefore, this paper studies the use of deep learning technology to identify rice ears, which can detect rice in the field environment faster and more accurately. In this paper, we used the SSD algorithm of deep learning object detection to train our own RICE dataset to obtain a rice ear detection model suitable for field environment feeding. The experimental results on the test set show that the mAP of this method can reach 38.1%, which provides a possibility for more in-depth research on neural network detection of rice, provides a basis for rice yield prediction, and better guides the production of rice crops.

Published
2020

33. A Multi-scale Network based on Attention Mechanism for Hyperspectral Image Classification

Author

Shu Baiyi, Wang Hong-jie, Yu Haoyang, Luo Xin, and Mu Jiong

Subjects
Pixel, business.industry, Computer science, Dimensionality reduction, Deep learning, Hyperspectral imaging, Pattern recognition, Mutual information, Artificial intelligence, business, Convolutional neural network, Spatial analysis, Block (data storage)
Abstract

In recent years, with the theoretical progress of deep learning and the improvement of computational power, more and more deep learning based work has been proposed and achieved good results. However, due to its particularity, hyperspectral image (HSI) is difficult to directly apply the theory and experience of traditional deep learning. For HSI, we mainly face the following problems: effective use of spatial and spectral information, lack of annotated datasets and large spectral dimensions. These problems make it difficult to classify. Generally, in order to solve these problems, some pre-processing methods, such as PCA, and mutual information, will be taken, but this will lose some useful information. On the other hand, people usually consider spatial information on a joint-learning way (take a pixel-centric patch as input), but this approach may lead to some useless information being taken into account. Therefore, we apply the attention model to the HSI classification and reduce the dimension in a way that can be learned, we believe that this can also help the network to be more easily concentrated on similar pixels without being affected by abnormal pixels. In summary, we propose a new attention-based network called ABMN (attention based multiscale network), which is mainly composed of a dimension reduction block and a multi-scale spatial information extraction block. And excellent results are obtained on two popular hyperspectral image sets (Pavia University scene, Indian Pines), OA is 99.66% and 100% respectively.

Published
2019

Catalog

Books, media, physical & digital resources
See catalog results