Search

Your search keyword '"Wang, Runtao"' showing total 39 results
Start Over Author "Wang, Runtao"
39 results on '"Wang, Runtao"'

5. Detection of pig based on improved RESNET model in natural scene

Author

Song Weixian, Fang Junlong, Wang Runtao, and Tan Kezhu

Subjects
deep learning, object detection, resnet model, feature classification, Mathematics, QA1-939
Abstract

The behaviours of the pig are often closely related to their health. Pig recognition is very important for pig behaviour analysis and digital breeding. Currently, the early signs and abnormal behaviours of sick pigs in breeding farms are mainly completed by human observation. However, visual inspection is labour intensive and time-consuming, and it suffers from the problems of individual experiences and varying environments. An improved ResNet model was proposed and applied to detect individual pigs in this study based on deep learning knowledge. The developed model captured the features of pigs applying across layer connections, and the ability of feature expression was improved by adding a new residual module. The number of layers was reduced to minimise the net complexity. Generally, the ResNet frame was developed by reducing the number of convolution layers, constructing different types of the residual module and adding the number of convolution kernels. The training accuracy and testing accuracy reached 98.2% and 96.4%, respectively, when using the improved model. The experiment results showed that the method proposed in this paper for checking living situations and disease prevention of commercial pigs in pig farms is potential.

Published
2021
Full Text
View/download PDF

6. DCBLD1 modulates angiogenesis by regulating of the VEGFR-2 endocytosis in endothelial cells

Author

Feng, Qi, primary, Guo, Lingling, additional, Yu, Chao, additional, Liu, Xiaoning, additional, Lin, Yan-Ling YL, additional, Li, Chenyang, additional, Zhang, Wenjun, additional, Zong, Yanhong, additional, Yang, Weiwei, additional, Ma, Yuehua, additional, Wang, Runtao, additional, Li, Lijing, additional, Pei, Yunli, additional, Wang, Hui-Fang, additional, Liu, Demin, additional, Han, Mei, additional, Niu, Honglin, additional, and Nie, Lei, additional

Published
2023
Full Text
View/download PDF

16. A prediction model of NH3 concentration for swine house in cold region based on Empirical Mode Decomposition and Elman neural network

Author

Bilegtsaikhan Lkhagva, Wang Runtao, Jian Sun, Yan Zhang, Weizheng Shen, Xiao Fu, Udaybeer Singh, and Yanling Yin

Subjects
Artificial neural network, Mean squared error, lcsh:T58.5-58.64, lcsh:Information technology, 020209 energy, 010401 analytical chemistry, Mode (statistics), Forestry, 02 engineering and technology, Aquatic Science, 01 natural sciences, lcsh:S1-972, Hilbert–Huang transform, 0104 chemical sciences, Computer Science Applications, Light intensity, Mean absolute percentage error, Concentration prediction, 0202 electrical engineering, electronic engineering, information engineering, Animal Science and Zoology, lcsh:Agriculture (General), Biological system, Agronomy and Crop Science, Reliability (statistics), Mathematics
Abstract

In order to improve the accuracy and reliability of ammonia (NH3) concentration prediction, which can provides a support to the ventilation control strategy, so as to reduce the impact of NH3 on the health and productivity of swine, this paper proposed an NH3 concentration prediction method based on Empirical Mode Decomposition (EMD) and Elman neural network modelling. The NH3 concentration and other four environmental parameters including temperature, humidity, carbon dioxide and light intensity were decomposed into several different time-scale intrinsic mode functions (IMFs). Then, the Elman neural network prediction model was used to predict each IMF. The predicted NH3 was obtained by reconstructing all the IMFs by EMD. The results show that for the proposed method, the determination coefficient between the predicted and real measured value is 0.9856, the Mean Absolute Error is 0.7088 ppm, the Root Mean Square Error is 0.9096 ppm, and the Mean Absolute Percentage Error is 0.41%. Compared with the Elman neural network, the proposed method has a good improvement in the accuracy, and provide effective parameters for the environmental monitoring of the swine house and the regulation of the NH3 concentration. Keywords: Cold region’ swine house, Elman neural network, Empirical Mode Decomposition, NH3 concentration prediction, Environmental monitoring

Published
2019

18. Developing D-pi-D hole-transport materials for perovskite solar cells : the effect of the pi-bridge on device performance

Author

Ou, Yangmei, Sun, Anxin, Li, Haibei, Wu, Tai, Zhang, Dongyang, Xu, Peng, Zhao, Rongmei, Zhu, Liqiong, Wang, Runtao, Xu, Bo, Hua, Yong, Ding, Liming, Ou, Yangmei, Sun, Anxin, Li, Haibei, Wu, Tai, Zhang, Dongyang, Xu, Peng, Zhao, Rongmei, Zhu, Liqiong, Wang, Runtao, Xu, Bo, Hua, Yong, and Ding, Liming

Abstract

Three cost-effective D-pi-D hole transport materials (HTMs) with different pi-bridges, including biphenyl (SY1), phenanthrene (SY2), and pyrene (SY3), have been synthesized via a one-pot reaction with cheap commercially available starting materials for application in organic-inorganic hybrid perovskite solar cells (PSCs). The effects of the various pi-bridges on the photophysical, electrochemical, and electrical properties, and film morphologies of the materials, as well as on the photovoltaic properties of the PSCs, have been systematically investigated accordingly. Our results clearly show that HTM-SY3 with pyrene as the pi-bridge exhibits higher hole mobility and better hole extraction/transport and film formation abilities than the other two HTMs. Devices that employed SY3 as the HTM show impressive power conversion efficiency (PCE) values of 19.08% and 13.41% in (FAPbI(3))(0.85)(MAPbBr(3))(0.15)- and CsPbI2Br-based PSCs, respectively, which are higher than those of the reference HTM-SY1- and SY2-based ones. Our studies demonstrate a promising strategy to rationally design and synthesize low-cost and efficient HTMs through structural engineering for use in PSCs., QC 20210318.

Published
2021
Full Text
View/download PDF

32. Estimating Canopy Nitrogen Content of Rice Using Hyperspectral Reflectance Combined with SG-FD-CARS-ELM in Cold Region

Author

Xiu Cheng, Li Xiaowei, Zhang Yan, A Mani, Wang Runtao, Wang Shuwen, and Zhao Qinghe

Subjects
Noise (signal processing), Partial least squares regression, Hyperspectral imaging, Feature selection, Variable elimination, Biological system, Smoothing, Mathematics, Extreme learning machine, Second derivative
Abstract

In this study, visible and near infrared hyperspectral imaging technique was used to predict canopy leaf nitrogen content (CLNC) of rice in cold region. Canopy hyperspectral images of rice were acquired at tillering, jointing and heading stage, respectively. Original spectra was extracted using ENVI5.0 software, and leaf nitrogen content was obtained by chemical analysis method. 5 pre-processing methods of savitzky-golay smoothing (SG), multiplicative scatter correction (MSC), standard normal variate (SNV), first derivative (FD) and second derivative (SD) were used to eliminate unexpected noise. After comparing the performance of PLSR models based on spectra of full wavelengths after pre-processing, SG combined with FD had the best performance for eliminating the noise interference and improving the performance of models. In order to further simplify and enhance the models, 3 variable selection methods of successive projections algorithm (SPA), uninformative variable elimination (UVE) and competitive adaptive reweighted sampling (CARS) were used to select the characteristic wavelengths, and partial least square regression (PLSR) and extreme learning machine (ELM) were used to establish prediction models. After comparing the performance of PLSR models and ELM models, CARS could effectively select the wavelengths that had strong information and were not sensitive to external disturbance factors, and the nonlinear ELM model was more suitable for predicting CLNC of rice in cold region, the specific values of RC2 and RP2 of ELM models based on CARS were 0.906 and 0.888 for tillering stage, 0.903 and 0.892 for jointing stage, and 0.894, 0.887 for heading stage, respectively. The results of this study could provide a reference for quantitative analysis of nitrogen content of rice using hyperspectral technology.

Published
2018

36. Data Resources and Services at CAsDC

Author

Cui, Chenzhou, primary, He, Boliang, additional, Xiao, Jian, additional, Yu, Ce, additional, Li, Jian, additional, Cao, Zihuang, additional, Su, Liying, additional, Fan, Dongwei, additional, Qiao, Cuilan, additional, Li, Changhua, additional, Chen, Yue, additional, Wang, Runtao, additional, and Zhao, Yongheng, additional

Published
2013
Full Text
View/download PDF

39. DCBLD2 deletion increases hyperglycemia and induces vascular remodeling by inhibiting insulin receptor recycling in endothelial cells.

Author

Guo, Lingling, Zong, Yanhong, Yang, Weiwei, Lin, Yanling, Feng, Qi, Yu, Chao, Liu, Xiaoning, Li, Chenyang, Zhang, Wenjun, Wang, Runtao, Li, Lijing, Pei, Yunli, Wang, Huifang, Liu, Demin, Niu, Honglin, and Nie, Lei

Abstract

Discoidin, CUB, LCCL domain‐containing 2 (DCBLD2) is a type I transmembrane protein with a similar structure to neuropilin, which acts as a co‐receptor for certain receptor tyrosine kinases (RTKs). The insulin receptor is an RTK and plays a critical role in endothelial cell function and glycolysis. However, how and whether DCBLD2 regulates insulin receptor activity in endothelial cells is poorly understood. Diabetes was induced through treatment of Dcbld2 global‐genome knockout mice and endothelium‐specific knockout mice with streptozotocin. Vascular ultrasound, vascular tension test, and hematoxylin and eosin staining were performed to assess endothelial function and aortic remodeling. Glycolytic rate assays, real‐time PCR and western blotting were used to investigate the effects of DCBLD2 on glycolytic activity and insulin receptor (InsR)/phosphatidylinositol 3‐kinase (PI3K)/protein kinase B (Akt) pathway in endothelial cells. Co‐immunoprecipitation was used to assess the effects of DCBLD2 on insulin receptor endocytosis and recycling. Membrane and cytoplasmic proteins were isolated to determine whether DCBLD2 could affect the localization of the insulin receptor. We found that Dcbld2 deletion exacerbated endothelial dysfunction and vascular remodeling in diabetic mice. Both Dcbld2 knockdown and Dcbld2 deletion inhibited glycolysis and the InsR/PI3K/Akt signaling pathway in endothelial cells. Furthermore, Dcbld2 deletion inhibited insulin receptor recycling. Taken together, Dcbld2 deficiency exacerbated diabetic endothelial dysfunction and vascular remodeling by inhibiting the InsR/PI3K/Akt pathway in endothelial cells through the inhibition of Rab11‐dependent insulin receptor recycling. Our data suggest that DCBLD2 is a potential therapeutic target for diabetes and cardiovascular diseases. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results