http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Chuanyun Wang,Enyan Sun,Feng Tian 보안공학연구지원센터 2016 International Journal of Grid and Distributed Comp Vol.9 No.9
Optimal coverage of wireless sensor networks is one of the most fundamental problems for constructing efficient perception layer of the Internet of Things. On the basis of research on spatial neighborhood, the node coverage and area coverage models are analyzed, then an optimal coverage algorithm of wireless sensor networks is proposed based on particle swarm optimization with coherent velocity. Experimental results show that the algorithm can significantly improve the network coverage; in addition, the coherent velocity can effectively avoid network prematurely into a local optimal solution, so as to enhance the network coverage.
Synthesis of Co:MgAl2O4 nano-powders for saturable absorber
Wang Chuanyun,Yang Wei,Wang Zhiqi,Liu Bina,Li Shihua,Lu Taoa,,Li Xueren,Miao Weipeng,Luo Wei 한양대학교 청정에너지연구소 2023 Journal of Ceramic Processing Research Vol.24 No.2
Uniform Co:MgAl2O4 nano-powders for saturable absorber were prepared using inverse-drip co-precipitation method. Effectsof the precipitant and the metal ion solution on the composition and morphology of Co:MgAl2O4 nano-powders were studied. The results show that pure Co:MgAl2O4 nano-powders can be obtained, using the mixed solution of ammonium carbonate andammonia as the precipitant. The specific surface area of the particles reached 36 m2/g and the primary particle size was 39nm according to the SEM images and BET results.
Construction of Risk Prediction Model of Type 2 Diabetic Kidney Disease Based on Deep Learning
Chuan Yun,Fangli Tang,Zhenxiu Gao,Wenjun Wang,Fang Bai,Joshua D. Miller,Huanhuan Liu,Yaujiunn Lee,Qingqing Lou 대한당뇨병학회 2024 Diabetes and Metabolism Journal Vol.48 No.4
Background: This study aimed to develop a diabetic kidney disease (DKD) prediction model using long short term memory (LSTM) neural network and evaluate its performance using accuracy, precision, recall, and area under the curve (AUC) of the receiver operating characteristic (ROC) curve.Methods: The study identified DKD risk factors through literature review and physician focus group, and collected 7 years of data from 6,040 type 2 diabetes mellitus patients based on the risk factors. Pytorch was used to build the LSTM neural network, with 70% of the data used for training and the other 30% for testing. Three models were established to examine the impact of glycosylated hemoglobin (HbA1c), systolic blood pressure (SBP), and pulse pressure (PP) variabilities on the model’s performance.Results: The developed model achieved an accuracy of 83% and an AUC of 0.83. When the risk factor of HbA1c variability, SBP variability, or PP variability was removed one by one, the accuracy of each model was significantly lower than that of the optimal model, with an accuracy of 78% (<i>P</i><0.001), 79% (<i>P</i><0.001), and 81% (<i>P</i><0.001), respectively. The AUC of ROC was also significantly lower for each model, with values of 0.72 (<i>P</i><0.001), 0.75 (<i>P</i><0.001), and 0.77 (<i>P</i><0.05).Conclusion: The developed DKD risk predictive model using LSTM neural networks demonstrated high accuracy and AUC value. When HbA1c, SBP, and PP variabilities were added to the model as featured characteristics, the model’s performance was greatly improved.