http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Baek, Hee Sun,Lee, Youngok,Jang, Hea Min,Cho, Joonyong,Hyun, Myung Chul,Kim, Yeo Hyang,Hwang, Su-Kyeong,Cho, Min Hyun The Korean Pediatric Society 2020 Clinical and Experimental Pediatrics (CEP) Vol.63 No.4
Background: Acute kidney injury (AKI) is one of the most significant postoperative complications of pediatric cardiac surgery. Because serum creatinine has limitations as a diagnostic marker of AKI, new biomarkers including neutrophil gelatinase-associated lipocalin (NGAL), kidney injury molecule-1 (KIM-1), and interleukin-18 (IL-18) are being evaluated to overcome these limitations and detect AKI at an early stage after cardiac surgery. Purpose: This study aimed to investigate the clinical usefulness of these biomarkers in young children. Methods: Thirty patients with congenital heart diseases who underwent cardiac surgery using cardiopulmonary bypass (CPB) were selected, and their urine and blood samples were collected at baseline and 6, 24, and 48 hours after surgery. Serum creatinine and blood urea nitrogen levels as well as NGAL, KIM-1, and IL-18 levels in urine samples were measured, and clinical parameters were evaluated. Results: Of the 30 patients, 12 developed AKI within 48 hours after cardiac surgery. In the AKI group, 8 of 12 (66.6%) met AKI criteria after 24 hours, and urine KIM-1/creatinine (Cr) level (with adjustment of urine creatinine) peaked at 24 hours with significant difference from baseline level. Additionally, urine KIM-1/Cr level in the AKI group was significantly higher than in the non-AKI group at 6 hours. However, urine NGAL/Cr and IL-18/Cr levels showed no specific trend with time for 48 hours after cardiac surgery. Conclusion: It is suggested that urine KIM-1/Cr concentration could be considered a good biomarker for early AKI prediction after open cardiac surgery using CPB in young children with congenital heart diseases.
Kim, Joonyong,Lee, Chungu,Kwon, Tae-Hyung,Park, Geonhwan,Rhee, Joong-Yong Korean Society for Agricultural Machinery 2013 바이오시스템공학 Vol.38 No.1
Purpose: The objective of this study is to develop a data middleware for u-IT convergence in agricultural environment monitoring, which can support non-standard data interfaces and solve the compatibility problems of heterogenous sensor networks. Methods: Six factors with three different interfaces were chosen as target data among the environmental monitoring factors for crop cultivation. PostgresSQL and PostGIS were used for database and the data middleware was implemented by Python programming language. Based on hierarchical model design and key-value type table design, the data middleware was developed. For evaluation, 2,000 records of each data access interface were prepared. Results: Their execution times of File I/O interface, SQL interface and HTTP interface were 0.00951 s/record, 0.01967 s/record and 0.0401 s/record respectively. And there was no data loss. Conclusions: The data middleware integrated three heterogenous sensor networks with different data access interfaces.
Development of Multilayer Perceptron Model for the Prediction of Alcohol Concentration of Makgeolli
( Joonyong Kim ),( Shin-joung Rho ),( Yun Sung Cho ),( Eunsun Cho ) 한국농업기계학회 2018 바이오시스템공학 Vol.43 No.3
Purpose: Makgeolli is a traditional alcoholic beverage made from rice with a fermentation starter called “nuruk.” The concentration of alcohol in makgeolli depends on the temperature of the fermentation tank. It is important to monitor the alcohol concentration to manage the makgeolli production process. Methods: Data were collected from 84 makgeolli fermentation tanks over a year period. Independent variables included the temperatures of the tanks and the room where the tanks were located, as well as the quantity, acidity, and water concentration of the source. Software for the multilayer perceptron model (MLP) was written in Python using the Scikit-learn library. Results: Many models were created for which the optimization converged within 100 iterations, and their coefficients of determination R<sup>2</sup> were considerably high. The coefficient of determination R<sup>2</sup> of the best model with the training set and the test set were 0.94 and 0.93, respectively. The fact that the difference between them was very small indicated that the model was not overfitted. The maximum and minimum error was approximately 2% and the total MSE was 0.078%. Conclusions: The MLP model could help predict the alcohol concentration and to control the production process of makgeolli. In future research, the optimization of the production process will be studied based on the model.
Development of Multilayer Perceptron Model for the Prediction of Alcohol Concentration of Makgeolli
Kim, JoonYong,Rho, Shin-Joung,Cho, Yun Sung,Cho, EunSun Korean Society for Agricultural Machinery 2018 바이오시스템공학 Vol.43 No.3
Purpose: Makgeolli is a traditional alcoholic beverage made from rice with a fermentation starter called "nuruk." The concentration of alcohol in makgeolli depends on the temperature of the fermentation tank. It is important to monitor the alcohol concentration to manage the makgeolli production process. Methods: Data were collected from 84 makgeolli fermentation tanks over a year period. Independent variables included the temperatures of the tanks and the room where the tanks were located, as well as the quantity, acidity, and water concentration of the source. Software for the multilayer perceptron model (MLP) was written in Python using the Scikit-learn library. Results: Many models were created for which the optimization converged within 100 iterations, and their coefficients of determination $R^2$ were considerably high. The coefficient of determination $R^2$ of the best model with the training set and the test set were 0.94 and 0.93, respectively. The fact that the difference between them was very small indicated that the model was not overfitted. The maximum and minimum error was approximately 2% and the total MSE was 0.078%. Conclusions: The MLP model could help predict the alcohol concentration and to control the production process of makgeolli. In future research, the optimization of the production process will be studied based on the model.
Multilayer Perceptron Model to Estimate Solar Radiation with a Solar Module
( Joonyong Kim ),( Joongyong Rhee ),( Seunghwan Yang ),( Chungu Lee ),( Seongin Cho ),( Youngjoo Kim ) 한국농업기계학회 2018 바이오시스템공학 Vol.43 No.4
Purpose: The objective of this study was to develop a multilayer perceptron (MLP) model to estimate solar radiation using a solar module. Methods: Data for the short-circuit current of a solar module and other environmental parameters were collected for a year. For MLP learning, 14,400 combinations of input variables, learning rates, activation functions, numbers of layers, and numbers of neurons were trained. The best MLP model employed the batch backpropagation algorithm with all input variables and two hidden layers. Results: The root-mean-squared error (RMSE) of each learning cycle and its average over three repetitions were calculated. The average RMSE of the best artificial neural network model was 48.13 W·m-2. This result was better than that obtained for the regression model, for which the RMSE was 66.67 W·m-2. Conclusions: It is possible to utilize a solar module as a power source and a sensor to measure solar radiation for an agricultural sensor node.
Building a Private Cloud-Computing System for Greenhouse Control
( Joonyong Kim ),( Chun Gu Lee ),( Dong-hyeok Park ),( Heun Dong Park ),( Joong-yong Rhee ) 한국농업기계학회 2018 바이오시스템공학 Vol.43 No.4
Purpose: Cloud-computing technology has several advantages, including maintenance, management, accessibility, and computing power. A greenhouse-control system utilizing these advantages was developed using a private cloud-computing system. Methods: A private cloud needs a collection of servers and a suite of software tools to monitor and control cloud-computing resources. In this study, a server farm, operated by OpenStack as a cloud platform, was constructed using servers, and other network devices. Results: The greenhouse-control system was developed according to the fundamental cloud service models: infrastructure as a service, platform as a service, and software as a service. This system has four additional advantages - security, control function, public data use, and data exchange. There are several considerations that must be addressed, such as service level agreement, data ownership, security, and the differences between users. Conclusions: When the advantages are utilized and the considerations are addressed, cloud-computing technology will be beneficial for agricultural use.
Building a Private Cloud-Computing System for Greenhouse Control
Kim, JoonYong,Lee, Chun Gu,Park, Dong-Hyeok,Park, Heun Dong,Rhee, Joong-Yong Korean Society for Agricultural Machinery 2018 바이오시스템공학 Vol.43 No.4
Purpose: Cloud-computing technology has several advantages, including maintenance, management, accessibility, and computing power. A greenhouse-control system utilizing these advantages was developed using a private cloud-computing system. Methods: A private cloud needs a collection of servers and a suite of software tools to monitor and control cloud-computing resources. In this study, a server farm, operated by OpenStack as a cloud platform, was constructed using servers, and other network devices. Results: The greenhouse-control system was developed according to the fundamental cloud service models: infrastructure as a service, platform as a service, and software as a service. This system has four additional advantages - security, control function, public data use, and data exchange. There are several considerations that must be addressed, such as service level agreement, data ownership, security, and the differences between users. Conclusions: When the advantages are utilized and the considerations are addressed, cloud-computing technology will be beneficial for agricultural use.
Multilayer Perceptron Model to Estimate Solar Radiation with a Solar Module
Kim, Joonyong,Rhee, Joongyong,Yang, Seunghwan,Lee, Chungu,Cho, Seongin,Kim, Youngjoo Korean Society for Agricultural Machinery 2018 바이오시스템공학 Vol.43 No.4
Purpose: The objective of this study was to develop a multilayer perceptron (MLP) model to estimate solar radiation using a solar module. Methods: Data for the short-circuit current of a solar module and other environmental parameters were collected for a year. For MLP learning, 14,400 combinations of input variables, learning rates, activation functions, numbers of layers, and numbers of neurons were trained. The best MLP model employed the batch backpropagation algorithm with all input variables and two hidden layers. Results: The root-mean-squared error (RMSE) of each learning cycle and its average over three repetitions were calculated. The average RMSE of the best artificial neural network model was $48.13W{\cdot}m^{-2}$. This result was better than that obtained for the regression model, for which the RMSE was $66.67W{\cdot}m^{-2}$. Conclusions: It is possible to utilize a solar module as a power source and a sensor to measure solar radiation for an agricultural sensor node.