• Horticultural Science & Technology
• /
• v.33 no.5
• /
• pp.647-657
• /
• 2015

To investigate a method for calculation of the heating load for environmental designs of horticultural facilities, measurements of total heating load, infiltration rate, and floor heat flux in a large-scale plastic greenhouse were analyzed comparatively with the calculation results. Effects of ground heat exchange and infiltration loss on the greenhouse heating load were examined. The ranges of the indoor and outdoor temperatures were $13.3{\pm}1.2^{\circ}C$ and $-9.4{\sim}+7.2^{\circ}C$ respectively during the experimental period. It was confirmed that the outdoor temperatures were valid in the range of the design temperatures for the greenhouse heating design in Korea. Average infiltration rate of the experimental greenhouse measured by a gas tracer method was $0.245h^{-1}$. Applying a constant ventilation heat transfer coefficient to the covering area of the greenhouse was found to have a methodological problem in the case of various sizes of greenhouses. Thus, it was considered that the method of using the volume and the infiltration rate of greenhouses was reasonable for the infiltration loss. Floor heat flux measured in the center of the greenhouse tended to increase toward negative slightly according to the differences between indoor and outdoor temperature. By contrast, floor heat flux measured at the side of the greenhouse tended to increase greatly into plus according to the temperature differences. Based on the measured results, a new calculation method for ground heat exchange was developed by adopting the concept of heat loss through the perimeter of greenhouses. The developed method coincided closely with the experimental result. Average transmission heat loss was shown to be directly proportional to the differences between indoor and outdoor temperature, but the average overall heat transfer coefficient tended to decrease. Thus, in calculating the transmission heat loss, the overall heat transfer coefficient must be selected based on design conditions. The overall heat transfer coefficient of the experimental greenhouse averaged $2.73W{\cdot}m^{-2}{\cdot}C^{-1}$, which represents a 60% heat savings rate compared with plastic greenhouses with a single covering. The total heating load included, transmission heat loss of 84.7~95.4%, infiltration loss of 4.4~9.5%, and ground heat exchange of -0.2~+6.3%. The transmission heat loss accounted for larger proportions in groups with low differences between indoor and outdoor temperature, whereas infiltration heat loss played the larger role in groups with high temperature differences. Ground heat exchange could either heighten or lessen the heating load, depending on the difference between indoor and outdoor temperature. Therefore, the selection of a reference temperature difference is important. Since infiltration loss takes on greater importance than ground heat exchange, measures for lessening the infiltration loss are required to conserve energy.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.15 no.3
• /
• pp.208-218
• /
• 2012

Numerical simulation technique has been developed to calculate microwave backscattering from water surface. The simulation plays a role of a substitute for experiments. Validation of the simulation was shown by comparing with experimental results. Water area observations by microwave radar have been simulated to evaluate algorithms and systems. Furthermore, the simulation can be used to understand microwave scattering mechanism on the water surface. The simulation has applied to the various methods for water area observations, and the utilizations of the simulation are introduced in this paper. In the case of fixed radar, we show following examples, 1. Radar image with a pulse Doppler radar, 2. Effect of microwave irradiation width and 3. River observation (Water level observation). In addition, another application (4.Synthetic aperture radar image) is also described. The details of the applications are as follows. 1. Radar image with a pulse Doppler radar: A new system for the sea surface observation is suggested by the simulation. A pulse Doppler radar is assumed to obtain radar images that display amplitude and frequency modulation of backscattered microwaves. The simulation results show that the radar images of the frequency modulation is useful to measure sea surface waves. 2. Effect of microwave irradiation width: It is reported (Rheem[2008]) that microwave irradiation width on the sea surface affects Doppler spectra measured by a CW (Continuous wave) Doppler radar. Therefore the relation between the microwave irradiation width and the Doppler spectra is evaluated numerically. We have shown the suitable condition for wave height estimation by a Doppler radar. 3. River observation (Water level observation): We have also evaluated algorithms to estimate water current and water level of river. The same algorithms to estimate sea surface current and sea surface level are applied to the river observation. The simulation is conducted to confirm the accuracy of the river observation by using a pulse Doppler radar. 4. Synthetic aperture radar (SAR) image: SAR images are helpful to observe the global sea surface. However, imaging mechanisms are complicated and validation of analytical algorithms by SAR images is quite difficult. In order to deal with the problems, SAR images in oceanic scenes are simulated.

• Journal of the Korean Society of Radiology
• /
• v.14 no.6
• /
• pp.773-780
• /
• 2020

With the development of the 4th industrial, research is being conducted to prevent diseases and reduce damage in various fields of science and technology such as medicine, health, and bio. As a result, artificial intelligence technology has been introduced and researched for image analysis of radiological examinations. In this paper, we will directly apply a deep learning model for classification and detection of pneumonia using chest X-ray images, and evaluate whether the deep learning model of the Inception series is a useful model for detecting pneumonia. As the experimental material, a chest X-ray image data set provided and shared free of charge by Kaggle was used, and out of the total 3,470 chest X-ray image data, it was classified into 1,870 training data sets, 1,100 validation data sets, and 500 test data sets. I did. As a result of the experiment, the result of metric evaluation of the Inception V3 deep learning model was 94.80% for accuracy, 97.24% for precision, 94.00% for recall, and 95.59 for F1 score. In addition, the accuracy of the final epoch for Inception V3 deep learning modeling was 94.91% for learning modeling and 89.68% for verification modeling for pneumonia detection and classification of chest X-ray images. For the evaluation of the loss function value, the learning modeling was 1.127% and the validation modeling was 4.603%. As a result, it was evaluated that the Inception V3 deep learning model is a very excellent deep learning model in extracting and classifying features of chest image data, and its learning state is also very good. As a result of matrix accuracy evaluation for test modeling, the accuracy of 96% for normal chest X-ray image data and 97% for pneumonia chest X-ray image data was proven. The deep learning model of the Inception series is considered to be a useful deep learning model for classification of chest diseases, and it is expected that it can also play an auxiliary role of human resources, so it is considered that it will be a solution to the problem of insufficient medical personnel. In the future, this study is expected to be presented as basic data for similar studies in the case of similar studies on the diagnosis of pneumonia using deep learning.

• Journal of Food Hygiene and Safety
• /
• v.32 no.5
• /
• pp.411-417
• /
• 2017

This study was conducted to establish the analysis method for the contents of choline in infant formulas and follow-up formulas by ion chromatograph (IC). To optimize the method, we compared several conditions for extraction, purification and instrumental measurement using spiked samples and certified reference material (CRM; NIST SRM 1849a) as test materials. IC method for choline was established using Ion Pac CG column and 18 mM $H_2SO_4$ mobile phase. The parameters of validation were specificity, linearity, LOD, LOQ, recovery, accuracy, precision and repeatability. The specificity was confirmed by the retention time and the linearity, $R_2$ was over 0.999 in range of 0.5~10 mg/L. The detection limit and quantification limit were 0.14, 0.43 mg/L. The accuracy and precision of this method using CRM were 95%, 2.1% respectively. Optimized methods were applied in sample analysis to verify the reliability. All the tested products were acceptable contents of choline compared with component specification for nutrition labeling. The standard operating procedures were prepared for choline to provide experimental information and to strengthen the management of nutrient in infant formula and follow-up formula.

• Korean Journal of Environmental Agriculture
• /
• v.31 no.4
• /
• pp.318-327
• /
• 2012

BACKGROUND: For Non-Point Source(NPS) loads reduction, pollutant loads need to be quantified for major farming methods. The objective of this study was to evaluate impacts of farming methods on NPS pollutant loads from a paddy rice field during the growing season. METHODS AND RESULTS: The height of drainage outlet, amount of fertilizer, irrigation water quality were considered as farming factors for scenarios development. The control was derived from conventional farming methods and four different scenarios were developed based combination of farming factors. A field scale model, CREAMS-PADDY(Chemicals, Runoff, and Erosion from Agricultural Management Systems for PADDY), was used to calculate pollutant nutrient loads. The data collected from an experimental plot located downstream of the Idong reservoir were used for model calibration and validation. The simulation results agreed well with observed values during the calibration and validation periods. The calibrated model was used to evaluate farming scenarios in terms of NPS loads. Pollutant loads for T-N, T-P were reduced by 5~62%, 8~37% with increasing the height of drainage outlet from 100 mm of 100 mm, respectively. When amount of fertilizer was changed from standard to conventional, T-N, T-P pollutant loads were reduced by 0~22%, 0~24%. Irrigation water quality below water criteria IV of reservoir increased T-N of 9~65%, T-P of 9~47% in comparison with conventional. CONCLUSION(S): The results indicated that applying increased the height of drainage after midsummer drainage, standard fertilization level during non-rainy seasons, irrigation water quality below water criteria IV of reservoir were effective farming methods to reduce NPS pollutant loads from paddy in Korea.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.159-172
• /
• 2010

The recommender system is one of the possible solutions to assist customers in finding the items they would like to purchase. To date, a variety of recommendation techniques have been developed. One of the most successful recommendation techniques is Collaborative Filtering (CF) that has been used in a number of different applications such as recommending Web pages, movies, music, articles and products. CF identifies customers whose tastes are similar to those of a given customer, and recommends items those customers have liked in the past. Numerous CF algorithms have been developed to increase the performance of recommender systems. Broadly, there are memory-based CF algorithms, model-based CF algorithms, and hybrid CF algorithms which combine CF with content-based techniques or other recommender systems. While many researchers have focused their efforts in improving CF performance, the theoretical justification of CF algorithms is lacking. That is, we do not know many things about how CF is done. Furthermore, the relative performances of CF algorithms are known to be domain and data dependent. It is very time-consuming and expensive to implement and launce a CF recommender system, and also the system unsuited for the given domain provides customers with poor quality recommendations that make them easily annoyed. Therefore, predicting the performances of CF algorithms in advance is practically important and needed. In this study, we propose an efficient approach to predict the performance of CF. Social Network Analysis (SNA) and Artificial Neural Network (ANN) are applied to develop our prediction model. CF can be modeled as a social network in which customers are nodes and purchase relationships between customers are links. SNA facilitates an exploration of the topological properties of the network structure that are implicit in data for CF recommendations. An ANN model is developed through an analysis of network topology, such as network density, inclusiveness, clustering coefficient, network centralization, and Krackhardt's efficiency. While network density, expressed as a proportion of the maximum possible number of links, captures the density of the whole network, the clustering coefficient captures the degree to which the overall network contains localized pockets of dense connectivity. Inclusiveness refers to the number of nodes which are included within the various connected parts of the social network. Centralization reflects the extent to which connections are concentrated in a small number of nodes rather than distributed equally among all nodes. Krackhardt's efficiency characterizes how dense the social network is beyond that barely needed to keep the social group even indirectly connected to one another. We use these social network measures as input variables of the ANN model. As an output variable, we use the recommendation accuracy measured by F1-measure. In order to evaluate the effectiveness of the ANN model, sales transaction data from H department store, one of the well-known department stores in Korea, was used. Total 396 experimental samples were gathered, and we used 40%, 40%, and 20% of them, for training, test, and validation, respectively. The 5-fold cross validation was also conducted to enhance the reliability of our experiments. The input variable measuring process consists of following three steps; analysis of customer similarities, construction of a social network, and analysis of social network patterns. We used Net Miner 3 and UCINET 6.0 for SNA, and Clementine 11.1 for ANN modeling. The experiments reported that the ANN model has 92.61% estimated accuracy and 0.0049 RMSE. Thus, we can know that our prediction model helps decide whether CF is useful for a given application with certain data characteristics.

• Korean Journal of Microbiology
• /
• v.52 no.2
• /
• pp.140-147
• /
• 2016

A process for manufacturing virally-safe porcine bone hydroxyapatite (HA) has been developed to serve as advanced xenograft material for dental applications. Porcine bone pieces were defatted with successive treatments of 30% hydrogen peroxide and 80% ethyl alcohol. The defatted porcine bone pieces were heat-treated in an oxygen atmosphere box furnace at $1,300^{\circ}C$ to remove collagen and organic compounds. The bone pieces were ground with a grinder and then the bone powder was sterilized by gamma irradiation. Morphological characteristics such as SEM (Scanning Electron Microscopy) and TEM (Transmission Electron Microscopy) images of the resulting porcine bone HA (THE Graft$^{(R)}$) were similar to those of a commercial bovine bone HA (Bio-Oss$^{(R)}$). In order to evaluate the efficacy of $1,300^{\circ}C$ heat treatment and gamma irradiation at a dose of 25 kGy for the inactivation of porcine viruses during the manufacture of porcine bone HA, a variety of experimental porcine viruses including transmissible gastroenteritis virus (TGEV), pseudorabies virus (PRV), porcine rotavirus (PRoV), and porcine parvovirus (PPV) were chosen. TGEV, PRV, PRoV, and PPV were completely inactivated to undetectable levels during the $1,300^{\circ}C$ heat treatment. The mean log reduction factors achieved were $${\geq_-}4.65$$ for TGEV, $${\geq_-}5.81$$ for PRV, $${\geq_-}6.28$$ for PRoV, and $${\geq_-}5.21$$ for PPV. Gamma irradiation was also very effective at inactivating the viruses. TGEV, PRV, PRoV, and PPV were completely inactivated to undetectable levels during the gamma irradiation. The mean log reduction factors achieved were $${\geq_-}4.65$$ for TGEV, $${\geq_-}5.87$$ for PRV, $${\geq_-}6.05$$ for PRoV, and $${\geq_-}4.89$$ for PPV. The cumulative log reduction factors achieved using the two different virus inactivation processes were $${\geq_-}9.30$$ for TGEV, $${\geq_-}11.68$$ for PRV, $${\geq_-}12.33$$ for PRoV, and $${\geq_-}10.10$$ for PPV. These results indicate that the manufacturing process for porcine bone HA from porcine-bone material has sufficient virus-reducing capacity to achieve a high margin of virus safety.

• Information Systems Review
• /
• v.16 no.3
• /
• pp.161-177
• /
• 2014

Corporate credit rating assessment consists of complicated processes in which various factors describing a company are taken into consideration. Such assessment is known to be very expensive since domain experts should be employed to assess the ratings. As a result, the data-driven corporate credit rating prediction using statistical and artificial intelligence (AI) techniques has received considerable attention from researchers and practitioners. In particular, statistical methods such as multiple discriminant analysis (MDA) and multinomial logistic regression analysis (MLOGIT), and AI methods including case-based reasoning (CBR), artificial neural network (ANN), and multiclass support vector machine (MSVM) have been applied to corporate credit rating.2) Among them, MSVM has recently become popular because of its robustness and high prediction accuracy. In this study, we propose a novel optimized MSVM model, and appy it to corporate credit rating prediction in order to enhance the accuracy. Our model, named 'GAMSVM (Genetic Algorithm-optimized Multiclass Support Vector Machine),' is designed to simultaneously optimize the kernel parameters and the feature subset selection. Prior studies like Lorena and de Carvalho (2008), and Chatterjee (2013) show that proper kernel parameters may improve the performance of MSVMs. Also, the results from the studies such as Shieh and Yang (2008) and Chatterjee (2013) imply that appropriate feature selection may lead to higher prediction accuracy. Based on these prior studies, we propose to apply GAMSVM to corporate credit rating prediction. As a tool for optimizing the kernel parameters and the feature subset selection, we suggest genetic algorithm (GA). GA is known as an efficient and effective search method that attempts to simulate the biological evolution phenomenon. By applying genetic operations such as selection, crossover, and mutation, it is designed to gradually improve the search results. Especially, mutation operator prevents GA from falling into the local optima, thus we can find the globally optimal or near-optimal solution using it. GA has popularly been applied to search optimal parameters or feature subset selections of AI techniques including MSVM. With these reasons, we also adopt GA as an optimization tool. To empirically validate the usefulness of GAMSVM, we applied it to a real-world case of credit rating in Korea. Our application is in bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. The experimental dataset was collected from a large credit rating company in South Korea. It contained 39 financial ratios of 1,295 companies in the manufacturing industry, and their credit ratings. Using various statistical methods including the one-way ANOVA and the stepwise MDA, we selected 14 financial ratios as the candidate independent variables. The dependent variable, i.e. credit rating, was labeled as four classes: 1(A1); 2(A2); 3(A3); 4(B and C). 80 percent of total data for each class was used for training, and remaining 20 percent was used for validation. And, to overcome small sample size, we applied five-fold cross validation to our dataset. In order to examine the competitiveness of the proposed model, we also experimented several comparative models including MDA, MLOGIT, CBR, ANN and MSVM. In case of MSVM, we adopted One-Against-One (OAO) and DAGSVM (Directed Acyclic Graph SVM) approaches because they are known to be the most accurate approaches among various MSVM approaches. GAMSVM was implemented using LIBSVM-an open-source software, and Evolver 5.5-a commercial software enables GA. Other comparative models were experimented using various statistical and AI packages such as SPSS for Windows, Neuroshell, and Microsoft Excel VBA (Visual Basic for Applications). Experimental results showed that the proposed model-GAMSVM-outperformed all the competitive models. In addition, the model was found to use less independent variables, but to show higher accuracy. In our experiments, five variables such as X7 (total debt), X9 (sales per employee), X13 (years after founded), X15 (accumulated earning to total asset), and X39 (the index related to the cash flows from operating activity) were found to be the most important factors in predicting the corporate credit ratings. However, the values of the finally selected kernel parameters were found to be almost same among the data subsets. To examine whether the predictive performance of GAMSVM was significantly greater than those of other models, we used the McNemar test. As a result, we found that GAMSVM was better than MDA, MLOGIT, CBR, and ANN at the 1% significance level, and better than OAO and DAGSVM at the 5% significance level.

• Journal of Energy Engineering
• /
• v.24 no.4
• /
• pp.200-210
• /
• 2015

The modeling for fast pyrolysis of biomass in fluidized bed reactor has been developed for accurate prediction of bio-oil and gas products and for yield improvement. The purpose of this study is to analyze and to compare the CFD(Computational Fluid Dynamics) simulation results with the experimental data from the CFD simulation results with the experimental data from the reference(Mellin et al., 2014) for gas products generated during fast pyrolysis of biomass in fluidized bed reactor. CFD(ANSYS FLUENT v.15.0) was used for the simulation. Complex pyrolysis reaction scheme of biomass subcomponents was applied for the simulation of pyrolysis reaction. This pyrolysis reaction scheme was included reaction of cellulose, hemicellulose, lignin in detail, gas products obtained from pyrolysis were mainly $CO_2$, CO, $CH_4$, $H_2$, $C_2H_4$. The deviation between the simulation results from this study and experimental data from the reference was calculated about 3.7%p, 4.6%p, 3.9%p for $CH_4$, $H_2$, $C_2H_4$ respectively, whereas 9.6%p and 6.7%p for $CO_2$ and CO which are relatively high. Through this study, it is possible to predict gas products accurately by using CFD simulation approach. Moreover, this modeling approach should be developed to predict fluidized bed reactor performance and other gas product yields.

• Journal of Navigation and Port Research
• /
• v.42 no.6
• /
• pp.427-436
• /
• 2018

In this study, experimental and numerical analysis were performed on the survivability of a long pipe-type buoy structure in waves. The buoy structure is an articulated tower consisting of an upper structure, buoyancy module, and gravity anchor with long pipes forming the base frame. A series of experiment were performed in the ocean engineering basin of KRISO with the scaled model of 1/ 22 to evaluate the survivability of the buoy structure at West Sea in South Korea. Survival condition was considered as the wave of 50 year return period. Additional experiments were performed to investigate the effects of current and wave period. The factors considered for the evaluation of the buoy's survival were the pitch angle of the structure, anchor reaction force, and the number of submergence of the upper structure. Numerical simulations were carried out with the OrcaFlex, the commercial program for the mooring analysis, with the aim of performing mutual validation with the experimental results. Based on the evaluation, the behavior characteristics of the buoy structure were first examined according to the tidal conditions. The changes were investigated for the pitch angle and anchor reaction force at HAT and LAT conditions, and the results directly compared with those obtained from numerical simulation. Secondly, the response characteristics of the buoy structure were studied depending on the wave period and the presence of current velocity. Third, the number of submergence through video analysis was compared with the simulation results in relation to the submergence of the upper structure. Finally, the simulation results for structural responses which were not directly measured in the experiment were presented, and the structural safety discussed in the survival waves. Through a series of survivability evaluation studies, the behavior characteristics of the buoy structure were examined in survival waves. The vulnerability and utility of the buoy structure were investigated through the sensitivity studies of waves, current, and tides.