• Journal of the Korean Wood Science and Technology
• /
• v.46 no.1
• /
• pp.73-84
• /
• 2018

Recently, the importance of flame retardation treatment technology has been emphasized due to the increase in urban fire accidents and fire damage incidents caused by building exterior materials. Particularly, in the utilization of wood-based building materials, the flame retarding treatment technology is more importantly evaluated. An Intumescent system is one of the non-halogen flame retardant treatment technologies and is a system that realizes flame retardancy through foaming and carbonization layer formation. To apply the Intumescent system, composite material was prepared by using Ethylene vinyl acetate (EVA) as a matrix. To enhance the flame retardant properties of the Intumescent system, a nano-clay was applied together. Composite materials with Intumescent system and nano - clay technology were processed into sheet - like test specimens, and then a new structure of cross laminated timber with improved flame retardant properties was fabricated. In the evaluation of combustion characteristics of composite materials using Intumescent system, it was confirmed that the maximum heat emission was reduced efficiently. Depending on the structure attached to the surface, the CLT had two stages of combustion. Also, it was confirmed that the maximum calorific value decreased significantly during the deep burning process. These characteristics are expected to have a delayed combustion diffusion effect in the combustion process of CLT. In order to improve the performance, the flame retardation treatment technique for the surface veneer and the optimization technique of the application of the composite material are required. It is expected that it will be possible to develop a CLT structure with improved fire characteristics.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.17 no.1
• /
• pp.57-71
• /
• 2015

This study was conducted to develop the fertigation system with a peristaltic hose pump and brushless DC motor. The fertigation system was consisted of sensor, main controller, motor control unit, peristaltic pump, water supply pump, control panel, and filter. The peristaltic pump discharges liquid by squeezing the tube with rollers. Rollers attached to the external circumference of the rotor compresses the flexible tube. The fluid is contained within a flexible tube fitted inside a circular pump casing. The developed fertigation system has no mixing tank but instead injects directly a concentrated nutrient solution into a water supply pipe. The revolution speed of the peristaltic pump is controlled by PWM (Pulse width modulation) method. When the revolution speed of the peristaltic pump was 300rpm, the flow rate of the 3.2, 4.8, 6.3mm diameter tube was 202, 530, 857mL/min, respectively. As increasing revolution speed, the flow rate of the peristaltic pump linearly increased. As the inner diameter of a tube larger, a slope of graph is more steep. Flow rate of three roller was more than that of four roller. Flow rate of a norprene tube with good restoring force was more than that of a pharmed tube. As EC sensor probe was installed in direct piping in comparison with bypass piping showed good performance. After starting the system, it took 16~17 seconds to stabilize EC. The maximum value of EC was 1.44~1.7dS/m at a setting value of 1.4dS/m. The developed fertigation system showed ±0.06dS/m deviation from the setting value of EC. In field test, Cucumber plants generally showed good growth. From these findings, this fertigation system can be appropriately suitable for fertigation culture for crops.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.43-62
• /
• 2019

At one time, the anomaly detection sector dominated the method of determining whether there was an abnormality based on the statistics derived from specific data. This methodology was possible because the dimension of the data was simple in the past, so the classical statistical method could work effectively. However, as the characteristics of data have changed complexly in the era of big data, it has become more difficult to accurately analyze and predict the data that occurs throughout the industry in the conventional way. Therefore, SVM and Decision Tree based supervised learning algorithms were used. However, there is peculiarity that supervised learning based model can only accurately predict the test data, when the number of classes is equal to the number of normal classes and most of the data generated in the industry has unbalanced data class. Therefore, the predicted results are not always valid when supervised learning model is applied. In order to overcome these drawbacks, many studies now use the unsupervised learning-based model that is not influenced by class distribution, such as autoencoder or generative adversarial networks. In this paper, we propose a method to detect anomalies using generative adversarial networks. AnoGAN, introduced in the study of Thomas et al (2017), is a classification model that performs abnormal detection of medical images. It was composed of a Convolution Neural Net and was used in the field of detection. On the other hand, sequencing data abnormality detection using generative adversarial network is a lack of research papers compared to image data. Of course, in Li et al (2018), a study by Li et al (LSTM), a type of recurrent neural network, has proposed a model to classify the abnormities of numerical sequence data, but it has not been used for categorical sequence data, as well as feature matching method applied by salans et al.(2016). So it suggests that there are a number of studies to be tried on in the ideal classification of sequence data through a generative adversarial Network. In order to learn the sequence data, the structure of the generative adversarial networks is composed of LSTM, and the 2 stacked-LSTM of the generator is composed of 32-dim hidden unit layers and 64-dim hidden unit layers. The LSTM of the discriminator consists of 64-dim hidden unit layer were used. In the process of deriving abnormal scores from existing paper of Anomaly Detection for Sequence data, entropy values of probability of actual data are used in the process of deriving abnormal scores. but in this paper, as mentioned earlier, abnormal scores have been derived by using feature matching techniques. In addition, the process of optimizing latent variables was designed with LSTM to improve model performance. The modified form of generative adversarial model was more accurate in all experiments than the autoencoder in terms of precision and was approximately 7% higher in accuracy. In terms of Robustness, Generative adversarial networks also performed better than autoencoder. Because generative adversarial networks can learn data distribution from real categorical sequence data, Unaffected by a single normal data. But autoencoder is not. Result of Robustness test showed that he accuracy of the autocoder was 92%, the accuracy of the hostile neural network was 96%, and in terms of sensitivity, the autocoder was 40% and the hostile neural network was 51%. In this paper, experiments have also been conducted to show how much performance changes due to differences in the optimization structure of potential variables. As a result, the level of 1% was improved in terms of sensitivity. These results suggest that it presented a new perspective on optimizing latent variable that were relatively insignificant.

• Korean Journal of Soil Science and Fertilizer
• /
• v.45 no.2
• /
• pp.293-300
• /
• 2012

This study was to investigate the unsuitable rate of the storage facilities, the changes in corrosion process over time after installation according to the status, the time to install the facilities, years elapsed after facilities installation, inspection of methods and motivation, and so on, based on the results of the inspection at the petroleum storage facilities conducted by domestic soil-relate specialized agency to derive optimal management plans which meet the status of soil contamination facilities. The results showed that the facilities more than 5 years after the initial leak test at the time of the installation need to be inspected periodically by considering costs of leak test and remediation of polluted soil. The inspection period can be decided by cost and leak test methods showing discrepancies for the results obtained from individual test whether it was direct or indirect. To compensate these matters, we suggested that the direct inspection method on regular schedule is recommended. On the other hand, the inspection can be voluntarily completed to ease burden of the results by inspection or equivalent level to this inspection method. Also, it may need improved construction supervision and performance test system to minimize the occurrence of the nature defects in installing the facilities as well as the upgrade program for the facilities during intervals of inspection period.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.237-262
• /
• 2022

There has been a growing interest in IPOs (Initial Public Offerings) due to the profitable returns that IPO stocks can offer to investors. However, IPOs can be speculative investments that may involve substantial risk as well because shares tend to be volatile, and the supply of IPO shares is often highly limited. Therefore, it is crucially important that IPO investors are well informed of the issuing firms and the market before deciding whether to invest or not. Unlike institutional investors, individual investors are at a disadvantage since there are few opportunities for individuals to obtain information on the IPOs. In this regard, the purpose of this study is to provide individual investors with the information they may consider when making an IPO investment decision. This study presents a model that uses machine learning and text analysis to predict whether an IPO stock price would move up or down after the first 5 trading days. Our sample includes 691 Korean IPOs from June 2009 to December 2020. The input variables for the prediction are three tone variables created from IPO prospectuses and quantitative variables that are either firm-specific, issue-specific, or market-specific. The three prospectus tone variables indicate the percentage of positive, neutral, and negative sentences in a prospectus, respectively. We considered only the sentences in the Risk Factors section of a prospectus for the tone analysis in this study. All sentences were classified into 'positive', 'neutral', and 'negative' via text analysis using TF-IDF (Term Frequency - Inverse Document Frequency). Measuring the tone of each sentence was conducted by machine learning instead of a lexicon-based approach due to the lack of sentiment dictionaries suitable for Korean text analysis in the context of finance. For this reason, the training set was created by randomly selecting 10% of the sentences from each prospectus, and the sentence classification task on the training set was performed after reading each sentence in person. Then, based on the training set, a Support Vector Machine model was utilized to predict the tone of sentences in the test set. Finally, the machine learning model calculated the percentages of positive, neutral, and negative sentences in each prospectus. To predict the price movement of an IPO stock, four different machine learning techniques were applied: Logistic Regression, Random Forest, Support Vector Machine, and Artificial Neural Network. According to the results, models that use quantitative variables using technical analysis and prospectus tone variables together show higher accuracy than models that use only quantitative variables. More specifically, the prediction accuracy was improved by 1.45% points in the Random Forest model, 4.34% points in the Artificial Neural Network model, and 5.07% points in the Support Vector Machine model. After testing the performance of these machine learning techniques, the Artificial Neural Network model using both quantitative variables and prospectus tone variables was the model with the highest prediction accuracy rate, which was 61.59%. The results indicate that the tone of a prospectus is a significant factor in predicting the price movement of an IPO stock. In addition, the McNemar test was used to verify the statistically significant difference between the models. The model using only quantitative variables and the model using both the quantitative variables and the prospectus tone variables were compared, and it was confirmed that the predictive performance improved significantly at a 1% significance level.

• Journal of Radiation Protection and Research
• /
• v.39 no.1
• /
• pp.54-60
• /
• 2014

IAEA has employed various types of radiation detectors - HPGe, NaI, CZT - for accountancy of nuclear material. Among them, HPGe has been mainly used in verification activities required for high accuracy. Due to its essential cooling component(a liquid-nitrogen cooling or a mechanical cooling system), it is large and heavy and needs long cooling time before use. New hand-held portable HPGe has been developed to address such problems. This paper deals with results of performance evaluation test of the new hand-held portable HPGe prototype which was used during IAEA's inspection activities. Radioactive spectra obtained with the new portable HPGe showed different characteristics depending on types and enrichments of nuclear materials inspected. Also, Gamma-rays from daughter radioisotopes in the decay series of $^{235}U$ and $^{238}U$ and characteristic x-rays from uranium were able to be remarkably separated from other peaks in the spectra. A relative error of enrichment measured by the new portable HPGe was in the range of 9 to 27%. The enrichment measurement results didn't meet partially requirement of IAEA because of a small size of a radiation sensing material. This problem might be solved through a further study. This paper discusses how to determine enrichment of nuclear material as well as how to apply the new hand-held portable HPGe to safeguard inspection. There have been few papers to deal with IAEA inspection activity in Korea to verify accountancy of nuclear material in national nuclear facilities. This paper would contribute to analyzing results of safeguards inspection. Also, it is expected that things discussed about further improvement of a radiation detector would make contribution to development of a radiation detector in the related field.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.121-139
• /
• 2014

Predicting corporate failure has been an important topic in accounting and finance. The costs associated with bankruptcy are high, so the accuracy of bankruptcy prediction is greatly important for financial institutions. Lots of researchers have dealt with the topic associated with bankruptcy prediction in the past three decades. The current research attempts to use ensemble models for improving the performance of bankruptcy prediction. Ensemble classification is to combine individually trained classifiers in order to gain more accurate prediction than individual models. Ensemble techniques are shown to be very useful for improving the generalization ability of the classifier. Bagging is the most commonly used methods for constructing ensemble classifiers. In bagging, the different training data subsets are randomly drawn with replacement from the original training dataset. Base classifiers are trained on the different bootstrap samples. Instance selection is to select critical instances while deleting and removing irrelevant and harmful instances from the original set. Instance selection and bagging are quite well known in data mining. However, few studies have dealt with the integration of instance selection and bagging. This study proposes an improved bagging ensemble based on instance selection using genetic algorithms (GA) for improving the performance of SVM. GA is an efficient optimization procedure based on the theory of natural selection and evolution. GA uses the idea of survival of the fittest by progressively accepting better solutions to the problems. GA searches by maintaining a population of solutions from which better solutions are created rather than making incremental changes to a single solution to the problem. The initial solution population is generated randomly and evolves into the next generation by genetic operators such as selection, crossover and mutation. The solutions coded by strings are evaluated by the fitness function. The proposed model consists of two phases: GA based Instance Selection and Instance based Bagging. In the first phase, GA is used to select optimal instance subset that is used as input data of bagging model. In this study, the chromosome is encoded as a form of binary string for the instance subset. In this phase, the population size was set to 100 while maximum number of generations was set to 150. We set the crossover rate and mutation rate to 0.7 and 0.1 respectively. We used the prediction accuracy of model as the fitness function of GA. SVM model is trained on training data set using the selected instance subset. The prediction accuracy of SVM model over test data set is used as fitness value in order to avoid overfitting. In the second phase, we used the optimal instance subset selected in the first phase as input data of bagging model. We used SVM model as base classifier for bagging ensemble. The majority voting scheme was used as a combining method in this study. This study applies the proposed model to the bankruptcy prediction problem using a real data set from Korean companies. The research data used in this study contains 1832 externally non-audited firms which filed for bankruptcy (916 cases) and non-bankruptcy (916 cases). Financial ratios categorized as stability, profitability, growth, activity and cash flow were investigated through literature review and basic statistical methods and we selected 8 financial ratios as the final input variables. We separated the whole data into three subsets as training, test and validation data set. In this study, we compared the proposed model with several comparative models including the simple individual SVM model, the simple bagging model and the instance selection based SVM model. The McNemar tests were used to examine whether the proposed model significantly outperforms the other models. The experimental results show that the proposed model outperforms the other models.

• Journal of Animal Environmental Science
• /
• v.18 no.3
• /
• pp.207-220
• /
• 2012

There are around 7,500 manure tanks to treat the manures from pigs in Korea. In the tank, there are too much sediments deposited on the base and wall, which causes low efficiency of stock capacity and manure fermentation. In order to minimize sediments and to ferment manure effectively, we developed a 2-fluid jet mixer for mixing sediments in liquid livestock manure tank. For developing the prototype, we tested a factorial experimental system with various nozzles, and simulated CFD models with two kinds of nozzle arrangement. From the results of factorial experiment and CFD simulation, we concluded the dia. ratio of primary : secondary nozzle should be 1:2 and the nozzles should be arranged at the same distances toward to the circumferential direction. With this results, we manufactured a 2-fluid jet mixer which is consists of four 2-phase nozzles, centrifugal slurry pump and root's type air blower. And, we carried out the performance test of the prototype in the round shaped liquid manure tank in the farm. The performance test results showed that the uniformity of TS (Total Solid) and VS (Volatile Solid) was raised from 21.3 g/L, 13.3 g/L In steady state to TS and VS to 23.0 g/L, 14.1 g/L in the mixing operation. Therefore, we could conclude that the prototype of 2-fluid mixer could make the solid material which could be sediments in the tank not to be deposited in the tank and to be contacted to air bubbles which could enhance the efficiency of the fermentation of livestock manure.

• Horticultural Science & Technology
• /
• v.30 no.5
• /
• pp.586-595
• /
• 2012

This study was conducted to determine the effects of horticultural therapy (HT) program using hydroponics on work adjustment skills of students with mental retardation. Based on the critical role transitional model and special education curriculum for agriculture, especially hydroponics, HT program (total 22 sessions) using hydroponics procedure for Lettuce (Lactuca sativa L. 'Asia Heuk Romaine') was developed. Fourteen (10 males, 4 females) graded $1^{st}$ to $2^{nd}$ with intellectual disabilities were recruited from a special education class in a high school located in Inchon, Korea and then a special farm for hydroponics in Inchon, Korea was offered for the HT program. The students with intellectual disabilities participated in the HT program for 4-month (from September to December of 2011, twice a week, approximately 60 minutes per session). Before and after the HT program, the McCarron assessment neuromuscular development, emotional behavioral checklist, interpersonal negotiation strategies, and KEPAD picture vocational interest test were performed by the teachers and horticultural therapists. As the results, the students significantly improved motor performance (p = 0.002), emotional behavioral strategies (p = 0.00), and interpersonal negotiation strategies (p = 0.05). However, no significant difference between before and after the HT program for vocational interest was observed. In conclusion, the HT program using hydroponics, consists of simple and easy tasks so that it would be applicable for the students with intellectual disabilities positively affected to work adjustment skills by improving the motor performance, emotional behavioral strategies, and interpersonal negotiation strategies. Additionally, HT programs using hydroponics with various kinds of vegetables are required to develop and to apply in practical settings for improving work adjustment skills.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.47
• /
• pp.63-94
• /
• 2002

On the purpose to suggest an advanced scheme in assessing the domestic wheat quality, this paper reviewed the inspection systems of wheat in major wheat producing countries as well as the quality criteria which are being used in wheat grading and classification. Most wheat producing countries are adopting both classifications of class and grade to provide an objective evaluation and an official certification to their wheat. There are two main purposes in the wheat classification. The first objectives of classification is to match the wheat with market requirements to maximize market opportunities and returns to growers. The second is to ensure that payments to glowers aye made on the basis of the quality and condition of the grain delivered. Wheat classes has been assigned based on the combination of cultivation area, seed-coat color, kernel and varietal characteristics that are distinctive. Most reputable wheat marketers also employ a similar approach, whereby varieties of a particular type are grouped together, designed by seed coat colour, grain hardness, physical dough properties, and sometimes more precise specification such as starch quality, all of which are genetically inherited characteristics. This classification in simplistic terms is the categorization of a wheat variety into a commercial type or style of wheat that is recognizable for its end use capabilities. All varieties registered in a class are required to have a similar end-use performance that the shipment be consistent in processing quality, cargo to cargo and year to year, Grain inspectors have historically determined wheat classes according to visual kernel characteristics associated with traditional wheat varieties. As well, any new wheat variety must not conflict with the visual distinguishability rule that is used to separate wheats of different classes. Some varieties may possess characteristics of two or more classes. Therefore, knowledge of distinct varietal characteristics is necessary in making class determinations. The grading system sets maximum tolerance levels for a range of characteristics that ensure functionality and freedom from deleterious factors. Tests for the grading of wheat include such factors as plumpness, soundness, cleanliness, purity of type and general condition. Plumpness is measured by test weight. Soundness is indicated by the absence or presence of musty, sour or commercially objectionable foreign odors and by the percentage of damaged kernels that ave present in the wheat. Cleanliness is measured by determining the presence of foreign material after dockage has been removed. Purity of class is measured by classification of wheats in the test sample and by limitation for admixtures of different classes of wheat. Moisture does not influence the numerical grade. However, it is determined on all shipments and reported on the official certificate. U.S. wheat is divided into eight classes based on color, kernel Hardness and varietal characteristics. The classes are Durum, Hard Red Spring, Hard Red Winter, Soft Red Winter, Hard White, soft White, Unclassed and Mixed. Among them, Hard Red Spring wheat, Durum wheat, and Soft White wheat are further divided into three subclasses, respectively. Each class or subclass is divided into five U.S. numerical grades and U.S. Sample grade. Special grades are provided to emphasize special qualities or conditions affecting the value of wheat and are added to and made a part of the grade designation. Canadian wheat is also divided into fourteen classes based on cultivation area, color, kernel hardness and varietal characteristics. The classes have 2-5 numerical grades, a feed grade and sample grades depending on class and grading tolerance. The Canadian grading system is based mainly on visual evaluation, and it works based on the kernel visual distinguishability concept. The Australian wheat is classified based on geographical and quality differentiation. The wheat grown in Australia is predominantly white grained. There are commonly up to 20 different segregations of wheat in a given season. Each variety grown is assigned a category and a growing areas. The state governments in Australia, in cooperation with the Australian Wheat Board(AWB), issue receival standards and dockage schedules annually that list grade specifications and tolerances for Australian wheat. AWB is managing "Golden Rewards" which is designed to provide pricing accuracy and market signals for Australia's grain growers. Continuous payment scales for protein content from 6 to 16% and screenings levels from 0 to 10% based on varietal classification are presented by the Golden Rewards, and the active payment scales and prices can change with market movements.movements.