• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.99-112
• /
• 2010

Ensemble learning is a method for improving the performance of classification and prediction algorithms. It is a method for finding a highly accurateclassifier on the training set by constructing and combining an ensemble of weak classifiers, each of which needs only to be moderately accurate on the training set. Ensemble learning has received considerable attention from machine learning and artificial intelligence fields because of its remarkable performance improvement and flexible integration with the traditional learning algorithms such as decision tree (DT), neural networks (NN), and SVM, etc. In those researches, all of DT ensemble studies have demonstrated impressive improvements in the generalization behavior of DT, while NN and SVM ensemble studies have not shown remarkable performance as shown in DT ensembles. Recently, several works have reported that the performance of ensemble can be degraded where multiple classifiers of an ensemble are highly correlated with, and thereby result in multicollinearity problem, which leads to performance degradation of the ensemble. They have also proposed the differentiated learning strategies to cope with performance degradation problem. Hansen and Salamon (1990) insisted that it is necessary and sufficient for the performance enhancement of an ensemble that the ensemble should contain diverse classifiers. Breiman (1996) explored that ensemble learning can increase the performance of unstable learning algorithms, but does not show remarkable performance improvement on stable learning algorithms. Unstable learning algorithms such as decision tree learners are sensitive to the change of the training data, and thus small changes in the training data can yield large changes in the generated classifiers. Therefore, ensemble with unstable learning algorithms can guarantee some diversity among the classifiers. To the contrary, stable learning algorithms such as NN and SVM generate similar classifiers in spite of small changes of the training data, and thus the correlation among the resulting classifiers is very high. This high correlation results in multicollinearity problem, which leads to performance degradation of the ensemble. Kim,s work (2009) showedthe performance comparison in bankruptcy prediction on Korea firms using tradition prediction algorithms such as NN, DT, and SVM. It reports that stable learning algorithms such as NN and SVM have higher predictability than the unstable DT. Meanwhile, with respect to their ensemble learning, DT ensemble shows the more improved performance than NN and SVM ensemble. Further analysis with variance inflation factor (VIF) analysis empirically proves that performance degradation of ensemble is due to multicollinearity problem. It also proposes that optimization of ensemble is needed to cope with such a problem. This paper proposes a hybrid system for coverage optimization of NN ensemble (CO-NN) in order to improve the performance of NN ensemble. Coverage optimization is a technique of choosing a sub-ensemble from an original ensemble to guarantee the diversity of classifiers in coverage optimization process. CO-NN uses GA which has been widely used for various optimization problems to deal with the coverage optimization problem. The GA chromosomes for the coverage optimization are encoded into binary strings, each bit of which indicates individual classifier. The fitness function is defined as maximization of error reduction and a constraint of variance inflation factor (VIF), which is one of the generally used methods to measure multicollinearity, is added to insure the diversity of classifiers by removing high correlation among the classifiers. We use Microsoft Excel and the GAs software package called Evolver. Experiments on company failure prediction have shown that CO-NN is effectively applied in the stable performance enhancement of NNensembles through the choice of classifiers by considering the correlations of the ensemble. The classifiers which have the potential multicollinearity problem are removed by the coverage optimization process of CO-NN and thereby CO-NN has shown higher performance than a single NN classifier and NN ensemble at 1% significance level, and DT ensemble at 5% significance level. However, there remain further research issues. First, decision optimization process to find optimal combination function should be considered in further research. Secondly, various learning strategies to deal with data noise should be introduced in more advanced further researches in the future.

• Journal of Bio-Environment Control
• /
• v.27 no.4
• /
• pp.400-406
• /
• 2018

In this experiment the effect of supplemental lighting on the growth and yield of cucumber (Cucumis sativus L. 'Fresh') plants during low radiation period of winter season were investigated in glasshouses using common high-pressure sodium (HPS) lamps and newly developed plasma lighting system (PLS) lamps. Plants grown without supplemental lighting were considered as a control. Supplemental lighting was provided from November 20th, 2015 to March 15th, 2016 to ensure 14-hour photoperiod (natural+supplemental light), also lamps were operated automatically when the outside sun radiation levels were less than $100W{\cdot}m^{-2}$. Spectral analysis showed that HPS lamp had a discrete spectrum, lacked of the radiation in the 400-550 nm wave band (blue-green light), but had a high output in the orange-red region (550-650 nm). A higher red light output resulted in an increased red to far-red (R/FR) ratio in HPS lamp. PLS had a continuous spectrum and had a peak radiation in green region (490-550 nm). HPS has 12.6% lower output in photosynthetically active radiation (PAR) but 12.6% higher output in near infra-red (NIR) spectral regions compared to PLS. Both HPS and PLS lamps emitted very low levels of ultra-violet radiation (300-400 nm). Supplemental lighting both from HPS and PLS lamps increased plant height, leaf number, internode number and dry weight of cucumber plants compared to control. Photosynthetic activity of cucumber plants grown under two supplemental lighting systems was comparable. Number of fruits per cucumber plant (fruit weight per plant) in control, PLS, and HPS plots were 21.2 (2.9 kg), 38.7 (5.5 kg), and 40.4 (5.6 kg), respectively, thereby increasing yield by 1.8-1.9 times in comparison with control. An analysis of the economic feasibility of supplemental lighting in cucumber cultivation showed that considering lamp installation and electricity costs the income from supplemental lighting increased by 37% and 62% for PLS and HPS lamps, respectively.

• Journal of Marine Bioscience and Biotechnology
• /
• v.1 no.2
• /
• pp.91-97
• /
• 2006

For efficient removal of nitrogenous compounds produced in recirculating aquaculture system, the N removal characteristics of immobilized mixed microorganisms were investigated at various mixing ratios of photosynthetic bacteria (PSB) immobilized in PVA beads or CTA cubes and ammonium utilizing bacteria (AUB) immobilized in PVA beads. On the optimal medium of AUB, the maxium gas production rate was obtained at the mixing ratio of 10:40 (PSB:AUB), and the gas production rate increased as the portion of AUB beads in the mixed beads increased. When the mixing ratios of PSB:AUB beads were 50:0, 40:10, 25:25 and 10:40, the final pHs were measured to be 6.29, 6.01, 5.69 and 5.13, respectively. On the optimal medium of PSB, however, the volume and the rate of gas production decreased remarkably as the portion of AUB beads in the mixed beads increased. The final pH was measured to be approximately 6.5, regardless of the mixing ratio. In the reactions by the mixed culture of PSB cubes and AUB beads, all results showed the same tendency of those by the mixed culture of PSB and AUB beads, but the volume and the rate of gas production decreased remarkably, even with 0.2ml of gas production in control. From all the results, the use of mixed PSB and AUB beads at the ratio of 10:40 seems to be efficient to remove nitrogenous compounds in wastewater from recirculating aquaculture system.

• Journal of Food Hygiene and Safety
• /
• v.29 no.4
• /
• pp.268-277
• /
• 2014

This study assessed microbiological hazards at postharvest stage of dropwort farms (A, B, C, D, E, F, G, H, I) located in 4 different areas in Korea. The samples were assessed for sanitary indication bacteria (total aerobic bacteria, coliform, and Escherichia coli) and pathogenic bacteria (Escherichia coli O157:H7, Listeria monocytogenes, Staphylococcus aureus and Bacillus cereus). Total aerobic bacteria and coliform in 9 dropwort farms were detected at the levels of 0~7.00 and 0~4.25 log CFU/g, mL, of $100cm^2$. In particular, microbial contamination in worker's hand showed higher than cultivation environment factors. Escherichia coli was detected in several farms of soil, irrigation water, washing water and worker's hand and also, dropwort in these farms was contaminated with E. coli (positive reaction). In case of pathogenic bacteria, B. cereus was detected at the highest levels in soil. S. aureus was detected qualitatively from only one sample of dropwort washed by water. E. coli O157:H7 and L. monocytogenes were not detected. Although dropwort pass through 2 process (trimming and washing), the microbial contamination was not differ significantly before and after which indicates that current washing system was not effect on reduction of microorganism. From these results, the postharvest environment and workers have been considered as cross-contamination factors. Thus, processing equipments and personal hygiene should be managed to reduce the microbial contamination of dropwort. Accordingly management system such as good agricultural practices (GAP) criteria is needed for the safety of dropwort

• Journal of Life Science
• /
• v.28 no.11
• /
• pp.1347-1353
• /
• 2018

The fermentation of non-digestible soy meal can convert polysaccharides into many compounds that have a wide variety of biological functions. Bacillus strains are capable of hydrolyzing non-digestible saccharides, such as melibiose, raffinose, and stachyose, found in soy meal components. A highly active ${\alpha}$-galactosidase (${\alpha}$-d-galactoside galactohydrolase, EC 3.2.1.22) was isolated from a bacterium in a traditional Korean fermented medicinal herb preparation. The isolate, T2-16, was identified as Bacillus coagulans based on its 16S rRNA sequence and biochemical properties, and the strain was named Bacillus coagulans NRR-1207. When incubated in 10%(w/v) skim milk, Bacillus coagulans NRR1207 caused a decrease in the pH of the culture medium, as well as an increase in titratable acidity and viable cell counts. This strain also showed higher activities of ${\alpha}$-galactosidase, ${\beta}$-galactosidase, ${\alpha}$-glucosidase, naphthol-AS-BO-phosphohydrolase, and acid phosphatase when compared to other enzymes. It hydrolyzed oligomeric substrates, such as raffinose and stachyose, and liberated galactose, indicating that the Bacillus coagulans NRR1207 ${\alpha}$-galactosidase hydrolyzed the ${\alpha}$-1,6 glycoside linkage. These results suggest that the decreased stachyose and raffinose contents observed in fermented soy meal are due to this ${\alpha}$-galactosidase activity. Bacillus coagulans NRR1207 therefore has potential probiotic activity and could be utilized in feed manufacturing, as well as for hydrolyzing non-digestible soy meal components.

• Journal of Korean Home Economics Education Association
• /
• v.33 no.2
• /
• pp.135-152
• /
• 2021

The purpose of this study was to examine the effectiveness of the curriculum implementation of 「Food Safety and Health」, a Home Economics elective course, for high school students. Accordingly, several units of the 「Food Safety and Health」curriculum were piloted in six high schools in Chungbuk, Gyeonggi, Daejeon, and Sejong, and 1,199 questionnaires collected from students who participated in the classes were analyzed. The results are as follows. The 「Food Safety and Health」class had a significant effect on improving the total score of 'food safety and health' knowledge of high school students and scores for sub-dimensional area. Compared to the pre-test, the overall rate of correct answers for the post-test has increased by 7.99%p, and schools that implemented the relevant unit class relatively more had higher improvement scores. In addition, the 「Food Safety and Health」class has positively changed the eating behavior of high school students, and had a significant effect on having a habit of eating a variety of foods evenly. High school students who participated in the 「Food Safety and Health」class evaluated their classes very positively (4.27 out of 5 points), and responded that the content of the class was interesting, easy to understand, and helpful for their diet in daily life. According to the responses to the open-ended questions, students responded that the class was helpful in acquiring food-related knowledge in their real lives, while there were so many limitations for experiencing lab class and group activities due to COVID 19. In preparation for the high school credit system, this study is meaningful that it has expanded the elective courses in home economics area, as well as the right to choose subjects for high school students.

• Korean Journal of School Psychology
• /
• v.17 no.2
• /
• pp.165-180
• /
• 2020

As a tiered system of supports, School-Wide Positive Behavior Support (SWPBS) is an evidence-based practice in the educational system of Korea. An important aspect of SWPBS is the ongoing progress monitoring and evaluation of implementation fidelity. This study aimed to develop and validate the Korean Tier 3 School-Wide Positive Behavior Support Implementation Fidelity Checklist (KT3-FC). The preliminary KT3-FC consisted of a 37-item, 6-factor checklist. In the first phase of the study, 10 experts reported that the range of content validity of the KT3-FC was adequate. In the second phase of the study, 185 teachers (52 men and 133 women) who implemented SWPBS completed the KT3-FC, Individualized Supports Questionnaire, School Climate Questionnaire, School Discipline Practice Scale, and PBS Effectiveness Scale. An exploratory factor analysis resulted in a 5-factor structure, with 20 items, instead of 37 items, consisting of: (a) progress monitoring and evaluation of the individualized supports, (b) provision of supports by aligning and integrating mental health and SWPBS, (c) crisis management planning, (d) problem behavior assessment, and (e) establishment of individualized support team. The internal consistency of the KT3-FC was good (full scale α = .950, sub-factor α = .888 ~ .954). In addition, the KT3-FC showed good convergent validity, having statistically significant correlations with the Individualized Support Questionnaire, School Climate Questionnaire, School Discipline Practice Scale, and the PBS Effectiveness Scale. Finally, the confirmatory factor analysis showed that the 5-factor model of the KT3-FC had some good model fits, indicating that the newly developed fidelity measure could be a reliable and valid tool to assess the implementation of Tier 3 supports in Korean schools. Accordingly, the KT3-FC could contribute to implement SWPBS as an evidence-based behavioral intervention for Korean students.

• Journal of Gastric Cancer
• /
• v.23 no.1
• /
• pp.3-106
• /
• 2023

Gastric cancer is one of the most common cancers in Korea and the world. Since 2004, this is the 4th gastric cancer guideline published in Korea which is the revised version of previous evidence-based approach in 2018. Current guideline is a collaborative work of the interdisciplinary working group including experts in the field of gastric surgery, gastroenterology, endoscopy, medical oncology, abdominal radiology, pathology, nuclear medicine, radiation oncology and guideline development methodology. Total of 33 key questions were updated or proposed after a collaborative review by the working group and 40 statements were developed according to the systematic review using the MEDLINE, Embase, Cochrane Library and KoreaMed database. The level of evidence and the grading of recommendations were categorized according to the Grading of Recommendations, Assessment, Development and Evaluation proposition. Evidence level, benefit, harm, and clinical applicability was considered as the significant factors for recommendation. The working group reviewed recommendations and discussed for consensus. In the earlier part, general consideration discusses screening, diagnosis and staging of endoscopy, pathology, radiology, and nuclear medicine. Flowchart is depicted with statements which is supported by meta-analysis and references. Since clinical trial and systematic review was not suitable for postoperative oncologic and nutritional follow-up, working group agreed to conduct a nationwide survey investigating the clinical practice of all tertiary or general hospitals in Korea. The purpose of this survey was to provide baseline information on follow up. Herein we present a multidisciplinary-evidence based gastric cancer guideline.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.1
• /
• pp.28-36
• /
• 2023

Solar radiation that is measured at relatively small number of weather stations is one of key inputs to crop models for estimation of crop productivity. Solar radiation products derived from GK-2A and Himawari 8 satellite data have become available, which would allow for preparation of input data to crop models, especially for assessment of crop productivity under an agrivoltaic system where crop and power can be produced at the same time. The objective of this study was to compare the degree of agreement between the solar radiation products obtained from those satellite data. The sub hourly products for solar radiation were collected to prepare their daily summary for the period from May to October in 2020 during which both satellite products for solar radiation were available. Root mean square error (RMSE) and its normalized error (NRMSE) were determined for daily sum of solar radiation. The cumulative values of solar radiation for the study period were also compared to represent the impact of the errors for those products on crop growth simulations. It was found that the data product from the Himawari 8 satellite tended to have smaller values of RMSE and NRMSE than that from the GK-2A satellite. The Himawari 8 satellite product had smaller errors at a large number of weather stations when the cumulative solar radiation was compared with the measurements. This suggests that the use of Himawari 8 satellite products would cause less uncertainty than that of GK2-A products for estimation of crop yield. This merits further studies to apply the Himawari 8 satellites to estimation of solar power generation as well as crop yield under an agrivoltaic system.

• Journal of Bio-Environment Control
• /
• v.26 no.4
• /
• pp.393-401
• /
• 2017

The nitrate ($NO_3{^-}$) accumulation of hydroponically grown leafy vegetables may increase in the condition of a closed-type plant production system with low light intensity due to low activity of enzymes involved in nitrogen assimilation and the use of $NO_3-N$ as major nitrogen source. The objective of this study is to investigate the effects of light intensities, nutrient solution compositions and the time of nutrient solution removal before harvest on nitrate contents of hydroponically-grown lettuces in a closed plant production system. The reduction of nitrate contents in leafy lettuces 'Cheongchima' was higher in the treatments of 'TW' (nutrient solution removal) and '$(NH_4)_2CO_3$' (use of ammonium carbonate as nitrogen source) than those in other treatments, which significantly lowered fresh weight and leaf area of the plants. In the light intensity of $100{\mu}mol{\cdot}m^{-2}{\cdot}s^{-1}$, the nitrate content was effectively reduced without causing any growth retardation, by substitution of the nutrient solution composition that $NO_3-N$ was removed ('$NO_3-N$ removal' treatment) or the half strength of standard nutrient solution was applied ('1/2 S' treatment), for 7days before harvest. The effects of light intensity and the time of nutrient solution removal before harvest on growth and nitrate contents in leafy lettuces were investigated. The nitrate contents in leaves under the light condition of $300{\mu}mol{\cdot}m^{-2}{\cdot}s^{-1}$ before nutrient solution removal were lower than those of 100 or $200{\mu}mol{\cdot}m^{-2}{\cdot}s^{-1}$. The removal of nutrient solution for 7 days before harvest quickly reduced the amount of nitrates in leaves in all the light intensities with a greater degree under the $300{\mu}mol{\cdot}m^{-2}{\cdot}s^{-1}$ of light condition, while the 7 days-removal with both 200 and $300{\mu}mol{\cdot}m^{-2}{\cdot}s^{-1}$ of light conditions caused decrease in 16~31% of leaf area and 20~35% of fresh weight, compared to the 3 days-removal treatment. The nitrate contents were greatly reduced from 3,018 to 1,035 in $200{\mu}mol{\cdot}m^{-2}{\cdot}s^{-1}$, and 2,021 to 480 ppm in the light condition of $300{\mu}mol{\cdot}m^{-2}{\cdot}s^{-1}$, with the nutrient solution removal for 3 days before harvest, without causing any deterioration in growth and product quality. The vitamin C contents in leaves were higher in the treatment of nutrient solution removal for both 3 and 5 days before harvest with the light condition of $300{\mu}mol{\cdot}m^{-2}{\cdot}s^{-1}$ than those in the light condition of 100 or $200{\mu}mol{\cdot}m^{-2}{\cdot}s^{-1}$.