• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1115-1121
• /
• 2018

In this paper, we have studied a data analysis method by deep learning to predict learning achievements based on accumulated data in cyber university learning management system. By predicting learner's academic achievement, it can be used as a tool to enhance learner's learning and improve the quality of education. In order to improve the accuracy of prediction of learning achievements, the autoencoder based attendance prediction method is developed to improve the prediction performance and deep learning algorithm with ongoing evaluation metrics and predicted attendance are used to predict the final score. In order to verify the prediction results of the proposed method, the final grade was predicted by using the evaluation factor attendance data of the learning process. The experimental result showed that we can predict the learning achievements in the middle of semester.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2008.11a
• /
• pp.843-846
• /
• 2008

There are a lot of municipalities that do not grasp even by the current state of having public facilities though various management&maintenance researches have been done. Therefore this research aimed to make it to the foundation of the maintenance management plan establishment of the municipality in the future through investigating, analyzing the current state of management&maintenance of the public facilities. Tn the beginning, I collected data through a questionnaire of the community facilities of the municipality. To read the current state of the management condition of the object facilities from the collection data, I applied the radar chart that used the deviation value of the evaluation index and PPM matrix. As a result of the analysis, I discovered that there is a municipality thought to having efficient facilities maintenance management.

• Journal of the Korea Concrete Institute
• /
• v.28 no.2
• /
• pp.187-196
• /
• 2016

The current seismic design code prescribes that coupling beam should be reinforced using diagonally bundled bars. However, the use of a diagonally bundled bars has a negative effect on constructability and economic efficiency. In the present study, the seismic performance of 4 coupling beams with the different details of reinforcement was evaluated through a cyclic reversal loading test. The specimens were constructed to measure the results of the experimental variable regarding the details of shear reinforcement. Next, the seismic performance of the coupled shear wall system evaluated by methods proposed in the FEMA P695. The cyclic reversal loading test results of this study showed that the performance of coupling beams with relaxed reinforcement detail was almost similar to that of a coupling beam with the ACI detail and meet the level which requested from standard. The result of the seismic evaluation showed that all coupling beams are satisfied with the design code and seismic performance.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.6
• /
• pp.1-9
• /
• 2000

This paper presents a Cluster Oriented Multistage Interconnection Network called COMR. COMR can be constructed suitable for the parallel application with localized communication by providing the shortcut path inside the processor-memory cluster which has frequent data communication. We evaluate the performance of COMR with respect to probability of acceptance, bandwidth, cost-effectiveness and average distance under varying degrees of localized communication. According to the result of analysis for performance evaluation, COMR shows higher performance than the regular MINs of the same network size in the highly localized communication. In the worst case, the diameter of an N$\times$N COMR is only n+1 which has only one stage more as compared the MIN with the same network size. Therefore COMR can be used as an attractive interconnection network for parallel applications with not only the localized communication distribution but also the uniform distribution in shared-memory multiprocessor system.

• Journal of Korea Soil Environment Society
• /
• v.5 no.3
• /
• pp.65-75
• /
• 2001

This study purpose to elucidate the characteristics of water quality by elevation and groundwater samples has been studied with the samples from 150 selected groundwater represented the watershed of groundwater wells in Cheju Island. The evaluation of the characteristics of water quality utilized the physical and chemical property and the statistical analysis. According to the piper diagram, groundwater in the under 50 m region is shown N $a^{+}$＋ $K^{+}$-C $l^{[-10]}$ type, and that groundwater in the 50~100 m region is shown N $a^{+}$＋ $K^{+}$-HC $O_3$$^{[-10]}$ ＋C $O_3$$^{2-}$ type. and partly N $a^{+}$＋ $K^{+}$-C $l^{[-10]}$ type. In the above 100 m region belongs to N $a^{+}$＋ $K^{+}$-HC $O_3$$^{[-10]}$ ＋C $O_3$$^{2-}$ type. The result of factor analysis, commonly two factors as TDS(Total Dissolved Solid) and the contaminants extracted in the under 50m region and above 100 m region. Three factors were obtained from the result of the factor analysis in the 50~100 m region. Factor 1, consisting of TRS content. Factor 2, consisting of the contaminant and the dissolution of minerals. and Factor 3, consisting of HC $O_3$$^{[-10]}$ content. content.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.7
• /
• pp.73-83
• /
• 2017

This study was conducted to evaluate the chemical composition, digestibility, and energy value of 15 non-conventional feeds produced in South Korea as ruminant feeds. Three Hanwoo steers (body weight, $520{\pm}20.20kg$) fitted with a permanent rumen cannula and duodenal cannula were housed individually in tie-stall barns, followed by a 14-day adaptation period and 3-day experimental period. Chemical composition analysis, in situ nylon bag, and mobile bag technique were used as experiments. As a result of the chemical composition analysis offeeds, crude protein (CP) contentsofmalt meal, perilla meal, soy sauce cake, and soymilk residue were greater than 30%. As a result of the degradability characteristics analysis of feeds using an in situ nylon bag, rumen undegraded protein (RUP) contents of beet pulp, brewer's grain, coffee meal, malt meal, milo bran, perilla meal, ramen residue, and soymilk residue were greater than 50%. Analysis of total digestible nutrient (TDN) values of feeds using an in situ mobile bag showed that TDN values of beet pulp, brewer's grain, makgeolli residue, milo bran, perilla meal, ramen residue, rice bran, soy sauce cake, soybean curd cake, soymilk residue, and wheat bran weregreater than 50%. In summary, these non-conventional feeds have high potential value as good feed resources to replace formulated feeds or roughage. Therefore, the chemical composition, digestibility, and energy value of non-conventional feeds obtained from this study can be used as base data for the manufacture of ruminant total mixed ration (TMR) with improved feed efficiency, reduced feed costs, and reduction of environmental pollution.

• Journal of Chest Surgery
• /
• v.32 no.6
• /
• pp.549-555
• /
• 1999

Background: Patients who are considered for major pulmonary resection are generally evaluated by spirometry and clinical assessment to predict morbidity and mortality. Despite this, none has yet proved to be a convenient and reliable estimate of risk. Material and Method: A retrospective analysis was performed in 167 patients who were diagnosed for lung cancer, bronchiectasis, pulmonary tuberculosis, and other benign pulmonary disease, and who underwent major lung resections. The relationship of 25 preoperative or postoperative variables to 19 postoperative events were classified into categories as operative mortality, pulmonary or cardiovascular morbidity, and other morbidity was assessed. Logistic regression analysis and $\chi$2 analysis were used to identify the relationship of the operative risk factors to the grouped postoperative complications. Result: The best single predictor of complications was the percent predicted postoperative diffusing capacity (pulmonary morbidity, p<0.009; cardiovascular morbidity, p<0.003: overall morbidity, p<0.004). Conclusion: The diffusing capacity of the lung for carbon monoxide was an important predictor of postoperative complications than the spirometry, and it usually should be a part of the evaluation of patients being considered for pulmonary resection.

• Ecology and Resilient Infrastructure
• /
• v.6 no.4
• /
• pp.258-266
• /
• 2019

This study was conducted to apply natural river technologies to levees and examine the results. The new eco-friendly bio-polymer was applied, a combination of eco-friendly biopolymers and soil, to levee slope to enhance durability and eco-friendliness and to establish reinforcement measures against unstable levees due to overtopping. A semi-prototype levee of 1 m in height, 3 m in width, with a 1:2 slope and 5 m length, was constructed at the Andong River Experiment Center. The bio-soil mixed with the biopolymer and the soil at an appropriate ratio was treated with a 5 cm thickness on the surface of levee to perform the stability evaluation according to overtopping. Using the pixel-based analysis technique using the image analysis program, the breached area of levee slope was calculated over time. As a result, the time for complete decay occurs more than 12 times than that of ordinary soil levee. Therefore, when the new substance is applied to the surface of levee, the decay delay effect appears to be high.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.3
• /
• pp.505-514
• /
• 2012

This study is for effectiveness of golf skills to average score using path analysis in Professional golf association. The variables in this study were that seven independent variable were driving accuracy, green in regulation, driving distance, sand save ratio, scrambling, putting average, and two endogenous variables were birdie average, bogey average, and dependent variable was the scoring average. To analyze these variables, path analysis was used through AMOS 18.0 program and Alpha level sets at.05. As the result, the final model had significant goodness-of-fit (GFI=.989, RMSEA=.044, TLI=.991, CFI=.998) and showed that green in regulation, driving distance, sand save ratio, scrambling, and putting average significantly affected average score directly. Especially, the scrambling was the highest affectation to average score and the sand save ratio was the lowest affectation to the average score.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.38 no.4
• /
• pp.56-63
• /
• 2015

Recently, companies and organizations are becoming increasingly dependent on external resources to keep their competitive advantages under the turbulence of global business environmental changes. Therefore, they focus on the paradigm 'Open Innovation (OI)' which is reported as a convincing strategy to improve competitive advantage in terms of budget and time-to-market. The management of Incheon International Airport Corporation (IIAC) also considers the introduction of Open Innovation not only to adapt the business environmental changes but also to be devoted its social role as a public corporation. In this paper, we describe how we derived the promotion tasks for the introduction of OI and prioritized the tasks, performing our research on the IIAC Open Innovation. For these purposes, this research conducted the following three steps; the first stage for the analysis of current situation on the IIAC Open Innovation, the second stage for the elicitation of promotion tasks, and the last stage for the prioritization of the promotion tasks. In the first stage, critical success factors (CSFs) for open innovation introduction were derived from different research papers and case studies. In the following stage, promotion tasks were elicited from the IIAC based on the CSFs. In the last stage, the promotion tasks were evaluated on the base of criteria by using Analytic Hierarchy Process (AHP). And then the promotion tasks were grouped by the result of the evaluation. In this case, thirteen promotion tasks were derived for open innovation, ten promotion tasks except three inevitable promotion tasks were evaluated, and then they were grouped into four categories based on the importance-possibility analysis.