• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.37-43
• /
• 2021

This study proposed an effective automatic classification technique to identify dropout patterns of university students, and based on this, an intelligent recommender system to prevent dropouts. To this end, 1) a data processing method to improve the performance of machine learning was proposed based on actual enrollment/dropout data of university students, and 2) performance comparison experiments were conducted using five types of machine learning algorithms. 3) As a result of the experiment, the proposed method showed superior performance in all algorithms compared to the baseline method. The precision rate of discrimination of enrolled students was measured to be up to 95.6% when using a Random Forest(RF), and the recall rate of dropout students was measured to be up to 80.0% when using Naive Bayes(NB). 4) Finally, based on the experimental results, a method for using a counseling recommender system to give priority to students who are likely to drop out was suggested. It was confirmed that reasonable decision-making can be conducted through convergence research that utilizes technologies in the IT field to solve the educational issues, and we plan to apply various artificial intelligence technologies through continuous research in the future.

• Information Systems Review
• /
• v.25 no.2
• /
• pp.57-76
• /
• 2023

This study classifies the success of creators and YouTubers who have created channels on YouTube recently, which is the most influential digital platform. Based on the actual information disclosure of YouTubers who are in the field of science and technology category, video upload cycle, video length, number of selectable multilingual subtitles, and information from other social network channels that are being operated, the success of YouTubers using machine learning was classified and analyzed, which is the closest to the YouTube revenue structure. Our findings showed that neural network algorithm provided the best performance to predict the success or failure of YouTubers. In addition, our five factors contributed to improve the performance of the classification. This study has implications in suggesting various approaches to new individual entrepreneurs who want to start YouTube, influencers who are currently operating YouTube, and companies who want to utilize these digital platforms. We discuss the future direction of utilizing digital platforms.

• Journal of Distribution Science
• /
• v.9 no.4
• /
• pp.15-27
• /
• 2011

Although a huge number of academic researchers have paid considerable attention to exploring both the degree to which store image influences retailer brand customers and how to develop store personality, they have overlooked the contemporary retail context in which retailers have developed many different types of retailer brands, that is, price-oriented or quality-oriented retailer brands. Rather than focusing on the latter, much literature has looked at the former. Accordingly, even though there are many articles related to store image, a few authors have shown their interest in identifying the extent to which store personality affects customers purchasing retailer brands at lower prices. As a result, their efforts have been to illustrate the relationship between store image and consumer behaviours buying retailer brands. In that multiple retailers over the world such as E-Mart, Lotte-Mart, Tesco Korea and Tesco UK have actively introduced not only the quality-focused retailer brands that quality is better than, or equal to national brands, and prices are slightly higher than, or equal to them, but also price-focused retailer brands, academicians should make an effort to investigate how store image affects customers purchasing a quality-oriented retailer brand, comparing with previous research results. That is why the authors illustrate the extent to which store personality components influence retailer brand customers, including particularly quality-oriented retailer brand customers through an empirical research. By adopting a questionnaire method as a research technique to illuminate the relationship between store image components and retailer brand customers, research validity increases and further, data gathered through a field survey are analysed through a few statistic analysis methods, in order to minimise statistical deviations. Compared with the prior research concentrated on price-focused retailer brands, the authors have significantly shed light on customer behaviours purchasing retailer brand products with higher quality. When it comes to store personality components, the research suggests the following five items: merchandise attributes, services, physical facilities, promotions, and institutional image, considering the subcomponents mentioned by the previous research. Proposing the conceptual research model which those elements are differently hypothesised, according to retailer brand types: PR (Price-oriented Retailer brand) and QR (Quality-oriented Retailer brand), the research is proceeded. Through empirical research, the authors found that amongst the five items, only promotion influenced retailer brand customers in the Korean retailing marketplace, unlike other countries explored by many researchers, such as UK. Although much literature emphasises that those elements are closely related to retailer brand buying proneness, it is completely not fit to the Korean market. Also, research findings provide new insights into the degree of store image effects on retailer brand customers for academiciansand practitioners. Whether the retailer brand development program that a retailer has carried simultaneously both price-focused and quality-focused retailer brand types is practically profitable should be explored in the future.

• Investigative Magnetic Resonance Imaging
• /
• v.2 no.1
• /
• pp.104-112
• /
• 1998

Purpose : To evaluate the clinical utility of diffusion-weighted imaging by analyzing the signal intersity of lesions in patients with various intracranial diseases. Materials and Methods : difusion-weighted MR imaging was prospectively perormed in randomly selected 70 patients with various intracranial idseases. They consisted of 20 patients with acute infarct, 21 patients with chronic infarct of small vessel disease, 14 patients with primary intracranial tumor, three patients with brain metastasis, five patient with brain abscess, five patients with brain abscess, five patients with cerebral hemorrhage, one patient with neurocysticercosis, and one patient with epidermoid cyst. the diffusion-weighted images were obtained immediately after routine T2-weighted imaging on a 1.5T MR unit using single shot spin echo EPI technique with 6500 ms TR, 107ms TE, $128{\times}128$ matrix, 1 number of excitation, $24{\times}24$ field of view, 5-7 mm slice thickness, 2-3 mm inter-slice gap. The diffusion-gradients (b value of ($1000s{\;}/{\;}textrm{mm}^2$)) were applied along three directions(x, y, z). On visual inspection of diffusion-weighted images, the signal intersity of lesions was arbitrarily graded as one of 5 grades. In quantitative assessment, we measured the signal intensity of all the lesions and the contralateral corresponding normal area using round region of interest(ROI), and then calculated the signal intensity ratio of the lesion to the normal brain parenchyma. Results : On visual inspection, markedly hyperintense signals were seen in all cases of acute infarct, brain abscess, epidermoid cyst, and neurocysticercosis in degenerating stage. In all cases of cerebral hematoma, the very high signal internsity was intermingled with low signal intensity. focal very high signal intersity was also seen in a solid portion of the tumor in a patient. the mean signal intensity ratios of all those lesions to the normal brain parenchyma were above 2.5. Gliosis, solid component of brain tumor, brain metastasis, and vasogenic dedma appeared isointense to the normal brain parenchyma in 71%, 64%, 100%, and 67%, respectively ; the mean signal intensity ratios of those lesions to the normal brain parenchyma ranged 1.15 to 1.28 and there was no significant difference among these(p>0.1). Cystic cerebromalacia and necrotic or cystic portions in tumor were markedly or slightly hypointense, and the mean signal intensity ratios were 0.45 and 0.42, respectively. Conclusion : Very high signal intensity of acute infarct, brain abscess, epidermoid cyst, and cystic neurocysticercosis in degenerating stage on diffusion-weighted images may be helpful in differentiating from other diseases that are hypointense or isointense to the normal brain parenchyma. It may be especially useful differentiation of brain abscess from brain tumor with necrotic or cystic portion.

• Resources Recycling
• /
• v.27 no.1
• /
• pp.31-37
• /
• 2018

To enhance the recycling rate of used metal resources, it is strongly desired to develop a metal sorting system that can automatically identify metal type from mixed metal scraps and sort them separately. Laser-induced breakdown spectroscopy(LIBS) is a technique that enables real time classification of different metals based on multi-elemental and in-air analysis. In this work, we report the results of LIBS elemental analysis of field scrap samples acquired from a recycling company. By applying multivariate analysis, it was found that the LIBS signals of five different metals could be perfectly classified if surface contamination was removed. The classification accuracy degraded for LIBS signals including contaminant emission, which however could be overcome by performing the multivariate analysis using properly selected emission lines of higher correlation only. The significant improvement in classification accuracy and process speed by the selection of proper emission lines demonstrated the feasibility of LIBS technique as an industrial tool for metal scrap sorting.

• 대한공업교육학회지
• /
• v.33 no.2
• /
• pp.1-25
• /
• 2008

In this study, theory of school consulting for founding the development strategy of industrial high school was explored, consulting model and performing technique model was suggested, case of consulting of industrial high school performed by the model and performing technique suggested. Up to now, research field of school consulting was instruction and supervision consulting mostly, there was not much school management consulting. In this paper, a school consulting model for industrial high school was developed, which was five step such as entry, diagnosis, action planning, action, and termination. A case of consulting for C technical high school applied by the consulting model suggested was analyzed, it will be used any other consulting project of industrial high school. According to the 5 step school consulting model, analysis of the present state of C technical high school, survey research, SWOT analysis, Issue Tree, school assesment were performed. In order to set up a development strategy for C technical high school, a table of problem and improvement based on issue tree was made, and then a Pay-Off Matrix was made out. Finally, a development plan of short and mid- and long-term for C technical high school was constructed.

• Progress in Medical Physics
• /
• v.18 no.2
• /
• pp.93-97
• /
• 2007

This study was designed to evaluate radiosurgery technique using multiple noncoplanar arc therapy with intensity modulated fine MLC shaped photon beam. The stereotactic radiosurgery was performed with 6-MV X-ray beams from a Clinac 21EX LINAC (Varian, Palo Alto, CA, USA) with a MLC-120, which features a full $40{\times}40cm$ field and is the first MLC for general use that offers 0.5 cm resolution for high precision treatment of small and irregular fields. We used a single isocenter and five gantry-couch combinations with a set of intensity modulated arc therapy. We investigated dosimetric characteristics of 2 cm sized spherical target volume with film (X-OMAT V2 film, Kodak Inc, Rochester NY, USA) dosimetry within $25{\times}25cm$ acrylic phantom. A simulated single isocentric treatment using inversely Planned 3D radiotherapy planning system demonstrated the ability to conform the dose distribution to an spherical target volume. The 80% dose level was adequate to encompass the target volume in frontal, sagittal, and transverse planes, and the region between the 40% and 80% isodose lines was $4.0{\sim}4.5mm$ and comparable to the dose distribution of the Boston Arcs. We expect that our radiosurgery technique could be a treatment option for irregular-shaped large intracranial target.

• Journal of the Korean earth science society
• /
• v.38 no.7
• /
• pp.535-545
• /
• 2017

Maritime accidents around the Korean Peninsula are increasing, and the ship detection research using remote sensing data is consequently becoming increasingly important. This study presented a new ship detection algorithm using hyperspectral images that provide the spectral information of several hundred channels in the ship detection field, which depends on high resolution optical imagery. We applied a spectral matching algorithm between the reflection spectrum of the ship deck obtained from two field observations and the ship and seawater spectrum of the hyperspectral sensor of an airborne visible/infrared imaging spectrometer. A total of five detection algorithms were used, namely spectral distance similarity (SDS), spectral correlation similarity (SCS), spectral similarity value (SSV), spectral angle mapper (SAM), and spectral information divergence (SID). SDS showed an error in the detection of seawater inside the ship, and SAM showed a clear classification result with a difference between ship and seawater of approximately 1.8 times. Additionally, the present study classified the vessels included in hyperspectral images by presenting the adaptive thresholds of each technique. As a result, SAM and SID showed superior ship detection abilities compared to those of other detection algorithms.

• Journal of the Korean Applied Science and Technology
• /
• v.32 no.4
• /
• pp.649-660
• /
• 2015

Data obtained from the Calpuff inverse modeling estimate the emission amount of pollutants, and enable to establish the aim for reduction through the comparison of various cases. This study pursued to accumulate the fundamental data by the Calpuff inverse modeling for five areas in the vicinity of Donghae harbor, which focused on reduction of atmospheric fine dust. As a result of evaluation of the allowed emission amount for local sites, site-D required the most reduction, $4.95{\mu}g/m^2{\cdot}S$, based on the atmospheric guideline, $50{\mu}g/m^3$. The theoretical mitigation could decrease the average concentration of PM10 to $42.6{\mu}g/m^3$ for the study field (Donghae waste water treatment plant). Modeling only for site-A emission showed the potential concentration around the residential area of Donghae harbor, $40{\sim}50{\mu}g/m^3$. However, it will rise over $50{\mu}g/m^3$ with the addition of background level. Therefore no more emission would be allowed. Site-B including commercial area and unpaved field required the reduction of $0.11{\mu}g/m^2{\cdot}S$ due to vehicles and fugitive dust. Site-C and E did not emit additional pollutants.

• The Journal of the Korea Contents Association
• /
• v.21 no.5
• /
• pp.234-246
• /
• 2021

The purpose of this study is to develop the main subjects of the job-based curriculum by deriving the job analysis results of general security job workers in the physical protection field responsible for responding to threats to nuclear materials and nuclear facilities. In the job analysis stage, FGI was conducted on 7 content experts to derive 8 duties and 55 tasks. In addition, knowledge and skills were drawn for each task. In the analysis of educational needs, surveys were conducted for workers in general security jobs to derive the top 25 educational priorities through t-test and Borich needs assess model. At the stage of selecting core tasks and organizing required/optional contents, 42 tasks, both above average or at least one of them, were derived as core tasks based on the result of evaluation of importance and difficulty ratings of 55 tasks through a questionaire. In addition, tasks applied to the top 25 rankings derived from Borich needs assess model were applied as the required contents when designing courses, and tasks which applied only one of them were selected as optional contents. At the stage of required/optional modules and educational contents, four required modules and five optional modules were derived by drifting similar tasks between the required and optional contents. Based on the above results, the study suggested academic and practical implications and future suggestions.