• Journal of The Korean Astronomical Society
• /
• v.52 no.6
• /
• pp.217-225
• /
• 2019

We apply a modified Convolutional Neural Network (CNN) model in conjunction with transfer learning to predict whether an active region (AR) would produce a ≥C-class or ≥M-class flare within the next 24 hours. We collect line-of-sight magnetogram samples of ARs provided by the SHARP from May 2010 to September 2018, which is a new data product from the HMI onboard the SDO. Based on these AR samples, we adopt the approach of shuffle-and-split cross-validation (CV) to build a database that includes 10 separate data sets. Each of the 10 data sets is segregated by NOAA AR number into a training and a testing data set. After training, validating, and testing our model, we compare the results with previous studies using predictive performance metrics, with a focus on the true skill statistic (TSS). The main results from this study are summarized as follows. First, to the best of our knowledge, this is the first time that the CNN model with transfer learning is used in solar physics to make binary class predictions for both ≥C-class and ≥M-class flares, without manually engineered features extracted from the observational data. Second, our model achieves relatively high scores of TSS = 0.640±0.075 and TSS = 0.526±0.052 for ≥M-class prediction and ≥C-class prediction, respectively, which is comparable to that of previous models. Third, our model also obtains quite good scores in five other metrics for both ≥C-class and ≥M-class flare prediction. Our results demonstrate that our modified CNN model with transfer learning is an effective method for flare forecasting with reasonable prediction performance.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.5
• /
• pp.415-419
• /
• 2008

Detecting and correcting defects on LCD glasses early in the manufacturing process becomes important for panel makers to reduce the manufacturing costs and to improve productivity. Many attempts have been made and were successfully applied to detect and identify simple defects such as scratches, dents, and foreign objects on glasses. However, it is still difficult to robustly detect low-contrast defect region, called Mura or blemish area on glasses. Typically, these defect areas are roughly defined as relatively large, several millimeters of diameter, and relatively dark and/or bright region of low Signal-to-Noise Ratio (SNR) against background of low-frequency signal. The aim of this article is to present a robust algorithm to segment these blemish defects. Early 90's, a highly robust estimator, known as the Model-Fitting (MF) estimator was developed by X. Zhuang et. al. and have been successfully used in many computer vision application. Compared to the conventional Least-Square (LS) estimator the MF estimator can successfully estimate model parameters from a dataset of contaminated Gaussian mixture. Such a noise model is defined as a regular white Gaussian noise model with probability $1-\varepsilon$ plus an outlier process with probability $varepsilon$. In the sense of robust estimation, the blemish defect in images can be considered as being a group of outliers in the process of estimating image background model parameters. The algorithm developed in this paper uses a modified MF estimator to robustly estimate the background model and as a by-product to segment the blemish defects, the outliers.

• The Journal of the Korea Contents Association
• /
• v.13 no.11
• /
• pp.59-68
• /
• 2013

iPod Touch provided so various application software beyond the early music playback function, and enhanced its UI to the level of UX. Because of these, it was evaluated as innovative. In addition, even though various images were provided through the Internet, some people still classify MP3P as audio device in its product category. As for how audio device became video or image device and which factor contributed to such happening, there may be various factors, such as social, cultural, and technical change, other than fundamental change of medium itself. This study is regarding medium characteristics of MP3Player. In other words, this study classified genealogical changes, which can be categorized into 4 points. This study also analyzed the property of each point according to this classification. The result of analysis showed that there is a relation with technological as well as social context in such genealogical change in MP3player. Even though there are various elements in the change of a device, it can be suggested that the factors of genealogical change in MP3player are influenced by a totality of social needs and contexts and technical changes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.4
• /
• pp.855-860
• /
• 2014

Currently, aircraft and automobile simulator for training provides a variety of training by making hypothetical situation on a simulator installed on the ground currently. And the instructor maximizes the effectiveness of the training by monitoring training and instructing the required training. When trainees are boarding the aircraft or automobile. The Instructor in the ground is not able to monitoring aircraft, automobile. The assessment of the training is not easy after the end of the training. Therefore, it is difficult to provide high quality of education to the students. In this paper, simulation system is to develop the following. Collecting GPS and real-time information for aircraft, automobile $\grave{a}$implementing 3D simulation. Implementing current image of the aircraft or automobile in the screen by 3D real-time monitoring of training situation at the control center utilizing for training saving 3D video files analysis, evaluation on training after the end of the training.

• Journal of Broadcast Engineering
• /
• v.18 no.2
• /
• pp.196-203
• /
• 2013

The importance of Digital Rights Protection technologies, especially the forensic marking, is getting larger and larger as the demand for the digital contents is increased. But the technologies for the evaluation of forensic marking is not set up properly due to the conflicts between interested parties and technical difficulties. Therefore to evaluate the performance of forensic marking objectively, image and video modification items/levels and evaluation criteria are essential. This paper suggests the quantitative system for evaluating the performance of forensic marking objectively. By providing the opportunity to evaluate the Digital Rights Protection product in objective and quantitative manner, forensic marking industry can expedite its technology development and consumer can get objective and universally validated performance result. It is expected this technology could help revitalizing the related industries and help expediting the development of forensic mark technologies.

• Journal of the Korean Society of Costume
• /
• v.32
• /
• pp.117-130
• /
• 1997

The purpose of this study were to identify the design elements and the changing flow of advertisement from 1970's to 1990's by using content analysis of men's magazines. Finding were as followed; First through the analysis of men's wear advertisement in magazine it was found that the closer to 1990's the more various men's wear styles and backgrounds were advertized. These were more image oriented than product oriented. Since 1980 the advertisement about the licenced and the imported brands have been increased and the serial advertisement has shown more fre-quently than the 1-page advertisement since 1990's ; Second two piece suit was dominated in men's wear during 1970's and 1980's From 1990's this style was decresed in stead combi suit was increased. In 1970's the X silhouette was infashion and the y and the X silhouette was in fashion and the y and X sillhouette were increased during 1980's . The H silhouette was dominated in 1990's The brighter and the more various colors appeared in 1990's than in 1970's. The brighter and the more various colors appeared in 1990's than in 1970's The solid pattern was the main flow in men's wear however the stripes and the the check patterns were added in 1990's Third single breasted jacket style with two buttons and tailored collar was in fashion during 1970's . The length of the v-zone was shorter than half at this time however it was lengthened in 1980's . Also the the length of the jacket was lengthened. In 1990's the double breasted jacket style and two buttons were increased. The length of the v-zone and jacket were also lengthened.

• Journal of the Korean Society of Costume
• /
• v.61 no.6
• /
• pp.60-73
• /
• 2011

Men's fashion has not much changed due to the pervasive patriarchy Because of the change of gender roll and attitude towards one's appearance and fashion, men began to express themselves with fashion in the late 90's. The purpose of this study is to categorize men's image and their fashion styles from Korean TV dramas to provide informations for predicting men's fashion trend in rapidly changing market. Through the analysis of three dramas with 30% or more of audience rating by all age groups from January to July, 2009, nine distinctive male images were selected and their styles were analyzed; silhouette, details, materials, color, accessories, and hair-style. The results are as follows: In the past holding neat and straight line silhouettes but today shows tight silhouette. In color and detail, the use of brilliant chromatic colors, use of hight saturation colors, big and brilliant pattern, ruffles, frills, beads, knitwear, mix matched new composed materials, and light materials are dominant. While short and simple shape of hair-styles were predominant in the past, now we see more varied hair length. Not only that, variety of perms and colors are showed on TV screens. Hence, the results show that a lot of radical change has happened in the men's fashion, and marketing propositions that reflects this change in men's fashion market are requested along with trendy emotional product development and coordination proposals, and finally calls for more multilateral study and market search of male consumers.

• Journal of Cadastre & Land InformatiX
• /
• v.44 no.2
• /
• pp.103-112
• /
• 2014

The objective of this study is to suggest the possibility on land cover classification using hyperspectal imagery on area which includes lands and waters. After atmospheric correction as a preprocessing work was conducted on hyperspectral imagery acquired by airborne hyperspectral sensor CASI-1500, the effect of atmospheric correction to a few land cover class in before and after atmospheric correction was compared and analyzed. As the result of accuracy of land cover classification by highspectral imagery using reference data as airphoto and digital topographic map, maximum likelihood method represented overall accuracy as 67.0% and minimum distance method showed overall accuracy as 52.4%. Also product accuracy of land cover classification on road, dry field and green house, but that on river, forest, grassland showed low because the area of those was composed of complex object. Therefore, the study needs to select optimal band to classify specific object and to construct spectral library considering spectral characteristics of specific object.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.6
• /
• pp.874-880
• /
• 2018

3D modeling is extensively used in the field of architecture, machinery and contents production such as movies. Modeling is a time-consuming task. In order to compensate for these drawbacks, attempts have recently been made to reduce the production period by applying 3D scanning technology. 3D scanning for small objects can be done directly with laser or optics, but large buildings and sculptures require expensive equipment, which makes it difficult to acquire data directly. In this study, 3D modeling data for a large object is acquired using photometry with using drones to acquire the image data. The maintenance method for uniform spacing between the sculpture and the drone, the measurement method for the flight line were presented. In addition, we presented a production environment that can utilize the obtained 3D point cloud data for animation and a rendered animation result to find ways to make it in various environments.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.5
• /
• pp.541-550
• /
• 2003

It is important for the strategy of product sales to investigate the consumer's sensitivity and preference degree in the environment that the process of material development has been changed focusing on the consumer renter. In the present study, we propose the Fashion Design Recommender System (FDRS) of textile design applying collaborative filtering personalization technique as one of methods in the material development centered on consumer's sensibility and preferences. In collaborative filtering personalization technique based on textile, Pearson Correlation Coefficient is used to calculate similarity weights between users. We build the database founded on the sensibility adjective to develop textile designs by extracting the representative sensibility adjective from users' sensibility and preferences about textile designs. FDRS recommends textile designs to a consumer who has a similar propensity about textile. Ultimately, this paper sugeests empirical applications to verify the adequacy and the validity on this system with the development of Fashion Design Recommender System (FDRS)