• Journal of the Korean Data Analysis Society
• /
• v.20 no.6
• /
• pp.2873-2881
• /
• 2018

It is very important to obtain objective and credible information through election polls in order to contribute to the correct voting behavior of the voters or to establish appropriate election strategies for candidates or political parties. Therefore, many related organizations such as political parties, media organizations, and research institutions have been making efforts to improve the accuracy of the results of the polls and the election prediction. Kim et al. (2017) analyzed whether the non-response group responded that there is no support candidate in the election survey to increase the accuracy of the estimation of the vote rate. As a result, it has been confirmed that the accuracy of the estimation of the vote rate can be significantly improved by performing an appropriate classification on the non-response layer. In this study, we propose a method to estimate the turnout by each strata (sex, age group) under the condition that the total turnout rate is given for a specific district (region) and propose a procedure to predict the vote rate by reflecting the turnout. In addition, case studies were conducted using data gathered through telephone interviews for the 20th National Assembly elections in 2016.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.3
• /
• pp.525-532
• /
• 2021

In the ocean, it is difficult to separate the effects of one cause due to the multiple causes, but the self-organizing map can be analyzed by adding other factors to the cluster result. Therefore, in this study, the results of the clustering of sea level data were applied to sea surface temperature. Sea level data was clustered into a total of 6 nodes. The difference between sea surface temperature and sea level height has a one-month delay, which applied sea surface temperature data a month ago to the clustered results. As a result of comparing the mean of sea surface temperature of 140 to 150°E, where the sea surface temperature was variously distributed, in the case of nodes 1, 3, and 5, it was possible to find a meandering sea surface temperature distribution that is clearly distinguished from the sea level data. While nodes 2, 4 and 6, the sea surface temperature distribution was smooth. In this study, sea surface temperature data were applied to the clustered results of sea level data, but later it is necessary to apply wind or geostrophic velocity data to compare.

• Journal of Ecology and Environment
• /
• v.44 no.4
• /
• pp.275-285
• /
• 2020

Background: In Korea, Symplocos prunifolia Siebold. & Zucc. is only found on Jeju Island. Conservation of the species is difficult because little is known about its distribution and natural habitat. The lack of research and survey data on the characteristics of native vegetation and distribution of this species means that there is insufficient information to guide the management and conservation of this species and related vegetation. Therefore, this study aims to identify the distribution and vegetation associated with S. prunifolia. Results: As a result of field investigations, it was confirmed that the native S. prunifolia communities were distributed in 4 areas located on the southern side of Mt. Halla and within the evergreen broad-leaved forest zones. Furthermore, these evergreen broad-leaved forest zones are themselves located in the warm temperate zone which are distributed along the valley sides at elevations between 318 and 461 m. S. prunifolia was only found on the south side of Mt. Halla, and mainly on south-facing slopes; however, small communities were found to be growing on northwest-facing slopes. It has been confirmed that S. prunifolia trees are rare but an important constituent species in the evergreen broad-leaved forest of Jeju. The mean importance percentage of S. prunifolia community was 48.84 for Castanopsis sieboldii, 17.79 for Quercus acuta, and 12.12 for Pinus thunbergii; S. prunifolia was the ninth most important species (2.6). Conclusions: S. prunifolia can be found growing along the natural streams of Jeju, where there is little anthropogenic influence and where the streams have caused soil disturbance through natural processes of erosion and deposition of sediments. Currently, the native area of S. prunifolia is about 3300 ㎡, which contains a confirmed population of 180 individual plants. As a result of these low population sizes, it places it in the category of an extremely endangered plant in Korea. In some native sites, the canopy of evergreen broad-leaved forest formed, but the frequency and coverage of species were not high. Negative factors that contributed to the low distribution of this species were factors such as lacking in shade tolerance, low fruiting rates, small native areas, and special habitats as well as requiring adequate stream disturbance. Presently, due to changes in climate, it is unclear whether this species will see an increase in its population and habitat area or whether it will remain as an endangered species within Korea. What is clear, however, is that the preservation of the present native habitats and population is extremely important if the population is to be maintained and expanded. It is also meaningful in terms of the stable conservation of biodiversity in Korea. Therefore, based on the results of this study, it is judged that a systematic evaluation for the preservation and conservation of the habitat and vegetation management method of S. prunifolia should be conducted.

• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.13-21
• /
• 2020

The Android author identification study can be interpreted as a method for revealing the source in a narrow range, but if viewed in a wide range, it can be interpreted as a study to gain insight to identify similar works through known works. The problem found in the Android author identification study is that it is an important code on the Android system, but it is difficult to find the important feature of the author due to the meaningless codes. Due to this, legitimate codes or behaviors were also incorrectly defined as malicious codes. To solve this, we introduced the concept of survival network to solve the problem by removing the features found in various Android apps and surviving unique features defined by authors. We conducted an experiment comparing the proposed framework with a previous study. From the results of experiments on 440 authors' identified apps, we obtained a classification accuracy of up to 92.10%, and showed a difference of up to 3.47% from the previous study. It used a small amount of learning data, but because it used unique features without duplicate features for each author, it was considered that there was a difference from previous studies. In addition, even in comparative experiments with previous studies according to the feature definition method, the same accuracy can be shown with a small number of features, and this can be seen that continuously overlapping meaningless features can be managed through the concept of a survival network.

• Journal of Convergence for Information Technology
• /
• v.11 no.6
• /
• pp.33-39
• /
• 2021

Speech recognition technology is being combined with deep learning and is developing at a rapid pace. In particular, voice recognition services are connected to various devices such as artificial intelligence speakers, vehicle voice recognition, and smartphones, and voice recognition technology is being used in various places, not in specific areas of the industry. In this situation, research to meet high expectations for the technology is also being actively conducted. Among them, in the field of natural language processing (NLP), there is a need for research in the field of removing ambient noise or unnecessary voice signals that have a great influence on the speech recognition recognition rate. Many domestic and foreign companies are already using the latest AI technology for such research. Among them, research using a convolutional neural network algorithm (CNN) is being actively conducted. The purpose of this study is to determine the non-voice section from the user's speech section through the convolutional neural network. It collects the voice files (wav) of 5 speakers to generate learning data, and utilizes the convolutional neural network to determine the speech section and the non-voice section. A classification model for discriminating speech sections was created. Afterwards, an experiment was conducted to detect the non-speech section through the generated model, and as a result, an accuracy of 94% was obtained.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.133-139
• /
• 2021

Currently, the process of constructing a high-definition road map has a high proportion of manual labor, so there are limitations in construction time and cost. Research to automate map production with high-definition road maps using artificial intelligence is being actively conducted, but since the construction of training data for the map construction is also done manually, there is a need to automatically build training data. Therefore, in this study, after converting to images using point clouds acquired by a mobile mapping system, the road marking areas were extracted through image reclassification and overlap analysis using thresholds. Then, a methodology was proposed to automatically construct training data for deep learning data for the high-definition road map through the classification of the polygon types in the extracted regions. As a result of training 2,764 lane data constructed through the proposed methodology on a deep learning-based PointNet model, the training accuracy was 99.977%, and as a result of predicting the lanes of three color types using the trained model, the accuracy was 99.566%. Therefore, it was found that the methodology proposed in this study can efficiently produce training data for high-definition road maps, and it is believed that the map production process of road markings can also be automated.

• The Journal of Korean Obstetrics and Gynecology
• /
• v.34 no.1
• /
• pp.1-14
• /
• 2021

Objectives: We studied for the adjustment of the patterns of 'The Diagnostic Tool for Climacteric and Postmenopausal Syndrome Pattern Identification (hereinafter CaPSPI)' (studyI) and the correlation between CaPSPI and Korean medicine doctors' diagnosis which was carried out without knowing the results of CaPSPI (studyII). Methods: The studyI followed the previous study method in 2018 (2018-3). The studyII was conducted from June 1, 2019 to July 10, 2020 with ◯◯ University Korean Medicine Hospital IRB's approval (2019-4). Doctors' diagnosis was conducted face-to-face with the subjects. Doctors' diagnosis was carried out based on the Kupperman's questionnaire, 'Diagnosis System of Oriental Medicine (hereinafter DSOM)' and four examinations (四診) records. The diagnosis was marked with 0 for 'no', 1 for 'somewhat', 2 for 'yes' and 3 for 'very yes'. The correlation between CaPSPI and the mean of doctors diagnostic scores were investigated statistically. Results: The studyI showed that heart-heat (心火) pattern was added. The Factor loading coefficient for heart-heat was 0.551 to 0.789, and the Cronbach's coefficient was 0.896. The studyII showed that the diagnosis (Kappa statistic) of two doctors showed statistically significant concordance (all eight patterns), with correlation of them were 0.3 or higher. And the correlation between the CaPSPI score and the mean of doctors' diagnostic score showed a statistically significant correlation, with liver qi depression (肝鬱) being the highest at 0.552 and dual deficiency of the heart-spleen (心脾兩虛) being the lowest at 0.301. Conclusions: Since the diagnosis results of CaPSPI showed a significant correlation with the diagnosis of Korean traditional medicine experts, it was believed that the CaPSPI results can be trusted and used for clinical purposes.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1523-1535
• /
• 2020

In order to produce crop information using remote sensing, we use classification and growth monitoring based on crop phenology. Therefore, time-series satellite images with a short period are required. However, there are limitations to acquiring time-series satellite data, so it is necessary to use fusion with other earth observation satellites. Before fusion of various satellite image data, it is necessary to overcome the inherent difference in radiometric characteristics of satellites. This study performed Korea Multi-Purpose Satellite-3 (KOMPSAT-3) cross calibration with Landsat-8 as the first step for fusion. Top of Atmosphere (TOA) Reflectance was compared by applying Spectral Band Adjustment Factor (SBAF) to each satellite using hyperspectral sensor band aggregation. As a result of cross calibration, KOMPSAT-3 and Landsat-8 satellites showed a difference in reflectance of less than 4% in Blue, Green, and Red bands, and 6% in NIR bands. KOMPSAT-3, without on-board calibrator, idicate lower radiometric stability compared to ladnsat-8. In the future, efforts are needed to produce normalized reflectance data through BRDF (Bidirectional reflectance distribution function) correction and SBAF application for spectral characteristics of agricultural land.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.577-582
• /
• 2021

Recently, with the development of AR, VR, and smart device technologies, the demand for services based on non-face-to-face environments is also increasing in the fitness industry. The non-face-to-face online home training service has the advantage of not being limited by time and place compared to the existing offline service. However, there are disadvantages including the absence of exercise equipment, difficulty in measuring the amount of exercise and chekcing whether the user maintains an accurate exercise posture or not. In this study, we develop a standard exercise program that can compensate for these shortcomings and propose a new non-face-to-face home training application by using a deep learning-based body posture estimation image processing algorithm. This application allows the user to directly watch and follow the trainer of the standard exercise program video, correct the user's own posture, and perform an accurate exercise. Furthermore, if the results of this study are customized according to their purpose, it will be possible to apply them to performances, films, club activities, and conferences

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1489-1503
• /
• 2022

Drone and sensor technologies are enabling digitalization of agricultural crop's growth information and accelerating the development of the precision agriculture. These technologies could be able to assess damage of crops when natural disaster occurs, and contribute to the scientification of the crop insurance assessment method, which is being conducted through field survey. This study was aimed to calculate lodged damage rate from the vegetation indices extracted by drone based RGB images for soybean. Support Vector Classifier (SVC) models were considered by adding vegetation indices to the Crop Surface Model (CSM) based lodged damage rate. Visible Atmospherically Resistant Index (VARI) and Green Red Vegetation Index (GRVI) based lodged damage rate classification were shown the highest accuracy score as 0.709 and 0.705 each. As a result of this study, it was confirmed that drone based RGB images can be used as a useful tool for estimating the rate of lodged damage. The result acquired from this study can be used to the satellite imagery like Sentinel-2 and RapidEye when the damages from the natural disasters occurred.