Elon·Musk is a business man who attracts the world’s most attention, not only because of its unusual business mind, advanced challenging consciousness and legendary entrepreneurial experience which made him the world's richest man, but also because he is good at using the trend of social network society (SNS) platform to achieve social interaction. This study uses python 3.11 software to capture and filter Musk's Weibo articles on August 18th, 2023, and makes logical analysis based on the chronological related events, so as to extract Musk’s cognitive characteristics of Chinese social media. This paper finds that Chinese social media builds Musk's image cognition through reporting and judging his career development and hot issues, the cognition varies with the dynamic changes of character events; Chinese social media focuses on fields of Tesla intelligent driving, spaceship and brain neural technology, as well as social media; Weibo articles’ cognitive characteristics of Musk's image are extreme, where the extremely positive proportion accounts for more than 60%, and the extremely negative proportion accounts for more than 10%.

This study was conducted to develop a model for predicting the growth of kimchi cabbage using image data and environmental data. Kimchi cabbages of the ‘Cheongmyeong Gaual’ variety were planted three times on July 11th, July 19th, and July 27th at a test field located at Pyeongchang-gun, Gangwon-do (37°37′ N 128°32′ E, 510 elevation), and data on growth, images, and environmental conditions were collected until September 12th. To select key factors for the kimchi cabbage growth prediction model, a correlation analysis was conducted using the collected growth data and meteorological data. The correlation coefficient between fresh weight and growth degree days (GDD) and between fresh weight and integrated solar radiation showed a high correlation coefficient of 0.88. Additionally, fresh weight had significant correlations with height and leaf area of kimchi cabbages, with correlation coefficients of 0.78 and 0.79, respectively. Canopy coverage was selected from the image data and GDD was selected from the environmental data based on references from previous researches. A prediction model for kimchi cabbage of biomass, leaf count, and leaf area was developed by combining GDD, canopy coverage and growth data. Single-factor models, including quadratic, sigmoid, and logistic models, were created and the sigmoid prediction model showed the best explanatory power according to the evaluation results. Developing a multi-factor growth prediction model by combining GDD and canopy coverage resulted in improved determination coefficients of 0.9, 0.95, and 0.89 for biomass, leaf count, and leaf area, respectively, compared to single-factor prediction models. To validate the developed model, validation was conducted and the determination coefficient between measured and predicted fresh weight was 0.91, with an RMSE of 134.2 g, indicating high prediction accuracy. In the past, kimchi cabbage growth prediction was often based on meteorological or image data, which resulted in low predictive accuracy due to the inability to reflect on-site conditions or the heading up of kimchi cabbage. Combining these two prediction methods is expected to enhance the accuracy of crop yield predictions by compensating for the weaknesses of each observation method.

The use of heat exchangers in various applications such as chemical, air conditioning systems, fuel processing, and power industries is increasing. In order to improve the performance of the heat exchanger, the problem of bonding quality of the copper tube, which is a major member, is emerging. However, since the copper tube is in the form of a pipe, it is difficult to identify internal defects with external factors. In this study, a thermal imaging camera was used to develop and verify an algorithm for detecting defects in the brazing part, and in the process, the brazing performance characteristics were analyzed according to the electrode position, and finally, a learning model was developed and performance evaluation was performed. It was confirmed that the method of supplying heat to the base material and melting the filler metal through the heat transfer effect is more effective than supplying heat input to the filler metal in the bonding process of copper tubes through high-frequency induction heating brazing. Thermal image data was used to develop a defect discrimination model, and 80% of training data and 20% of test data were selected, and a neural network-based single-layer copper tube brazing defect discrimination model was developed through k-Flod cross-validation., the prediction accuracy of 95.2% was confirmed as a result of the error matrix analysis.

본 연구는 다중빔 음향측심 자료를 바탕으로 침몰선박의 정확한 형상 및 해저지형에 대한 정보를 분석하였다. 다양한 영상 자료처리를 통해 현재 침몰선박의 상태를 분석하였다. 해당 자료와 과거 조사 자료의 비교를 통하여 침몰선박 상태 변화 및 주변지형의 변화를 해석하였다. 분석대상 선박 중 퍼시픽프랜드호의 경우 조류에 의한 침·퇴적으로 인해 선수-선미의 지형변화가 뚜렷하게 나타나는 특징을 알 수 있었다. 그리고 제7해성호의 경우 2011년 국립해양조사원 영상자료에서는 선수 일부가 유지된 상태였으나, 2015년 조사 영상에서는 선수 일부가 붕괴된 것을 확인할 수 있었다. 이는 오랜 기간 선박이 해저에 방치되면서 조류 및 화물의 하중 등과 지속적인 부식으로 선체가 붕괴된 것으로 추정된다. 따라서 잔존연료 유출 및 주변 해양오염이 발생할 수 있어 지속적인 모니터링이 필요할 것으로 판단된다. 침몰선박의 영상분석을 통해 침몰선박이 수심과 조류에 의한 영향을 많이 받은 지역일 경우 지질학적 특성과 퇴적물의 침·퇴적 양상에 따라 침몰선박의 구조 안전성에 상당한 영향을 줄 것으로 판단되며, 부식으로 인한 선체의 변화는 계속적으로 변화될 것으로 추정된다. 따라서 지질학적 특성을 고려한 잔존연료 유출 및 주변 환경 변화에 대하여 침몰선박의 변화에 따라 예측‧대응하는 기술의 개발이 필요하다.

전정색과 다중분광 위성영상으로부터 고해상도 컬러영상을 제작하는 융합기법에 대한 연구가 원격탐사 분야에서 활발하게 진행되어왔다. 기 개발된 많은 영상융합 기법들은 분광대체, 산술병합 그리고 공간영역 등 세 개의 범주로 구분될 수 있다. 본 연구는 기존 고해상도 위성에 비해 공간해상도와 분광해상도가 향상된 WorldView-2 위성에서 제공하는 전정색과 다중분광영상에 적용된 각 범주의 융합영상 결과물 특성을 색상과 공간정보 왜곡 측면에서 분석하였다. 색상정보의 왜곡을 평가하기 위해 평균차, 분산차 및 ERGAS 등의 정량지표를 산출하였고, 공간정보의 왜곡은 시각적 분석에 의해 평가하였다. 본 연구의 결과에 의하면 공간영역에 기초한 융합기법이 다른 범주의 융합에 비해 상대적으로 분광 및 공간정보의 왜곡이 적은 것으로 분석되었다. 따라서 공간영역에 기반한 융합영상은 대축척 주제도 뿐 아니라 온라인 영상지도 제작을 위해 적절한 입력자료로 활용될 것으로 기대된다.

본 연구에서는 CCD 카메라가 장착된 Skyviewer로부터 촬영된 하늘 영상 자료를 이용하여 전운량을 산출하는 알고리즘을 개발하였다. 전운량 산출은 RGB 영상 내의 차폐 영역을 제거하고 GBR 빈도분포에 따른 영상을 분류하며, RBR 경계값을 결정하여 구름 화소를 분류한다. 분류된 구름 화소에서 태양광 영역을 제거한 후 유효성 검사를 통해 전운량을 산출하게 된다. 전운량 산출 알고리즘의 정확성을 검증하기 위하여 관측소와 가장 가까운 강원지방기상청의 목측 전운량 자료와 편이(Bias), 평균제곱근오차(RMSE), 상관계수를 분석하였다. 선정된 사례는 계절별 일 사례로 8시부터 17시까지의 정시 자료를 사용하였다. 분석 결과 Skyviewer로부터 산출된 전운량의 편이는 평균적으로 −0.8할의 차이를 보였으며, 평균제곱근오차는 1.6할로 전운량의 차이가 2할 내에서 나타나고 있었다. 또한, 두 관측소는 떨어진 거리의 차이가 있음(약 4 km)에도 불구하고 상관계수가 모든 사례에서 평균 0.91 이상으로 매우 높았다.

This study was performed to investigate the eating habit, body image, and weight control behavior by BMI in Korean female high school students. Data on the 16, 574 subjects was obtained from the sixth Korea Youth Risk Behavior Web-based Survey (2010). Only 52.2% of the subjects had regular breakfast. The rate of skipping breakfast was higher in the underweight group than in the obese group, but the rate of skipping dinner was on the contrary to this. Underweight students had a higher intake frequency of fruits, fast food, instant noodle, and snacks than the obese groups. 3.5% of underweight students considered themselves to be overweight or obese. 53.4% of obese students considered themselves to be overweight. The experience of weight control increased according to BMI, but underweight students considered weight control as an effort to be slimmer. Meal restriction was used more frequently to control weight. The perceived stress level was higher in obese student, especially due to appearance. Therefore, an appropriate, integrated and personalized high school nutrition program should be established for proper body image perception and to develop the self-esteem of female high school students.

호모몰픽 필터링은 푸리에 변환에 기초를 둔 기법으로 주파수 영역에서 저주파 신호는 약화시키고 고주파 신호는 강화하여 영상의 대비 차를 강화시키는 처리기법이다. 호모몰픽 필터링을 위한 응용 프로그램을 개발하여 인공위성영상과 지구물리 자력탐사 자료를 이미지화한 영상에 시험적으로 적용하여 그 결과를 분석하였다. 영상평활화 기법이나 커널 마스크 처리 등과 같은 영상강화 기법에서는 추출 가능한 경계부의 위치를 변화시키거나 영상의 화소값이 전체 영상을 대상으로 변화시키는 반면에 호모몰픽 필터링은 세부적인 영상 정보의 내용을 선택적으로 강조할 수 있다. 호모몰픽 필터링은 인공위성 영상에서 복잡한 지형지물의 특성을 추출하거나 분리하는 데 효과적인 방법으로 나타났으며 지구물리 영상자료에서 이상대를 조사하는 경우에도 유용하게 적용될 수 있을 것으로 생각된다.

We have developed a graphic software for image processing of astronomical data obtained by observational equipment in Astronomical Observatory of Kyung Hee University. The essential hardware for running our computer program is simply composed of a PC with the graphic card to handle 256 colors and the color graphic monitor, including CCD camera system. Our software has been programmed in WINDOWS to provide good environments for users, by using various techniques of image processing on astronomical image data recorded in FITS format by KHCCD program(Jin and Kim, 1994) with a compressional mode. We are convinced that our results will be a fundamental and useful technique in the construction of data processing system and can be effectively used in any other observatories, as well as in data processing system of Kyung Hee University.

In the ground environment, mobile robot research uses sensors such as GPS and optical cameras to localize surrounding landmarks and to estimate the position of the robot. However, an underwater environment restricts the use of sensors such as optical cameras and GPS. Also, unlike the ground environment, it is difficult to make a continuous observation of landmarks for location estimation. So, in underwater research, artificial markers are installed to generate a strong and lasting landmark. When artificial markers are acquired with an underwater sonar sensor, different types of noise are caused in the underwater sonar image. This noise is one of the factors that reduces object detection performance. This paper aims to improve object detection performance through distortion and rotation augmentation of training data. Object detection is detected using a Faster R-CNN.

최근 PACS에서 장기간 저장장치로 디스크 배열이 많이 사용되고 있으나, 디스크에 대한 년 간 불량률에 관해서 신뢰성이 부족한 실정이다. 2016년 10월부터 2017년 2월까지 PACS 판독기에서 의료영상을 읽거나 저장하면서 하드디스크의 직렬포트단자를 조사하였으며, PACS 영상저장 장치에 사용되었던 하드디스크 98대와 개인용 컴퓨터에 사용되었던 하드디스크 101대에 저장된 데이터에서 전송률을 산출하였다. PACS 판독기에서 CT영상을 읽었을 경우에는 수십 MB이하 단위로 읽기는 87.8%, 쓰기는 12.2%가 수행되었다. PACS 판독기에서 CT 영상을 저장할 때는 수십 MB이하 단위로 읽기는 11.4%, 쓰기는 88.6%가 수행되었다. 개인용 컴퓨터에서 엑셀 파일을 읽을 경우에는 3 MB 이하단위로 읽기는 75%, 쓰기는 25%가 수행되었다. 개인용 컴퓨터에서 엑셀 파일 저장을 진행하면서 하드디스크와의 통신은 3 MB이하단위로 읽기는 38%, 쓰기는 62%가 수행되었다. PACS내 영상저장장치에 사용되는 하드디스크의 전송률은 10 GB/h, 개인용 컴퓨터의 하드디스크의 전송률은 5 GB/h로 나타났다. PACS내 영상저장에 사용되던 하드디스크의 년간 불량률은 0.97 ~ 1.13%를 보였고, 개인용 컴퓨터 내 하드디스크의 년간 불량률은 0.51~0.7%를 보였다. 전송량이 높을수록 년 간 불량률도 높아졌다. 이러한 결과는 하드디스크의 수명예측이나 연간 고장률을 예측하기 위한 기초 자료로 활용될 것이다.

This research aims at comparing the accuracy of flood discharge estimation. For this, we focused on the Oedo watershed of Jeju Island and compared flood discharge by analyzing the values as follows: (1) the concentration of the lumped model (HEC-HMS) and distributed model (Vflo), and (2) the in-situ data using Fixed Surface Image Velocimetry (FSIV). The flood discharge estimation from the HEC-HMS model is slightly larger than the Vflo model results. This result shows that the estimations of the HEC-HMS are larger than the flood discharge data by 4.43 to 36.24% and that of the Vflo are larger by 8.49 to 11%. In terms of the error analysis at the peak discharge occurrence time of each mapping, HEC-HMS is one hour later than the measured data, but Vflo is almost the same as the measured data.

To get the empirical data of GPR detection and to develop the image prosessing program of GPR detection data, GPR detection were proceed by the underground pipes and cavities buried in the Chamber. In the case of non pavement and asphalt pavement, water filled cavity that was buried in 0.7m depth was able to detection. But in the case of 1.0 m and 1.3 m buring depth, water filled cavity was not able to detection. In the case of non-reinforced and reinforced concrete pavement, it was difficult to detect the cavity caused by signal interference. GPRiPP programs was developed for image processing of the GPR detection data. The major processing algorithm were background removal, stacking and gain function. With proper image processing of gain function and background removal in GPRiPP program, it was showed that similar results can be obtained with conventional image processing program.