• Korean Journal of Agricultural Science
• /
• 제49권3호
• /
• pp.561-570
• /
• 2022

This study investigated the changes in planting environment and growing conditions of 'Arisoo' apple trees under shading net treatments. Apple tree canopies were fully covered with Blue (blue color net, mesh size: 4 mm × 5 mm), Black-A (black color net, mesh size: 4 mm × 5 mm), Black-B (black color net, mesh size: 5 mm × 6 mm), and uncovered trees were used as the control. Inside the tree canopies, the illuminance was observed as 100% (85.0 Klux) in the control, but it decreased to 75% (64.3 Klux) in the Blue, 73% (63.0 Klux) in the Black-A, and 77% (65.9 Klux) in the Black-B nets, respectively. The solar irradiance was observed as 755 w·m^-3 in the control, but it was decreased to 715 w·m^-3 in the Blue, 624 w·m^-3 in the Black-A, and 647 w·m^-3 in the Black-B nets, respectively. The average daily temperature was observed to be the highest in the Black-A net (31.8℃) while it was observed to be around 30.0℃ in the control, Blue, and Black-B nets. In addition, the average fruit surface temperature was observed to be the highest (39.4℃) in the control, but it was decreased to 38.1℃ in the Blue, 37.3℃ in the Black-A, and 39.0℃ in the Black-B nets. However, the average soil temperature, the shoot growth rate, and leaf SPAD values were not different in all the treatments. Fruit sunburn disorders were the highest in the control while it was observed to be lower in the fruits from trees covered with the shading nets. However, at harvest, the fruit quality parameters were not different in all the treatments. Overall, this study suggests that the apple trees covered with the shading nets reduced the illuminance, solar irradiance, fruit surface temperature, and fruit sunburn disorders. However, the shading nets did not affect tree growth and apple fruit quality.

• Korean Journal of Remote Sensing
• /
• 제39권6_3호
• /
• pp.1679-1692
• /
• 2023

South Korea is a country that emits a large amount of pollutants as a result of population growth and industrial development and is also severely affected by transboundary air pollution due to its geographical location. As pollutants from both domestic and foreign sources contribute to air pollution in Korea, the location of air pollutant emission sources is crucial for understanding the movement and distribution of pollutants in the atmosphere and establishing national-level air pollution management and response strategies. Based on this background, this study aims to effectively acquire spatial information on domestic and international air pollutant emission sources, which is essential for analyzing air pollution status, by utilizing high-resolution optical satellite images and deep learning-based image segmentation models. In particular, industrial parks and quarries, which have been evaluated as contributing significantly to transboundary air pollution, were selected as the main research subjects, and images of these areas from multi-purpose satellites 3 and 3A were collected, preprocessed, and converted into input and label data for model training. As a result of training the U-Net model using this data, the overall accuracy of 0.8484 and mean Intersection over Union (mIoU) of 0.6490 were achieved, and the predicted maps showed significant results in extracting object boundaries more accurately than the label data created by course annotations.

• Journal of Internet Computing and Services
• /
• 제8권3호
• /
• pp.19-32
• /
• 2007

This paper present a new face recognition method based on LVQ neural net to construct a real time face recognition system. The previous researches which used PCA, LDA combined neural net usually need much time in training neural net. The supervised LVQ neural net needs much less time in training and can maximize the separability between the classes. In this paper, the proposed method transforms the input face image by PCA and LDA sequentially into low-dimension feature vectors and recognizes the face through LVQ neural net. In order to make the system robust to external light variation, light compensation is performed on the detected face by max-min normalization method as preprocessing. PCA and LDA transformations are applied to the normalized face image to produce low-level feature vectors of the image. In order to determine the initial centers of LVQ and speed up the convergency of the LVQ neural net, the K-Means clustering algorithm is adopted. Subsequently, the class representative vectors can be produced by LVQ2 training using initial center vectors. The face recognition is achieved by using the euclidean distance measure between the center vector of classes and the feature vector of input image. From the experiments, we can prove that the proposed method is more effective in the recognition ratio for the cases of still images from ORL database and sequential images rather than using conventional PCA of a hybrid method with PCA and LDA.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• 제48권6호
• /
• pp.947-959
• /
• 2015

Variations in the species composition, biomass and size distribution of fisheries resources in the Uljin marine ranching area were investigated using trammel nets at two stations (artificial reef and natural rocky area) from 2009 to 2010. During the survey, a total of 74 species were sampled with a mean density of 132 ind./net and mean biomass of 21.56 kg/net. In the natural rocky area, a total of 45 species were sampled at a mean density of 202 ind./net and mean biomass of 28.81 kg/net, while in the artificial reef area, samples included a total of 56 species, with means of 62 ind./net and 14.30 kg/net. The dominant species, comprising over 3% of the total number of individuals, were Suberites ficus (30.8%), Ovalipes punctatus (19.2%), Paralichthys olivaceus (11.7%), Pleuronectes herzensteini (4.7%), Kareius bicoloratus (3.5%), Pseudopleuronectes yokohamae (3.5%) and Eopsetta grigorjewi (3.0%). The dominant species, in terms of biomass, comprising over 5% of the total biomass, were P. olivaceus (22.1%), S. ficus (18.7%), O. punctatus (7.2%), Hexagrammos otakii (6.6%), P. yokohamae (5.7%), K. bicoloratus and P. herzensteini (5.3%). A cluster analysis and non-metric multidimensional scaling (nMDS) analysis based on the Bray-Curtis similarity of fourth root transformed data for number of species and individuals, was divided into two groups: the artificial reef area (group A) and the natural rocky area (group B).

• Proceedings of the Korean Information Science Society Conference
• /
• 한국정보과학회 2007년도 한국컴퓨터종합학술대회논문집 Vol.34 No.1 (D)
• /
• pp.40-43
• /
• 2007

보안운영체제에서는 등급기반 사용자, 프로세스, 파일에 대한 영역분리 및 등급별 보안관리를 하는 다중등급보안(Multi Level Security)을 구현하고 있다. 안전한 운영체제에서는 사용자가 등급 즉, 자신의 보안등급과 보호범주를 설정하기 위해 권한 인증절차를 수행한다. 권한은 보안운영체제에서 강제적 접근 제어(Mandatory Access Control)의 기본이 되므로 그 보안에 중요성이 크다. 따라서, 권한 인증 절차의 보안이 부각되고 있다. 본 논문에서는 PKI 기반 전자서명 인증절차를 이용하여 신원 확인과 권한 인증을 한번에 수행할 수 있는 방법을 제시한다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 한국정밀공학회 1994년도 추계학술대회 논문집
• /
• pp.205-209
• /
• 1994

The main purpose of this study is constructing new velocity fields on the base of shape function used in finite element method and showing the possibility of application it to metal forming processes. Utilizing the 8-node quadratic rectangular element, we expressed the velocity within the deformation region by interpolating the velocity of each nodal points. And the upper-bound formulation from this velocity fields was derived. In order to confirm the validity of this method we applied it to axisymmetic combined extrusion problem. the results of load show that this method is on better agreement with experiment than the conventional UBET, and also the flow pattern and profile of extruded part are reasonable.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.279-282
• /
• 2002

With the development of industrial society, the interest of new material is growing even in machining center. Composite materials in the new materials are superior to the metals In measure stability of strength, modulus and heat, moreover when mould is prepared, it can be done net shape manufacturing so it can be used widely in all sorts of machine parts, interior materials of car structural construct ions, the space aerial industry, ship materials, sports goods and so on. Therefore in this study, the property of processing drill on CFRP in composite materials by experimental study and some problems were examined.

• Journal of the Korean Society for Heat Treatment
• /
• 제20권1호
• /
• pp.1-10
• /
• 2007

The deformation behaviors of full annealed and T6 treated 6061, 7075 aluminum tubes are investigated at various temperature performing uniaxial tensile test. Full annealed Al 6061 and Al7075 tubes, and T6 treated Al7075 tube don't show sharp local necking with an elongation of 50% at $300^{\circ}C$. So it is expected that influenced by elevated tempterature. At $300^{\circ}C$ and strain rate of 0.001/s, many micro-cracks are observed in T6 treated Al 6061 tube, which is believed to be responsible for the decrease of total elongation.

• Annual Conference on Human and Language Technology
• /
• 한국정보과학회언어공학연구회 2015년도 제27회 한글 및 한국어 정보처리 학술대회
• /
• pp.250-254
• /
• 2015

본 논문은 한국어 의미역을 정의하고, 기계학습에 기반하여 한국어 의미역 인식 기술을 개발할 때 필요한 학습 말뭉치를 구축할 때 지켜야할 가이드라인을 제시하고자 한다. 한국어 의미역 정의는 전세계적으로 널리 쓰이고 있는 Proposition Bank를 따르면서, 한국어의 특성을 반영하였다. 또한 정의된 의미역 및 태깅 가이드라인에 따라 반자동 태깅 툴을 이용하여 말뭉치를 구축하였다.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 한국건축시공학회 2023년도 가을학술발표대회논문집
• /
• pp.83-84
• /
• 2023

In this study, in order to utilize waste fishing net as a building materail, the possibility of replacing the fiber used in polymer repair mortar with waste fishing net fiber was confirmed. As for basic characteristics, flow, compressive strength, and flexural strength tests were performed to compare and analyze fiber performance, and the test results showed performance equal to or better than existing fibers.