• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.5
• /
• pp.363-371
• /
• 2015

Feature extraction is one of the main goals in many remote sensing analyses. After high-resolution imagery became more available, it became possible to extract more detailed and specific features. Thus, considerable image segmentation algorithms have been developed, because traditional pixel-based analysis proved insufficient for high-resolution imagery due to its inability to handle the internal variability of complex scenes. However, the individual segmentation method, which simply uses color layers, is limited in its ability to extract various target features with different spectral and shape characteristics. Spectral indices can be used to support effective feature extraction by helping to identify abundant surface materials. This study aims to evaluate a feature extraction method based on a segmentation technique with spectral indices. We tested the extraction of diverse target features-such as buildings, vegetation, water, and shadows from eight band WorldView-2 satellite image using decision tree classification and used the result to draw the appropriate spectral indices for each specific feature extraction. From the results, We identified that spectral band ratios can be applied to distinguish feature classes simply and effectively.

• The Korean Journal of Ecology
• /
• v.23 no.1
• /
• pp.65-70
• /
• 2000

Field collections were made from six gypsy moth (Lymantria dispar L.) Populations in Kyonggy and Cheju areas during the period 1987∼1997. Characteristics of gypsy moth populations at different phases were examined in terms of egg mass density, relative larval density, plant damage, and fecundity. Males captured in pheromone trap were recorded, and we examined if there was a relationship between numbers captured and the population density during the following generation. Egg mass density was closely related with larval density, and furthermore these densities were correlated with the level of plant damage, indicating that larval dispersion was limited in oviposition areas. The gypsy moth population cycle was short in Korea with the period from population development to innocuous level usually lasting 2∼3 years. Male caught by pheromone trap (mean number of males caught per trap per day in peak emergence period) was positively correlated with egg mass densities in the following season (r²=0.93). A low fecundity was detected from outbreak populations which accompanied defoliation. Fecundity of gypsy moth ranged from 538 to 601 at other phases.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.9
• /
• pp.76-83
• /
• 2017

Fish respond sensitively to light, so it is possible to develop fish management technology using this feature. In this study, we developed a light-based fish barrier and analyzed itsblocking effect using the difference in illuminance for the major fish species in Korea, bass and bluegill. The light was generated by a light emitting diode and the facility was installed vertically from the bottom. Considering the fish's ability to travel upstream, the flow rate was divided into three stages (0.2, 0.1, and 0.05 m/s). To prevent the learning effect, an experiment was carried out with fish that had rested for more than one day in a rearing tank. The experiment was carried out in such a way as tocompare the number of fish which travelled upstream after the introductionof the fish barrier and that of the fish which travelled upstream after itsremoval. It was also carried out after sunset to increase the effectiveness of the barrier. According to the results of the experiment, the fish blocking effect depending on the difference in illuminance was high and, overall, the blocking rate for bass was lower than that for bluegill. Based on the total size of the experimental population, the blocking rates for bass and bluegill were 96.33% and 99.00%, respectively. Based on the number of fish that travelled upstream, the blocking rates for bass and bluegill were 91.73% and 98.73%, respectively.

• Korean Journal of Agricultural Science
• /
• v.28 no.1
• /
• pp.18-26
• /
• 2001

Application of the Asian ladybird (Harmonia axyridis) to control several species of aphids in the plastic green houses in mind, control effects of aphid populations regulated by the Asian ladybird were observed. The green peach aphid, the turnip aphid, and the cotton aphid were present on mustard plants, Angelia utlis, ornamental kales, and egg plants at greenhouses in spring, summer, and winter. Adults and larvae of the Asian ladybird used in experiments were collected from aggregated sites at Taejon in the autumn and reared on the cotton aphid in the laboratory. In winter, more number of adults and larvae of ladybirds than in other seasons were needed to control aphid population in successively double plastic greenhouses with supplied subterranean water for keeping warmth. In spring and summer, it was possible to keep the aphid populations low when necessary by manipulating ladybird populations according to the density of aphids. On the other hand, the innate increasing rate of aphid, the aphid population density at the time of applying ladybird, the predacious ability of ladybird at specific developmental stages, and needed periods should be taken into account to control aphids. In addition, the environmental factors, for example, optimum temperature and humidity should be considered to be biologically effective when ladybirds are released to greenhouses.

• Proceedings of the Korean Society of Applied Pharmacology
• /
• 1997.11a
• /
• pp.81-85
• /
• 1997

인체에 투여된 약물의 반응은 개체간에 현저한 차이가 있으며 특히 환자에게 투여된 약물의 효과가 상이하게 나타남으로써 치료의 실패나 흑은 약물의 유해작용으로 나타나기도 한다. 이러한 개체 상호간의 약물반응의 차이는 환경적인 요소, 영양학적인 요소, 연령, 병용한 다른 약물 및 이미 앓고 있는 질병 등에 의해서도 영향을 받으나 특히 유전적으로 결정된 약물대사 능력의 차이에 의해서도 기인된다. 이러한 측면에서 약물 대사의 유전적인 다양성과 비정상적인 반응을 다루는 약물유전학의 중요성은 최근 두드러지게 대두되고 있다. 특히 유전적인 요인으로 개체간의 차이는 효소의 유전적인 결핍과 관련이 있으며 이 결핍은 생체이물질에 대한 반응의 다양성을 설명할 수 있는 약물대사 능력의 다형성에 기인한다. 또한 약물반응의 다양성은 인종간, 특히 동양인과 서양인에서의 약물반응에서도 차이가 있어 각 인종간의 약물반응의 차이에 대한 연구와 이의 원인규명에 대하여 많은 관심이 집중되고 있다. 이와 같은 견지에서 약물용량과 약물반응, 특히 약동학적 변화의 인종간의 차이와 각 개인의 차이 및 이의 원인에 대하여 살펴보고자 한다.

• Proceedings of the KSAR Conference
• /
• 2003.06a
• /
• pp.23-23
• /
• 2003

프리마틴(freemartin)이라 함은 반추동물들 중 특히 소에서 나타나는 간성(intersex)형태로 이성 쌍자의 경우 태어난 암컷의 대부분이 정상적인 자성 생식기의 발육 및 발생양상을 지니지 못하여 생식불능상태로 되는 것으로 알려져 있다. 최근 실용화된 수정란이식이나 쌍자유기 등의 기술은 현재 일반 농가에 까지 정책적으로 확대 보급되어 산업화되고 있는 실정이나 불행히도 이러한 기술들을 이용하여 생산된 개체들 중 상당수가 이성쌍자로 이들 중 암컷 개체들은 거의 freemartin으로 생산되어 실지 노력에 비해 경제적 효과들을 크게 반감시키고 있다. 뿐만 아니라 생산된 freemartin 개체들에 대하여 조기 진단 없이 다만 형태적으로 암컷으로 판단하여 번식우로 사양관리 함에 따른 경제적 손실이 매우 크다 할 수 있겠다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.218-222
• /
• 2006

우수한 능력의 인공지능 개체로 구성된 게임은 그렇지 못한 게임에 비해 더 나은 흥미를 사용자에게 제공할 수 있다. 미국 Valve사의 Half-Life, Counter-Strike 및 한국 Dragonfly사의 Special-Force와 같은 실시간 FPS 전투게임에서 상대편에 대한 검색 및 목표 화하는(Targeting) 기법은 인공개체의 전투력에 중요한 하나의 요소이다. 하지만 이 같은 경우의Targeting은 정적인 대상에 대한 것이 아니라 동적인 대상에 대한 것이므로 단순한 산술 계산으로는 실용적인 효과를 내기 힘들다. 본 논문에서는 Neural Network를 이용한 학습기법을 사용하여 동적인 개체에 대한 효과적인 Targeting기법을 제안한다. 제안한 기법은 매 순간 변화하는 상황정보와 Virtual bullet이라는 가상 미사일 개념을 활용하여 학습 Data를 모델링한 후 Neural Network로 학습시켜 효과적인 Targeting이 가능하도록 구현하였다. 제안한 기법은 Java기반의 탱크전투 시뮬레이션 Framework인 Robocode에 적용하여 그 성능을 평가하였다. 제안된 기법으로 제작된 Robot(Crystal 1.0)은 ‘2006 Robocode Korea Cup에서 우승을 차지하였다.

• Proceedings of the Korea Contents Association Conference
• /
• 2012.05a
• /
• pp.51-52
• /
• 2012

본 논문은 논문, 특허, 연구보고서 등과 같은 다양한 과학기술문헌에 포함된 기술 지식을 효과적으로 추출하는데 필요한 기반 텍스트 분석 엔진들의 성능 평가 및 개선을 위한 테스트베드 툴킷을 소개한다. 이 툴킷은 과학기술분야의 전문용어를 비롯한 인명, 지명, 기관명 등을 자동으로 인식하는 기술개체인식엔진을 위한 테스트베드와 인식된 기술개체 간의 의미적 연관관계를 자동으로 추출하는 기술개체 간 관계추출 테스트베드 로 구성되어 있다.

• 한국해양학회지
• /
• v.27 no.4
• /
• pp.268-276
• /
• 1992

Multitrophic interactions among gelatinous planktivores, zooplankton, and phytoplankton were in vestigated in Reeves Bay. New York from mid-March to July in 1989 to evaluate the top-down effect by gelatinous macrozooplankton on the Gyrodinium aureolum bloom through cascading tropic interactions. Zooplankton abundances reached maximal density following a decrease in gelatinous macrozooplankton (hydromedusae and scyphomedusae) abundances, and phytoplankton biomass was low at this time. Subsequently, as ctenophore populations increased zooplankton abundances decreased sharply, and the cell concnetration of G. aureolum began to increase. This field observation supports that the top-down control by gelatinous macrozooplankton on grazers, resulting in low grazing pressure on phytoplankton, can cause an algal bloom. The minimal zooplankton grazing measured using /SUP 14/C tracer technique during the bloom period indicated that zooplankton did not prefer G. aureolum as a good source.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.9
• /
• pp.2299-2308
• /
• 1997

While most machine learning research has been primarily concerned with the development of systems that implement one type of learning strategy, we use a multistrategy approach which integrates rule induction learning and instance-based learning, and show how this marriage allows for overall better performance. In the rule induction learning phase, we derive an entropy function, based on Hellinger divergence, which can measure the amount of information each inductive rule contains, and show how well the Hellinger divergence measures the importance of each rule. We also propose some heuristics to reduce the computational complexity by analyzing the characteristics of the Hellinger measure. In the instance-based learning phase, we improve the current instance-based learning method in a number of ways. The system has been implemented and tested on a number of well-known machine learning data sets. The performance of the system has been compared with that of other classification learning technique.