• 인터넷정보학회논문지
• /
• 제21권5호
• /
• pp.31-37
• /
• 2020

Last year's Goseong-Sokcho forest fires have highlighted the limitations of extinguishing work for night-time forest fire and the importance of quick identification for information on the spread of forest fire. However, it is not easy to find services that take into account the characteristics of forest fires, as most existing disaster-related mobile applications and research assume various disaster situations rather than just forest fire situations. Therefore, a system that can provide information quickly is needed, taking into account the characteristics of forest fires and the limitations of extinguishing work. In this paper, we propose evacuation route guidance services that bypass areas where fire has already spread, supplement existing methods of extinguishing work, and provide general information on forest fire situations in real time, by putting drones into forest fire situations. It has been implemented to automate image analysis using the Rekognition service of Amazon Web Service (AWS), and the results of fire detection and the T Map API guide the evacuation path. It is expected that the results of this paper will allow efficient and rapid rescue and extinguishing work to be carried out, and further reduce the damage of human life caused by forest fires.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.310-315
• /
• 1999

We extracted narrow open water streams from JERS-1 SAR images of the Amazon rain forest. The extracted range of these streams were almost comparable to a high level extraction of the same streams from near-IR images of JERS-1 VNIR data notwithstanding that these features in SAR images show the strong dependence of the observation angle. Large water bodies are relatively easy to extract from JERS-1 SAR images, as they tend to appear as very dark areas; but streams whose width is nearly equal to or less than the spatial resolution no longer appear as very dark features. By using strong scatterers distributed sparsely along the radar facing sides of the streams, we can successfully estimate approximate ranges of waterways and then extract relatively dark line-like features within these ranges.

• Advances in environmental research
• /
• 제4권4호
• /
• pp.247-262
• /
• 2015

The few lignin biomarker studies conducted in tropical environments are hampered by having to use references signatures established for plants and soils characteristic of the temperate zone. This study presents a lignin biomarker analysis (vanillyls (V), p-hydroxyls (P), syringyls (S), cinnamyls (C)) of the dominant plant species and soil horizons as well as an analysis of the interrelated terrigenous organic matter (TOM) dynamics between vegetation and soil of the $Tapaj{\acute{o}}s$ river region, an active colonization front in the Brazilian Amazon. We collected and analyzed samples from 17 fresh dominant plant species and 48 soil cores at three depths (0-5 cm, 20-25 cm, 50-55 cm) from primary rainforest, fallow forest, subsistence agriculture fields and pastures. Lignin signatures in tropical plants clearly distinguish from temperate ones with high ratios of Acid/aldehyde of vanillyls ((Ad/Al)v) and P/V+S. Contrary to temperate environments, similarly high ratios in tropical soils are not related to TOM degradation along with pedogenesis but to direct influence of plants growing on them. Lignin signatures of both plants and soils of primary rainforest and fallow forest clearly distinguish from those of non-forested areas, i.e., agriculture fields and pastures. Attalea speciosa Palm trees, an invasive species in all perturbed landscapes of the Amazon, exhibit lignin signatures clearly distinct from other dominant plant species. The study of lignin signatures in tropical areas thus represents a powerful tool to evaluate the impact of primary rainforest clearing on TOM dynamics in tropical areas.

• 한국환경과학회지
• /
• 제10권5호
• /
• pp.337-342
• /
• 2001

The Rondonia Boundary Layer Experiment (RBLE-II) was conceived to collect data the atmospheric boundary layer over two representative surface in the Amazon region of Brazil; tropical forest and a deforested, pasture area. The present study deals with the observations of atmospheric boundary layer growth and decay. Although the atmospheric boundary layer measurements made in RBLE-II were not made simultaneously over the two different surface types, some insights can be gained from analysing and comparing with their structure. The greater depth of the nocturnal boundary layer at the forest site may be due to influence of mechanical turbulence. The pasture site is aerodynamically smoother and so the downward turbulent diffusion will be much pasture than over the forest. The development of the convective boundary layer is stronger over the pasture than over the forest. The influence of the sensible heat flux is important but may be not enough to explain the difference completely. It seems that energy advection may occur from the wet and colder(forest) to the dry and warmer area(pasture), rapidly breaking up the nocturnal inversion. Such advection can explain the abrupt growth of the convective boundary layer at the pasture site during the early morning.

• 한국IT서비스학회지
• /
• 제14권4호
• /
• pp.159-169
• /
• 2015

Customer reviews are one of the important sources for purchase decision makings in online stores. Online stores have tried to provide useful reviews in product pages to customers. To assess the usefulness of customer reviews before other users have voted enough on the reviews, diverse aspects of reviews were utilized in prevous studies. Style and semantic information were utilized in many studies. This study aims to test diverse alogrithms and datasets for identifying a proper classification method and threshold to classify useful reviews. In particular, most researches utilized ratio type helpfulness index as Amazon.com used. However, there is another type of usefulness index utilized in TripAdviser.com or Yelp.com, count type helpfulness index. There was no proper threshold to classify useful reviews yet for count type helpfulness index. This study used reivews and their usefulness votes on restaurnats from Yelp.com to devise diverse datasets and applied text mining approaches to classify useful reviews. Random Forest, SVM, and GLMNET showed the greater values of accuracy than other approaches.

• 한국농림기상학회지
• /
• 제13권2호
• /
• pp.101-108
• /
• 2011

기후변화는 자연 및 농업생태계에 막대한 영향을 미칠 수 있다. 이러한 기후변화 영향 평가를 위해 모형의 입력자료로서 예측된 기후자료가 사용되고 있다. 그러나 이러한 연구들은 자주 수행되지는 않기 때문에, 실제의 컴퓨터 자원들을 구축하거나 유지하지 않고 필요에 따라 자료처리를 하기 위해서는 가상적으로 다수의 운영체제를 구동할 수 있는 클라우드 컴퓨팅을 사용하는 것이 유용하다. 또한, 클라우드 컴퓨팅을 사용할 때 소프트웨어 라이센스를 필요로 하지 않는 오픈소스 지리분석용 소프트웨어를 사용하는 것이 유리하다. 예비실험에서, Amazon Web Service-Elastic Compute Cloud(EC2)를 사용하여 월 강우일수를 계산하였다. 총 70기가바이트에 이르는 일별 기후 예측 자료를 사용하여 자체 제작된 데이타베이스 처리 응용프로그램을 가상머신에서 처리하였다. 이 응용프로그램은 기후자료 처리와 데이타베이스 접속을 위해 오픈소스 라이브러리를 기반으로하여 제작되었다. 이 분석에서는 21세기 동안 전지구적으로 강우일수를 계산하기 위해 10대의 가상 클라이언트와 1대의 서버를 이용하여 약 170억개의 자료를 32시간 내에 처리하였다. 이번 연구 결과는 클라우드 컴퓨팅이 막대한 양의 자료 처리를 필요로하는 기후변화 영향평가 연구와 분석에 큰 도움이 될 수 있음을 보여 준다.

• 한국정보통신학회논문지
• /
• 제22권9호
• /
• pp.1153-1158
• /
• 2018

다양한 온라인 고객 평가 및 소셜 미디어 정보는 고객의 의사결정에 영향을 미치기 때문에 기업에게 매우 중요한 정보 출처라고 할 수 있다. 설문 조사를 통해 고객의 다양한 요구와 불만 사항을 파악하는 데는 많은 비용과 시간적인 제약이 발생하고 있다. 온라인 쇼핑몰의 고객 후기 데이터는 제품에 대한 고객들의 감성을 분석할 수 있는 이상적인 자료를 제공하고 있다. 본 연구에서는 삼성과 애플 스마폰에 대한 감성분석을 위해 아마존 쇼핑몰로부터 고객 리뷰 데이터를 수집하였다. 선행 연구에서 대표적인 감성분석 기법으로 사용된 5가지 분류 알고리즘을 적용하였다. 5가지 분류알고리즘은 support vector machines, bagging, random forest, classification or regression tree, maximum entropy 등이다. 본 연구에서는 분류 알고리즘의 수행도를 종합적으로 평가할 수 있는 entropy score를 제안하였다. Entropy score를 이용하여 5가지 알고리즘을 평가한 결과에 따르면 support vector machines 알고리즘의 entropy score가 가장 높은 것으로 분석되었다.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2007년도 추계학술대회 논문집
• /
• pp.307-308
• /
• 2007

This work shows the experimental results obtained from ageing at a temperature of 100 C for 48, 70 and 312 h, although the application of AC electrical tension in samples and the measuring of current leakage are presented. The measurements in samples were carried out with samples prepared from the deformulated commercial materials and respectively reformulated into thin films. The obtained results showed the mechanisms of conduction of samples in low and high electric fields. It was also identified an electric tension transition showing that in low fields it prevails the Ohm's law conduction, and in high electric fields it prevails the conduction of space charge limited current (SCLC). These results can support the natural rubber formulation process having as their main objective the reducing of the mechanisms that occur under high conduction current in high electric fields, which leads the material to a dielectric breakdown. Raw Natural rubber in Brazil is extracted from rubber trees (Hevea brasiliensis) in farms in So Paulo State by using some new plantation technology in smaller spaces, with trees placed a few meters from each other. In the Amazon rain forest the rubber trees are found naturally and their spacing may be of hundreds of meters or even kilometers between them. It is necessary to research this raw material from different internationally standard clones to characterize dielectric and electric properties for industrial applications. Moreover, this natural material has a low commercial price when compared to the synthetic ones.

• 한국산학기술학회논문지
• /
• 제19권1호
• /
• pp.75-84
• /
• 2018

본 철도 유지보수 산업의 효율화를 위해서는 핵심부품의 적시 관리를 통한 부품 가동률 향상 및 철도 운행의 안정성 향상이 필요하다. 또한 유지보수 시스템 고속화에 따른 신뢰성 향상과 핵심부품의 유지보수 비용 절감의 두 가지 측면을 모두 만족시키기 위해, 부품 이력관리와 대규모 빅데이터의 자동화된 분석 기술을 활용한 부품 상태 진단 기술 수요가 증가하고 있다. 이 논문에서는 철도차량의 차상 및 지상 장치로부터 발생되는 실시간 빅데이터 수집, 처리, 분석을 위해서 빅데이터 플랫폼 기반의 철도차량 부품의 상태 데이터 관리시스템을 개발하였으며, 이 시스템의 활용으로 철도차량의 부품 상태정보 및 시스템 리소스에 대한 실시간 모니터링이 가능하다. 또한 빅데이터 플랫폼으로부터 수집된 상태 데이터를 기반으로 분산/병렬처리 및 자동화된 부품 고장진단이 가능한 머신러닝 기법을 제안하였다. 실험결과, 분산/병렬처리 기술이 적용된 알고리즘의 실행시간 단축을 아마존 웹서비스의 가상 인스턴스 생성 시스템을 통해 증명하였으며, random forest 머신러닝 기법을 활용한 고장 진단 모델의 베어링 및 차륜 부품에 대한 상태 예측 정확도가 83%임을 확인하였다.