• 한국지능시스템학회논문지
• /
• 제14권2호
• /
• pp.195-200
• /
• 2004

컴퓨터 게임은 보이드들의 군집 행동 모델링을 위하여 플로킹이라는 지능적인 기법을 사용하고 있다. 플로킹은 약간의 컴퓨터 자원만을 이용하여 조류나 물고기와 같은 예측할 수 없는 형태의 군집 행동 패턴을 자연스럽게 모델링 할 수 있다. 단 논문에서 우리는 사실적인 수중 생태계 군집 행동 모델링을 위하여, 포식자 및 먹이로 구성되는 생태계를 구현하였다. 또한 퍼지 논리를 생태계 요소들의 본능적인 욕망을 구현하기 위하여 적용하였다 그 결과 본 모델은 생태계의 파괴를 극복하고, 자연스럽게 생태계 행동을 모델링 할 수 있다는 것을 확인하였다.

• 수산해양기술연구
• /
• 제54권2호
• /
• pp.124-137
• /
• 2018

Due to the decrease in coastal productivity and deterioration in the quality of ecosystem which result from the excessive overfishing of fisheries resources and the environmental pollution, fisheries resources in the Korean waters hit the dangerous level in respect of quantity and quality. In order to manage sustainable and effective fisheries resources, it is necessary to suggest the potential yield (PY) for clarifying available fisheries resources in the Korean waters. So far, however, there have been few studies on the estimation methods for PY in Korea. In addition, there have been no studies on the comparative analysis of the estimation methods and the substantial estimation methods for PY targeted for large marine ecosystem (LME) For the reasonable management of fisheries resources, it is necessary to conduct a comprehensive study on the estimation methods for the PY which combines population dynamics and ecosystem dynamics. To reflect the research need, this study conducts a comparative analysis of estimation methods for the PY in the Korean waters of the East Sea to understand the advantages and disadvantages of each method, and suggests the estimation method which considered both population dynamics and ecosystem dynamics to supplement shortcomings of each method. In this study, the maximum entropy (ME) model of the holistic production method (HPM) is considered to be the most reasonable estimation method due to the high reliability of the estimated parameters. The results of this study are expected to be used as significant basic data to provide indicators and reference points for sustainable and reasonable management of fisheries resources.

• 한국환경복원기술학회지
• /
• 제17권1호
• /
• pp.111-122
• /
• 2014

The provided habitat of many services from natural capital is important. But because most ecosystem services tools qualitatively evaluated biodiversity or habitat quality, this study quantitatively analyzed those aspects using the species distribution model (MaxEnt). This study used location point data of the goat(Naemorhedus caudatus), marten(Martes flavigula), leopard cat(Prionailurus bengalensis), flying squirrel(Pteromys volans aluco) and otter(Lutra lutra) from the 3rd National Ecosystem Survey. Input data utilized DEM, landcover classification maps, Forest-types map and digital topographic maps. This study generated the MaxEnt model, randomly setting 70% of the presences as training data, with the remaining 30% used as test data, and ran five cross-validated replicates for each model. The threshold indicating maximum training sensitivity plus specificity was considered as a more robust approach, so this study used it to conduct the distribution into presence(1)-absence(0) predictions and totalled up a value of 5 times for uncertainty reduction. The test data's ROC curve of endangered mammals was as follows: growing down goat(0.896), otter(0.857), flying squirrel(0.738), marten(0.725), and leopard cat(0.629). This study was divided into two groups based on habitat: the first group consisted of the goat, marten, leopard cat and flying squirrel in the forest; and the second group consisted of the otter in the river. More than 60 percent of endangered mammals' distribution probability were 56.9% in the forest and 12.7% in the river. A future study is needed to conduct other species' distribution modeling exclusive of mammals and to develop a collection method of field survey data.

• 한국BIM학회 논문집
• /
• 제9권1호
• /
• pp.32-41
• /
• 2019

As population in Sarasota and Manatee Counties, Florida in the United States is projected to increase, land use changes from land development happen continuously. The more land development means the more impervious surfaces and stormwater runoff to Sarasota Bay, which causes critical impact on the resiliency of the ecosystem. In order to decrease its impact on water quality and the ecosystem function of Sarasota Bay, it is important to assess the resilient status of communities that create negative impacts on the ecosystem. Three types of guiding principles of resiliency for Sarasota Bay watershed are suggested. To assess resiliency status, three indexes - vulnerability index, socio-economic index, and ecological index are developed and analyzed by using geographic information system for each census tract in the two counties. Since each indicator for vulnerability index, socio-economic index, and ecological index is measured with different metrics, statistical standardizing method - distance from the best and worst performers is used for this study to directly compare and combine them all to show total resilience score for each census tract. Also, the ten most and the ten least scores for the total resilience index scores are spatially distributed for better understanding which census tracts are most or least resilient. As Sarasota Watershed boundary is also overlaid, it is easy to understand how each census tract attains its resilience and how each census tract impacts to Sarasota Bay ecosystem. Based on results of the resiliency assessment several recommendations, guidelines, or policies for attaining or enhancing resiliency are suggested.

• 수산해양교육연구
• /
• 제29권2호
• /
• pp.513-525
• /
• 2017

In the estimation of the exploitable carrying capacity (ECC) in the Korean water of the East China Sea, two approaches, which are the ecosystem modeling method (EMM) and the holistic production method (HPM), were applied. The EMM is accomplished by Ecopath with Ecosim model using a number of ecological data and fishery catch for each species group, which was categorized by a self-organizing mapping (SOM) based on eight biological characteristics of species. In this method, the converged value during the Ecosim simulation by setting the instantaneous rate of fishing mortality (F) as zero was estimated as the ECC of each group. The HPM is to use surplus production models for estimateing ECC. The ECC estimates were 4.6 and 5.1 million mt (mmt) from EMM and HPM, respectiverly. The estimate from the EMM has a considerable uncertainty due to the lack of confidence in input ecological parameters, especially production/biomass ratio (P/B) and consumption/biomass ratio (Q/B). However, ECC from the HPM was estimated on the basis of relatively fewer assumptions and long time-series fishery data as input, so the estimate from the HPM is regarded as more reasonable estimate of ECC, although the ECC estimate could be considerd as a preliminary one. The quality of input data should be improved for the future study of the ECC to obtain more reliable estimate.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2003년도 가을 학술발표논문집 Vol.30 No.2 (1)
• /
• pp.73-75
• /
• 2003

게임 세계에 존재하는 수많은 보이드들의 지능적인 집단 행동을 모델링하기 위한 방법으로 플로킹 기법이 많이 사용되고 있다. 특히 생태계에 존재하는 객체들의 행동을 재현하기 위한 연구가 활발하게 진행되고 있는 실정이다. 따라서 본 연구에서는 생태계에서 흔히 볼 수 있는 먹고 먹히는 관계를 퍼지 논리를 통해 게임의 보이드 행동을 모델링하고 구현한다.

• 한국건설관리학회논문집
• /
• 제19권4호
• /
• pp.93-101
• /
• 2018

생명체와 같이 살아있는 도시는 성장과 소멸의 과정을 거치는 생태계와 같은 특징을 가지고 있다. 최근의 도시들은 자연발생되는 경우 보다는 설계자에 의해 설계되는 경우가 많은 데, 만약 도시가 최적화되어 설계되지 않으면, 이를 개선하는 것이 매우 어렵다. 이로 인하여, 많은 사람들은 잘못된 설계로 인한 불편을 감수하고, 그러한 도시에 적응하여 살아가게 된다. 그러므로 설계단계에서부터 오류없이 최적화된 도시설계가 이루어지는 것이 중요하다. 도시가 최적화 설계되지 못하는 이유들 중 하나는 복잡성인데, 과거의 도시 설계방법에서 도시의 복잡성 문제를 해결할 때에는 주로 경험과 지식에 의한 하향식 문제해결 방법이 적용되었다. 그런데 이는 도시의 생태적 특성을 반영하지 않는 설계방법으로, 생태계의 생성원리를 적용한 상향식 문제해결 방법이 적용되지 못하게 된다. 따라서 본 연구에서는 작은 단위문제 해결의 합이 큰 단위문제 해결이 되는 인공 생명의 일반원리를 도시설계방법에 적용하였다. 그 결과, 다양한 도시설계 대안들을 도출할 수 있었으며, 도출된 대안들은 제한된 모델링 임에도 불구하고 전문가가 설계 한 것과 차이가 없다는 점과 향후 개발의 가능성이 있다는 점을 확인할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권2호
• /
• pp.841-854
• /
• 2020

The paper explains the method to process, analyze and predict traffic patterns in Los Angeles county using Big Data and Machine Learning. The dataset is used from a popular navigating platform in the USA, which tracks information on the road using connected users' devices and also collects reports shared by the users through the app. The dataset mainly consists of information about traffic jams and traffic incidents reported by users, such as road closure, hazards, accidents. The major contribution of this paper is to give a clear view of how the large-scale road traffic data can be stored and processed using the Big Data system - Hadoop and its ecosystem (Hive). In addition, analysis is explained with the help of visuals using Business Intelligence and prediction with classification machine learning model on the sampled traffic data is presented using Azure ML. The process of modeling, as well as results, are interpreted using metrics: accuracy, precision and recall.

• 농촌계획
• /
• 제29권4호
• /
• pp.81-92
• /
• 2023

The purpose of this study is to identify rural research topics, differences in research topics over time, and key mediators through the analysis of academic research trends using topic modeling. This study analyzed a total of 1,183 articles published in the Journal of Rural Planning and Rural Society over a 23-year period (2000-2022). We categorized rural research topics into 30, examined the proportion of research in each topic, and identified major changes in research topics over time. We also identified key words that mediate between research topics. The study found that, first, rural research trends can be categorized into five types (resources and utilization, area/space, people, ecosystem/environment, and tourism), with area/space being the most studied. Subtopics include rural amenities, rural disappearance/village miniaturization, and rural landscape management. Second, the research topics for each period were different. In the first period(2003-2007), the main research topics were rural amenities and Agricultural production- based climate vulnerability assessment. In the second period(2008-2012), the main research topics were Rural extinction and village depopulation, and rural landscape management, and in the third period(2013-2017), the main research topics were rural sixth industrialization and rural ecotourism. In the fourth period(2018-2022), rural development planning and rural life services(life SOC) were the main research topics. The significance of this study is that it extends the existing method of analyzing research trends and provides basic data to enhance comprehensive insights and understanding of rural research.

• Ecology and Resilient Infrastructure
• /
• 제10권4호
• /
• pp.161-170
• /
• 2023

본 연구에서는 제주도에서 자생하는 준맹그로브인 황근 (Hibiscus hamabo)과 갯대추나무 (Paliurus ramosissimus)의 탄소 저장량을 원격탐사로 추정하고 기후요인에 의하여 공간변이를 예측하는 인공지능 모델을 구축하고자 하였다. 준맹그로브의 지상부 탄소 축적량은 Global Ecosystem Dynamics Investigation (GEDI) 라이다에 의하여 제공되는 지상부 생물량 밀도(aboveground biomass density, AGBD)를 Sentinel-2 영상으로부터 추출한 normalized difference vegetation index (NDVI)으로 해상도를 상향하여 추정하였다. 제주도에서 단위면적당 탄소 축적량은 황근이 16.6 t C/ha, 갯대추나무가 21.1 t C/ha이었다. 제주도 전 해안에서 준맹그로브의 탄소 축적량은 11.5 t C로 추정되었다. 환경요인에 따른 준맹그로브의 탄소 축적량을 예측하기 위하여 랜덤 포레스트 기술을 적용하였다. 제주도 준맹그로브림의 분포면적 대비 지상부 생물량의 잔차를 계산하였다. 이 잔차에 영향을 미치는 주요 환경요인으로는 가장 습한 달의 강수량, 가장 더운 달의 최고온도, 등온성 및 가장 습한 달의 평균 온도가 선정되었다. 제주도에서 랜덤 포레스트 분석으로 예측된 준맹그로브의 탄소 축적량은 12.0 t C/ha - 27.6 t C/ha 범위의 공간적 변이를 나타내었다. 본 연구에서 개발된 탄소 축적량의 원격탐사 추정법과 환경요인에 따른 인공지능 예측법은 한반도에서 탄소흡수원으로서 맹그로브의 보전과 조성에 필요한 기초자료로 활용할 수 있을 것이다.