• The KIPS Transactions:PartB
• /
• v.15B no.4
• /
• pp.331-340
• /
• 2008

Feature Selection is one of methods to improve the classification accuracy of data in the field of machine learning. Many feature selection algorithms have been proposed and discussed for years. However, the problem of finding the optimal feature subset from full data still remains to be a difficult problem. Bio-inspired algorithms are well-known evolutionary algorithms based on the principles of behavior of organisms, and very useful methods to find the optimal solution in optimization problems. Bio-inspired algorithms are also used in the field of feature selection problems. So in this paper we proposed new improved bio-inspired algorithms for feature selection. We used well-known bio-inspired algorithms, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), to find the optimal subset of features that shows the best performance in classification accuracy. In addition, we modified the bio-inspired algorithms considering the prior importance (prior relevance) of each feature. We chose the mRMR method, which can measure the goodness of single feature, to set the prior importance of each feature. We modified the evolution operators of GA and PSO by using the prior importance of each feature. We verified the performance of the proposed methods by experiment with datasets. Feature selection methods using GA and PSO produced better performances in terms of the classification accuracy. The modified method with the prior importance demonstrated improved performances in terms of the evolution speed and the classification accuracy.

• Journal of Environmental Impact Assessment
• /
• v.26 no.6
• /
• pp.385-403
• /
• 2017

This study showed the national ecosystem classification for the spatial standards of ecosystems-based approaches to the risk assessments and adaptation plan. The characteristics of climate change risk assessment, implement national adaptation plans, and ecosystem/habitat classification status was evaluated. Focusing on the land cover classification widely utilized as spatial data for the assessments of biodiversity and ecosystem services in the UK and other countries in Europe, the applicability of the national land cover classification for climate change risk assessments was reviewed. Considering the ecosystem classification for climate change risk assessment and establishing adaptation measures, it is difficult to apply rough classification method to the land cover system because of lack of information on habitat trend by categorization. The results indicated that forest ecosystems and agro-ecosystem occupied 62.3% and 25.0% of land cover, respectively, of the entire country. Although the area is small compared with the land area, wetland ecosystem (2.9%), marine ecosystem (0.4%), coastal ecosystem (0.6%), and urban ecosystem (6.1%) can be included in the risk assessments. Therefore, it is necessary to subdivide below the medium classification for the forest and agricultural land, as well as Inland wetland, which has a higher proportion of habitat preference of taxa than land area, marine/coastal habitat, and transition areas such as urban and natural ecosystem.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.2
• /
• pp.529-534
• /
• 2020

The development of civilization is in line with evolution of cities and transportation technology caused by industrialization. Up to now, a city has been developed owing to transportation cost reduction and needs for land utilization as a limited core business district. Continuous increase of urban population density has accompanied by lots of problems socioeconomically such as rise of land value, traffic congestion, gap between the rich and poor, air pollution, etc. Those issues are difficult to be solved in existing city ecosystem. However, a clue for solving the problems could be found in there. The design of Seoul mid-night bus route was from analysis of movement of people in the rural area by using ICT so that a city ecosystem should be firstly analyzed for solving rural issues. If the cause of those is found, big data platform construction is required to raise the life quality of citizen and the problems could be solved. Big data should be located in the middle of the platform connected with every element of city based on ICT for real-time collection, analysis and application. This paper addresses construction of big data platform and its application for sustainable smart city.

• Informatization Policy
• /
• v.24 no.3
• /
• pp.42-66
• /
• 2017

This study investigated the ecological change of public software industry, comparing the pre and post structure of industry network based on the application of the regulation restricting large company participation in public software market. For this purpose, we used big data of the software market from Korea Public Procurement Service and used the SNA(Social Network Analysis) methodology which is being actively used in the area of social science recently. Finally, we highlighted the contribution of open public data. By analyzing order and contract data of the public software industry for 3 years - from 2013 to 2015 - we found out two main things. First, we observed that Power Law distribution had been going on in the public software industry, regardless of the external impact of regulation. Second, despite the existence of such Power Law distribution, we also observed the ecological change of industry structure from year to year. We presented the implication of such findings and discussed the advantage of open public data as the original motivator of this study.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.69-71
• /
• 2022

The 4th industrial revolution is regarded as a paradigm that determines future national competitiveness through the convergence and intelligence of various ICT technologies. In order to ensure the realization of the Korean military's national tasks and the successful implementation of Defense Reform 2.0, the vision for the promotion of the 'Defense Innovation Plan in the Era of the 4th Industrial Revolution' was set as 'implementation of smart defense innovation based on the 4th industrial revolution'. However, it is time to review whether the data value chain, which is the core of the 4th industrial revolution, is considered before full-scale business promotion according to the vision. In this paper, we compared and analyzed the smart defense innovation promotion project and the military and pan-government data platform project in terms of the data value chain, and suggested policy alternatives to build a defense data ecosystem.

• Proceedings of KOSOMES biannual meeting
• /
• 2007.11a
• /
• pp.193-195
• /
• 2007

해양생태계로 유입되는 화학물질의 총합적인 평가 및 관리를 위해서는 동 화합물의 해양환경중의 거동 및 운영, 생태계에의 영향, 관리방안에 따른 화학물질의 변화 예측 및 리스크 평가 등을 행할 필요가 있으며, 이를 위하여는 화학물질에 대한 생태계 모델이 유용한 수단이 될 수 있다. 본 연구에서는 여러 화학물질에 적용할 수 있으며, 지역특성, 존재 데이터 상황, 대상 수산물의 특성을 고려하여 여러 상태함수 및 프로세스의 추가와 삭제가 가능한 3차원 생태계 모델(EMT-3D)을 사용하여 해양환경중의 PFCs 관련물질을 대상으로 그 적용성을 검토하였으며, 민감도 분석 및 시나리오 분석을 행하여 영향인자를 판별하고 대안에 따른 영향을 평가하였다.

• Annual Conference of KIPS
• /
• 2009.04a
• /
• pp.294-297
• /
• 2009

다방면적인 과학기술의 발달은 우리에게 대량의 데이터와 또한 새로운 영역으로의 접근 가능성을 열어주었다. 유전자 정보와 같은 대량의 정보를 다루는 시대가 열리면서 바이오 데이터를 분석하여 새로운 연관성과 정보를 찾아내는 바이오인포매틱스가 고부가가치 창출을 위한 학문으로 특히 부각되고 있다. 본 논문에서는 이러한 연구의 일환으로 보다 효율적인 바이오 데이터 분석을 위해 BNP에 내장된 생태계 모방 알고리즘의 특성을 연구하고, 이를 분류화에 접목시킨 방법에 대해 논하고자 한다.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.12 no.4
• /
• pp.18-33
• /
• 2009

The purpose of this study is to analyze the effect that consumption patterns of human affect the ecosystem using analysis of ecological footprint(EF) and assessment of ecosystem service value in Daegu Metropolitan Area. The data for analysis were constructed from statistical yearbook of each city and average of public land price on land category. According to the EF analysis on city, total EF of Goryeong was showed the highest by 3.3052gha in 2007. However, total EF of Daegu was assessed the lowest by 2.0134gha among 8 cities. In the results of ecological deficit, 7 cities except Gunwi were assessed by condition of ecological deficit and had exceeded environmental capacity until 2007. Specially, it was analyzed that Daegu may need additional area more than about 30 times to maintain the present consumption patterns. On the one side, the results of analysis of ecosystem service value in Daegu were assessed that citizens of Daegu have borrowed about 1,078.6 million wons to ecosystem per year and one person.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.16 no.3
• /
• pp.159-175
• /
• 2021

Business ecosystem is becoming more inclined towards platform ecosystem, which attracts multi-side participants based on digital technology. The burgeoning interest in digital ecosystem leads to the rapid rise of research. In this paper, we suggest a research agenda, focusing on the benefits of complementors in platform ecosystem. First, we outline the extant papers on benefits from platform to participants from economic perspective, strategic management perspective, technology management perspective, and economic sociological perspective to provide comprehensive understanding about platform ecosystem. Second, we suggest systemic framework to provide integrative insights on the the topic of benefit from platform to complementors- (1) open innovation view, (2) economic performance view, and (3) sociological view. Specifically, we focus on empirical studies that investigate the relationship between the benefits from platform and spillover effects on complementors based on various dataset. In addition, by reviewing the past empirical research, we suggest future research agenda and implications for policy in platform ecosystem.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.180-180
• /
• 2011

하천의 정상적인 기능 및 상태를 유지하기 위하여 필요한 최소유량을 의미하는 하천유지유량은 하천수질보전, 하천생태계보호, 하천경관보전, 염수침입 방지, 하구막힘 방지, 하천시설물 및 취수원보호, 지하수위 유지 등을 감안하여 산정하게 된다. 하천유량 변화는 하천내 동 식물에 영향을 미치며, 특히 고등 생물인 어류의 서식처, 산란장소 및 산란조건 등은 유량 및 수위변화에 민감하게 반응하므로 하천구간별 어류의 서식처 유지에 적절한 수심, 유속 등 수리 조건을 제공할 수 있는 유량을 산정하게 된다. 국내에서는 90년대 후반부터 생태계를 고려한 하천유지유량 개념이 도입되었으며, 어류의 적절한 수생 서식환경 평가를 위해 주로 유량 점증 방법론(IFIM, Instream Flow Incremental Methodology) 개념에 입각한 물리서식처 모형을 이용한 연구가 진행되어 왔다. 본 연구에서는 낙동강수계 13개 지점을 선정하여 어류상 조사를 실시하여 어류의 물리서식처 모형과 수심-유속-유량 관계곡선을 이용한 간단법을 이용하여 생태계 보전을 위한 필요유량을 산정하였다. 어류 물리서식처 모형으로는 어류서식환경 평가에 가장 광범위하게 이용되고, 생태적 특성을 반영할 수 있는 유량점증방법론의 PHABSIM(Physical HABitat SIMulation) 모형을 선택하였다. 현장 모니터링 및 문헌조사를 통해 각 지점별 대표어종을 선정하고, 유량, 수심, 저수로 하천단면, 하상재료와 같은 수리특성을 조사하고, 선정된 한계단면에 대한 유량측정을 실시하였으며, 수심-유속-유량 관계곡선을 통하여 각 지점의 대표어종이 서식할 수 있는 최소유량을 산정하였다. 또한 지점별로 서식처 적합도 지수(HSI, Habitat Suitability Index)와 가중가용면적(WUA, Weighted Usable Area)를 산정하였으며, 이는 PHABSIM 모형의 적용에 이용되었다. 물리서식처 모형과 간단법 적용결과를 비교해본 결과, 모든 지점에서 물리서식처 모형 적용결과가 간단법에 비해 크게 산정되었는데, 이는 간단법이 성어기 서식에 필요한 최소 수리조건을 선택하였지만, PHABSIM의 경우 성어기 어류서식의 최적 수심 및 유속을 이용하여 가중가용면적을 산정하기 때문인 것으로 판단된다. 어류서식과 관련된 많은 관련 데이터가 축적된다면 어류서식처에 맞는 최적의 생태유량을 보다 정확하게 산정할 수 있을 것으로 판단된다.