• 제목/요약/키워드: Water classification

검색결과 941건 처리시간 0.032초

텍스트 문서 분류에서 범주간 유사도와 계층적 분류 방법의 성과 관계 연구 (A Study on the Relationship between Class Similarity and the Performance of Hierarchical Classification Method in a Text Document Classification Problem)

  • 장수정;민대기
    • 한국전자거래학회지
    • /
    • 제25권3호
    • /
    • pp.77-93
    • /
    • 2020
  • 비정형 텍스트 문서를 다중 범주로 분류하는 문제에 있어서, 계층적 분류 방법이 비계층적 분류 방법에 비하여 분류 성능이 우수한 것으로 알려져 있다. 기존 문헌과 다르게 본 연구에서는 사전에 범주들의 계층 구조가 정의된 상황에서 계층적 분류 방법과 비계층적 분류 방법의 성능을 비교하였다. 수자원 분야 기후변화 적응기술과 관련한 논문 분류 데이터와 20NewsGroup 오픈 데이터를 대상으로 계층적/비계층적 분류 방법의 성능을 비교하였다. 본 연구결과 기존 문헌과 다르게 계층적 분류 방법이 비계층적 분류 방법에 비하여 언제나 성능이 우수한 것은 아님을 확인하였다. 계층 구조의 상위/하위 수준에서의 상대적 유사도에 따라서 계층적/비계층적 분류 방법의 성능에 차이가 있음을 확인하였다. 즉, 상위 수준의 유사도가 하위 수준보다 상대적으로 낮은 경우 상위 수준에서의 오분류 감소로 계층적 분류 방법의 성능이 개선됨을 확인하였다.

「일본유용수산분류표」의 특징과 편찬 목적에 대한 분석 (An Analysis on the Characteristics and Compilation Purpose of Japanese Useful Fisheries Classification Table)

  • 서경순;이근우
    • 수산경영론집
    • /
    • 제54권3호
    • /
    • pp.69-92
    • /
    • 2023
  • The 'Japanese Useful Fisheries Classification Table', published in advance before the publication of the "Useful Fisheries of Japan", is the first data to classify and introduce fisheries animals and plants in a single table. Therefore, it had received public attention immediately. However, The academy of animal studies at that time quickly pointed out that this classification table was a mixture of traditional and modern classifications, and that there were too many errors. However, Yoshio Tanaka, who was in charge of revising Yamamoto Arikatana, that wrote the classification table, was not an adherent of traditional taxonomy, nor was he ignorant of modern taxonomy. Nevertheless, the classification table, which was quite different from the well-known zoological classification at that time, was prepared. For example, the top classifications of marine organism are not at the same level, but rather a mixture of phylum and class, while the water insect contains several phylums, including Arthropoda, Echinodermata, Mollusca, and Coelenterata. As such, the method of classification of animals in the classification table was hard to understand in the zoological academy at that time. The reason for this unusual taxonomy was that the classification table showed classification of useful fisheries products, not intended to convey academic classification. In other words, it is not for the purpose of academic classification of all fishery products, but for the purpose of presenting standards that can be easily understood by those engaged in the collection, manufacture, and aquaculture of fishery products. This principle of 'Useful Fisheries of Japan' is also ascertained in the "Fishing Methods of Japan" and "Fishery Products of Japan". Regarding the collection and processing of marine products, it could have shown how to catch whales, which are mammals, and how to dismantle whales and obtain oil and meat, according to academic classifications. However, the first appearances in the book include dried squid, abalone, shark fins, and sea cucumbers. In other words, the most important fishery products at that time are presented first. The contents of the classification table, which is considered somewhat bizarre, show where the purpose to compile Useful Fisheries of Japan.

천해 배경잡음 환경에 적합한 과도신호의 특징 및 변별력 분석 (Analysis of Features and Discriminability of Transient Signals for a Shallow Water Ambient Noise Environment)

  • 이재일;강윤정;이종현;이승우;배진호
    • 전자공학회논문지
    • /
    • 제51권7호
    • /
    • pp.209-220
    • /
    • 2014
  • 본 논문에서는 천해 배경잡음 환경에서 과도신호 분류에 적합한 특징 선택을 위해 특징의 변별력을 분석하였다. 과도신호 분류는 해양환경 특성상 낮은 신호대잡음비(SNR)를 가지므로 잡음변화에 강인한 특징이 요구된다. 천해 배경잡음을 모델링하기 위해 이론적인 잡음 모델과 Wenz의 천해 관측 자료 그리고 Yule walker 필터를 이용하였다. 과도신호의 SNR에 따른 각 특징의 변별력은 Fisher score를 이용하여 분석하였다. 변별력이 높은 특징을 선택하여 24 클래스의 과도신호원에 대한 분류정확도를 분석한 결과 잡음이 없는 환경에서 선택된 특징에서 상대적으로 높은 분류정확도를 보였다. 이러한 결과를 토대로 최종적으로 선택된 특징은 전체 28가지 특징 중 16가지 특징이 선택되었다. 다중 클래스 SVM분류기를 이용하여 선택된 특징의 인식률 분석결과 과도신호의 SNR 20dB 환경에서 약92%의 분류정확도를 보였다.

공동주택 내부소음 기준과 바닥 및 벽체 차음성능 기준 고찰 (A Survey on Foreign and Domestic Interior Noise Criteria for Walls and Floors)

  • 김선우;송민정
    • KIEAE Journal
    • /
    • 제4권3호
    • /
    • pp.37-44
    • /
    • 2004
  • In this study, foreign and domestic noise criteria on walls, floors, and water supply facilities were reviewed and the results are as follows : regulation can be divided two things, one is on thickness the other is sound insulation performance. Green Building regulation based on the law and this have sound classification systems. Since these regulations are not established in Korea. The noise regulation on water supply-drain facilities and domestic guideline on interior noise level is needed. Foreign regulations are stricter than those of ours. And those has sound classification system for the better acoustic condition of inhabitants'.

터빈 사이클의 보정 성능 계산을 위한 급수 유량의 검증 모델 (Verification Model of the Feedwater Flow for the Calculation of Corrective Performance of Turbine Cycle)

  • 김성근;양학진;이강희;최광희
    • 설비공학논문집
    • /
    • 제24권6호
    • /
    • pp.538-544
    • /
    • 2012
  • Analysis of thermal performance is required for the economic operation of turbine cycle of power plant. We developed corrective model of main feed water flow which is the most important parameter for the precise analysis of turbine cycle performance. Classification model for the identification of feed water flow measurement status was applied to increase the suitability of the corrective model. We used neural network and support vector machine to develop estimation model of main feed water flow with more generalization capability. The estimation model can be used practically to evaluate corrective performance of turbine cycle plant.

주급수 유량의 유효 모델(커널 회귀)에 대한 연구 (A Study of the Valid Model(Kernel Regression) of Main Feed-Water for Turbine Cycle)

  • 양학진;김성근
    • 한국산학기술학회논문지
    • /
    • 제20권12호
    • /
    • pp.663-670
    • /
    • 2019
  • 터빈 사이클 보정 열 성능 분석은 발전소의 현재 성능을 결정하고 향상된 경제성 운전을 위해 요구된다. 본 연구에서는 신뢰성있는 성능 분석을 위해서 산업 표준인 ASME(American Society of Mechanical Engineers) PTC(Performance Test Code)를 기본으로 성능 분석에서 우선적으로 중요하게 적용되는 주급수 유량을 대상으로 영역별 판정 알고리즘을 개발하고 각 영역별로 현재의 터빈 사이클 성능을 추정하는 알고리즘을 개발하였다. 추정 알고리즘은 측정 상태량의 상관 관계를 기반으로 영역별로 형상 분류를 제시하고, 이를 기반으로 커널 회귀 모델을 이용하여 학습된 추정 모델을 구성하였으며, 커널 회귀 모델링의 우수성을 검증하기 위하여 신경 회로망 모델의 학습 결과와 비교하였다. 주급수 유량의 형상 특성에 따른 분류 및 추정 모델은 터빈 사이클에서 정확한 보정 열 성능 분석을 제공함으로써 성능 분석의 신뢰도를 증가시킬 수 있었으며 다른 성능 결정 변수에 대한 학습 및 검증 모델로 사용될 수 있다.

한국 호소 상층부의 영양상태지수 제안 (Suggestion for Trophic State Index of Korean Lakes (Upper Layer))

  • 공동수;김범철
    • 한국물환경학회지
    • /
    • 제35권4호
    • /
    • pp.340-351
    • /
    • 2019
  • In this study, the relationship between trophic state indices was analyzed based on the monthly or weekly water quality data of 81 lakes (mostly man-made) in Korea between 2013-2017. Carlson's $TSI_C$ and Aizaki's $TSI_m$ were calculated using the summer (Jun.-Sep.) average data at the upper water layer. The previous Korean trophic state index ($TSI_{KO}$) and the newly suggested index ($TSI_{KON}$) was calculated using the annual average data at the whole layer and at the upper layer, respectively. While previous trophic state index (TSI) such as Carlson's TSI included logarithmic function, we devised newly Monod-type $TSI_{KON}$(Chl) that is 50 when half-saturation concentration of chlorophyll ${\alpha}$ ($Chl.{\alpha}$) measured by UNESCO-method is $10{\mu}gL^{-1}$. MMF-type $TSI_{KON}$(TP) was derived based on the relationship between TP and $Chl.{\alpha}$. A comprehensive $TSI_{KON}$ was decided as the larger one of the two $TSI_{KON}$ values. The range of previous TSI was usually 40-50 for the mesotrophic state, which seemed narrow to discriminate trophic characteristics of the class. The upper limits of $TSI_{KON}$ for oligotrophic, mesotrophic, and eutrophic state were set to 23, 50 and 75, respectively. Classification by $TSI_C$ and $TSI_m$ showed higher frequency of eutrophic class compared to $TSI_{KO}$ and $TSI_{KON}$. This means that the estimation by TSIs developed in foreign natural lakes can lead to distorted results in the classification of the trophic state of Korean lakes. This is due to the decrease of transparency by non-algal material and the reduction in phosphorus availability to algal growth, particularly in Monsoon period.

Fuyo-1 OPS 자료를 이용한 낙동강 하류지역의 환경계측 시고 (A Pilot Study on Environmental Understanding and Estimation of the Nak-Dong River Basin Using Fuyo-1 OPS Data)

  • 김천
    • 대한원격탐사학회지
    • /
    • 제12권2호
    • /
    • pp.169-198
    • /
    • 1996
  • 본 연구는 낙동강 하류지역의 지속가능한 개발과 환경보전을 위하여 위성탑재 Fuyo-1 OPS VNIR 주사자료에 의한 겨울철 환경계측을 시범·고찰하였다 따라서 그림자 효과가 강하게 발생하는 산림에 대해 방향성 분광반사특성과 식생지수를 중점분석하고 분광각대응분류를 통하여 겨울철 토지피복도를 산출하였다. 그리고 해·담수 분포도와 낙동강 하류의 수질오염도를 작성하기 위하여 가림기법, 최대우도추정분류기, 그리고 유색밀도편분기법을 응용하였다. 본 연구에서 획득된 결과를 요약하면 첫째로 양지사면의 분광반사치와 식생지수값 모두 음지사면보다 높다. 둘째로 위장반사현상이 일어나는 지역을 주제별 분류를 할 경우 분광각대응분류 산법이 유용하다 셋째로 겨울철 낮은 태양고도에도 해·담수분포도를 산출하는데 최대우도추정분류산법이 적합하다. 넷째로 근적외선밴드를 사용하여 가림·유색밀도편분기법에 의해 산출된 수질오염 도는 낙동강의 수질상태를 분석할 수 있다. 마지막으로 유색코드 정규식생지수 화상은 사면방위에 따른 임관밀도를 파악하는데 이용된다.

Object-oriented Information Extraction and Application in High-resolution Remote Sensing Image

  • WEI Wenxia;Ma Ainai;Chen Xunwan
    • 대한원격탐사학회:학술대회논문집
    • /
    • 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
    • /
    • pp.125-127
    • /
    • 2004
  • High-resolution satellite images offer abundance information of the earth surface for remote sensing applications. The information includes geometry, texture and attribute characteristic. The pixel-based image classification can't satisfy high-resolution satellite image's classification precision and produce large data redundancy. Object-oriented information extraction not only depends on spectrum character, but also use geometry and structure information. It can provide an accessible and truly revolutionary approach. Using Beijing Spot 5 high-resolution image and object-oriented classification with the eCognition software, we accomplish the cultures' precise classification. The test areas have five culture types including water, vegetation, road, building and bare lands. We use nearest neighbor classification and appraise the overall classification accuracy. The average of five species reaches 0.90. All of maximum is 1. The standard deviation is less than 0.11. The overall accuracy can reach $95.47\%.$ This method offers a new technology for high-resolution satellite images' available applications in remote sensing culture classification.

  • PDF

SHADOW EXTRACTION FROM ASTER IMAGE USING MIXED PIXEL ANALYSIS

  • Kikuchi, Yuki;Takeshi, Miyata;Masataka, Takagi
    • 대한원격탐사학회:학술대회논문집
    • /
    • 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
    • /
    • pp.727-731
    • /
    • 2003
  • ASTER image has some advantages for classification such as 15 spectral bands and 15m ${\sim}$ 90m spatial resolution. However, in the classification using general remote sensing image, shadow areas are often classified into water area. It is very difficult to divide shadow and water. Because reflectance characteristics of water is similar to characteristics of shadow. Many land cover items are consisted in one pixel which is 15m spatial resolution. Nowadays, very high resolution satellite image (IKONOS, Quick Bird) and Digital Surface Model (DSM) by air borne laser scanner can also be used. In this study, mixed pixel analysis of ASTER image has carried out using IKONOS image and DSM. For mixed pixel analysis, high accurated geometric correction was required. Image matching method was applied for generating GCP datasets. IKONOS image was rectified by affine transform. After that, one pixel in ASTER image should be compared with corresponded 15×15 pixel in IKONOS image. Then, training dataset were generated for mixed pixel analysis using visual interpretation of IKONOS image. Finally, classification will be carried out based on Linear Mixture Model. Shadow extraction might be succeeded by the classification. The extracted shadow area was validated using shadow image which generated from 1m${\sim}$2m spatial resolution DSM. The result showed 17.2% error was occurred in mixed pixel. It might be limitation of ASTER image for shadow extraction because of 8bit quantization data.

  • PDF