인공신경망의 알고리즘에 의한 토지적합성분석 = Analysis on the Land Suitability Using Algorithms of Artificial Neural Network

다국어 초록 (Multilingual Abstract)

Current GSIS(Geo-Spatial Information System) is mostly dependent on the method of spatial overlay using vector or raster map for analysis of land suitability. This conventional method of map making modelling, however, couldn't indicate the reasonable solution for classifying the data and deciding relative weight, so, it was inevitable that the result was determined by knowledge or intention of subjective view of analyst. There are few possibility to improve these situation in some day. As following the rule made by subjective decision of analyst, most analysis part couldn't be supported by firmly theoretical basis.
This study is tried to organic combination in implementing the suitability analysis of urban landuse between GSIS and ANN(Artificial Neural Network). ANN has merits that can decide rationally connectivity weights among neural network nodes through procedure of learning. It is possible to replace the weight among factors by the connectivity weights of neural network. Therefore, as this point of view it is to enough the possibility of ANN application in a GSIS. This study is composed of two kinds of neural networks to be executed. First neural network was used in the suitability analysis of landuse and second one was oriented to analyze of optimum landuse pattern. These neural networks were learned with back-propagation algorithm using the steepest gradient and genetic algorithm which are coded by ^(++). Also, These neural networks used sigmoid function as a active function. The results are given on chapter 4. Analysis results show landuse suitability map and optimum landuse pattern of Naju city consisted of residential, commercial, industrial and green zone in present zoning system. Each result map was written by the grid format of Arc/Info. Also, suitability area presented in the suitability map and optimum landuse pattern show distribution pattern consistent with theoretical concept of urban landuse plan in aspect of location and space structure.

목차 (Table of Contents)

• 목차 = ⅰ
• 표목차 = ⅲ
• 그림목차 = ⅳ
• ABSTRACT = ⅵ
• 제1장 서론 = 1
• 1.1 연구 배경 및 목적 = 1
• 1.2 연구 연혁 = 2
• 1.3 연구 범위 및 방법 = 6
• 제2장 토지이용계획과 지형공간정보분석 = 8
• 2.1 토지이용계획 = 8
• 2.2 적합성 분석 = 12
• 2.3 지형공간정보체계 공간분석 = 18
• 제3장 인공신경망과 유전자 알고리즘 = 27
• 3.1 인공신경망 = 27
• 3.2 역전파 관측학습 알고리즘 = 31
• 3.3 유전자 알고리즘 = 35
• 제4장 분석인자 및 관측학자료 선정 = 42
• 4.1 대상지역의 현황 및 자료구축 = 42
• 4.2 토지이용 적합성분석 인자 = 44
• 4.3 토지이용 적합성 분석모형 = 55
• 4.4 인공신경망 관측학습자료 선정 = 64
• 제5장 적용 및 고찰 = 70
• 5.1 인공신경망의 구성 = 70
• 5.2 유전자 알고리즘의 적용 = 71
• 5.3 역전파와 유전자 알고리즘의 적용 및 관측학습 = 74
• 5.4 토지이용별 적합성분석 = 78
• 5.5 최적토지이용 형태분석 = 95
• 제6장 결론 = 99
• 참고문헌 = 101
• 부록 = 105
• 부록1. 토양특성 분류표 = 105
• 부록2. 유전자 관측학습 알고리즘 = 110