首页--天文学、地球科学论文--测绘学论文--大地测量学论文--椭球面大地测量(高等测量)论文

人工智能方法在大地测量坐标转换中的应用研究

Curriculum Vitae第7-9页
中文摘要第9-12页
ABSTRACT第12-15页
Chapter 1: Introduction第21-33页
    1:1 Background to the Study第21-26页
    1:2 Statement of the Research Problem第26-29页
    1:3 Aims and Objectives of study第29页
        1.3.1 Aims of the Research第29页
        1.3.2 Objectives of the Research第29页
    1:4 Research Questions第29-30页
    1:5 Significance of the Research第30-31页
    1:6 Scope of the Research第31-32页
    1:7 Outline of the Thesis Structure第32-33页
Chapter 2: Literature Review第33-104页
    2:1 Introduction第33页
    2:2 Coordinate Operation第33-76页
        2.2.1 Coordinate Conversion第34-39页
        2.2.2 Reverse Conversion Methods applied in Ghana第39-51页
        2.2.3 Coordinate Transformation Models Applied in Ghana第51-76页
    2:3 Artificial Intelligence第76-104页
        2.3.1 Concept of Artificial Neural Network第77-104页
Chapter 3: Capability of Artificial Neural Network for Forward Conversion of Geodetic Coordinates (φ,λ,h) to Cartesian Coordinates (x, y, z)第104-152页
    3:1 Summary第104-105页
    3:2 Introduction第105-109页
    3:3 Artificial Neural Network Methods第109-119页
        3.3.1 Data and Selection of Input Parameters第111-112页
        3.3.2 Data Normalization第112-113页
        3.3.3 ANN Architecture第113页
        3.3.4 Network Training第113-115页
        3.3.5 Backpropagation Artificial Neural Network第115-117页
        3.3.6 Radial Basis Function Neural Network第117-119页
    3:4 Multiple Linear Regression第119-120页
    3:5 Assessment of Model Quality第120-121页
    3:6 Results and Discussion第121-150页
        3.6.1 ANN Models Developed第121-135页
        3.6.2 Residual Analysis第135-145页
        3.6.3 Dimensioned Error Statistic第145-146页
        3.6.4 Model Efficiency Based Statistics第146-147页
        3.6.5 Comparing ANN and Multiple Linear Regression第147-150页
    3:7 Conclusions第150-151页
    3:8 Recommendations第151-152页
Chapter 4: Novel Approach to Improve Geocentric Translation Model Performance using Artificial Neural Network Technology第152-179页
    4:1 Summary第152页
    4:2 Introduction第152-156页
    4:3 Study Area and Data Source第156-158页
    4:4 Methods第158-164页
        4.4.1 Geocentric Translation Model第158-159页
        4.4.2 Artificial Neural Network第159页
        4.4.3 Proposed Approach第159-164页
    4:5 Accuracy Analysis第164-165页
    4:6 Results and Interpretation第165-176页
        4.6.1 Geocentric Translation Model第165-170页
        4.6.2 Artificial Neural Network-Error Compensation Model (ANN-ECM)第170-173页
        4.6.3 Comparison of ANN-ECM and GTM第173-176页
    4:7 Concluding remarks第176-178页
    4:8 Recommendation第178-179页
Chapter 5: Coordinate Transformation by Hybrid Approach of Total Least Squares and Artificial Neural Network for Geographic Information System Applications: A Case Study第179-217页
    5:1 Summary第179-180页
    5:2 Introduction第180-183页
    5:3 Ghana Geodetic System第183-186页
    5:4 Data Source and Applied Methodology第186-198页
        5.4.1 Data第186-187页
        5.4.2 Data Conversion第187页
        5.4.3 Coordinate Transformation using Total Least Squares第187-190页
        5.4.4 Coordinate Transformation using Radial Basis Function Neural Network (RBFNN)第190-193页
        5.4.5 Proposed Hybrid Model第193-198页
    5:5 Performance Criteria第198-199页
    5:6 Numerical Application第199-214页
        5.6.1 Test Residual Analysis第199-203页
        5.6.2 Model Performance Analysis第203-207页
        5.6.3 Model Selection Criterion第207-208页
        5.6.4 Coordinate transformation using entire dataset第208-214页
    5:7 Conclusion第214-215页
    5:8 Recommendation第215-217页
Chapter 6: 2D Coordinate Transformation Based on Artificial Intelligent Models for Cadastral Applications in Ghana第217-267页
    6:1 Summary第217-218页
    6:2 Introduction第218-224页
    6:3 Study Area and Data Source第224-226页
    6:4 Artificial Intelligent Methods第226-244页
        6.4.1 Coordinate Transformation using Back propagation neural network model第226-229页
        6.4.2 Coordinate Transformation using Radial basis function neural network model第229-232页
        6.4.3 Coordinate Transformation using Support Vector Machine model第232-234页
        6.4.4 Coordinate Transformation using Least Square-Support Vector Machine model第234-237页
        6.4.5 Coordinate Transformation using Multivariate Adaptive Regression Spline model第237-238页
        6.4.6 Coordinate Transformation using Extreme Learning Machine Model第238-241页
        6.4.7 2D Conformal Transformation Model第241-242页
        6.4.8 2D Affine Transformation Model第242页
        6.4.9 Model Building第242-244页
    6:5 Model Adequacy Assessment第244-245页
    6:6 Results and Discussion第245-264页
        6.6.1 Coordinate transformation from Leigon datum to Accra datum第245-264页
    6:7 Conclusions第264-266页
    6:8 Recommendations第266-267页
Chapter 7: General Conclusions, Recommendations and Innovations of the Entire Study第267-274页
    7:1 Study Conclusions第267-271页
    7:2 Study recommendations第271-272页
    7:3 Innovations of the entire study第272-274页
Acknowledgement第274-276页
Reference第276-306页

论文共306页,点击 下载论文
上一篇:家庭能源消耗与健康响--以阿比让为例
下一篇:华南黔桂地区铝土矿沉积—成矿作用