LEAST SQUARES SUPPORT VECTOR MACHINE MODEL FOR COORDINATE TRANSFORMATION

• Published in: Geodesy and cartography (Vilnius) Vol. 45; no. 5; pp. 16 - 27
• Main Authors: Ziggah, Yao Yevenyo, Hu, Youjina, Issaka, Yakubu, Laari, Prosper Basommi
• Format: Journal Article
• Language: English
• Published: Vilnius Vilnius Gediminas Technical University 01-04-2019
• Subjects: 2D affine model; 2D Conformal model; Artificial neural networks; Back propagation; Cadastral mapping; Coordinate transformation; Coordinate transformations; Least squares; Least squares support vector machine; Neural networks; Radial basis function; Soft computing; Statistical methods; Support vector machine; Support vector machines; Surveying; Transformations (mathematics)
• ISSN: 2029-6991; 2029-7009
• DOI: 10.3846/gac.2019.6053

In coordinate transformation, the main purpose is to provide a mathematical relationship between coordinates related to different geodetic reference frames. This gives the geospatial professionals the opportunity to link different datums together. Review of previous studies indicates that empirical and soft computing models have been proposed in recent times for coordinate transformation. The main aim of this study is to present the applicability and performance of Least Squares Support Vector Machine (LS-SVM) which is an extension of the Support Vector Machine (SVM) for coordinate transformation. For comparison purpose, the SVM and the widely used Backpropagation Neural Network (BPNN), Radial Basis Function Neural Network (RBFNN), 2D conformal and affine methods were also employed. To assess how well the transformation results fit the observed data, the root mean square of the residual horizontal distances and standard deviation were used. From the results obtained, the LS-SVM and RBFNN had comparable results and were better than the other methods. The overall statistical findings produced by LS-SVM met the accuracy requirement for cadastral surveying applications in Ghana. To this end, the proposed LS-SVM is known to possess promising predictive capabilities and could efficiently be used as a supplementary technique for coordinate transformation.