The impact of data normalization on 2D coordinate transformation using GRNN
The coordinate transformation has always been a hot topic in the field of geodesy. The artificial neural network (ANN) has been used as an alternative tool to determine the relationship between any two coordinate systems. Construction of an effective neural network depends on the network architectur...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Association of Surveyors of Slovenia (Zveza geodetov Slovenije)
2019-12-01
|
| Series: | Geodetski Vestnik |
| Subjects: | |
| Online Access: | http://www.geodetski-vestnik.com/63/4/gv63-4_cakir.pdf |
| _version_ | 1818757133706985472 |
|---|---|
| author | Leyla Cakir Berkant Konakoglu |
| author_facet | Leyla Cakir Berkant Konakoglu |
| author_sort | Leyla Cakir |
| collection | DOAJ |
| description | The coordinate transformation has always been a hot topic in the field of geodesy. The artificial neural network (ANN) has been used as an alternative tool to determine the relationship between any two coordinate systems. Construction of an effective neural network depends on the network architecture, learning parameters and normalization technique used. Finding the best data normalization technique is an important step when designing a neural network. This study investigated the performances of eight normalization techniques on two-dimensional (2D) coordinate transformation using a generalized regression neural network (GRNN). The methods examined included the maximize, min-max, median, median-median absolute deviation (median-MAD), mean-mean absolute deviation (mean-MAD), statistical column, tanh, and z-score. Comparisons revealed that the min-max, median-MAD, mean-MAD, tanh, and z-score techniques achieved superior results compared to the other normalization techniques studied. In addition, the GRNN was found to be an effective, feasible and practical tool for 2D coordinate transformation. |
| first_indexed | 2024-12-18T06:06:06Z |
| format | Article |
| id | doaj.art-964c07988fbf4d129aa7caa3042ce5f2 |
| institution | Directory Open Access Journal |
| issn | 0351-0271 1581-1328 |
| language | English |
| last_indexed | 2024-12-18T06:06:06Z |
| publishDate | 2019-12-01 |
| publisher | Association of Surveyors of Slovenia (Zveza geodetov Slovenije) |
| record_format | Article |
| series | Geodetski Vestnik |
| spelling | doaj.art-964c07988fbf4d129aa7caa3042ce5f22022-12-21T21:18:32ZengAssociation of Surveyors of Slovenia (Zveza geodetov Slovenije)Geodetski Vestnik0351-02711581-13282019-12-01630454155310.15292/geodetski-vestnik.2019.04.541-553The impact of data normalization on 2D coordinate transformation using GRNNLeyla Cakir0Berkant Konakoglu1Karadeniz Technical University, Faculty of Engineering, Department of Geomatics Engineering, Kanuni Campus TR-61080 Trabzon, TurkeyeKaradeniz Technical University, Faculty of Engineering, Department of Geomatics Engineering, Kanuni Campus TR-61080 Trabzon, TurkeyeThe coordinate transformation has always been a hot topic in the field of geodesy. The artificial neural network (ANN) has been used as an alternative tool to determine the relationship between any two coordinate systems. Construction of an effective neural network depends on the network architecture, learning parameters and normalization technique used. Finding the best data normalization technique is an important step when designing a neural network. This study investigated the performances of eight normalization techniques on two-dimensional (2D) coordinate transformation using a generalized regression neural network (GRNN). The methods examined included the maximize, min-max, median, median-median absolute deviation (median-MAD), mean-mean absolute deviation (mean-MAD), statistical column, tanh, and z-score. Comparisons revealed that the min-max, median-MAD, mean-MAD, tanh, and z-score techniques achieved superior results compared to the other normalization techniques studied. In addition, the GRNN was found to be an effective, feasible and practical tool for 2D coordinate transformation.http://www.geodetski-vestnik.com/63/4/gv63-4_cakir.pdfartificial neural networkgeneralized regression neural networkcoordinate transformationnormalization technique |
| spellingShingle | Leyla Cakir Berkant Konakoglu The impact of data normalization on 2D coordinate transformation using GRNN Geodetski Vestnik artificial neural network generalized regression neural network coordinate transformation normalization technique |
| title | The impact of data normalization on 2D coordinate transformation using GRNN |
| title_full | The impact of data normalization on 2D coordinate transformation using GRNN |
| title_fullStr | The impact of data normalization on 2D coordinate transformation using GRNN |
| title_full_unstemmed | The impact of data normalization on 2D coordinate transformation using GRNN |
| title_short | The impact of data normalization on 2D coordinate transformation using GRNN |
| title_sort | impact of data normalization on 2d coordinate transformation using grnn |
| topic | artificial neural network generalized regression neural network coordinate transformation normalization technique |
| url | http://www.geodetski-vestnik.com/63/4/gv63-4_cakir.pdf |
| work_keys_str_mv | AT leylacakir theimpactofdatanormalizationon2dcoordinatetransformationusinggrnn AT berkantkonakoglu theimpactofdatanormalizationon2dcoordinatetransformationusinggrnn AT leylacakir impactofdatanormalizationon2dcoordinatetransformationusinggrnn AT berkantkonakoglu impactofdatanormalizationon2dcoordinatetransformationusinggrnn |