Cite Article

Improving the Neural Network Testing Performance by Transforming the Normalized Data Nonlinearly for Trip Distribution Modelling

Choose citation format

BibTeX

@article{IJASEIT2130,
   author = {Gusri Yaldi},
   title = {Improving the Neural Network Testing Performance by Transforming the Normalized Data Nonlinearly for Trip Distribution Modelling},
   journal = {International Journal on Advanced Science, Engineering and Information Technology},
   volume = {7},
   number = {4},
   year = {2017},
   pages = {1395--1402},
   keywords = {Artificial Neural Networks; Data Transformation; Sigmoid Transfer function; Generalization Ability.},
   abstract = {Previous studies have suggested that the Artificial Neural Network (NN) trip distribution models were unable to calibrate and generalize work trip numbers with the same level accuracy as the Doubly-Constrained Gravity models (DGCM). This study presents some new NN model forms aimed at overcoming these problems trained by using the Levenberg-Marquardt algorithm. A further modification was applied to the model, namely transforming the input data nonlinearly by using logistic functions (Sigmoid) in order to improve the testing/generalization of NN models. This resulted in better performance of NN models, where the average Root Mean Square Error (RMSE) is statistically lower than the DCGM indicating the NN models could have higher generalization ability than DCGM.},
   issn = {2088-5334},
   publisher = {INSIGHT - Indonesian Society for Knowledge and Human Development},
   url = {http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=2130},
   doi = {10.18517/ijaseit.7.4.2130}
}

EndNote

%A Yaldi, Gusri
%D 2017
%T Improving the Neural Network Testing Performance by Transforming the Normalized Data Nonlinearly for Trip Distribution Modelling
%B 2017
%9 Artificial Neural Networks; Data Transformation; Sigmoid Transfer function; Generalization Ability.
%! Improving the Neural Network Testing Performance by Transforming the Normalized Data Nonlinearly for Trip Distribution Modelling
%K Artificial Neural Networks; Data Transformation; Sigmoid Transfer function; Generalization Ability.
%X Previous studies have suggested that the Artificial Neural Network (NN) trip distribution models were unable to calibrate and generalize work trip numbers with the same level accuracy as the Doubly-Constrained Gravity models (DGCM). This study presents some new NN model forms aimed at overcoming these problems trained by using the Levenberg-Marquardt algorithm. A further modification was applied to the model, namely transforming the input data nonlinearly by using logistic functions (Sigmoid) in order to improve the testing/generalization of NN models. This resulted in better performance of NN models, where the average Root Mean Square Error (RMSE) is statistically lower than the DCGM indicating the NN models could have higher generalization ability than DCGM.
%U http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=2130
%R doi:10.18517/ijaseit.7.4.2130
%J International Journal on Advanced Science, Engineering and Information Technology
%V 7
%N 4
%@ 2088-5334

IEEE

Gusri Yaldi,"Improving the Neural Network Testing Performance by Transforming the Normalized Data Nonlinearly for Trip Distribution Modelling," International Journal on Advanced Science, Engineering and Information Technology, vol. 7, no. 4, pp. 1395-1402, 2017. [Online]. Available: http://dx.doi.org/10.18517/ijaseit.7.4.2130.

RefMan/ProCite (RIS)

TY  - JOUR
AU  - Yaldi, Gusri
PY  - 2017
TI  - Improving the Neural Network Testing Performance by Transforming the Normalized Data Nonlinearly for Trip Distribution Modelling
JF  - International Journal on Advanced Science, Engineering and Information Technology; Vol. 7 (2017) No. 4
Y2  - 2017
SP  - 1395
EP  - 1402
SN  - 2088-5334
PB  - INSIGHT - Indonesian Society for Knowledge and Human Development
KW  - Artificial Neural Networks; Data Transformation; Sigmoid Transfer function; Generalization Ability.
N2  - Previous studies have suggested that the Artificial Neural Network (NN) trip distribution models were unable to calibrate and generalize work trip numbers with the same level accuracy as the Doubly-Constrained Gravity models (DGCM). This study presents some new NN model forms aimed at overcoming these problems trained by using the Levenberg-Marquardt algorithm. A further modification was applied to the model, namely transforming the input data nonlinearly by using logistic functions (Sigmoid) in order to improve the testing/generalization of NN models. This resulted in better performance of NN models, where the average Root Mean Square Error (RMSE) is statistically lower than the DCGM indicating the NN models could have higher generalization ability than DCGM.
UR  - http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=2130
DO  - 10.18517/ijaseit.7.4.2130

RefWorks

RT Journal Article
ID 2130
A1 Yaldi, Gusri
T1 Improving the Neural Network Testing Performance by Transforming the Normalized Data Nonlinearly for Trip Distribution Modelling
JF International Journal on Advanced Science, Engineering and Information Technology
VO 7
IS 4
YR 2017
SP 1395
OP 1402
SN 2088-5334
PB INSIGHT - Indonesian Society for Knowledge and Human Development
K1 Artificial Neural Networks; Data Transformation; Sigmoid Transfer function; Generalization Ability.
AB Previous studies have suggested that the Artificial Neural Network (NN) trip distribution models were unable to calibrate and generalize work trip numbers with the same level accuracy as the Doubly-Constrained Gravity models (DGCM). This study presents some new NN model forms aimed at overcoming these problems trained by using the Levenberg-Marquardt algorithm. A further modification was applied to the model, namely transforming the input data nonlinearly by using logistic functions (Sigmoid) in order to improve the testing/generalization of NN models. This resulted in better performance of NN models, where the average Root Mean Square Error (RMSE) is statistically lower than the DCGM indicating the NN models could have higher generalization ability than DCGM.
LK http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=2130
DO  - 10.18517/ijaseit.7.4.2130