Multivariate Statistical Analysis for Training Process Optimization in Neural Networks-Based Forecasting Models
Data forecasting is very important for electrical analysis development, transport dimensionality, marketing strategies, etc. Hence, low error levels are required. However, in some cases data have dissimilar behaviors that can vary depending on such exogenous variables as the type of day, weather con...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/8/3552 |
| id |
doaj-3c7b8aa4aaa4492c945380bdba5de7a2 |
|---|---|
| record_format |
Article |
| spelling |
doaj-3c7b8aa4aaa4492c945380bdba5de7a22021-04-15T23:04:48ZengMDPI AGApplied Sciences2076-34172021-04-01113552355210.3390/app11083552Multivariate Statistical Analysis for Training Process Optimization in Neural Networks-Based Forecasting ModelsJamer Jimenez0Loraine Navarro1Christian G. Quintero M.2Mauricio Pardo3Department of Electrical and Electronics Engineering, Universidad del Norte, Barranquilla 081007, ColombiaDepartment of Electrical and Electronics Engineering, Universidad del Norte, Barranquilla 081007, ColombiaDepartment of Electrical and Electronics Engineering, Universidad del Norte, Barranquilla 081007, ColombiaDepartment of Electrical and Electronics Engineering, Universidad del Norte, Barranquilla 081007, ColombiaData forecasting is very important for electrical analysis development, transport dimensionality, marketing strategies, etc. Hence, low error levels are required. However, in some cases data have dissimilar behaviors that can vary depending on such exogenous variables as the type of day, weather conditions, and geographical area, among others. Commonly, computational intelligence techniques (e.g., artificial neural networks) are used due to their generalization capabilities. In spite of the above, they do not have a unique way to reach optimal performance. For this reason, it is necessary to analyze the data’s behavior and their statistical features in order to identify those significant factors in the training process to guarantee a better performance. In this paper is proposed an experimental method for identifying those significant factors in the forecasting model for time series data and measure their effects on the Akaike information criterion (AIC) and the Mean Absolute Percentage Error (MAPE). Additionally, we seek to establish optimal parameters for the proper selection of the artificial neural network model.https://www.mdpi.com/2076-3417/11/8/3552neural networks designparameter optimizationmultivariate statistical analysis |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Jamer Jimenez Loraine Navarro Christian G. Quintero M. Mauricio Pardo |
| spellingShingle |
Jamer Jimenez Loraine Navarro Christian G. Quintero M. Mauricio Pardo Multivariate Statistical Analysis for Training Process Optimization in Neural Networks-Based Forecasting Models Applied Sciences neural networks design parameter optimization multivariate statistical analysis |
| author_facet |
Jamer Jimenez Loraine Navarro Christian G. Quintero M. Mauricio Pardo |
| author_sort |
Jamer Jimenez |
| title |
Multivariate Statistical Analysis for Training Process Optimization in Neural Networks-Based Forecasting Models |
| title_short |
Multivariate Statistical Analysis for Training Process Optimization in Neural Networks-Based Forecasting Models |
| title_full |
Multivariate Statistical Analysis for Training Process Optimization in Neural Networks-Based Forecasting Models |
| title_fullStr |
Multivariate Statistical Analysis for Training Process Optimization in Neural Networks-Based Forecasting Models |
| title_full_unstemmed |
Multivariate Statistical Analysis for Training Process Optimization in Neural Networks-Based Forecasting Models |
| title_sort |
multivariate statistical analysis for training process optimization in neural networks-based forecasting models |
| publisher |
MDPI AG |
| series |
Applied Sciences |
| issn |
2076-3417 |
| publishDate |
2021-04-01 |
| description |
Data forecasting is very important for electrical analysis development, transport dimensionality, marketing strategies, etc. Hence, low error levels are required. However, in some cases data have dissimilar behaviors that can vary depending on such exogenous variables as the type of day, weather conditions, and geographical area, among others. Commonly, computational intelligence techniques (e.g., artificial neural networks) are used due to their generalization capabilities. In spite of the above, they do not have a unique way to reach optimal performance. For this reason, it is necessary to analyze the data’s behavior and their statistical features in order to identify those significant factors in the training process to guarantee a better performance. In this paper is proposed an experimental method for identifying those significant factors in the forecasting model for time series data and measure their effects on the Akaike information criterion (AIC) and the Mean Absolute Percentage Error (MAPE). Additionally, we seek to establish optimal parameters for the proper selection of the artificial neural network model. |
| topic |
neural networks design parameter optimization multivariate statistical analysis |
| url |
https://www.mdpi.com/2076-3417/11/8/3552 |
| work_keys_str_mv |
AT jamerjimenez multivariatestatisticalanalysisfortrainingprocessoptimizationinneuralnetworksbasedforecastingmodels AT lorainenavarro multivariatestatisticalanalysisfortrainingprocessoptimizationinneuralnetworksbasedforecastingmodels AT christiangquinterom multivariatestatisticalanalysisfortrainingprocessoptimizationinneuralnetworksbasedforecastingmodels AT mauriciopardo multivariatestatisticalanalysisfortrainingprocessoptimizationinneuralnetworksbasedforecastingmodels |
| _version_ |
1721525827277946880 |