Enhanced Performance of Dynamic Neural Network Model using Wavelet Activation Functions
Both static and dynamic adaptive neural networks have been broadly utilized in mathematical modeling and numerical analysis. This study aimed to enhance the accomplishment of Dynamic Neural Networks (DNN) models by applying wavelet functions as activation functions. Research that models and forecast...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Udayana University, Institute for Research and Community Services
2023-12-01
|
| Series: | Lontar Komputer |
| Online Access: | https://ojs.unud.ac.id/index.php/lontar/article/view/99945 |
| _version_ | 1797372362473078784 |
|---|---|
| author | Syamsul Bahri Lailia Awalushaumi Nurul Fitriyani |
| author_facet | Syamsul Bahri Lailia Awalushaumi Nurul Fitriyani |
| author_sort | Syamsul Bahri |
| collection | DOAJ |
| description | Both static and dynamic adaptive neural networks have been broadly utilized in mathematical modeling and numerical analysis. This study aimed to enhance the accomplishment of Dynamic Neural Networks (DNN) models by applying wavelet functions as activation functions. Research that models and forecasts the intensity of solar radiation in Mataram City shows that combining B-Spline and Morlet wavelet activation functions can significantly increase the DNN model performance. Wavelet-DNN (W-DNN) was modeled with an identical architecture; the best showed the increase in the model achievement (0.7596 points for in-sample and 0.8502 points for out-sample data). Mainly for out-sample data, the model's performance using the W-DNN+ intervention model increased by 4.0492 points. |
| first_indexed | 2024-03-08T18:33:39Z |
| format | Article |
| id | doaj.art-6927949e800646e597130794984e158d |
| institution | Directory Open Access Journal |
| issn | 2088-1541 2541-5832 |
| language | English |
| last_indexed | 2024-03-08T18:33:39Z |
| publishDate | 2023-12-01 |
| publisher | Udayana University, Institute for Research and Community Services |
| record_format | Article |
| series | Lontar Komputer |
| spelling | doaj.art-6927949e800646e597130794984e158d2023-12-29T16:03:04ZengUdayana University, Institute for Research and Community ServicesLontar Komputer2088-15412541-58322023-12-0114315016010.24843/LKJITI.2023.v14.i03.p0399945Enhanced Performance of Dynamic Neural Network Model using Wavelet Activation FunctionsSyamsul Bahri0Lailia Awalushaumi1Nurul Fitriyani2Universitas MataramDept. of Mathematics, Faculty of Mathematics and Natural Sciences, University of MataramDept. of Statistics, Faculty of Mathematics and Natural Sciences, University of MataramBoth static and dynamic adaptive neural networks have been broadly utilized in mathematical modeling and numerical analysis. This study aimed to enhance the accomplishment of Dynamic Neural Networks (DNN) models by applying wavelet functions as activation functions. Research that models and forecasts the intensity of solar radiation in Mataram City shows that combining B-Spline and Morlet wavelet activation functions can significantly increase the DNN model performance. Wavelet-DNN (W-DNN) was modeled with an identical architecture; the best showed the increase in the model achievement (0.7596 points for in-sample and 0.8502 points for out-sample data). Mainly for out-sample data, the model's performance using the W-DNN+ intervention model increased by 4.0492 points.https://ojs.unud.ac.id/index.php/lontar/article/view/99945 |
| spellingShingle | Syamsul Bahri Lailia Awalushaumi Nurul Fitriyani Enhanced Performance of Dynamic Neural Network Model using Wavelet Activation Functions Lontar Komputer |
| title | Enhanced Performance of Dynamic Neural Network Model using Wavelet Activation Functions |
| title_full | Enhanced Performance of Dynamic Neural Network Model using Wavelet Activation Functions |
| title_fullStr | Enhanced Performance of Dynamic Neural Network Model using Wavelet Activation Functions |
| title_full_unstemmed | Enhanced Performance of Dynamic Neural Network Model using Wavelet Activation Functions |
| title_short | Enhanced Performance of Dynamic Neural Network Model using Wavelet Activation Functions |
| title_sort | enhanced performance of dynamic neural network model using wavelet activation functions |
| url | https://ojs.unud.ac.id/index.php/lontar/article/view/99945 |
| work_keys_str_mv | AT syamsulbahri enhancedperformanceofdynamicneuralnetworkmodelusingwaveletactivationfunctions AT lailiaawalushaumi enhancedperformanceofdynamicneuralnetworkmodelusingwaveletactivationfunctions AT nurulfitriyani enhancedperformanceofdynamicneuralnetworkmodelusingwaveletactivationfunctions |