Optimizing neural network algorithms for submerged membrane bioreactor: A comparative study of OVAT and RSM hyperparameter optimization techniques
Hyperparameter tuning is an important process to maximize the performance of any neural network model. This present study proposed the factorial design of experiment for screening and response surface methodology to optimize the hyperparameter of two artificial neural network algorithms. Feed-forwar...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IWA Publishing
2024-04-01
|
| Series: | Water Science and Technology |
| Subjects: | |
| Online Access: | http://wst.iwaponline.com/content/89/7/1701 |
| _version_ | 1797200756170817536 |
|---|---|
| author | Syahira Ibrahim Norhaliza Abdul Wahab |
| author_facet | Syahira Ibrahim Norhaliza Abdul Wahab |
| author_sort | Syahira Ibrahim |
| collection | DOAJ |
| description | Hyperparameter tuning is an important process to maximize the performance of any neural network model. This present study proposed the factorial design of experiment for screening and response surface methodology to optimize the hyperparameter of two artificial neural network algorithms. Feed-forward neural network (FFNN) and radial basis function neural network (RBFNN) are applied to predict the permeate flux of palm oil mill effluent. Permeate pump and transmembrane pressure of the submerge membrane bioreactor system are the input variables. Six hyperparameters of the FFNN model including four numerical factors (neuron numbers, learning rate, momentum, and epoch numbers) and two categorical factors (training and activation function) are used in hyperparameter optimization. RBFNN includes two numerical factors such as a number of neurons and spreads. The conventional method (one-variable-at-a-time) is compared in terms of optimization processing time and the accuracy of the model. The result indicates that the optimal hyperparameters obtained by the proposed approach produce good accuracy with a smaller generalization error. The simulation results show an improvement of more than 65% of training performance, with less repetition and processing time. This proposed methodology can be utilized for any type of neural network application to find the optimum levels of different parameters.
HIGHLIGHTS
Membrane fouling in filtration is a complex process, and understanding the behaviour of the dynamic is crucial.;
This is the study of artificial neural network (ANN)-based dynamic model and optimization for a submerged membrane bioreactor (SMBR) filtration process.;
The ANN structure was able to model the dynamic behaviour of the filtration process under normal conditions.;
The optimization method improves the ANN structure for SMBR filtration model development.; |
| first_indexed | 2024-04-24T07:36:42Z |
| format | Article |
| id | doaj.art-c8bb7ab8ab2345c4b2debbad56d53d08 |
| institution | Directory Open Access Journal |
| issn | 0273-1223 1996-9732 |
| language | English |
| last_indexed | 2024-04-24T07:36:42Z |
| publishDate | 2024-04-01 |
| publisher | IWA Publishing |
| record_format | Article |
| series | Water Science and Technology |
| spelling | doaj.art-c8bb7ab8ab2345c4b2debbad56d53d082024-04-20T06:08:01ZengIWA PublishingWater Science and Technology0273-12231996-97322024-04-018971701172410.2166/wst.2024.099099Optimizing neural network algorithms for submerged membrane bioreactor: A comparative study of OVAT and RSM hyperparameter optimization techniquesSyahira Ibrahim0Norhaliza Abdul Wahab1 Faculty of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru 81310, Malaysia Faculty of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru 81310, Malaysia Hyperparameter tuning is an important process to maximize the performance of any neural network model. This present study proposed the factorial design of experiment for screening and response surface methodology to optimize the hyperparameter of two artificial neural network algorithms. Feed-forward neural network (FFNN) and radial basis function neural network (RBFNN) are applied to predict the permeate flux of palm oil mill effluent. Permeate pump and transmembrane pressure of the submerge membrane bioreactor system are the input variables. Six hyperparameters of the FFNN model including four numerical factors (neuron numbers, learning rate, momentum, and epoch numbers) and two categorical factors (training and activation function) are used in hyperparameter optimization. RBFNN includes two numerical factors such as a number of neurons and spreads. The conventional method (one-variable-at-a-time) is compared in terms of optimization processing time and the accuracy of the model. The result indicates that the optimal hyperparameters obtained by the proposed approach produce good accuracy with a smaller generalization error. The simulation results show an improvement of more than 65% of training performance, with less repetition and processing time. This proposed methodology can be utilized for any type of neural network application to find the optimum levels of different parameters. HIGHLIGHTS Membrane fouling in filtration is a complex process, and understanding the behaviour of the dynamic is crucial.; This is the study of artificial neural network (ANN)-based dynamic model and optimization for a submerged membrane bioreactor (SMBR) filtration process.; The ANN structure was able to model the dynamic behaviour of the filtration process under normal conditions.; The optimization method improves the ANN structure for SMBR filtration model development.;http://wst.iwaponline.com/content/89/7/1701computational timedoe implementationneural networkoptimization techniquessubmerged membrane bioreactor data |
| spellingShingle | Syahira Ibrahim Norhaliza Abdul Wahab Optimizing neural network algorithms for submerged membrane bioreactor: A comparative study of OVAT and RSM hyperparameter optimization techniques Water Science and Technology computational time doe implementation neural network optimization techniques submerged membrane bioreactor data |
| title | Optimizing neural network algorithms for submerged membrane bioreactor: A comparative study of OVAT and RSM hyperparameter optimization techniques |
| title_full | Optimizing neural network algorithms for submerged membrane bioreactor: A comparative study of OVAT and RSM hyperparameter optimization techniques |
| title_fullStr | Optimizing neural network algorithms for submerged membrane bioreactor: A comparative study of OVAT and RSM hyperparameter optimization techniques |
| title_full_unstemmed | Optimizing neural network algorithms for submerged membrane bioreactor: A comparative study of OVAT and RSM hyperparameter optimization techniques |
| title_short | Optimizing neural network algorithms for submerged membrane bioreactor: A comparative study of OVAT and RSM hyperparameter optimization techniques |
| title_sort | optimizing neural network algorithms for submerged membrane bioreactor a comparative study of ovat and rsm hyperparameter optimization techniques |
| topic | computational time doe implementation neural network optimization techniques submerged membrane bioreactor data |
| url | http://wst.iwaponline.com/content/89/7/1701 |
| work_keys_str_mv | AT syahiraibrahim optimizingneuralnetworkalgorithmsforsubmergedmembranebioreactoracomparativestudyofovatandrsmhyperparameteroptimizationtechniques AT norhalizaabdulwahab optimizingneuralnetworkalgorithmsforsubmergedmembranebioreactoracomparativestudyofovatandrsmhyperparameteroptimizationtechniques |