Hyperparameter optimization is an important stage in modeling using machine learning, especially using deep learning algorithm, in which there are many combinations of parameters that will be used to produce a high-accuracy model. There are various methods for hyperparameter optimization of a model architecture, ranging from simple methods, namely trial error, to the most advanced and complex method, such as genetic algorithms. This paper will explain the hyperparameter optimization using the Grid Search Cross Validation (GSVC) method which is relatively simple but quite efficient in calculation time and produces an acceptable model accuracy. The hyperparameter to be optimized are optimizer and activation function. The options for optimizer are Adam, Adamax, Nadam, Stochastic Gradient Descent (SGD), and Root Mean Squared Propagation (RMSProp). The options for activation functions are TanH, Sigmoid, Elu and Relu. The options for optimizer and activation function are combined and selected using GSCV to provide the best performance at a given network architecture. The GSCV method will be used to optimize a model for aerodynamic coefficient of an amphibious aircraft (N219A) based on test data in wind tunnels, i.e. namely CL (coefficient of lift), CD (coefficient of drag) and CM25 (coefficient of bending moment). The best combination of hyperparameters for the aerodynamic coefficient model is (Adam & Sigmoid) for CL, (Adam & Elu) for CD and (Adamax & Elu) for CM25. The results of validation using testing data produce the following RMSE (Root Mean Square Error) and R2 (R-Squared) i.e. (0.0137 & 0.9949) for CL; (0.0113 & 0.9969) for CD and (0.02096 & 0.9984) for CM25 show that the error of the prediction in CL, CD and CM25 is acceptable and the relationship between independent and dependent variables are quite strong.
Skip Nav Destination
,
,
,
Article navigation
11 December 2023
THE 9TH INTERNATIONAL SEMINAR ON AEROSPACE SCIENCE AND TECHNOLOGY – ISAST 2022
22–23 November 2022
Bogor, Indonesia
Research Article|
December 11 2023
Optimization of deep learning hyperparameters to predict amphibious aircraft aerodynamic coefficients using grid search cross validation
Sigit Tri Atmaja;
Sigit Tri Atmaja
a)
1
Research Center for Transportation Technology, National Research and Innovation Agency
, Puspiptek Area, Tangerang Selatan, Indonesia
a)Corresponding author: [email protected]
Search for other works by this author on:
Muhammad Fajar;
Muhammad Fajar
b)
2
Research Center for Aeronautics Technology, National Research and Innovation Agency
, Sukamulya, Kec. Rumpin, Kabupaten Bogor, Indonesia
Search for other works by this author on:
Rizqon Fajar;
Rizqon Fajar
c)
1
Research Center for Transportation Technology, National Research and Innovation Agency
, Puspiptek Area, Tangerang Selatan, Indonesia
Search for other works by this author on:
Agus Aribowo
Agus Aribowo
d)
2
Research Center for Aeronautics Technology, National Research and Innovation Agency
, Sukamulya, Kec. Rumpin, Kabupaten Bogor, Indonesia
Search for other works by this author on:
Sigit Tri Atmaja
1,a)
Muhammad Fajar
2,b)
Rizqon Fajar
1,c)
Agus Aribowo
2,d)
1
Research Center for Transportation Technology, National Research and Innovation Agency
, Puspiptek Area, Tangerang Selatan, Indonesia
2
Research Center for Aeronautics Technology, National Research and Innovation Agency
, Sukamulya, Kec. Rumpin, Kabupaten Bogor, Indonesia
a)Corresponding author: [email protected]
AIP Conf. Proc. 2941, 020008 (2023)
Citation
Sigit Tri Atmaja, Muhammad Fajar, Rizqon Fajar, Agus Aribowo; Optimization of deep learning hyperparameters to predict amphibious aircraft aerodynamic coefficients using grid search cross validation. AIP Conf. Proc. 11 December 2023; 2941 (1): 020008. https://doi.org/10.1063/5.0181453
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
29
Views
Citing articles via
Inkjet- and flextrail-printing of silicon polymer-based inks for local passivating contacts
Zohreh Kiaee, Andreas Lösel, et al.
The implementation of reflective assessment using Gibbs’ reflective cycle in assessing students’ writing skill
Lala Nurlatifah, Pupung Purnawarman, et al.
Effect of coupling agent type on the self-cleaning and anti-reflective behaviour of advance nanocoating for PV panels application
Taha Tareq Mohammed, Hadia Kadhim Judran, et al.
Related Content
Performance comparison of the convolutional neural network optimizer for photosynthetic pigments prediction on plant digital image
AIP Conf. Proc. (March 2019)
Transfer learning based VGG-16 model for detection of COVID-19 from chest X-ray images
AIP Conf. Proc. (August 2024)
The effects of hyperparameters on deep learning of turbulent signals
Physics of Fluids (December 2024)
Efficient Alzheimer’s disease segmentation on MRI brain image and classification using machine learning
AIP Conf. Proc. (August 2023)
Efficiency of machine learning optimizers and meta-optimization for nanophotonic inverse design tasks
APL Mach. Learn. (January 2025)