• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.32-42
• /
• 2019

The performance of machine learning algorithms significantly depends on how a configuration of hyperparameters is identified and how a neural network architecture is designed. However, this requires expert knowledge of relevant task domains and a prohibitive computation time. To optimize these two processes using minimal effort, many studies have investigated automated machine learning in recent years. This paper reviews the conventional random, grid, and Bayesian methods for hyperparameter optimization (HPO) and addresses its recent approaches, which speeds up the identification of the best set of hyperparameters. We further investigate existing neural architecture search (NAS) techniques based on evolutionary algorithms, reinforcement learning, and gradient derivatives and analyze their theoretical characteristics and performance results. Moreover, future research directions and challenges in HPO and NAS are described.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.11
• /
• pp.1129-1134
• /
• 2016

This paper suggests a new method of finding regularization parameter for image restoration problems. If the prior information is not available, separate optimization functions for Tikhonov regularization parameter are suggested in the literature such as generalized cross validation and L-curve criterion. In this paper, unified Bayesian interpretation of Tikhonov regularization is introduced and applied to the image restoration problems. The relationship between Tikhonov regularization parameter and Bayesian hyper-parameters is established. Update formular for the regularization parameter using both maximum a posteriori(: MAP) and evidence frameworks is suggested. Experimental results show the effectiveness of the proposed method.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.4
• /
• pp.412-424
• /
• 2022

Since traditional derivative-based optimization for noisy simulation shows bad performance, evolutionary algorithms are considered as substitutes. Especially in case when outputs are binary, more simulation trials are needed to get near-optimal solution since the outputs are discrete and have high and heterogeneous variance. In this paper, we propose a genetic algorithm called SARAGA which adopts dynamic resampling and fitness approximation using surrogate. SARAGA reduces unnecessary numbers of expensive simulations to estimate success probabilities estimated from binary simulation outputs. SARAGA allocates number of samples to each solution dynamically and sometimes approximates the fitness without additional expensive experiments. Experimental results show that this novel approach is effective and proper hyper parameter choice of surrogate and resampling can improve the performance of algorithm.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.6
• /
• pp.314-321
• /
• 2019

The Self-Adaptive Vision Correction Algorithm (SAVCA) developed in this study was suggested for improving usability by modifying four parameters (Modulation Transfer Function Rate, Astigmatic Rate, Astigmatic Factor and Compression Factor) except for Division Rate 1 and Division Rate 2 among six parameters in Vision Correction Algorithm (VCA). For verification, SAVCA was applied to two-dimensional mathematical benchmark functions (Six hump camel back / Easton and fenton) and 30-dimensional mathematical benchmark functions (Schwefel / Hyper sphere). It showed superior performance to other algorithms (Harmony Search, Water Cycle Algorithm, VCA, Genetic Algorithms with Floating-point representation, Shuffled Complex Evolution algorithm and Modified Shuffled Complex Evolution). Finally, SAVCA showed the best results in the engineering problem (speed reducer design). SAVCA, which has not been subjected to complicated parameter adjustment procedures, will be applicable in various fields.

• Korean Journal of Remote Sensing
• /
• v.34 no.4
• /
• pp.661-670
• /
• 2018

This study aims to develop a methodology of convolutional neural networks (CNNs) to produce thematic maps from remote sensing data. Optimizing the image size for CNNs was studied, since the size of the image affects to accuracy, working as hyper-parameter. The selected study area is Mt. Ung, located in Dangjin-si, Chungcheongnam-do, South Korea, consisting of both coniferous forest and deciduous forest. Spatial structure analysis and the classification of forest type using CNNs was carried in the study area at a diverse range of scales. As a result of the spatial structure analysis, it was found that the local variance (LV) was high, in the range of 7.65 m to 18.87 m, meaning that the size of objects in the image is likely to be with in this range. As a result of the classification, the image measuring 15.81 m, belonging to the range with highest LV values, had the highest classification accuracy of 85.09%. Also, there was a positive correlation between LV and the accuracy in the range under 15.81 m, which was judged to be the optimal image size. Therefore, the trial and error selection of the optimum image size could be minimized by choosing the result of the spatial structure analysis as the starting point. This study estimated the optimal image size for CNNs using spatial structure analysis and found that this can be used to promote the application of deep-learning in remote sensing.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.6
• /
• pp.251-258
• /
• 2023

It is necessary to predict peak load accurately in order to supply electric power and operate the power system stably. Especially, it is more important to predict peak load accurately in winter and summer because peak load is higher than other seasons. If peak load is predicted to be higher than actual peak load, the start-up costs of power plants would increase. It causes economic loss to the company. On the other hand, if the peak load is predicted to be lower than the actual peak load, blackout may occur due to a lack of power plants capable of generating electricity. Economic losses and blackouts can be prevented by minimizing the prediction error of the peak load. In this paper, the latest deep learning model such as TCN is used to minimize the prediction error of peak load. Even if the same deep learning model is used, there is a difference in performance depending on the hyper-parameters. So, I propose methods for optimizing hyper-parameters of TCN for predicting the peak load. Data from 2006 to 2021 were input into the model and trained, and prediction error was tested using data in 2022. It was confirmed that the performance of the deep learning model optimized by the methods proposed in this study is superior to other deep learning models.

• Nuclear Engineering and Technology
• /
• v.55 no.6
• /
• pp.2276-2282
• /
• 2023

We deploy artificial neural networks to unfold neutron spectra from measured energy-integrated quantities. These neutron spectra represent an important parameter allowing to compute the absorbed dose and the kerma to serve radiation protection in addition to nuclear safety. The built architectures are inspired from convolutional neural networks. The first architecture is made up of residual transposed convolution's blocks while the second is a modified version of the U-net architecture. A large and balanced dataset is simulated following "realistic" physical constraints to train the architectures in an efficient way. Results show a high accuracy prediction of neutron spectra ranging from thermal up to fast spectrum. The dataset processing, the attention paid to performances' metrics and the hyper-optimization are behind the architectures' robustness.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.4
• /
• pp.34-40
• /
• 2019

We performed shape optimization of an anti-vibration rubber assembly which is used in the field option cabin of agricultural tractors to improve the vibration isolation capability. To characterize the hyper-elastic material property of rubber, we performed uniaxial and biaxial tension tests and used the data to calibrate the material model applied in the finite element analyses. We conducted a field test to characterize the input excitation from the tractor and the output response at the cabin frame. To account for the nonlinear behavior of rubber, we performed static analyses to derive the load-displacement curve of the anti-vibration rubber assembly. The stiffness of the rubber assembly could be calculated from this curve and was input to the harmonic analyses of the cabin. We compared the results with the test data for verification. We utilized Taguchi's parameter design method to determine the optimal shape of the anti-vibration rubber assembly and found two distinct shapes with reduced stiffness. Results show that the vibration at the cabin frame was reduced by approximately 35% or 47.6% compared with the initial design using the two optimized models.

• Transactions of Materials Processing
• /
• v.29 no.4
• /
• pp.218-228
• /
• 2020

The prediction of final mass and optimized process conditions of injection molded products using Artificial Neural Network (ANN) were demonstrated. The ANN was modeled with 10 input parameters and one output parameter (mass). The input parameters, i.e.; melt temperature, mold temperature, injection speed, packing pressure, packing time, cooling time, back pressure, plastification speed, V/P switchover, and suck back were selected. To generate training data for the ANN model, 77 experiments based on the combination of orthogonal sampling and random sampling were performed. The collected training data were normalized to eliminate scale differences between factors to improve the prediction performance of the ANN model. Grid search and random search method were used to find the optimized hyper-parameter of the ANN model. After the training of ANN model, optimized process conditions that satisfied the target mass of 41.14 g were predicted. The predicted process conditions were verified through actual injection molding experiments. Through the verification, it was found that the average deviation in the optimized conditions was 0.15±0.07 g. This value confirms that our proposed procedure can successfully predict the optimized process conditions for the target mass of injection molded products.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.4
• /
• pp.657-663
• /
• 2018

In this study, shape optimization was performed to improve the vibration isolation capability of an anti-vibration rubber assembly, which is used in the field option cabin of agricultural tractors. A uniaxial tension test and biaxial tension test were performed to characterize the hyper-elastic material properties of rubber, and the data were used to calibrate the material model used in the finite element analyses. A field test was performed to quantify the input excitation from the tractor and the output response at the cabin frame. To account for the nonlinear behavior of rubber, static analyses were performed and the load-displacement curve of rubber was derived. The stiffness of the rubber was calculated from this curve and input to the harmonic analyses of the cabin. The results were verified using the test data. Taguchi's parameter design method was used to find the optimal shape of the anti-vibration rubber assembly, which indicated a shape with reduced stiffness. The vibration of the cabin frame was reduced by the optimization by as much as 35% compared to the initial design.