• Electronics and Telecommunications Trends
• /
• 제34권4호
• /
• 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.

• International Journal of Internet, Broadcasting and Communication
• /
• 제13권1호
• /
• pp.100-106
• /
• 2021

Over the past few decades, natural language processing research has not made much. However, the widespread use of deep learning and neural networks attracted attention for the application of neural networks in natural language processing. Sentiment analysis is one of the challenges of natural language processing. Emotions are things that a person thinks and feels. Therefore, sentiment analysis should be able to analyze the person's attitude, opinions, and inclinations in text or actual text. In the case of emotion analysis, it is a priority to simply classify two emotions: positive and negative. In this paper we propose the deep learning based sentimental analysis system according to various optimizer that is SGD, ADAM and RMSProp. Through experimental result RMSprop optimizer shows the best performance compared to others on IMDB data set. Future work is to find more best hyper parameter for sentimental analysis system.

• Journal of information and communication convergence engineering
• /
• 제19권4호
• /
• pp.241-247
• /
• 2021

Particulate matter has emerged as a serious global problem, necessitating highly reliable information on the matter. Therefore, various algorithms have been used in studies to predict particulate matter. In this study, we compared the prediction performance of neural network models that have been actively studied for particulate matter prediction. Among the neural network algorithms, a deep neural network (DNN), a recurrent neural network, and long short-term memory were used to design the optimal prediction model using a hyper-parameter search. In the comparative analysis of the prediction performance of each model, the DNN model showed a lower root mean square error (RMSE) than the other algorithms in the performance comparison using the RMSE and the level of accuracy as metrics for evaluation. The stability of the recurrent neural network was slightly lower than that of the other algorithms, although the accuracy was higher.

• Nuclear Engineering and Technology
• /
• 제55권6호
• /
• 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.

• Korean Journal of Agricultural and Forest Meteorology
• /
• 제19권3호
• /
• pp.174-179
• /
• 2017

Soil parameters are required inputs to crop models, which estimate crop yield under a given environment condition. The Korean Soil Information System (KSIS), which provides detailed soil profile record of 390 soil series in the HTML (HyperText Markup Language) format, would be useful to prepare soil input files. Korean Soil Information System Processing Tool (KSISPT) was developed to aid generation of soil input data based on the KSIS database. Java was used to implement the tool that consists of a set of modules for parsing the HTML document of the KSIS, storing data required for preparing soil input file, calculating additional soil parameter, and writing soil input file to a local disk. Using the automated soil data preparation tool, about 940 soil input data were created for the DSSAT model and the ORYZA 2000 model, respectively. In combination with soil series distribution map at 30m resolution, spatial analysis of crop yield could be projected under climate change, which would help the development of adaptation strategies.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제20권6호
• /
• 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.

• Journal of Broadcast Engineering
• /
• 제25권6호
• /
• pp.980-993
• /
• 2020

Deep-learning based style transfer has recently attracted great attention, because it provides high quality transfer results by appropriately reflecting the high level structural characteristics of images. This paper deals with the problem of providing more stable and more diverse style transfer results of such deep-learning based style transfer method. Based on the investigation of the experimental results from the wide range of hyper-parameter settings, this paper defines the problem of the stability and the diversity of the style transfer, and proposes a partial loss normalization method to solve the problem. The style transfer using the proposed normalization method not only gives the stability on the control of the degree of style reflection, regardless of the input image characteristics, but also presents the diversity of style transfer results, unlike the existing method, at controlling the weight of the partial style loss, and provides the stability on the difference in resolution of the input image.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제25권6호
• /
• pp.749-756
• /
• 2021

Thanks to PLC and IoT Sensor, huge amounts of data has been accumulated onto the companies' databases. Machine Learning Algorithms for the predictive model with good performance have been widely utilized in the manufacturing process. We present how to improve the performance of machine learning predictive models. To improve the performance of the predictive model, typical techniques such as increasing the sample size, optimizing the hyper parameters for the algorithm, and selecting a proper machine learning algorithm for the predictive model would be shown. We suggest some new ways to make the model performance much better. With the proposed methods, we can build a better predictive model for predicting and controlling product qualities and save incredibly large amount of quality failure cost.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.374-376
• /
• 2021

For the diagnosis of cancer-related diseases in clinical practice, pathological examination using biopsy is essential after basic diagnosis using imaging equipment. In order to proceed with such a biopsy, the assistance of an oncologist, clinical pathologist, etc. with specialized knowledge and the minimum required time are essential for confirmation. In recent years, research related to the establishment of a system capable of automatic classification of cancer cells using artificial intelligence is being actively conducted. However, previous studies show limitations in the type and accuracy of cells based on a limited algorithm. In this study, we propose a method to identify a total of 4 cancer cells through a convolutional neural network, a kind of deep learning. The optical images obtained through cell culture were learned through EfficientNet after performing pre-processing such as identification of the location of cells and image segmentation using OpenCV. The model used various hyper parameters based on EfficientNet, and trained InceptionV3 to compare and analyze the performance. As a result, cells were classified with a high accuracy of 96.8%, and this analysis method is expected to be helpful in confirming cancer.

• Journal of Korea Water Resources Association
• /
• 제55권10호
• /
• pp.761-774
• /
• 2022

Accurate hydrologic prediction is essential to analyze the effects of drought, flood, and climate change on flow rates, water quality, and ecosystems. Disentangling the uncertainty of the hydrological model is one of the important issues in hydrology and water resources research. Hydrologic data assimilation (DA), a technique that updates the status or parameters of a hydrological model to produce the most likely estimates of the initial conditions of the model, is one of the ways to minimize uncertainty in hydrological simulations and improve predictive accuracy. In this study, the two ensemble-based sequential DA techniques, ensemble Kalman filter, and particle filter are comparatively analyzed for the daily discharge simulation at the Yongdam catchment using airGRdatassim. The results showed that the values of Kling-Gupta efficiency (KGE) were improved from 0.799 in the open loop simulation to 0.826 in the ensemble Kalman filter and to 0.933 in the particle filter. In addition, we analyzed the effects of hyper-parameters related to the data assimilation methods such as precipitation and potential evaporation forcing error parameters and selection of perturbed and updated states. For the case of forcing error conditions, the particle filter was superior to the ensemble in terms of the KGE index. The size of the optimal forcing noise was relatively smaller in the particle filter compared to the ensemble Kalman filter. In addition, with more state variables included in the updating step, performance of data assimilation improved, implicating that adequate selection of updating states can be considered as a hyper-parameter. The simulation experiments in this study implied that DA hyper-parameters needed to be carefully optimized to exploit the potential of DA methods.