• Journal of the Korea Society of Computer and Information
• /
• v.24 no.6
• /
• pp.11-19
• /
• 2019

In this paper, a new Scene-based Nonuniformity Correction (SBNUC) method is proposed by applying Image Roughness-like and Spatial Noise cost functions on deep neural network structure. The classic approaches for nonuniformity correction require generally plenty of sequential image data sets to acquire accurate image correction offset coefficients. The proposed method, however, is able to estimate offset from only a couple of images powered by the characteristic of deep neural network scheme. The real world SWIR image set is applied to verify the performance of proposed method and the result shows that image quality improvement of PSNR 70.3dB (maximum) is achieved. This is about 8.0dB more than the improved IRLMS algorithm which preliminarily requires precise image registration process on consecutive image frames.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.349-350
• /
• 2019

The autonomous driving drones experimented in the existing indoor corridor environment was a way to give the steering command to the drones by the neural network operation of the notebook due to the limitation of the operation performance of the drones. In this paper, to overcome these limitations, we have studied autonomous driving in indoor corridor environment using NVIDIA Jetson TX2 board.

• Nuclear Engineering and Technology
• /
• v.53 no.11
• /
• pp.3764-3771
• /
• 2021

Based on the convolutional neural network (CNN), a novel technique is investigated for lost gamma source detection in a room. The CNN is trained with the result of a GEANT4 simulation containing a gamma source inside a meshed room. The dataset for the training process is the deposited energy in the meshes of different n-step paths. The neural network is optimized with parameters such as the number of input data and path length. Based on the proposed method, the place of the gamma source can be recognized with reasonable accuracy without human intervention. The results show that only by 5 measurements of the energy deposited in a 5-step path, (5 sequential points 50 cm apart within 1600 meshes), the gamma source location can be estimated with 94% accuracy. Also, the method is tested for the room geometry containing the interior walls. The results show 90% accuracy with the energy deposition measurement in the meshes of a 5-step path.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1394-1397
• /
• 2020

The urine test used as a basic test method of in vitro diagnosis for health care has been used for a long time to be simple and convenient. The urine test method is using a color that appears depending on the change in the ion concentration that reacts over time buried in the standard color test paper(Strips) with a urine sample applied to some reaction reagents. In this paper, it was proposed a neural network algorithm to obtain a suitable and reproducibility and accuracy classifier suitable for the urine analysis system. The experimental results were compared with the visual colorimetric analysis, and the neural network algorithm showed better results.

• Journal of Integrative Natural Science
• /
• v.13 no.4
• /
• pp.147-151
• /
• 2020

In this paper, we propose a method to detect concept drift by applying Convolutional Neural Network (CNN) in a data stream environment. Since the conventional method compares only the final output value of the CNN and detects it as a concept drift if there is a difference, there is a problem in that the actual input value of the data stream reacts sensitively even if there is no significant difference and is incorrectly detected as a concept drift. Therefore, in this paper, in order to reduce such errors, not only the output value of CNN but also the probability vector are used. First, the data entered into the data stream is patterned to learn from the neural network model, and the difference between the output value and probability vector of the current data and the historical data of these learned neural network models is compared to detect the concept drift. The proposed method confirmed that only CNN output values could be used to reduce detection errors compared to how concept drift were detected.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.3
• /
• pp.177-183
• /
• 2022

To measure the size and weight of the fish, we developed an automatic fish size measurement system using a deep neural network, where the YOLO (You Only Look Once)v3 model was used. To detect fish, an IP camera with infrared function was installed over the fish pool to acquire image data and used as input data for the deep neural network. Using the bounding box information generated as a result of detecting the fish and the structure for which the actual length is known, the size of the fish can be obtained. A GUI (Graphical User Interface) program was implemented using LabVIEW and RTSP (Real-Time Streaming protocol). The automatic fish size measurement system shows the results and stores them in a database for future work.

• The Plant Pathology Journal
• /
• v.38 no.4
• /
• pp.395-402
• /
• 2022

To predict rice blast, many machine learning methods have been proposed. As the quality and quantity of input data are essential for machine learning techniques, this study develops three artificial neural network (ANN)-based rice blast prediction models by combining two ANN models, the feed-forward neural network (FFNN) and long short-term memory, with diverse input datasets, and compares their performance. The Blast_Weathe long short-term memory r_FFNN model had the highest recall score (66.3%) for rice blast prediction. This model requires two types of input data: blast occurrence data for the last 3 years and weather data (daily maximum temperature, relative humidity, and precipitation) between January and July of the prediction year. This study showed that the performance of an ANN-based disease prediction model was improved by applying suitable machine learning techniques together with the optimization of hyperparameter tuning involving input data. Moreover, we highlight the importance of the systematic collection of long-term disease data.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.4
• /
• pp.110-115
• /
• 2022

Accurate current-voltage modeling of solar cell systems plays an important role in power prediction. Solar cells have nonlinear characteristics that are sensitive to environmental conditions such as temperature and irradiance. In this paper, the output characteristics of photovoltaic module are accurately predicted by combining the artificial neural network and physical model. In order to estimate the performance of PV module under varying environments, the artificial neural network model is trained with randomly generated temperature and irradiance data. With the use of proposed model, the current-voltage and power-voltage characteristics under real environments can be predicted with high accuracy.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.130-134
• /
• 2022

An anti-reflective coating is used to improve the performance of the solar cell. The anti-reflective coating changes the value of the short-circuit current about the thickness. However, the current-voltage characteristics about the anti-reflective coating are difficult to calculate without simulation tool. In this paper, a modeling technique to determine the short-circuit current value and the current-voltage characteristics in accordance with the thickness is proposed. In addition, artificial neural network is used to predict the short-circuit current with the dependence of temperature and thickness. Simulation results incorporating the artificial neural network model are obtained using MATLAB/Simulink and show the current-voltage characteristic according to the thickness of the anti-reflective coating.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.3
• /
• pp.351-361
• /
• 2021

This study proposes an intelligent control of manufacturing robot with dual arm based on neural network for smart factory implementation. In the control method of robot system, the perspectron structure of single layer based on neural network is useful for simple computation. However, the limitations of computation are emerging in areas that require complex computations. To overcome limitation of complex parameters computation a new intelligent control technology is proposed in this study. The performance is illustrated by simulation and experiments for manufacturing robot dual arm robot with eight axes.