• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.5
• /
• pp.31-39
• /
• 2018

Recently, there has been active studies to provide a user-friendly interface in a virtual reality environment by recognizing user hand gestures based on deep learning. However, most studies use separate sensors to obtain hand information or go through pre-process for efficient learning. It also fails to take into account changes in the external environment, such as changes in lighting or some of its hands being obscured. This paper proposes a hand gesture recognition method based on deep learning that is strong in external environments without the need for pre-process of RGB images obtained from general webcam. In this paper we improve the VGGNet and the GoogLeNet structures and compared the performance of each structure. The VGGNet and the GoogLeNet structures presented in this paper showed a recognition rate of 93.88% and 93.75%, respectively, based on data containing dim, partially obscured, or partially out-of-sight hand images. In terms of memory and speed, the GoogLeNet used about 3 times less memory than the VGGNet, and its processing speed was 10 times better. The results of this paper can be processed in real-time and used as a hand gesture interface in various areas such as games, education, and medical services in a virtual reality environment.

• Journal of the Korean Society of Radiology
• /
• v.15 no.4
• /
• pp.547-554
• /
• 2021

In order to quickly and accurately diagnose pneumonia on a chest X-ray image, different batch sizes of 4, 8, 16, and 32 were applied to the same Xception deep learning model, and modeling was performed 3 times, respectively. As a result of the performance evaluation of deep learning modeling, in the case of modeling to which batch size 32 was applied, the results of accuracy, loss function value, mean square error, and learning time per epoch showed the best results. And in the accuracy evaluation of the Test Metric, the modeling applied with batch size 8 showed the best results, and the precision evaluation showed excellent results in all batch sizes. In the recall evaluation, modeling applied with batch size 16 showed the best results, and for F1-score, modeling applied with batch size 16 showed the best results. And the AUC score evaluation was the same for all batch sizes. Based on these results, deep learning modeling with batch size 32 showed high accuracy, stable artificial neural network learning, and excellent speed. It is thought that accurate and rapid lesion detection will be possible if a batch size of 32 is applied in an automatic diagnosis study for feature extraction and classification of pneumonia in chest X-ray images using deep learning in the future.

• Korean Journal of Cognitive Science
• /
• v.33 no.1
• /
• pp.23-50
• /
• 2022

Source memory is a cognitive process that combines the representation of the origin of the episodic experience with an item. By studying this daily process, researchers have made fundamental discoveries that make up the foundation of brain and behavior research, such as executive function and binding. In this paper, we review and conduct a bibliometric analysis on source memory papers published from 1989 to 2020. This review is based on keyword co-occurrence networks and author citation networks, providing an in-depth overview of the development of source memory research and future directions. This bibliometric analysis discovers a change in the research trends: while research prior to 2010 focused on individuality of source memory as a cognitive function, more recent papers focus more on the implication of source memory as it pertains to connectivity between disparate brain regions and to social neuroscience. Keyword network analysis shows that aging and executive function are continued topics of interest, although frameworks in which they are viewed have shifted to include developmental psychology and meta memory. The use of theories and models provided by source memory research seem essential for the future development of cognitive enhancement tools within and outside of the field of Psychology.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.429-440
• /
• 2021

With the recent development of deep convolutional neural network learning, deep learning techniques applied to single image super-resolution are showing good results. One of the existing deep learning-based super-resolution techniques is RDN(Residual Dense Network), in which the initial feature information is transmitted to the last layer using residual dense blocks, and subsequent layers are restored using input information of previous layers. However, if all hierarchical features are connected and learned and a large number of residual dense blocks are stacked, despite good performance, a large number of parameters and huge computational load are needed, so it takes a lot of time to learn a network and a slow processing speed, and it is not applicable to a mobile system. In this paper, we use the residual dense structure, which is a continuous memory structure that reuses previous information, and the residual dense channel attention block using the channel attention method that determines the importance according to the feature map of the image. We propose a method that can increase the depth to obtain a large receptive field and maintain a concise model at the same time. As a result of the experiment, the proposed network obtained PSNR as low as 0.205dB on average at 4× magnification compared to RDN, but about 1.8 times faster processing speed, about 10 times less number of parameters and about 1.74 times less computation.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.1
• /
• pp.51-58
• /
• 2023

In this paper, we propose an organ segmentation technique for the automatic extraction of medical diagnostic indicators from X-ray images. In order to calculate diagnostic indicators of heart disease and spinal disease such as VHS(vertebral heart scale) and Cobb angle, it is necessary to accurately segment the thoracic spine, carina, and heart in a chest X-ray image. A deep neural network model in which the high-resolution representation of the image for each layer and the structure converted into a low-resolution feature map are connected in parallel was adopted. This structure enables the relative position information in the image to be effectively reflected in the segmentation process. It is shown that learning performance can be improved by combining the OCR module, in which pixel information and object information are mutually interacted in a multi-step process, and the channel attention module, which allows each channel of the network to be reflected as different weight values. In addition, a method of augmenting learning data is presented in order to provide robust performance against changes in the position, shape, and size of the subject in the X-ray image. The effectiveness of the proposed theory was evaluated through an experiment using 145 human chest X-ray images and 118 animal X-ray images.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.697-703
• /
• 2022

Due to the recent economic downturn caused by Covid-19 and the unstable international situation, many investors are choosing the derivatives market as a means of investment. However, the derivatives market has a greater risk than the stock market, and research on the market of market participants is insufficient. Recently, with the development of artificial intelligence, machine learning has been widely used in the derivatives market. In this paper, reinforcement learning, one of the machine learning techniques, is applied to analyze the scalping technique that trades futures in minutes. The data set consists of 21 attributes using the closing price, moving average line, and Bollinger band indicators of 1 minute and 3 minute data for 6 months by selecting 4 products among futures products traded at trading firm. In the experiment, DNN artificial neural network model and three reinforcement learning algorithms, namely, DQN (Deep Q-Network), A2C (Advantage Actor Critic), and A3C (Asynchronous A2C) were used, and they were trained and verified through learning data set and test data set. For scalping, the agent chooses one of the actions of buying and selling, and the ratio of the portfolio value according to the action result is rewarded. Experiment results show that the energy sector products such as Heating Oil and Crude Oil yield relatively high cumulative returns compared to the index sector products such as Mini Russell 2000 and Hang Seng Index.

• Journal of Platform Technology
• /
• v.10 no.4
• /
• pp.47-55
• /
• 2022

Recently, diverse devices using different wireless technologies are gradually increasing in the IoT environment. In particular, it is essential to design an efficient feature extraction approach and detect the exact types of radio signals in order to accurately identify various radio signal modulation techniques. However, it is difficult to gather labeled wireless signal in a real environment due to the complexity of the process. In addition, various learning techniques based on deep learning have been proposed for wireless signal classification. In the case of deep learning, if the training dataset is not enough, it frequently meets the overfitting problem, which causes performance degradation of wireless signal classification techniques using deep learning models. In this paper, we propose a generative adversarial network(GAN) based on data augmentation techniques to improve classification performance when various wireless signals exist. When there are various types of wireless signals to be classified, if the amount of data representing a specific radio signal is small or unbalanced, the proposed solution is used to increase the amount of data related to the required wireless signal. In order to verify the validity of the proposed data augmentation algorithm, we generated the additional data for the specific wireless signal and implemented a CNN and LSTM-based wireless signal classifier based on the result of balancing. The experimental results show that the classification accuracy of the proposed solution is higher than when the data is unbalanced.

• Journal of the Korean Geotechnical Society
• /
• v.25 no.5
• /
• pp.53-64
• /
• 2009

Many slope failures are induced by rainfall infiltration. A lot of recent researches are therefore focused on rainfall-induced slope instability and the rainfall infiltration is recognized as the important triggering factor. The rainfall infiltrates into the soil slope and makes the matric suction lost in the slope and even the positive pore water pressure develops near the surface of the slope. They decrease the resisting shear strength. In Korea, a few public institutions suggested conservative slope design guidelines that assume a fully saturated soil condition. However, this assumption is irrelevant and sometimes soil properties are misused in the slope design method to fulfill the requirement. In this study, a more relevant slope stability evaluation method is suggested to take into account the real rainfall infiltration phenomenon. Unsaturated soil properties such as shear strength, soil-water characteristic curve and permeability for Korean weathered soils were obtained by laboratory tests and also estimated by artificial neural network models. For real-time assessment of slope instability, failure warning criteria of slope based on deterministic and probabilistic analyses were introduced to complement uncertainties of field measurement data. The slope stability evaluation technique can be combined with field measurement data of important factors, such as matric suction and water content, to develop an early warning system for probably unstable slopes due to the rainfall.

• Geophysics and Geophysical Exploration
• /
• v.25 no.4
• /
• pp.177-188
• /
• 2022

Recently, the application of distributed acoustic sensors (DAS), which can replace geophones and seismometers, has significantly increased along with interest in micro-seismic monitoring technique, which is one of the CO₂ storage monitoring techniques. A significant amount of temporally and spatially continuous data is recorded in a DAS monitoring system, thereby necessitating fast and accurate data processing techniques. Because event detection and seismic phase picking are the most basic data processing techniques, they should be performed on all data. In this study, a machine learning-based P, S wave phase picking algorithm was developed to compensate for the limitations of conventional phase picking algorithms, and it was modified using a transfer learning technique for the application of DAS data consisting of a single component with a low signal-to-noise ratio. Our model was constructed by modifying the convolution-based EQTransformer, which performs well in phase picking, to the ResUNet structure. Not only the global earthquake dataset, STEAD but also the augmented dataset was used as training datasets to enhance the prediction performance on the unseen characteristics of the target dataset. The performance of the developed algorithm was verified using K-net and KiK-net data with characteristics different from the training data. Additionally, after modifying the trained model to suit DAS data using the transfer learning technique, the performance was verified by applying it to the DAS field data measured in the Pohang Janggi basin.

• 전기의세계
• /
• v.27 no.5
• /
• pp.33-54
• /
• 1978

(차례) 1.산학협동심포지업 (1)우리나라에서의 연구개발과 산학협동 (2)산학협동과 산업계의 역할 (3)산학협동의 현황과 진로 2.학술회의A (1)전력게통의 계층구조와 협조원리에 관한 연구 (2)2중층괴상회전자 유도전동기의 이론해석 (3)초고주파가열장치에 사용하는 철공진변압기의 해석적 설계 (4)한국전기기시험연구소 대전력단락 시험설비설계 (5)직류전동기제어를 위한 Thyristor Chopper정류회로에 관한 연구 (6)선로의 개폐정보를 포함하는 전력계통의 상태추정 (7)단일신경세포에 대한 ITEM 신호 특성 3.학술회의B (1)MMM-1 Computer System의 설계 및 제작 (2)Adaptive Delta Modulation System의 성능비교 연구 (3)6GHZ FMD마이크로파 무선전송장치의 개발 (4)적선도에 의한 회로망함수의 결정 (5)동맥혈압의 해석과 그의 전기적 유사모델 (6)피부감각의 정보전달 특성에 관하여 (7)선형직접회로의 공정설계 및 그 특성 조성 (8)DH L.D의 전기적포화현상에 관한 이론적 해석 (9)Potocoupler를 이용한 Isolator 4.학술회의C (1)Al-Al$_{2}$O$_{3}$ -Al박막구조의 전기적 특성 (2)이종금속에 샌드위치된 고분자물질의 단락전조 (3)유전체가 일부체워진 직 6면체의 캐비티의 다중모오드 해석 (4)반도체 가스 검지소자의 제조 및 그의 전기적 특성 (5)실리콘 산화공정에 대한 실험적 고찰 (6)진공증착법에 의한 InSb 박막제도에서 열처리효과 (7)(Ba$_{1}$-xBix) Tio$_{3}$ PTC thermistor의 첨가량의 최적건안 (8)금속박막증착시 두께조절 5.특별강연회 (1)일본에 있어서의 절력계통공학연구 (2)Linear Motor의 최근개발동향량도 높았다. valine과 leucine 및 aspartic acid, glycine과 glutamic acid, leucine과 aspartic acid 간에는 고도의 정상관, glycine과 serine, valine과 phenylalanine, threonine과 proline, phenylalanine과 arginine, methionine과 glutamic acid, histidine과 lysine 간에는 유의 정상관, 그리고 isoleucine과 lysine 간에는 유의한 부상관이 있었다. 4. lysine 함량은 단백질 함량과 정산곤, isoleucine 함량은 단빅질 함량과 부상관을 보였으며, alanine, valine, leucine 함량은 지방함량과 각각 유의한 정산관을 보였다. 5. 대두 단백질은 7.5% acrylamide gel 전기영동에 의해 품종에 따라 12～16개의 구성분으로 분리되었으며, 이들중 주구성분들은 상대이동도가 0.06(a), 0.14(b). 0.24(d) 이었고, 구성분 b의 함량이 품종간에 가장 변이가 컸으며, 구성분 b는 그밖의 주요 구성분들의 함량과 부의 상관이 있었고, 구성분 a는 단백질 함량과 정상관이 있었다. 6. 종실단백질 구성분들의 조합 특성 면에서 공시 86품종은 11개 유형군으로 분류되었으며, 우리나라와 일본품종은 미국품종에 비해 단백질구성분 조성이 훨씬 다양하였다. 7. 이동도가 매우 빠른 단백질 구성분 o(Rm 0.77) p(Rm 0.81)를 모두 갖고 있는 품종은 3품종, 모두 갖고 있지 않은 품종은 1품종이었고, 나머지 82품종은 o나 p중 한 구성분을 갖고 있었으며 그 분포율은 30 : 65 이었는데 미국계 품종은 우리나라 품종에 비해 구성분 o를 간고 있는 비율이 현저히 적었다. 8. 대두 종실은 개화후 22일까지 완만히, 그 이후 20～30일간 급속히