• Journal of electromagnetic engineering and science
• /
• v.12 no.2
• /
• pp.166-170
• /
• 2012

This paper presents a tunable composite right/left-handed (CRLH) delay line for a delay line discriminator that linearizes modulated frequency sweep in a frequency modulated continuous wave (FMCW) radar transmitter. The tunable delay line consists of 8 cascaded unit cells with series varactor diodes and shunt inductors. The reverse bias voltage of the varactor diode controlled the group delay through its junction capacitance. The measured results demonstrate a group delay of 8.12 ns and an insertion loss of 4.5 dB at 250 MHz, while a control voltage can be used to adjust the group delay by approximately 15 ns. A group delay per unit cell of approximately 1 ns was obtained, which is very large when compared with previously published results. This group delay can be used effectively in FMCW radar transmitters.

• Proceedings of the KIEE Conference
• /
• 1987.07a
• /
• pp.61-63
• /
• 1987

In this paper, we develope a system which can perform signal processing for bar-code laser scanner. This system is composed of optical detector and preprocessor. The former detects the diffused light and converts it into TTL lebel output. The latter discriminator valid data from various raw data and transmits data to micro-processor. The preprocessor consists of edge transition detector, latch signal generator, module counter, register array, adder array, and buffer memory control circuit etc..

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1301-1303
• /
• 1996

A new automatic frequency control(AFC) tracking algorithm, which we call a rotational decision directed AFC(RDDAFC) is proposed for QPSK demodulation at the digital direct broadcasting satellite(DBS). In order to prevent the presence of the residual phase difference between symbols received at k and k-l by the CPAFC[1] as well as the AFC based on $tan^{-1}$ circuit[2], the RDDAFC rotates the decision boundary for the kth received symbol by the frequency detector output of the (k-1)th received symbol before passing through the cross product discriminator. Test results show that the total pull-in time of the RDDAFC and PLL was 0.13msec under a carrier frequency offset of 2.4MHz when S/N equals 2dB.

• Bulletin of the Korean Space Science Society
• /
• 1993.10a
• /
• pp.22-22
• /
• 1993

We developed the low energy electron detector (LEED) for KITSAT-B which was launched on September 26, 1998. The sensor head is mounted on the top of the satellite so that it can measure the precipitating electron flux along the Magnetic field line in the auroral zone at 820 km altitude. The detector system is composed of 4 parts : the electrostatic analyzer, the spira10on detector, the discriminator / Preamplifier, and the interface to the spacecraft. The analyzer limits the access to the spiraltron only to the electrons of certain energies which are determined by the electrostatic field across the two coaxial cylindrical analyzer plates. The energy spectrum of the detector in consideration is about 100 eV to 6.7 KeV, which is swept in 1.6 seconds and divided into 16 bins. It 81so is 1.6 second reset period after each swept, We will discuss the technical features of the system as well as the future observational schedule.

• Proceedings of the Optical Society of Korea Conference
• /
• 2000.08a
• /
• pp.148-149
• /
• 2000

파장분할다중(WDM) 광통신시스템에서 광원의 파장을 정확하게 측정하는 것은 매우 중요하다. 지금까지 광파장측정기는 격자나 Fabry-Perot 에탈론을 사용한 광대역 필터(optical bandpass filter) 및 파장에 따라 삽입손실이 다른 파장판별기(wavelength discriminator)등으로 구현되었지만 빛의 간섭 현상을 이용한 마이켈슨 간섭계가 가장 많이 사용되었다. 특히 푸리에 변환 마이켈슨 간섭계 파장측정기$^{(1)}$ 는 동시에 각각 다른 파장의 광원들이 입사되더라도 각각의 파장을 측정할 수 있는 장점이 있다. 즉 마이켈슨 간섭계에서 주기적인 간섭무늬에 의한 광검출기의 출력은 입력된 광파장에 따라 다른 주기를 가진다. 따라서 서로 다른 파장을 가진 빛이 입사했을 때 검출되는 각각의 광전력의 합을 표본화(sampling)한 뒤 FFT를 거치면 광파장과 광검출기로 수신한 신호의 중심 주파수의 관계를 알 수 있으므로, 서로 다른 파장을 가진 빛이 입사하더라도 각각의 파장을 측정할 수 있는 것이다. 본 논문에서는 푸리에 변환을 이용하되 마이켈슨 간섭계 대신 마하젠더 간섭계형 광변조기를 이용하여 광파장을 측정에 관한 실험적 구현과 개선 방안에 대해 제시한다. (중략)

• Journal of Korea Multimedia Society
• /
• v.22 no.5
• /
• pp.547-557
• /
• 2019

To extract the depth map from a single image, a number of CNN-based deep learning methods have been performed in recent research. In this study, the GAN structure of Pix2Pix is maintained. this model allows to converge well, because it has the structure of the generator and the discriminator. But the convolution in this model takes a long time to compute. So we change the convolution form in the generator to a depthwise convolution to improve the speed while preserving the result. Thus, the seven down-sizing convolutional hidden layers in the generator U-Net are changed to depthwise convolution. This type of convolution decreases the number of parameters, and also speeds up computation time. The proposed model shows similar depth map prediction results as in the case of the existing structure, and the computation time in case of a inference is decreased by 64%.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.2
• /
• pp.50-58
• /
• 2019

The clear and specific objective of this study is to design a false news discriminator algorithm for news articles transmitted on a text-based basis and an architecture that builds it into a system (H/W configuration with Hadoop-based in-memory technology, Deep Learning S/W design for bigdata and SNS linkage). Based on learning data on actual news, the government will submit advanced "fake news" test data as a result and complete theoretical research based on it. The need for research proposed by this study is social cost paid by rumors (including malicious comments) and rumors (written false news) due to the flood of fake news, false reports, rumors and stabbings, among other social challenges. In addition, fake news can distort normal communication channels, undermine human mutual trust, and reduce social capital at the same time. The final purpose of the study is to upgrade the study to a topic that is difficult to distinguish between false and exaggerated, fake and hypocrisy, sincere and false, fraud and error, truth and false.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1476-1485
• /
• 2020

Segmenting OCT retinal images into layers is important to diagnose and understand the progression of retinal diseases or identify potential symptoms. The task of manually identifying these layers is a difficult task that requires a lot of time and effort even for medical professionals, and therefore, various studies are being conducted to automate this using deep learning technologies. In this paper, we use cGAN-based neural network to automatically segmenting OCT retinal images into seven terrain-type regions defined by six layer boundaries. The network is composed of a Segnet-based generator model and a discriminator model. We also proposed a dynamic programming algorithm for refining the outputs of the network. We performed experiments using public OCT image data set and compared its performance with the Segnet-only version of the network. The experimental results show that the cGAN-based network outperforms Segnet-only version.

• Journal of Korea Multimedia Society
• /
• v.24 no.1
• /
• pp.13-20
• /
• 2021

A Wasserstein GAN(WGAN), optimum in terms of minimizing Wasserstein distance, still suffers from inconsistent convergence or unexpected output due to inherent learning instability. It is widely known some kinds of restriction on the discriminative function should be considered to solve such problems, which implies the importance of Lipschitz continuity. Unfortunately, there are few known methods to satisfactorily maintain the Lipschitz continuity of the discriminative function. In this paper we propose techniques to stably maintain the Lipschitz continuity of the discriminative function by adding effective regularization terms to the objective function, which limit the magnitude of the gradient vectors of the discriminator to one or less. Extensive experiments are conducted to evaluate the performance of the proposed techniques, which shows the single-sided penalty improves convergence compared with the gradient penalty at the early learning process, while the proposed additional penalty increases inception scores by 0.18 after 100,000 number of learning.

• KEPCO Journal on Electric Power and Energy
• /
• v.8 no.2
• /
• pp.137-141
• /
• 2022

To inspect the power facility faults using artificial intelligence, it need that improve the accuracy of the diagnostic model are required. Data augmentation skill using generative adversarial network (GAN) is one of the best ways to improve deep learning performance. GAN model can create realistic-looking fake images using two competitive learning networks such as discriminator and generator. In this study, we intend to verify the effectiveness of virtual data generation technology by including the fake image of power facility generated through GAN in the deep learning training set. The GAN-based fake image was created for damage of LP insulator, and ResNet based normal and defect classification model was developed to verify the effect. Through this, we analyzed the model accuracy according to the ratio of normal and defective training data.