• Journal of IKEEE
• /
• v.6 no.2 s.11
• /
• pp.152-160
• /
• 2002

This paper is the realization of the face recognition system for multimedia application. This system is focused on the design concerning the improvement of recognition rate and the reduction of processing time for face recognition. The non-modificated application of typical RGB color system enables the reduction of time required for color system transform. The neural network and the application of algorithm using face characteristic improves the recognition rate. After mosaicking an image, a face-color block has been selected through the color analysis of mosaic block. The characteristic of the face removes the mis-checked face-color candidate block. Finally, from the face color block, four special values are obtained. These values are processed to the neural network using the back propagation algorithm. The output values are the touchstone to decide the genuineness of face field. The realized system showed 90% of face recognition rate with less than 0.1 second of processing time. This result can be understood as sufficient processing time and recognition rate to find out the face block for multimedia application in dynamic image.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.41 no.6
• /
• pp.53-58
• /
• 2004

A novel UV sensor was manufactured and characterized using evanescent field coupling between photochromic dye dispersed polymer waveguide and side polished fiber. The spiroxazine (photochromic dye) dispersed polymer was used as planar waveguides. The resonant wavelength was shifted owing to refractive index variation of planar waveguide on exposed UV because of its photo-functional properties. The sensitivities are $1.21{\mu}W/mw$ and $2.75{\mu}W/mw$ when UV intensities increased after exposure times were fixed at 3 seconds and 5 seconds, respectively. Output optical power according to UV intensity increases and saturation time decreases as the intensity of UV radiations increases.

• The Journal of the Korea Contents Association
• /
• v.12 no.12
• /
• pp.639-646
• /
• 2012

To analyzed the shape of Yellow Dots which appeared on the paper printed HP color laser printer, and analyzed the characteristic of Yellow Dots according to time, month, year and same printers. As a result, documents that printed in same printers had an identical Yellow Dots's shapes according to time, month, year. It was presupposed that was not embedded time and date information in HP Color LaserJet printers against Xerox, and printers which have different serial number had similar shapes but it was not identical Yellow Dots. Finally, it was found to be identical patterns in Yellow Dots of HP Color LaserJet printers used analysis. Depending on the results, it could understand HP's pattern. In the future, it will decipher patterns of Yellow Dots which have other informations to include other printer manufacturer.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.3 no.4
• /
• pp.47-60
• /
• 1999

The stability and efficiency of structural control systems depend on the accuracy of mathematical model of the system to be controlled. In this study, state equation models of a small scale test structure and an AMD(active mass damper) are obtained separately using OKID(observer/Kalman filter identification) which is a time domain system identification method. The test structure with each floor acceleration as outputs is identified for two inputs - the ground acceleration and the acceleration of the moving mass of AMD relative to the installation floor - individually and the two identified state equation models are integrated into one by model reduction method. The AMD is identified with the motor control signal as an input and the relative acceleration of the moving mass as an output, and it is shown that the identified model has large damping ratio and phase shift. The transfer functions and the time histories reconstructed from the identified models of the test model and the AMD match well with those measured from the experiment.

• 전자공학회논문지 IE
• /
• v.43 no.3
• /
• pp.13-21
• /
• 2006

Ryu et al. proposed a multiple target angle tracking algorithm using the angular measurement obtained from the signal subspace estimated by the output of sensor array. Ryu's algorithm has good features that it has no data association problem and simple structure. But its performance is seriously degraded in the low signal-to-noise ratio, and it uses the angular measurement obtained from the signal subspace of sampling time, even though the signal subspace is continuously updated by the output of sensor array. For improving the tracking performance of Ryu's algorithm, a measurement fusion method is derived based on ML(Maximum Likelihood) in this paper, and it admits us to use the angular measurements obtained form the adjacent signal subspaces as well as the signal subspace of sampling time. The new target angle tracking algorithm is proposed using the derived measurement fusion method. The proposed algorithm has a better tracking performance than that of Ryu's algorithm and it sustains the good features of Ryu's algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.334-341
• /
• 2003

In this paper, we proposed a recurrent time delayed neural network(RTDNN) controller which compensate a output of neural network controller. Even if learn by neural network controller, it can occur an bad results from disturbance or load variations. So in order to adjust above case, we used the fuzzy compensator to get an expected results. And the weight of main neural network can be changed with the result of learning a inverse model neural network of plant, so a expected dynamic characteristics of plant can be got. As the results of simulation through the second order plant, we confirmed that the proposed recurrent time delayed neural network controller get a good response compare with a time delayed neural network(TDU) controller. We implemented the controller using the DSP processor and applied in a hydraulic servo system. And then we observed an experimental results.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.424-424
• /
• 2018

인공신경망(Artificial Neural Network; ANN)은 뇌에 존재하는 생물학적 신경세포와 이들의 신호처리 과정을 수학적으로 묘사하여 뇌가 나타내는 지능적 형태의 반응을 구현한 것이다. 인공신경망은 학습(training)을 통해 입력과 출력으로 구성되는 하나의 시스템을 병렬적이고 비선형적으로 구축할 수 있으며, 유연한 모델링 특성으로 인하여 시스템 예측, 패턴인식, 분류 및 공정제어 등의 다양한 분야에서 활용되고 있다. 인공신경망에 대한 최초의 이론은 Muculloch and Pitts(1943)가 제안한 Perceptron에서 시작 되었으며, 기본적인 학습기법인 오차역전파 기법(back-propagation Algorithm) 이 1980년대에 들어 수학적으로 정립된 이후 여러 분야에서 활용되기 시작하였다). 본 연구에서는 하도추적, 구체적으로는 상류단의 복수의 수위관측을 이용하여 하류단의 수위를 예측하기 위하여 인공신경망 모델을 구성하였다. 대상하도는 금강유역의 용담댐과 대청댐 사이의 본류이며, 상류단 입력자료로써 본류에 있는 수통, 호탄 관측소 관측수위와 지류인 송천 관측소 관측수위를 고려하였다. 출력 값으로는 하류단의 옥천 관측소 수위를 3시간 및 6시간의 선행시간으로 예측하도록 인공신경망 모형을 구성하였다. 인공신경망의 학습(testing), 시험(testing), 검증(validation)을 위해 2000년부터 2012년까지 13년간의 시수위자료를 이용하여 학습을 진행하였으며, 2013년부터 2014년의 2년간의 수위자료를 이용한 시험을 통해 최적의 모형을 선정하였다. 또한 선정된 최적의 모형을 이용하여 2015년부터 2016년까지의 수위예측을 수행하였다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.3
• /
• pp.231-238
• /
• 2021

In addition to individual calls and group calls, the Trunked Radio System (TRS), which belongs to a group, can make calls simultaneously, and many users can use it within a limited time by adjusting the call time. Also, the LCX infrastructure network of the subway Most of the FM, firefighting radio, TRS of the National Police Agency and the terrestrial DMB service built in 2005 are commonly connected to the network for service and operation. In connection with the analysis, call reception sensitivity, handoff, interference with other signals, time delay, etc. were analyzed, and tests such as reception field strength for each output of the repeater and the success rate of the call terminal were conducted and the test results were analyzed. In addition, it will help TRS cell design and network construction by predicting equipment output capacity and service coverage based on test results.

• Proceedings of the KIPE Conference
• /
• 2011.11a
• /
• pp.213-214
• /
• 2011

본 논문은 계통연계형 3-레벨 NPC 인버터 시스템의 중성점 전압 불평형 제어기법을 제안한다. 3-레벨 NPC 인버터는 직류단 커패시터를 2개로 나누어 사용하기 때문에 두 커패시터간의 전압차이가 발생할 수 있으며 이는 출력전류의 왜곡을 야기한다. 본 논문에서는 복잡한 모델링을 통한 제어기 설계나 공간 벡터 전압 변조 방법의 변형 없이 간단하게 시간오프셋을 추가하여 N형과 P형의 small 전압 벡터의 인가시간을 조절함으로써 중성점 전압 불평 형을 제어하고, 복잡한 계산 없이 적절한 시간오프셋을 구한다. 10kW급 계통연계 3-레벨 NPC 인버터 모델을 기반으로 수행된 시뮬레이션 결과를 바탕으로 제안하는 제어기법의 타당성을 보인다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.06a
• /
• pp.250-253
• /
• 2014

방송 서비스를 안정적으로 제공하기 위해서는 가시청시간율을 안정적으로 확보하는 것이 중요하다. 이를 위해서는 수신단에서 ToV SNR 부근에서의 추가적인 margin을 확보하는 기술이 요구된다. 기존 방송 시스템은 안테나를 하나만 사용하는 수신 환경을 가정하고 있으므로, 본 논문에서는 하나의 안테나로부터 수신된 신호를 서로 다른 equalizer 기법 2가지를 동시에 적용하여 마치 2개의 수신 안테나부터 신호를 수신한 효과를 얻었고, 그 출력을 weight combining 하여 최종 SNR 이득을 높이는 기술을 제안하였다. 특히, equalizer 기법은 기존에 성능이 우수하다고 알려져 있는 MMSE-DFE 기술과 최근 큰 주목을 받고 있는 compressed Sensing 기반 sparse-DFE 기술을 동시에 사용하였다. Simulation을 통해서 MMSE-DFE 또는 sparse-DFE를 단독으로 사용하는 것보다 두 기법을 가중치 결합을 통해서 사용함으로써 가시청시간율이 크게 향상되는 것을 확인하였다.