• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.126-129
• /
• 2018

기존 자율주행자동차의 영상 센서 시스템이 표지판에 약간의 부착물만 붙어도 인식이 되지 않는 점을 고려해 Semi-Passive RFID(Radio-Frequency Identification)기술을 이용한다. 각 표지판마다 소스코드를 설정한 후 RFID 태그를 부착하고 자동차의 룸미러 뒤쪽 중앙에 RFID 리더기를 부착해 원거리에서 태그와 리더기의 작용을 통해 영상 센서 시스템의 취약점을 보완해 오류를 줄인다. 태그의 건전지를 대체하여 M24LR16E칩을 적용한다. 이 칩은 기존에 낭비되는 전파와 폐열, 움직임에 따라 발생하는 동작 에너지의 미세한 에너지를 모아 메모리칩을 구동한다. 또한 GPS를 이용한 위치정보 획득 및 지리적 변화의 낮은 정확도를 보완해 도시 인프라에 부착된 RFID를 제안하여 이를 이용한 위치정보 획득과 처리방안의 문제점도 해결한다.

• Proceedings of the KIEE Conference
• /
• 2005.07b
• /
• pp.1471-1473
• /
• 2005

본 논문에서는 RFID 시스템을 이용한 전력설비 관리에 EPC 오브젝트 관리 시스템을 소개하였다. 기존의 전력설비 관리방법에 사용되었던 관리대장은 수작업에 의존함에 따라 오류발생으로 관리자나 사용자 모두에게 불편함을 초래하게 된다. RFID시스템을 이용한 전력량계 관리시스템을 EPCNetwork 표준 Middleware를 이용함으로써 생산에서부터 가정 설치에 이르기까지 추적 관리가 가능하며 오브젝트 정보를 PC나 PDA를 통하여 확인 할 수 있다. RFID를 이용한 전력설비 관리는 향후 센서기능까지 확대 적용이 된다면 전력산업 유비쿼터스 실현에 중요부분을 담당하게 될 것이다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.251-256
• /
• 2021

개체명 인식은 정보 추출의 하위 작업으로, 문서에서 개체명에 해당하는 단어를 찾아 알맞은 개체명을 분류하는 자연어처리 기술이다. 질의 응답, 관계 추출 등과 같은 자연어처리 작업에 대한 관심이 높아짐에 따라 세부 분류 개체명 인식에 대한 수요가 증가했다. 그러나 기존 개체명 인식 성능에 비해 세부 분류 개체명 인식의 성능이 낮다. 이러한 성능 차이의 원인은 세부 분류 개체명 데이터가 불균형하기 때문이다. 본 논문에서는 이러한 데이터 불균형 문제를 해결하기 위해 대분류 개체명 정보를 활용하여 세부 분류 개체명 인식을 수행하는 방법과 대분류 개체명 인식의 오류 전파를 완화하기 위한 2단계 학습 방법을 제안한다. 또한 레이블 주의집중 네트워크 기반의 구조에서 레이블의 공통 요소를 공유하여 세부 분류 개체명 인식에 효과적인 레이블 임베딩 구성 방법을 제안한다.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.4 no.4
• /
• pp.277-286
• /
• 2002

Most of the problems in dealing with the tunnel construction are the uncertainties and complexities of the stress conditions and rock strengths in ahead of the tunnel excavation. The limitations on the investigation technology, inaccessibility of borehole test in mountain area and public hatred also restrict our knowledge on the geologic conditions on the mountainous tunneling area. Nevertheless an extensive and superior geophysical exploration data is possibly acquired deep within the mountain area, with up to the tunnel locations in the case of alternative design or turn-key base projects. An appealing claim in the use of artificial neural networks (ANN) is that they give a more trustworthy results on our data based on identifying relevant input variables such as a little geotechnical information and biological learning principles. In this study, error back-propagation algorithm that is one of the teaching techniques of ANN is applied to presupposition on Rock Mass Ratings (RMR) for unknown tunnel area. In order to verify the applicability of this model, a 4km railway tunnel's field data are verified and used as input parameters for the prediction of RMR, with the learned pattern by error back propagation logics. ANN is one of basic methods in solving the geotechnical uncertainties and helpful in solving the problems with data consistency, but needs some modification on the technical problems and we hope our study to be developed in the future design work.

• Geophysics and Geophysical Exploration
• /
• v.11 no.4
• /
• pp.361-367
• /
• 2008

When constructing a synthetic seismogram in the earthquake study or in seismic data interpretation by using a ray-tracing technique, the most troublesome and error-prone task is to define a suite of ray codes for the corresponding rays to trace in advance. An infinite number of rays exist for any arbitrarily located source and receiver in a medium. Missing certain important rays or an inappropriate selection of ray codes in tracing rays may result in wrong interpretation of the earthquake record or seismogram. Automatic ray code generation could be able to eliminate those problems. In this study we have developed an efficient algorithm with which one can generate systematically all the ray codes for the source(s) and receiver(s) arbitrarily located in a model. The result of this work could be used not only in analysing multiples in seismic data processing and interpretation, but also in coda wave study, study on the amplification effects in a basin and phase identification of the waves multiply reflected/refracted in earthquake study.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.7
• /
• pp.1425-1431
• /
• 2005

In this paper, we consider the ISR(Intelligence, Surveillance, and Reconnaissance) system which collects the imagery intelligence from an airplane and CDL(common data link) communication system which transports the information obtained by the ISR system. The IMINT(imagery intelligence) consists of MPEG-2 transport stream packets and they transmit through CDL. We have some simulations for communication performances of CDL and show performance improvements using convolutional coding. We have compared BER performances under AWGN channel and fading channel which is caused by the velocity of an airplane.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.10 s.352
• /
• pp.27-34
• /
• 2006

This paper has implemented a very small($1.4{\times}2.8[Cm^2]$) 13.56[MHz] RFID reader ensuring machine ID recognition correctly in a noise space of Tag-to-Reader within 3Cm. For operation of the RFID system, at first, this paper has designed the loop antenna of a reader and the fading model of back-scattering on microwave propagation following to 13.56[MHz] RFID Air Interface ISO/IEC specification. Secondly, this paper has proposed the automatically path selected RF switching circuit and the firmware operation relationship by measuring and analyzing the very small RFID RF issues. Finally, as a very small reader main body, this paper has shown the DSP board and software functions made for extraction of $1{\sim}2$ machine ID information and error prevention simultaneously with carrying of 13.56[MHz] RFID signals that the international standard specification ISO/IEC 18000-3 defined.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.9 no.4
• /
• pp.462-472
• /
• 1998

In this paper, considering the Rayleigh fading, the lognormal shadowing, and the man-made noise which is occurred in urban area randomly, the mobile radio channel and the radio propagations are analyzed. The system affected by the noise is compared to other modelings. The fading, shadowing, and background noise are wholly considered to evaluate the mobile radio propagation effectively. For N=0.000001, the outage probability in the absence of noise is $5.264{times}10^{-6}$, in the fading only $3.1796{times}10^{-4}$, and in the presence of noise $6.0{\times}10^{-3}$. The analysis with the presence of noise is very important for the performance evaluation of mobile radio system.

• Korean Journal of Remote Sensing
• /
• v.15 no.1
• /
• pp.39-50
• /
• 1999

It is complicate and time-consuming process to classify a multi-band satellite imagery according to the application. In addition, classification rate sensitively depends on the selection of training data set and features in a supervised classification process. This paper introduced a classification network adopting a fuzzy-based $\gamma$-model in order to select a training data set and to extract feature which highly contribute to an actual classification. The features used in the classification were gray-level histogram, textures, and NDVI(Normalized Difference Vegetation Index) of target imagery. Moreover, in order to minimize the errors in the classification network, the Gradient Descent method was used in the training process for the $\gamma$-parameters at each code used. The trained parameters made it possible to know the connectivity of each node and to delete the void features from all the possible input features.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.197-202
• /
• 2021

Biometric technology using finger veins is receiving a lot of attention due to its high security, convenience and accuracy. And the recent development of deep learning technology has improved the processing speed and accuracy for authentication. However, the training data is a subset of real data not in a certain order or method and the results are not constant. so the amount of data and the complexity of the artificial neural network must be considered. In this paper, the deep learning model of Inception-Resnet-v2 was used to improve the high accuracy of the finger vein recognizer and the performance of the authentication system, We compared and analyzed the performance of the deep learning model of DenseNet-201. The simulations used data from MMCBNU_6000 of Jeonbuk National University and finger vein images taken directly. There is no preprocessing for the image in the finger vein authentication system, and the results are checked through EER.