• 한국정보통신학회논문지
• /
• 제25권11호
• /
• pp.1486-1494
• /
• 2021

문자 인식은 스마트 주차, text to speech 등 최근 다양한 플랫폼에서 필요로 하는 기술로써, 기존의 방법과 달리 새로운 시도를 통하여 그 성능을 향상시키려는 연구들이 진행되고 있다. 그러나 문자 인식에 사용되는 이미지의 품질이 낮을 경우, 문자 인식기 학습용 이미지와 테스트 이미지간에 해상도 차이가 발생하여 정확도가 떨어지는 문제가 발생된다. 이를 해결하기 위해 본 논문은 문자 인식 모델 성능이 다양한 품질 데이터에 대하여 강인하도록 이미지 초해상도 및 문자 인식을 결합한 통째학습 신경망을 설계하고, 대안적 통째학습 알고리즘을 구현하여 통째 신경망 학습을 수행하였다. 다양한 문자 이미지 중 차량 번호판 이미지를 이용하여 대안적 통째학습 및 인식 성능 테스트를 진행하였고, 이를 통해 제안하는 알고리즘의 효과를 검증하였다.

• Structural Engineering and Mechanics
• /
• 제23권2호
• /
• pp.177-193
• /
• 2006

Determining the hysteretic energy demand and dissipation capacity and level of damage of the structure to a predefined earthquake ground motion is a highly non-linear problem and is one of the questions involved in predicting the structure's response for low-performance levels (life safe, near collapse, collapse) in performance-based earthquake resistant design. Neural Network (NN) analysis offers an alternative approach for investigation of non-linear relationships in engineering problems. The results of NN yield a more realistic and accurate prediction. A NN model can help the engineer to predict the seismic performance of the structure and to design the structural elements, even when there is not adequate information at the early stages of the design process. The principal aim of this study is to develop and test multi-layered feedforward NNs trained with the back-propagation algorithm to model the non-linear relationship between the structural and ground motion parameters and the hysteretic energy demand in steel moment resisting frames. The approach adapted in this study was shown to be capable of providing accurate estimates of hysteretic energy demand by using the six design parameters.

• 한국IT서비스학회지
• /
• 제7권1호
• /
• pp.195-204
• /
• 2008

As the dependency to network system and demands of efficient storage systems rapidly grows in every networking filed, the current trends initiated by explosive networked data grow due to the wide-spread of internet multimedia data and internet requires a paradigm shift from computing-centric to data-centric in storage systems. Furthermore, the new environment of file systems such as SAN(Storage Area Network) is adopted to the existing storage paradigm for providing high availability and efficient data access. We describe the design issues and system components of $SANique^{TM}$, which is the cluster file system based on SAN environment. We, especially, present the comparative results of performance analysis for the intensive I/O test by using the DBMSs that are operated at the top of cluster file system $SANique^{TM}$, EXT3 and NFS respectively.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권3호
• /
• pp.118-121
• /
• 2023

Recently, green energy support policies have been announced around the world in accordance with environmental regulations, and asthe market grows rapidly, demand for batteries is also increasing. Therefore, various methodologies for battery diagnosis and recycling methods are being discussed, but current accurate life prediction of batteries has limitations due to the nonlinear form according to the internal structure or chemical change of the battery. In this paper, CS2 lithium-ion battery measurement data measured at the A. James Clark School of Engineering, University of Marylan was used to predict battery performance with high accuracy using a convolutional neural network (CNN) model among deep learning-based models. As a result, the battery performance was predicted with high accuracy. A data structure with a matrix of total data 3,931 ☓ 19 was designed as test data for the CS2 battery and checking the result values, the MAE was 0.8451, the RMSE was 1.3448, and the accuracy was 0.984, confirming excellent performance.

• 한국추진공학회지
• /
• 제10권2호
• /
• pp.15-22
• /
• 2006

PW206C 터보 축 엔진을 위해 신경회로망을 이용한 지능형 성능 진단 프로그램이 제안되었다. 이 엔진은 항공우주연구원에서 개발 중에 있는 틸트 로터 타입 스마트 무인기의 추진시스템으로 선정되었다. 1개의 은닉층, 입력층, 출력층을 가지는 BPN(Back Propagation Network)이 신경회로망을 학습시키기 위해 이용되었다 입력층은 7개의 뉴런을 가지는데 SHP, MF, PT2, TT2, PT4, TT4 및 TT5와 같은 측정파라미터이며 출력층은 6개의 뉴런으로 구성되어 있으며 각각은 압축기, 압축기 터빈, 동력 터빈의 유량함수 및 효율이다. 신경망을 훈련하고 테스트하기 위한 데이터 베이스는 가스터빈 성능모사 프로그램을 이용하여 구성하였다. 훈련된 신경망을 PW206C 터보 축 엔진의 진단에 적용한 결과 제안된 진단 알고리즘이 압축기 오염과 압축기 터빈의 침식과 같은 단일 손상을 탐지하는데 유용함을 확인하였다.

• 한국인터넷방송통신학회논문지
• /
• 제21권6호
• /
• pp.91-97
• /
• 2021

마이크로서버는 컴퓨팅 서버의 일종으로 2개 이상의 CPU 소켓을 별도의 컴퓨팅 보드에 구현하고, 다수 개의 컴퓨팅 보드를 메인 보드에 집적하는 형태를 지닌다. 클러스터 시스템을 구축하는데 있어서, 마이크로서버를 사용하면 기존의 서버를 여러 대 랙에 장착하는 방법에 비해, 에너지 효율, 상면, 관리 용이성 측면에서 이점이 있다. 또한, 마이크로서버는 컴퓨팅 보드내 CPU 소켓들, 혹은 컴퓨팅 보드끼리 별도의 내부 연결망을 사용할 수 있어서 성능 측면에서도 이점이 존재한다. 본 논문에서 제안된 마이크로서버는 4개의 CPU 소켓을 지닌 컴퓨팅 보드를 메인보드에 총 16개 장착할 수 있는 서버로 Serial-RapidIO (SRIO)를 내부 연결망으로 사용한다. 마이크로서버의 핵심 성능 이슈인 내부 연결망 측면에서의 성능 비교 분석을 위해, 상용 마이크로서버와 내부 연결망 성능을 비교하고 정량화한다. 시험 결과, 내부 연결망을 활용한 데이터 전송 시 대역폭 측면에서 최대 7배 높은 성능을 보였다. 아울러, 실제 클라우드 컴퓨팅에 사용되는 벤치마크 프로그램 적용 시험에서도 유사 CPU 성능 마이크로서버 대비 60%의 수행시간 감소 효과를 얻었다.

• Nuclear Engineering and Technology
• /
• 제49권5호
• /
• pp.989-995
• /
• 2017

Distributed Control System (DCS) communication networks, which use Fast Ethernet with redundant networks for the transmission of information, have been installed in digitalized nuclear power plants. Normally, failover tests are performed to verify the reliability of redundant networks during design and manufacturing phases; however, systematic integrity tests of DCS networks cannot be fully performed during these phases because all relevant equipment is not installed completely during these two phases. In additions, practical verification tests are insufficient, and there is a need to test the actual failover function of DCS redundant networks in the target environment. The purpose of this study is to verify that the failover functions works correctly in certain abnormal conditions during installation and commissioning phase and identify the influence of network failover on the entire DCS. To quantify the effects of network failover in the DCS, the packets (Protocol Data Units) must be collected and resource usage of the system has to be monitored and analyzed. This study introduces the use of a new methodology for verification of DCS network failover during the installation and commissioning phases. This study is expected to provide insight into verification methodology and the failover effects from DCS redundant networks. It also provides test results of network performance from DCS network failover in digitalized domestic nuclear power plants (NPPs).

• 한국군사과학기술학회지
• /
• 제4권2호
• /
• pp.189-201
• /
• 2001

For a design of multi-layer armor, the extensive full scale or sub-scale penetration test data are required. In generally, the collection of penetration data is in need of time-consuming and expensive processes. However, the application of numerical or analytical method is very limited due to poor understanding about penetration mechanics. In this paper, we have developed a neural network analyzer which can be used as a design tool for a new armor. Calculation results show that the developed neural network analyzer can predict relatively exact penetration depth of a new armor through the effective analysis of the pre-existing penetration database.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권11호
• /
• pp.780-785
• /
• 2004

In this paper, we proposed a ventricular fibrillation detection algorithm based on wavelet transform and artificial neural network. we selected RR intervals, the 6th and 7th wavelet coefficients(D6, D7) as features for classifying ventricular fibrillation. To evaluate the performance of the proposed algorithm, we compared the result of the proposed algorithm with that of fuzzy inference and fuzzy-neural network. MIT-BIH Arrhythmia database, Creighton University Ventricular Tachyarrhythmia database and MIH-BIH Malignant Ventricular Arrhythmia database were used as test and learning data. Among the algorithms, the proposed algorithm showed that the classification rate of normal and abnormal beat was sensitivity(%) of 96.10 and predictive positive value(%) of 99.07, and that of ventricular fibrillation was sensitivity(%) of 99.45. Finally. the proposed algorithm showed good performance compared to two other methods.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권2호
• /
• pp.114-118
• /
• 2005

Recently, in order to guarantee the quality of the final product from the production line, several equipments able to examine the polymer ingredients' quality are being used. Rheotruder is one of the equipments manufactured to measure the viscosity of the ingredient that is an important factor for the quality of final product. However, Rheotruder has nonlinear characteristics such as time delay which make systematic analysis difficult. In this paper, in order to enhance the performance of Rheotruder, a new scheme is introduced. It incorporates TDNN (Time Delay Neural Network) bank and Elman network to get a right decision on whether the tested ingredient is good or not. Furthermore, the proposed scheme is verified through real test execution.