• 전자공학회논문지A
• /
• 제31A권3호
• /
• pp.1-9
• /
• 1994

In this paper as a new approach for real-time multitarget tracking, a hybrid OptoNeural multitarget tracking system based on optical BJTC and neural networks data association algorithm is suggested. In the proposed hybrid tracking system, an optical BJTC is introduced as a preprocessor to reduce the massive input target data into a few correlation peak signals and then the neural networks data association algorithm is used for the massively parallel data association between measurement signals and targets in real-time. Finally, new hybrid type OptoNeural target tracking system is constructed and then some experimental results on multitarget tracking is included. The real-time implementation method of the proposed hybrid system is also discussed.

• 한국신재생에너지학회:학술대회논문집
• /
• 한국신재생에너지학회 2011년도 추계학술대회 초록집
• /
• pp.41.2-41.2
• /
• 2011

NREL NWTC Deside codes are analyzed and introduced to develop the system performance simulation program for wind turbine generator systems. In this paper, The AirfoilPrep generating the airfoil data, the IECWind generating hub-height wind data with extreme condition following IEC 61400-1, the TurbSim generating stochastic full-field turbulent wind data, the PreComp calculating structural and dynamic properties of composite blade and the BModes making mode shapes of blade and tower are explained respectively.

• 설비공학논문집
• /
• 제14권7호
• /
• pp.560-566
• /
• 2002

The fault detection and diagnosis technology may be applied in order to decrease the energy consumption and the maintenance cost of the air-conditioning system. In this study, two different types of faults in the air-conditioning system, such as the condenser fouling and the evaporator fan slowdown, were considered. The neural network algorithm combined with data preprocessor was developed and applied to detect the faults of the real system. Test results show that this method is very effective to detect the faults in the air-conditioning system. Therefore, this developed method can be used for the development of the air-conditioner fault detection system.

• 연구논문집
• /
• 통권25호
• /
• pp.67-76
• /
• 1995

A grid generation algorithm associated with turbomachinery cascade flow fields has been developed. The present grid generation system consists of four separate modules. The system input is made of the results of the preliminary design, i.e., flow-path, aerodynamic conditions along the spanwise direction, and the blade profile data. The grid generation method generates a series of two-dimensional grids in the blade-to-blade passage to build up the three-¬dimensional grid, The numerical algorithm adopts the combination of the algebraic and elliptic method to create the internal grids efficiently and quickly. The resultant grids generated from each module of the system are used as the preprocessor for the performance prediction of the turbomachinery blade using Naveir-Stokes method in addition to the blade surface modelling for CAD data. For purposes of illustration, the grid generation system is applied to several complex geometries inculding a turbine rotor with and without a tip flow grid. Application to the blade design of the LP compressor was demonstrated to be very reliable and practical in support of design activities. This customized system are coupled strongly with the design procedure and reduces the man-hours required to predict the aerodynamic performance of the turbomachinery cascades using the CFD technique.

• 한국산업융합학회 논문집
• /
• 제2권2호
• /
• pp.41-49
• /
• 1999

In general, FORTRAN is used for numerical analysis and OPS5 or LISP is used for expert systems, This causes problems at the interface because the various applications require different computing languages or environments. This paper describes the approach used to take AutoCAD as a user-interface for an existing finite element structural analysis package. Some principles concerning database management related to data-exchange interface of pre- and post-processing system for FORTRAN structural analysis program are discussed, and numerical examples demonstrate the power of the combination of these programs.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2012년도 추계학술발표대회
• /
• pp.118-120
• /
• 2012

이 논문에서는 MapReduce 프레임워크를 활용한 기후 시뮬레이션 결과의 데이터분석을 위한 전처리 과정을 다룬다. 이를 위해 기후 시뮬레이션 결과 데이터 셋으로부터 특정변수를 추출하여 자료를 변환한 후 변환된 자료를 HDFS 에 저장하기 위한 과학데이터 필터를 설계한다. 설계된 필터를 통해 저장된 자료는 Hadoop 의 MapReduce 응용을 통해 연도별 통계처리를 분산병렬 방식으로 수행한다.

• 한국멀티미디어학회논문지
• /
• 제24권12호
• /
• pp.1663-1672
• /
• 2021

There are various typing practice applications. In addition, research cases on learning applications that support typing practice have been reported. These services are usually provided in a way that utilizes their own built-in text. Learners collect various contents through web services and use them a lot for learning. Therefore, this paper proposes a learning application to increase the learning effect by collecting vast amounts of web content and applying it to typing practice. The proposed application is implemented using Tkinter, a GUI module of Python. BeautifulSoup module of Python is used to extract information from the web. In order to process the extracted data, the NLTK module, which is an English data preprocessor, and the KoNLPy module, which is a Korean language processing module, are used. The operation of the proposed function is verified in the implementation and experimental results.

• 한국정보통신학회논문지
• /
• 제25권4호
• /
• pp.537-542
• /
• 2021

스마트 TV는 인터넷을 기반으로 기존의 TV에 비해 다양한 서비스와 정보를 제공하고 있다. 보다 개인화된 서비스나 정보를 제공하기 위해서는 사용자의 시청 패턴을 분석하고 이를 기반으로 맞춤형 서비스나 정보를 제공해야한다. 제안하는 시스템은 사용자의 TV 시청 패턴을 입력받고 이를 분석하여 사용자에게 맞춤형 정보로써 TV 프로그램이나 영화를 추천한다. 이를 위해 전처리기와 딥러닝(deep learning) 모델로 시스템을 구성하였다. 전처리기는 사용자가 시청한 TV 프로그램의 이름과 해당 TV 프로그램을 시청한 날짜, 시청한 시간 등을 입력하면 이를 정제한다. 그리고 정제된 데이터를 다중속성 LSTM 모델이 학습하고 예측을 수행하게 된다. 제안하는 시스템은 사용자에게 맞춤형 정보를 제공하는 시스템으로써 기존의 IoT 기술과 딥러닝 기술을 융합한 디지털 컨버전스(convergence)의 선도 기술이 될 것으로 사료된다.

• 한국정보기술학회논문지
• /
• 제16권12호
• /
• pp.25-30
• /
• 2018

유전자 규정 네트워크 (GRN)에 RNA-시퀀싱 데이터를 활용할 때, 해당 유전자와 환경과의 상호 작용에 의해서 생기는 형질들 중에서 연관성이 높은 유전자로 GRN을 구성하는 것은 상당히 어려운 일이다. 본 연구에서는 Big-Data의 RNA-시퀀싱 자료들로, 지지 벡터 머신 회귀 특징 추출(SVM-RFE) 에 근거하여, 연관성이 높은 유전자(maximum-relevancy)는 추출하고, 연관성이 낮은 유전자(minimum-redundancy)는 제거하는 MRMR 필터 방법을 집중도 의존 정규화(intensity-dependent normalization, DEGSEQ)에 기반 하여 데이터의 정밀성을 높여, 소수 연관성 높은 유전자만 판별해 내는 방법을 사용한다. 제안한 방법은 R 언어 패키지를 사용하여 편리함과 동시에, 다른 기존의 방법을 비교하였을 때, Big-Data의 시간 활용도를 높이면서, 동시에 높은 연관성 있는 유전자만을 잘 추출해 냄을 확인하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2485-2489
• /
• 2005

This paper introduces a new preprocessing scheme to replace original data of gray scale images with particular ordered data so that performance of lossless compression can be improved more efficiently. As a kind of preprocessing technique to maximize performance of entropy encoder, the proposed method converts the input image data into more compressible form. Before encoding a stream of the input image, the proposed preprocessor counts co-occurrence frequencies for neighboring pixel pairs. Then, it replaces each pair of adjacent gray values with particular ordered numbers based on the investigated co-occurrence frequencies. When compressing ordered image using entropy encoder, we can expect to raise compression rate more highly because of enhanced statistical feature of the input image. In this paper, we show that lossless compression rate increased by up to 37.85% when comparing results from compressing preprocessed and non-preprocessed image data using entropy encoder such as Huffman, Arithmetic encoder.