• 산업공학
• /
• 제12권4호
• /
• pp.551-556
• /
• 1999

In this paper, we compare the performance of three data mining classification algorithms(neural network, decision tree, logistic regression) in consideration of various characteristics of categorical input and output data. $2^{4-1}$. 3 fractional factorial design is used to simulate the comparison situation where factors used are (1) the categorical ratio of input variables, (2) the complexity of functional relationship between the output and input variables, (3) the size of randomness in the relationship, (4) the categorical ratio of an output variable, and (5) the classification algorithm. Experimental study results indicate the following: decision tree performs better than the others when the relationship between output and input variables is simple while logistic regression is better when the other way is around; and neural network appears a better choice than the others when the randomness in the relationship is relatively large. We also use Taguchi design to improve the practicality of our study results by letting the relationship between the output and input variables as a noise factor. As a result, the classification accuracy of neural network and decision tree turns out to be higher than that of logistic regression, when the categorical proportion of the output variable is even.

• 한국통신학회논문지
• /
• 제24권12B호
• /
• pp.2415-2423
• /
• 1999

We propose a new optical method which conceals the data of authorized persons by encryption before they are stored or compared in the pattern recognition system for security systems. This proposed security system is made up of two subsystems : a proposed optical encryption system and a pattern recognition system based on the JTC which has been shown to perform well. In this system, each image of authorized persons as a reference image is stored in memory units through the proposed encryption system. And if a fingerprint image is placed in the input plane of this security system for access to a restricted area, the image is encoded by the encryption system then compared with the encrypted reference image. Therefore because the captured input image and the reference data are encrypted, it is difficult to decrypt the image if one does not know the encryption key bit stream. The basic idea is that the input image is encrypted by performing optical XOR operations with the key bit stream that is generated by digital encryption algorithms. The optical XOR operations between the key bit stream and the input image are performed by the polarization encoding method using the polarization characteristics of LCDs. The results of XOR operations which are detected by a CCD camera should be used as an input to the JTC for comparison with a data base. We have verified the idea proposed here with computer simulations and the simulation results were also shown.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1996년도 International Conference on Agricultural Machinery Engineering Proceedings
• /
• pp.1073-1080
• /
• 1996

The impact of the input and output probability distributions on the performance of neural networks to forecast two year peak stream flow (cubic meters per second) is examined for two major river basins of the US. The neural network input consisted of drainage area(square kilometers ) and elevation (meters). When data are normally distributed , the neural networks predict much better than when the data are non-normal and have larger tails in their distributions.

• 한국통신학회논문지
• /
• 제21권2호
• /
• pp.313-325
• /
• 1996

This paper presents a new architecture for full-search block-matching motion estimation. The architecture is based on linear systolic arrays. High speed operation is obtained by feeding reference data, search data, and control signals into the linear systolic array in a pipelined fashion. Input data are fed into the linear systolic array at a half of the processor speed, reducing the required data bandwidth to half. The proposed architecture has a good scalability with respect to the number of processors and input bandwidth when the size of reference block and search range change.

• 한국융합학회논문지
• /
• 제10권2호
• /
• pp.1-6
• /
• 2019

제안 모델은 소실 데이터를 포함하는 불완전한 데이터에서 정보의 손실을 최소화할 수 있도록 개발되었다. 이를 위한 과정은 우선 데이터 확장기법을 이용하여 손실 정보를 보상하도록 학습 데이터를 변환한다. 이 변환 과정에서 데이터의 속성값은 원-핫 인코딩으로 이진 또는 확률값으로 채워진다. 다음 이 변환 데이터는 딥러닝 모델에 입력되는데, 이때 각 속성의 카디너리티에 따라 엔트리 수가 일정하지 않게 된다. 그리고 각 속성의 엔트리 값들을 각각의 입력 노드에 할당하고 학습을 진행한다. 이점이 기존 학습 모델과의 차이점으로, 임의의 속성값이 입력층에서 여러 개의 노드로 분산되는 특이한 구조를 가진다. 제안 모델의 학습 성능을 평가하기 위해, 소실 데이터를 대상으로 다양한 실험을 수행하여 성능 면에서 우수함을 보인다. 제안 모델은 유비쿼터스 환경에서 손실을 최소화하기 위한 알고리즘으로 유용하게 사용될 것으로 본다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2003년도 춘계종합학술대회
• /
• pp.473-476
• /
• 2003

오늘날 인터넷은 하나의 거대한 분산 정보 서비스센터의 역할을 수행하며 여러 가지 많은 정보들과 이를 관리 운영하는 데이터 베이스 서버들은 분산된 네트워크 환경 속에서 광범위하게 존재하고 있다. 그러나 우리는 데이터 특성에 따라 입력 데이터를 처리할 서버를 결정하는데 여러 가지 어려움을 겪고 있다. 본 논문에서는 분산 환경 속에 존재하는 수많은 데이터들 가운데 신경망을 이용해 입력 데이터 패턴을 가장 효율적으로 처리할 수 있는 목적지 서버를 마이닝하는 기법과 이를 기반으로 한 지능적 데이터 마이닝 시스템 구조를 설계하였다. 그 결과로서 새로운 입력 데이터패턴이 신경망으로 구현된 동적 바인딩 방법에 따라 목적지 서버를 결정한 후 처리됨을 보였다. 이 기법은 데이터 웨어하우스, 통신 및 전력부하패턴 분석, 인구센서스 분석, 의료데이터 분석에 활용될 수 있다.

• 전자공학회논문지A
• /
• 제33A권11호
• /
• pp.1-9
• /
• 1996

In the following paper, new architectural algorithm of clock and data recovery circuit is proposed for 622.08 Mbps optical communication receiver. New algorithm makes use of charge pump PLL using voltage controlled ring oscillator and extracts 8-channel 77.76 MHz clock signals, which are delayed by i/8 (i=1,2, ...8), to convert and recover 8-channel parallel data from 662.08 Mbps MRZ serial data. This circuit includes clock genration block to produce clock signals continuously even if input data doesn't exist. And synchronization of data and clock is doen by the method which compares 1/2 bit delayed onput data and decided dta by extracted clock signals. Thus, we can stabilize frequency and phase of clock signal even if input data is distorted or doesn't exist and simplify receiver architecture compared to traditional receiver's. Also it is possible ot realize clock extraction, data decision and conversion simulataneously. Verification of this algorithm is executed by DESIGN CENTER (version 6.1) using test models which are modelized by analog behavior modeling and digital circuit model, modified to process input frequency sufficiently, in SPICE.

• 한국산학기술학회논문지
• /
• 제12권11호
• /
• pp.5164-5171
• /
• 2011

비선형 공정에 대한 퍼지 모델링은 일반적으로 주어진 데이터를 이용하여 입력 변수를 선정하고 각 입력 변수에 대한 입력 공간을 분할하여 이들 입력 변수 및 공간 분할에 의해 퍼지 규칙을 형성한다. 퍼지 규칙의 전반부는 입력 변수 선정, 공간 분할 수 및 소속 함수에 의해 동정되고 퍼지 규칙의 후반부는 간략 추론, 선형 추론에 의해 다항식 함수의 형태로 동정된다. 일반적으로 주어진 데이터를 이용한 비선형 공정에 대한 퍼지 규칙의 형성은 차원이 증가할수록 규칙의 수가 지수적으로 증가하는 문제를 가지고 있다. 이를 해결하기 위해 각 입력 공간의 퍼지 분할에 의한 퍼지 규칙을 개별적으로 형성함으로써 복잡한 비선형 공정을 모델링 할 수 있다. 따라서 본 논문에서는 개별적인 입력 공간을 활용하여 퍼지 규칙을 생성한다. 퍼지 규칙의 전반부 파라미터는 입력 데이터의 최소 값과 최대 값을 이용하는 최소-최대 방법을 이용하여 동정되고, 소속 함수는 삼각형, 범종형, 사다리꼴형 소속 함수를 사용한다. 마지막으로, 비선형 공정으로는 널리 이용되는 데이터를 이용하여 시스템 특성 및 성능을 평가한다.

• 전자공학회논문지B
• /
• 제31B권7호
• /
• pp.199-210
• /
• 1994

Most of clustering methods usually employ a center or predefined shape of a cluster to assign the input data into the cluster. When there is no information about data set, it is impossible to predict how many clusters are to be or what shape clusters take. (the shape of clusters could not be easily represented by the center or predefined shape of clusters) Therefore, it is difficult to assign input data into a proper cluster using previous methods. In this paper, to overcome such a difficulty a cluster is to be represented as a collection of several subclusters representing boundary of the cluster. And membership functions are used to represent how much input data bllongs to subclusters. Then the position of the nearest subcluster is adaptively corrected for expansion of cluster, which the subcluster belongs to by use of a competitive learning neural network. To show the validity of the proposed method a numerical example is illustrated where FMMC(Fuzzy Min-Max Clustering) algorithm is compared with the proposed method.

• 기술경영경제학회:학술대회논문집
• /
• 기술경영경제학회 1997년도 제11회 하계학술발표회 논문집
• /
• pp.160-171
• /
• 1997

This paper starts out by reviewing the literature that in different ways utilizes patent data as a output of R&D investment. The main focus, however, is an analysis of time-lag between R&D input and output. To achieve this research objective, the basic data associated with the R&D input(expenditure, researchers) and output(patent, utilities) for the past 15 years, from 1980 to 1994, in the areas of electrical-electronic, mechanical and chemical industries have been collected. And the raw output data were altered it to objective data using Laspeyres approach and analyzed using multiple regression analysis, especially stepwise regression analysis. The result of this study can be summarized as follows: a) The time-lag between R&D input and output is from 1 to 4 years. This result is equal to the research conclusion of the existing foreign studies. b) It was found that the time-lag of patents was longer than of utility models. c) It was showed that the time-lag of electrical-electronic, mechanical industry was longer than the chemical one.