• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.16-16
• /
• 2000

This paper describes a new structure re create a pseudo Gaussian function network (PGFN). The activation function of hidden layer does not necessarily have to be symmetric with respect to center. To give the flexibility of the network, the deviation of pseudo Gaussian function is changed according to a direction of given input. This property helps that given function can be described effectively with a minimum number of center by PGFN, The distribution of deviation is represented by level set method and also the loaming of deviation is adjusted based on it. To demonstrate the performance of the proposed network, general problem of function estimation is treated here. The representation problem of continuous functions defined over two-dimensional input space is solved.

• 품질경영학회지
• /
• 제36권1호
• /
• pp.72-79
• /
• 2008

The policy for credit card approval/disapproval is based on the applier's personal and financial information. In this paper, we will analyze 2 credit card approval data with several classification methods. We identify which variables are important factors to decide the approval of credit card. Our main tool is an open-source statistical programming environment R which is freely available from http://www.r-project.org. It is getting popular recently because of its flexibility and a lot of packages (libraries) made by R-users in the world. We will use most widely used methods, LDNQDA, Logistic Regression, CART (Classification and Regression Trees), neural network, and SVM (Support Vector Machines) for comparisons.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2006년도 춘계학술발표논문집
• /
• pp.311-315
• /
• 2006

"Dynamic Neural Unit"(DNU) based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our methodis different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its trainin

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2006년도 춘계학술발표논문집
• /
• pp.316-319
• /
• 2006

Connectionist networks, also called neural networks, have been broadly applied to solve many different problems since McCulloch and Pitts had shown mathematically their information processing ability in 1943. In this thesis, we present a genetic neuro-control scheme for nonlinear systems. Our method is different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its training.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 하계학술대회 논문집 D
• /
• pp.2486-2489
• /
• 2002

Pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our method is different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its training.

• 대한임베디드공학회논문지
• /
• 제15권2호
• /
• pp.43-49
• /
• 2020

In this paper, we propose a stage-wise knowledge transfer method that uses block-wise retraining to transfer the useful knowledge of a pre-trained residual network (ResNet) in a teacher-student framework (TSF). First, multiple hint information transfer and block-wise supervised retraining of the information was alternatively performed between teacher and student ResNet models. Next, Softened output information-based knowledge transfer was additionally considered in the TSF. The results experimentally showed that the proposed method using multiple hint-based bottom-up knowledge transfer coupled with incremental block-wise retraining provided the improved student ResNet with higher accuracy than existing KD and hint-based knowledge transfer methods considered in this study.

• 전자공학회논문지B
• /
• 제33B권8호
• /
• pp.124-133
• /
• 1996

This paper presents the implementation of variable structure control system for a linear or nonlinear system using neural networks. The overall control system consists of neural network controller and a reaching mode controller. While the former approximates the equivalent control input on the sliding surface, the latter is used to bring the entire system trajectories toward the sliding surface. No supervised learning procedures are needed and the weights of the neural network are tuned on-line automatically. The neural netowrk-based variable structure control system is applied to a nonlinare unstable inverted pendulum system through computer simulations, and implemented using a microcomputer (80486-50MHz) and applied to the DC servomotor position control system. Simulation and experimental results show the expected approximation sliding property is occurred. The proposed controller is compared with a PID controller and shows better performance than the PID controller in abrupt plant parameter change.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2016년도 춘계학술발표대회
• /
• pp.649-652
• /
• 2016

빅데이터 시대와 다양한 웨어러블 디바이스의 등장으로 사용자로부터 다양한 비정형 데이터를 수집할 수 있고 분석을 통해 정보를 제공하는 연구가 증가하고 있다. 본 논문에서 사용한 nymi 밴드를 통해 사용자의 ECG 신호에 대한 수집이 가능해졌고 수집된 데이터를 이용하여 부정맥과 관련된 데이터 분석이 가능해 졌다. 지도 학습의 방법중 하나인 분류 기법을 사용하여 수집 되는 ECG 신호 데이터에 대한 부정맥 질병을 판단할 수 있는 시스템을 제안한다.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2013년도 제25회 한글 및 한국어 정보처리 학술대회
• /
• pp.33-38
• /
• 2013

소셜미디어를 통한 여론분석과 브랜드 모니터링에 대한 요구가 증가하면서, 빅데이터로부터 감성을 분석하는 기술에 대한 필요가 늘고 있다. 이를 위해, 본 논문에서는 단순 긍/부정 감성이 아닌 20종류의 세분화된 감성을 분석하기 위한 감성어휘 구축 알고리즘을 제시한다. 감성어휘 구축을 위해서는 준지도학습을 사용하였으며, 도메인에 특화되지 않은 일반 감성어휘를 구축하도록 학습되었다. 학습된 감성어휘를 인물, 스마트기기, 정책 등 다양한 도메인의 트위터 데이터에 적용하여 세부감성을 분석한 결과, 알고리즘의 특성상 재현율이 낮다는 한계를 가지고 있었으나, 대부분의 감성에 대해 높은 정확도를 지닌 감성어휘를 구축할 수 있었고, 감성을 직간접적으로 나타내는 표현들을 학습할 수 있었다.

• 제어로봇시스템학회논문지
• /
• 제6권1호
• /
• pp.112-119
• /
• 2000

A die-casting junction method is usually used to manufacture the tub of an IH(induction heating) jar. If there is a very small air bubble in the junction area, the thermal conductivity is deteriorated and local overheat occurs. Such problem brings serious inferiority of the IH jar. In this paper, we propose a new method to detect such defect with simply measured thermal data. Thermal distribution of preheated tubs is obtained by scanning with infrared thermal sensors and analyzed with the statistic pattern recognition method. By defining the characteristic feature as the temperature difference between sensors and using ellipsoid function as decision boundary, a supervised learning method of genetic algorithm is proposed to obtain the required parpameters. After applying the proposed method to experiment, we have proved that the rate of recognition is high even for a small number of data set.