• The Journal of the Acoustical Society of Korea
• /
• 제22권2E호
• /
• pp.49-55
• /
• 2003

The modified neural net pattern recognition equations were attempted to apply to speech recognition. The proposed method has a dynamic process of self-organization that has been proved to be successful in recognizing a depth perception in stereoscopic vision. This study has shown that the process has also been useful in recognizing human speech. In the processing, input vocal signals are first compared with standard models to measure similarities that are then given to a process of self-organization in neural net equations. The competitive and cooperative processes are conducted among neighboring input similarities, so that only one winner neuron is finally detected. In a comparative study, it showed that the proposed neural networks outperformed the conventional HMM speech recognizer under the same conditions.

• Journal of information and communication convergence engineering
• /
• 제1권4호
• /
• pp.177-182
• /
• 2003

Conventional multilayer feedforward artificial neural networks are very effective in dealing with spatial problems. To deal with problems with time dependency, some kinds of memory have to be built in the processing algorithm. In this paper we show how the newly proposed Serial Input Neuron (SIN) convolutional decoders can be derived. As an example, we derive the SIN decoder for rate code with constraint length 3. The SIN is tested in Gaussian channel and the results are compared to the results of the optimal Viterbi decoder. A SIN approach to decode convolutional codes is presented. No supervision is required. The decoder lends itself to pleasing implementations in hardware and processing codes with high speed in a time. However, the speed of the current circuits may set limits to the codes used. With increasing speeds of the circuits in the future, the proposed technique may become a tempting choice for decoding convolutional coding with long constraint lengths.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.213-217
• /
• 1990

Neural networks are a class of systems that have many simple processors (neurons) which are highly interconnected. The function of each neuron is simple, and the behavior is determined predominately by the set of interconnections. Thus, a neural network is a special form of parallel computer. Although a major impetus for using neural networks is that they may be able to "learn" the solution to the problem that they are to solve, we argue that another, perhaps even stronger, impetus is that they provide a framework for designing massively parallel machines. The highly interconnected architecture of switching networks suggests similarities to neural networks. Here, we present two switching applications in which neural networks can solve the problems efficiently. We also show that a computational advantage can be gained by using nonuniform time delays in the network.e network.

• 전자공학회논문지SC
• /
• 제38권4호
• /
• pp.31-36
• /
• 2001

본 논문에서는 근육의 움직임에 의해 유발되는 전기적 선호인 근전도(EMG) 신호를 신경회로망을 통해 분류하여 인체의 움직임을 파악하는 방법을 제안한다. 신호분류를 위한 신경회로망으로 학습에 의해 스스로 출력뉴런을 구성하는 SOM을 사용하였으며， 기존의 방식과 다르게 전처리 과정 없이 신호자세를 SOM의 입력으로 사용하여 패턴을 분류하는 간단한 방식이다. 실험과 시뮬레이션을 통해 제안한 방식의 유용성을 확인하였다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 춘계학술대회 학술발표 논문집
• /
• pp.259-262
• /
• 1997

This paper presents a visual servoing of RV-M2 robot manipulators to track and grasp moving object, using pruned dynamic recurrent neural networks(DRNN). The object is stationary in the robot work space and the robot is tracking and grasping the object by using CCD camera mounted on the end-effector. In order to optimize the structure of DRNN, we decide the node whether delete or add, by mutation probability, first in case of delete node, the node which have minimum sum of input weight is actually deleted, and then in case of add node, the weight is connected according to the number of case which added node can reach the other nodes. Using evolutionary programming(EP) that search the struture and weight of the DRNN, and evolution strategies(ES) which train the weight of neuron, we pruned the net structure of DRNN. We applied the DRNN to the Visual Servoing of a robot manipulators to control position and orientation of end-effector, and the validity and effectiveness of the pro osed control scheme will be verified by computer simulations.

• 전자공학회논문지B
• /
• 제31B권8호
• /
• pp.211-218
• /
• 1994

In this paper we develope a hybrid learning rule to improve the robustness of multi-layer Perceptions. In most neural networks the activation of a neuron is deternined by a nonlinear transformation of the weighted sum of inputs to the neurons. Investigating the behaviour of activations of hidden layer neurons a new learning algorithm is developed for improved robustness for multi-layer Perceptrons. Unlike other methods which reduce the network complexity by putting restrictions on synaptic weights our method based on error-backpropagation increases the complexity of the underlying proplem by imposing it saturation requirement on hidden layer neurons. We also found that the additional gradient-descent term for the requirement corresponds to the Hebbian rule and our algorithm incorporates the Hebbian learning rule into the error back-propagation rule. Computer simulation demonstrates fast learning convergence as well as improved robustness for classification and hetero-association of patterns.

• 한국통신학회논문지
• /
• 제15권4호
• /
• pp.295-300
• /
• 1990

역 운동학 문제는 로보트 매니퓰레이터 제어에서 중요한 관점이 되어 왔다. 본 논문에서는 Jacobi 제어 기법을 실현하기 위하여 Hopfield, Tank의 신경회로망 모델을 사용하였다. 뉴런의 상태는 매니퓰레이터의 관절 속도를 나타내고, 연결강도는 Jacobi 행렬의 값으로 결정되어 진다. 회로망의 에너지 함수는 실제 관절 속도와 원하는 관절 속도간의 최소 자승 오차와 대응하도록 구성한다. 매 샘플링에서 연결 강도와 뉴런의 상태는 현재의 관절위치값에 따라서 변한다. 여유 자유도를 가지는 평면 매니퓰레이터에 대한 역 운동학 해를 컴퓨터 시뮬레이션을 통하여 구하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1269-1271
• /
• 1996

This paper presents a visual servoing combined by evolutionary algorithms and neural network for a robotic manipulators to control position and orientation of the end-effector. Using the multi layer feedforward neural network that permits the connection of other layers, evolutionary programming(EP) that search the structure and weight of the neural network, and evolution strategies(ES) which training the weight of neuron, we optimized the net structure of control scheme. Using the four feature image information from CCD camera attached to end-effector of RV-M2 robot manipulator having 5 dof, we generate the control input to agree the target image, to realize the visual servoing. The validity and effectiveness of the proposed control scheme will be verified by computer simulations.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2002년도 춘계학술발표논문집 (하)
• /
• pp.1579-1582
• /
• 2002

LonWorks 을 이용해 홈 네트워크를 구성할 수 있다. 기존에는 하나의 노드가 되는 조명, 딤머(dimmer), 스위치에 해당하는 디바이스를 중앙 집중식으로 제어할 수 있는 컨트롤러가 개발되어 왔다. 본 논문에서 제시하는 컨트롤러는 스위치와 조명사이에 데이터를 처리하는 중개자의 역할을 하는 중요한 오브젝트이다. 본 논문에서는 이 기술의 핵심인 LonTalk 프로토콜을 설명하고 네트워크에 구성되는 컨트롤러에 대해 주소 지정방식을 이용하여, 여러 개의 조명을 연결될 수 있도록 네트워크 변수 타입을 제시하였다. 뉴런(Neuron)C 로 펌웨어(Firmware)를 구성하여 결과값을 얻을 수 있었고, LonWorks의 어플리케이션인 LNS(Lonworks Network Service)를 통해 플러그 인 부분까지 구현하여 해당 결과값을 확인할 수 있었다.

• 한국컴퓨터정보학회논문지
• /
• 제7권4호
• /
• pp.204-210
• /
• 2002

자기조직화 지도(self-organizing feature map)는 학습시 수렴하기 위하여 많은 입력패턴을 필요로 하는 단점이 있다. 본 논문에서는 자기조직화 지도 학습시 학습률이 일정한 이웃 상호작용 집합을 동적 가우시안 함수로 변환하여 수렴속도와 수렴도를 개선할 수 있는 방법을 제안한다. 제안한 방법은 이웃 상호작용 함수로 사용된 가우시안 함수의 편차와 폭을 학습 회수에 따라 감소하는 동적 성질과 승자 뉴런으로부터의 위상학적 위치에 따라 각기 다른 학습률을 갖도록 하였다. 따라서 본 논문에서는 자기조직화 지도의 수렴속도와 수렴도를 향상시켰다.