• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.585-592
• /
• 2016

A topic segmentation module is to divide statements or conversations into certain topic units. Until now, topic segmentation has progressed in the direction of finding an optimized set of segments for a whole document, considering it all together. However, some applications need topic segmentation for a part of document which is not finished yet. In this paper, we propose a model to perform topic segmentation during the progress of the statement with a supervised learning model that uses a convolution neural network. In order to show the effectiveness of our model, we perform experiments of topic segmentation both on-line status and off-line status using C99 algorithm. We can see that our model achieves 17.8 and 11.95 of Pk score, respectively.

• Proceedings of the KIEE Conference
• /
• 1997.07b
• /
• pp.609-611
• /
• 1997

In this paper, we propose the self-tuning of PID controller using diagonal recurrent neural networks. The characteristic of the proposed structure is on-line adaptive learning scheme in spite of variations of feedback, signals. Control performance is compared with that of neural network based PID controller which was proposed by Iwasa. Computer simulation results show that the proposed controller is effective in controlling of unknown nonlinear plants.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.207-210
• /
• 2002

진화와 학습 사이의 상호 연관성을 연구하기 위해 인공 진화기법(artificial evolutionary algorithm)과 신경회로망(neural networks)을 이용한 학습 기법들이 사용되어 왔다. 신경 회로망 구조를 가지는 이동 로봇의 제어기의 구조와 파라미터를 결정하기 위한 방법으로 진화적 학습(evolutionary learning) 방법이 제안되었다. 제안된 방법에서 진화적 학습은 실제 로봇을 통해 on-line 방식으로 이루어지며, 장애물 회피 문제를 통해 유용성을 검증하고 진화 과정에 학습이 미치는 영향을 살펴보았다. 그리고 수학적으로 제시되기 힘든 진화 학습의 평가에 설계자의 개입을 허용하는 인터액티브 진화 알고리즘(interactive evolutionary algorithm)방법을 모색해 보았다.

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.254-257
• /
• 1993

This paper presents a new method to implement Hebbian learning method on artificial neural network. In hebbian learning algorithm, complexity in terms of multiplications is high. To save the chip area, we consider a new learning circuit. By calculating similarity, or correlation between $X_i$ and $O_i$, large portion of circuits commonly used in conventional neural networks is not necessary for this new hebbian learning circuit named COR. The output signals of COR is applied to weight storage capacitors for direct control the voltages of the capacitors. The weighted sum, ${\Sigma}W_{ij}O_j$, is realized by multipliers, whose output currents are summed up in one line which goes to learning circuit or output circuit. The drain current of the multiplier can produce positive or negative synaptic weights. The pass transistor selects eight learning mode or recall mode. The layout of an learnable six-neuron fully connected Hopfield neural network is designed, and is simulated using PSPICE. The network memorizes, and retrieves the patterns correctly under the existence of minor noises.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.1
• /
• pp.44-52
• /
• 2001

This paper describes an off-line method for recognizing totally unconstrained handwritten digits using modified chaotic neural networks(MCNN). The chaotic neural networks(CNN) is modified to be a useful network for solving complex pattern problems by enforcing dynamic characteristics and learning process. Since the MCNN has the characteristics of highly nonlinear dynamics in structure and neuron itself, it can be an appropriate network for the robust classification of complex handwritten digits. Digit identification starts with extraction of features from the raw digit images and then recognizes digits using the MCNN based classifier. The performance of the MCNN classifier is evaluated on the numeral database of Concordia University, Montreal, Canada. For the relative comparison of recognition performance, the MCNN classifier is compared with the recurrent neural networks(RNN) classifier. Experimental results show that the classification rate is 98.0%. It indicates that the MCNN classifier outperforms the RNN classifier as well as other classifiers that have been reported on the same database.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.4
• /
• pp.157-162
• /
• 2010

The cart-pole balancing problem is a pseudo-standard benchmark problem from the field of control methods including genetic algorithms, artificial neural networks, and reinforcement learning. In this paper, we propose a novel approach by using online reinforcement learning(OREL) to solve this cart-pole balancing problem. The objective is to analyze the learning method of the OREL learning system in the cart-pole balancing problem. Through experiment, we can see that approximate faster the optimal value-function than Q-learning.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.2 s.95
• /
• pp.211-217
• /
• 1999

감지기의 고장 발견, 확인, 보완은 복잡한 항공 시스템의 중요한 문제로 부각되어 왔으며, 그동안 칼만 필터를 이용한 기존 추정기술 혹은 온라인 학습 인공지능 알고리듬 등이 이 같은 문제를 해결하기 위해 제시되어 왔다. 본 연구에서는 여분의 감지기가 없는 항공제어계에 대해 온라인 학습 신경망을 이용한 감지기의 고장 발견, 확인, 그리고 보완에 관해 초점을 둔다. 이 내고장성 항공제어계는 주 신경조직망과 n개의 국소 신경조직망으로 이루어지는데, 포괄적인 감지기의 고장을 발견하는 능력을 가진다. 어떤 경우에서는 기존의 감지기 고장 발견 방법의 성능을 향상시키기 위해 수정된 감지방법이 소개되고 그 보완된 감지방법을 이용하여 기존의 방법과 성능비교가 이루어졌다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2001.04a
• /
• pp.1021-1024
• /
• 2001

Out of all metal-cutting processes, the hole-making process is the most widely used. It is estimated to be more than 30% of the total metal-cutting process. It is therefore desirable to monitor and detect drill wear during the hole-drilling process. In this paper, the vision system of the sensing methods of drill flank wear on the basis of image processing is used to detect the wear pattern by non-contact and direct method and get the reliable wear information about drill. In image processing of acquired image, median filter is applied for noise removal. The vision flank wear area of the drill was measured. Backpropagation neural networks (BPns) were used for no-line detection of drill wear. The neural network consisted of three layers: input, hidden and output. The input vectors comprised of spindle rotational speed, feed rates, vision flank wear, thrust and torque signals. The output was the drill wear state which was either usable or failure. Drilling experiments with various spindle rotational speed and feed rates were carried out. The learning process was peformed effectively by utilizing backpropagation. The detection of the abnormal states using BPNs achieved 96.4% reliability even when the spindle rotational speed and feedrate were changed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.11
• /
• pp.968-973
• /
• 2000

Fault diagnosis plays an important role in the performance and safe operation of many modern engineering plants. This paper investigates the problem of fault detection using neural networks in dynamic systems. A general framework for constructing a nonlinear fault detection scheme for nonlinear dynamic systems containing modeling uncertaintly is proposed. The main idea behind the proposed approach is to monitor the physical system with an off -line learning neural network and then to approximate the upper and lower thresholds of acceleration of the nominal system with the model-based threshold(ThMB) method, The performance of the proposed fault detection scheme is investigated through simulations of a pendulum with uncertainty.

• Structural Engineering and Mechanics
• /
• v.16 no.6
• /
• pp.643-654
• /
• 2003

Two real-time modeling prediction (RMP) schemes are presented in this paper for analyzing the behavior of deep excavations during construction. The first RMP scheme is developed from the traditional AR(p) model. The second is based on the simplified Elman-style recurrent neural networks. An on-line learning algorithm is introduced to describe the dynamic behavior of deep excavations. As a case study, in-situ measurements of an excavation were recorded and the measured data were used to verify the reliability of the two schemes. They proved to be both effective and convenient for predicting the behavior of deep excavations during construction. It is shown through the case study that the RMP scheme based on the neural network is more accurate than that based on the traditional AR(p) model.