• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.930-938
• /
• 2007

Captions which appear in images include information that relates to the images. In order to obtain the information carried by captions, the methods for text extraction from images have been developed. However, most existing methods can be applied to captions with fixed height of stroke's width. We propose a method which can be applied to various caption size. Our method is based on connected components. And then the edge pixels are detected and grouped into connected components. We analyze the properties of connected components and build a neural network which discriminates connected components which include captions from ones which do not. Experimental data is collected from broadcast programs such as news, documentaries, and show programs which include various height caption. Experimental result is evaluated by two criteria : recall and precision. Recall is the ratio of the identified captions in all the captions in images and the precision is the ratio of the captions in the objects identified as captions. The experiment shows that the proposed method can efficiently extract captions various in size.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.2B
• /
• pp.44-52
• /
• 2005

This paper proposes a neural network prediction model to improve the valid packet transmission rate for the QoS(Quality of Service) of multimedia transmission. The Round Trip Time(RTT) and Packet Loss Rate(PLR) are predicted using a neural network and then the transmission rate is decided based on the predicted RTT and the PLR. The suggested method will improve the transmission rate since it uses the rate control factors corresponding to time of data is being transmitted, while the conventional one uses the transmission rate determined based on the past informations. An experimental set-up has been established using a Linux PC system, and the multimedia data are transmitted using UDP protocol in real time. The valid transmitted packets are about 5% higher than the one in the conventional TCP-Friendly congestion control method when the suggested algorithm was applied.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.5
• /
• pp.667-675
• /
• 2002

In this Paper, we present a new nonlinear active noise control scheme using neural networks. Two neural network4 are used, one is for the active controller and another one is for the secondary path model. This scheme is suitable for the plant which has time-varing secondary path dynamics, because the secondary path modeling is performed via on-line fashion. Simulation results of active noise control with nonlinear primary/secondary path are presented. The results show that the new algorithm can reduce the noise level greatly.

• Journal of Biosystems Engineering
• /
• v.15 no.3
• /
• pp.186-198
• /
• 1990

인간 소뇌의 구조와 기능을 간략하게 수학적으로 모델링하여 입력에 따른 시스템의 적정 출력을 학습에 의한 적응 제어 방식으로 추출해 내는 소뇌모델 대수제어기(CMAC : Cerebellar Model Arithmetic Controller)가 제안되었다. 본 논문에서는 연구개발된 기존 신경회로망과의 비교 분석에 의거하여, 소뇌모델 대수제어기 대신 네트의 특성에 따라 소뇌모델 선형조합 신경망(CMLAN : Cerebellum Model Linear Associator Network)이라 하였다. 소뇌모델 선형조합 신경망은 시스템의 제어 함수치를 결정하는 데 있어, 기존의 제어방식이 시스템의 모델링을 기초로 하여 알고리즘에 의한 수치해석적 또는 분석적 기법으로 모델 해를 산출하는 것과 달리, 학습을 통하여 저장되는 분산기억 소자들의 함수치를 선형적으로 조합함으로써 시스템의 입출력을 결정한다. 분산기억 소자로의 함수치 산정 및 저장은 소뇌모델 선형조합 신경망이 갖는 고유의 구조적 상태공간 매핑(State Space Mapping)과 델타규칙(Delta Rule)에 의거한 시스템의 입출력 상태함수의 학습으로써 수행된다. 본 논문을 통하여 소뇌모델 선형조합신경망의 구조적 특성, 학습 성질과 상태공간 설정 및 시스템의 수렴성을 규명하였다. 또한 기존의 최대 편차수정 학습 알고리즘이 갖는 비능률성 및 적용 제한성을 극복한 효율적 학습 알고리즘들을 제시하였다. 언급한 신경망의 특성 및 제안된 학습 알고리즘들의 능률성을 다양한 학습이득(Learning Gain)하에서 비선형 함수를 컴퓨터로 모의 시험하여 예시하였다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.39 no.8
• /
• pp.725-734
• /
• 2011

At high angles of attack, aircraft dynamics can display an oscillatory lateral behavior that manifests itself as a limit cycle known as wing rock. In this paper, a classical and neural network based adaptive control design methods of adaptively stabilizing the oscillatory motion by adapting uncertainties are described in detail. All methods are simulated and compared using a model for an 80o swept delta wing.

• Journal of the Korean Society for Precision Engineering
• /
• v.34 no.2
• /
• pp.125-131
• /
• 2017

2-Axis Pan and Tilt Motion Platform, a complex multivariate non-linear system, may incur any disturbance, thus requiring system controller with robustness against various disturbances. In this study, we designed an adaptive backstepping compensated controller by estimating the disturbance and error using the Radial Basis Function Neural Network (RBF NN). In this process, Uniformly Ultimately Bounded (UUB) was demonstrated via Lyapunov and stability was confirmed. By generating progressive disturbance to the irregular frequency and amplitude changes, it was verified for various environmental disturbances. In addition, by setting the RBF NN input vector to the minimum, the estimated disturbance compensation process was analyzed. Only two input vectors facilitated compensatory function of RBF NN via estimating the modeling and control error values as well as irregular disturbance; the application of the process resulted in improved backstepping controller performance that was confirmed through simulation.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.15 no.3
• /
• pp.199-206
• /
• 2010

Matrix converter is an energy conversion device of controlled power semiconductor switches that directly connects the three-phase source to the three-phase load. With no dc-link components for energy storage in the matrix converter the input current depends directly upon the load currents and the switch state of the converter. Therefore the unbalanced and distorted input voltages can result in unwanted output harmonic currents. This paper presents a current compensator based on neural network to improving output current quality for matrix converter under abnormal input voltage conditions. The effectiveness and feasibility of the proposed technique has been proven through numerical simulations and experimental tests.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.13 no.1
• /
• pp.69-76
• /
• 1999

This paper proposed a design of intelligent supervisory control systems for maintenance of highway traffic information equiprrent and processing algorithm of equiprrent fault data. The fault data of highway traffic equipment are transmitted from rerrnte supervisory controller to central supervisory system by real time, the transmitted fault data are anaIyzed the characteristic using evaluation algorithm of fault data in central supervisory system. The evaluation algorithm includes a neural network and fault knowlOOge-base for processing the multi-generated fault data. For validating the evaluation algorithm of intelligent supervisory control systems, the rrethod of analysis used to the five pattern of binary signal by transmitted real time and the opTclting user-interface constructed in central supervisory system.

• Journal of Advanced Marine Engineering and Technology
• /
• v.28 no.1
• /
• pp.90-97
• /
• 2004

DC motor requires a rotor speed sensor for accurate speed control. The speed sensors such as resolvers and encoders are used as speed detectors. but they increase cost and size of the motor and restrict the industrial drive applications. So in these days. many Papers have reported on the sensorless operation or DC motor(3)-(5). This paper Presents a new sensorless strategy using neural networks(6)-(8). Neural network structure has three layers which are input layer. hidden layer and output layer. The optimal neural network structure was tracked down by trial and error and it was found that 4-16-1 neural network has given suitable results for the instantaneous rotor speed. Also. learning method is very important in neural network. Supervised learning methods(8) are typically used to train the neural network for learning the input/output pattern presented. The back-propagation technique adjusts the neural network weights during training. The rotor speed is gained by weights and four inputs to the neural network. The experimental results were found satisfactory in both the independency on machine parameters and the insensitivity to the load condition.

• New & Renewable Energy
• /
• v.8 no.3
• /
• pp.14-22
• /
• 2012

Performance of photovoltaic (PV) generator systems relies on its operating conditions. Maximum power extracted from PV generators depends strongly on solar irradiation, load impedance, and ambient temperature. A most maximum power point tracking (MPPT) algorithm is based on a perturb and observe method and an incremental conductance method. It is well known the latter is better in terms of dynamics and tracking characteristics under condition of rapidly changing solar irradiation. However, in case of digital implementation, the latter has some error for determining a maximum power point. This paper presents a PID based MPPT algorithm for such PV systems. We use neural network technique for determining PID parameters by online learning approach. And we construct a boost converter to regulate the output voltage from PV generator system. Computer simulation is carried out to evaluate the proposed MPPT method and we accomplish comparative study with a perturb and observe based MPPT method to prove its superiority.