• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.8
• /
• pp.1195-1200
• /
• 2013

In this paper, we proposed an enhanced Max-Min neural network by auto-tuning of learning rate using fuzzy control method. For the reduction of training time required in the competition stage, the method was proposed that arbitrates dynamically the learning rate by applying the numbers of the accuracy and the inaccuracy to the input of the fuzzy control system. The experiments using real concrete crack images showed that the enhanced Max-Min neural network was effective in the recognition of direction of the extracted cracks.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.5 no.1
• /
• pp.33-44
• /
• 2012

A class of recurrent neural networks is proposed and proven to be capable of identifying any discrete-time dynamical system. The applications of the proposed network are addressed in the encoding, identification, and extraction of finite state automata. Simulation results show that the identification of finite state automata using the proposed network, trained by the hybrid greedy simulated annealing with a modified error function in the learning stage, exhibits generally better performance than other conventional identification schemes.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.12
• /
• pp.6484-6487
• /
• 2013

This paper reports the direct controller for nonlinear plants using a neural network. The controller was composed of an approximate controller and a neural network auxiliary controller. The approximate controller provides rough control and the neural network controller gives the complementary signal to further reduce the output tracking error. This method does not place too much restriction on the type of nonlinear plant to be controlled. In this method, a RBF neural network was trained and the system showed stable performance for the inputs it has been trained for. The simulation results showed that it was quite effective and could realize satisfactory control of the nonlinear system.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.5
• /
• pp.1393-1402
• /
• 1999

This paper proposes an efficient principal feature extraction of the image data using neural networks of a new learning algorithm. The proposed learning algorithm is a backpropagation(BP) algorithm based on the steepest descent and dynamic tunneling. The BP algorithm based on the steepest descent is applied for high-speed optimization, and the BP algorithm based on the dynamic tunneling is also applied for global optimization. Converging to the local minimum by the BP algorithm of steepest descent, the new initial weights for escaping the local minimum is estimated by the BP algorithm of dynamic tunneling. The proposed algorithm has been applied to the 3 image data of 12${\times}$12pixels and the Lenna image of 128${\times}$128 pixels respectively. The simulation results shows that the proposed algorithm has better performances of the convergence and the feature extraction, in comparison with those using the Sanger method and the Foldiak method for single-layer neural networks and the BP algorithm for multilayer neural network.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.287-292
• /
• 2007

본 연구에서는 동적 수신호 패턴에 대한 효과적인 인식을 위하여, 특징추출 단계와 패턴 분류 단계의 두 모듈로 이루어지는 복합형 신경망 모델을 제안한다. 특징추출 모듈을 위하여 고유의 특징표현 기법과 3차원 수용영역 구조의 CNN 모델을 제안한다. 이는 3차원 형식의 데이터로 표현되는 수신호 패턴으로부터 특징점의 공간적 변이뿐만 아니라 시간적 변이에 강인한 특징추출 기능을 제공한다. 패턴 분류 모듈에서는 효율적인 학습과 인식 기능을 위하여 수정된 구조의 GFMM 모델을 제안한다. 또한 학습패턴의 빈도를 고려한 활성화 특성과 학습 방법을 정의함으로써 기존의 GFMM 모델이 갖는 단점인 학습결과가 학습순서에 종속되는 특성과 비정상적 패턴 및 노이즈 패턴에 민감한 현상을 개선한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.422-426
• /
• 2007

음성 질의에서 효율적으로 onset을 검출하기 위한 연구는 다양하게 이루어져 왔다. 특히 대부분의 연구는 확률론적 모델에서 큰 성과를 나타내고 있다. 그러나 이러한 모델들은 변화나 확장이 쉽지 않다는 단점을 가지고 있다. 본 논문에서는 동적 확장 가능한 다중 계층 신경망(Dynamic Expansible MLP)을 제안하여, 기존 방법론의 확장 가능성을 모색한다. 또한, 음성 질의의 onset을 검출하기 위해 MLP를 활용하기 위한 모델을 제시한다.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.16 no.9
• /
• pp.838-844
• /
• 2004

In a long road tunnel, a tunnel ventilation system may be used in order to reduce the pollution below the required level. To develop control algorithms for a tunnel ventilation system, a dynamic simulation program may be used to predict the pollution level in a tunnel. Research was carried out to develop better pollution models for a tunnel ventilation control system. A neural network structure was adopted and compared by using actual poilution data. Simulation results showed that the dynamic model developed by a neural network may be effective for the development of tunnel ventilation control algorithms.

• Journal of the Korean Geotechnical Society
• /
• v.39 no.12
• /
• pp.37-46
• /
• 2023

Dynamic soil properties are essential factors for predicting the detailed behavior of the ground. However, there are limitations to gathering soil samples and performing additional experiments. In this study, we used an artificial neural network (ANN) to predict dynamic soil properties based on static soil properties. The selected static soil properties were soil cohesion, internal friction angle, porosity, specific gravity, and uniaxial compressive strength, whereas the compressional and shear wave velocities were determined for the dynamic soil properties. The Levenberg-Marquardt and Bayesian regularization methods were used to enhance the reliability of the ANN results, and the reliability associated with each optimization method was compared. The accuracy of the ANN model was represented by the coefficient of determination, which was greater than 0.9 in the training and testing phases, indicating that the proposed ANN model exhibits high reliability. Further, the reliability of the output values was verified with new input data, and the results showed high accuracy.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.11
• /
• pp.2133-2146
• /
• 1994

In this paper, we present a method for dynamic Jaso segmentation and Hangeul recognition using neural network. It uses the feature vector which is extracted from the mesh depending on the segmentation result. At first, each character is converted to 256 dimension feature vector by four direction contributivity and $8\times8$ mesh. And then, the character is classified into 6 class by neural network and is segmented into Jaso using the classification result the statistic vowel location information and the structural information. After Jaso segmentation, Hanguel recognition using neural network is performed. We experiment on four font of which three fonts are used for training the neural net and the rest is used of testing. Each font has the 2350 characters which are comprised in KS C 5601. The overall recognition rates for the training data and the testing data are 97,4% and 94&% respectively. This result shows the effectivness of proposed method.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.6
• /
• pp.66-74
• /
• 2018

Recently, there has been active studies on hand gesture recognition to increase immersion and provide user-friendly interaction in a virtual reality environment. However, most studies require specialized sensors or equipment, or show low recognition rates. This paper proposes a hand gesture recognition method using Deep Learning technology without separate sensors or equipment other than camera to recognize static and dynamic hand gestures. First, a series of hand gesture input images are converted into high-frequency images, then each of the hand gestures RGB images and their high-frequency images is learned through the DenseNet three-dimensional Convolutional Neural Network. Experimental results on 6 static hand gestures and 9 dynamic hand gestures showed an average of 92.6% recognition rate and increased 4.6% compared to previous DenseNet. The 3D defense game was implemented to verify the results of our study, and an average speed of 30 ms of gesture recognition was found to be available as a real-time user interface for virtual reality applications.