• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.1021-1024
• /
• 1999

In this paper, we propose a modified feedback neural network structure for adaptive control of robot manipulators. The proposed structure is that all of network output feedback into hidden units and output units. Learning algorithm is standard back-propagation algorithm. The simulation showed the effectiveness of using the new neural network structure in the adaptive control of robot manipulators.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.2
• /
• pp.168-175
• /
• 1999

In this paper, a modified RBF(Radial Basis Function) network structure is suggested for the prediction of a time-series with non-linear, non-stationary characteristics. Coventional RBF network predicting time series by using past outputs sense the trajectory of the time series and react when there exists strong relation between input and hidden activation function's RBF center. But this response is highly sensitive to level and trend of time serieses. In order to overcome such dependencies, hidden activation functions are modified to react to the increments of input variable and multiplied by increment(or dectement) for prediction. When the suggested structure is applied to prediction of Macyey-Glass chaotic time series, Lorenz equation, and Rossler equation, improved performances are obtained.

• ETRI Journal
• /
• v.29 no.1
• /
• pp.59-69
• /
• 2007

We designed and fabricated a vision chip for edge detection with a $160{\times}120$ pixel array by using 0.35 ${\mu}m$ standard complementary metal-oxide-semiconductor (CMOS) technology. The designed vision chip is based on a retinal structure with a resistive network to improve the speed of operation. To improve the quality of final edge images, we applied a saturating resistive circuit to the resistive network. The light-adaptation mechanism of the edge detection circuit was quantitatively analyzed using a simple model of the saturating resistive element. To verify improvement, we compared the simulation results of the proposed circuit to the results of previous circuits.

• Journal of the Korea Safety Management & Science
• /
• v.14 no.1
• /
• pp.137-145
• /
• 2012

In the previous study, the construction guide line of IT infra-structure for a u-City was introduced. However, it is only concentrated on the components and construction procedure for provider-oriented and technology-oriented sensor networks. In this paper the architecture and building process of demander-oriented sensor networks for sustainable u-City service are proposed. In the paper it is described (1) the enhancement methods of the procedure that can be flexibly constructed according to the scale of the project, (2) the methods that can improve the structure from the wireless sensor network such as RFID/USN to the hybrid sensor network, and (3) the consideration factors for providing the sustainable u-City service.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• 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.

• Applied Microscopy
• /
• v.46 no.4
• /
• pp.171-175
• /
• 2016

A distinctive neuronal network in the brain is believed to make us unique individuals. Electron microscopy is a valuable tool for examining ultrastructural characteristics of neurons, synapses, and subcellular organelles. A recent technological breakthrough in volume electron microscopy allows large-scale circuit reconstruction of the nervous system with unprecedented detail. Serial-section electron microscopy-previously the domain of specialists-became automated with the advent of innovative systems such as the focused ion beam and serial block-face scanning electron microscopes and the automated tape-collecting ultramicrotome. Further advances in microscopic design and instrumentation are also available, which allow the reconstruction of unprecedentedly large volumes of brain tissue at high speed. The recent introduction of correlative light and electron microscopy will help to identify specific neural circuits associated with behavioral characteristics and revolutionize our understanding of how the brain works.

• Journal of Korea Multimedia Society
• /
• v.24 no.4
• /
• pp.519-527
• /
• 2021

Alzheimer's disease is one of the challenges to tackle in the coming aging era and is attempting to diagnose and predict through various biomarkers. While the application of various deep learning-based technologies as powerful imaging technologies has recently expanded across the medical industry, empirical design is not easy because there are various deep earning neural networks architecture and categorical hyperparameters that rely on problems and data to solve. In this paper, we show the possibility of optimizing a deep learning neural network structure and hyperparameters for Alzheimer's disease classification in amyloid brain images in a representative deep earning neural networks architecture using genetic algorithms. It was observed that the optimal deep learning neural network structure and hyperparameter were chosen as the values of the experiment were converging.

• Korean journal of communication and information
• /
• v.60
• /
• pp.75-103
• /
• 2012

The purpose of this study is to explore the meaning and the effect of communication as social capital, which needs to be evaluated empirically focusing on corporate reputation. Also, it tried to analyze consumers' communication network in the structural, substantial, and relational level, which is to verify how characteristics and meanings of communication network structure affect to a good corporate reputation. A survey toward 200 participants was conducted during 5 days from March 29 to April 3, 2012. Characteristics of communication network structure of a corporation with higher reputation is analyzed using the index such as degree, degree centrality, and density. The findings of the study show that a corporation with higher reputation has higher network degree, degree centrality, and density compared to a corporation with lower reputation. Consumers of a corporation with higher reputation get information from various overlapping sources. It allows them to share similar interpretation, which could elevate the degree, degree centrality, and density of network. It also proved that when the network density is high, a corporation with higher reputation can distribute information much faster and easier. Moreover, in the substantial level of social capital, product/service information network has high degree and density rather than corporate issue information network. Likewise, degree and density of information acquisition network was higher than those of information provision network. Also, this study verified the effect and relationship between the network structure characteristics and corporate loyalty in a relational level. In this way, the positive effect of the degree centrality on corporate loyalty was supported. In conclusion, as consumers share more information from overlapping sources, the degree of communication network gets higher. Throughout this network, the diffusion of information among consumers would be activated, and this confirmed that corporate reputation and corporate loyalty is closely related.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.6
• /
• pp.449-453
• /
• 2001

In this paper, we propose an algorithm to design the adaptive structure of wavelet neural network with F-projection and geometric growing criterion. Geometric growing criterion consists of estimated error criterion considering local error and angle criterion which attempts to assign a wavelet function that is nearly orthogonal to all other existing wavelet functions. These criteria provide a methodology that a network designer can construct wavelet neural network according to one's intention. We apply the proposed constructing algorithm of the adaptive structure of wavelet neural network to approximation problems of 1-D and 2-D function, and evaluate the effectiveness of the proposed algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2254-2259
• /
• 2005

In this paper, we propose a wavelet based fuzzy neural network(WFNN) based direct adaptive control scheme for the solution of the tracking problem of mobile robots. To design a controller, we present a WFNN structure that merges advantages of neural network, fuzzy model and wavelet transform. The basic idea of our WFNN structure is to realize the process of fuzzy reasoning of wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. In our control system, the control signals are directly obtained to minimize the difference between the reference track and the pose of mobile robot using the gradient descent(GD) method. In addition, an approach that uses adaptive learning rates for the training of WFNN controller is driven via a Lyapunov stability analysis to guarantee the fast convergence, that is, learning rates are adaptively determined to rapidly minimize the state errors of a mobile robot. Finally, to evaluate the performance of the proposed direct adaptive control system using the WFNN controller, we compare the control performance of the WFNN controller with those of the FNN, the WNN and the WFM controllers.