• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.1
• /
• pp.378-384
• /
• 2013

In this paper, we propose the fuzzy neural networks based on fuzzy c-means clustering algorithm. Typically, the generation of fuzzy rules have the problem that the number of fuzzy rules exponentially increases when the dimension increases. To solve this problem, the fuzzy rules of the proposed networks are generated by partitioning the input space in the scatter form using FCM clustering algorithm. The premise parameters of the fuzzy rules are determined by membership matrix by means of FCM clustering algorithm. The consequence part of the rules is expressed in the form of polynomial functions and the learning of fuzzy neural networks is realized by adjusting connections of the neurons, and it follows a back-propagation algorithm. The proposed networks are evaluated through the application to nonlinear process.

• Korean Institute of Interior Design Journal
• /
• v.14 no.4 s.51
• /
• pp.35-44
• /
• 2005

Light is the essential and symbolical entity In architecture. But the meaning of light has been changed as time has passed, and today it has plural meaning and more sophisticated role. Since 1960's 'Light and Space Art' has accomplished many successful experiments through light and space as artistic media, and they have changed the understanding of light from the electrical source to the phenomenological energy and sensual medium. And also the role of space in their works takes the more human-oriented field constituted from the coherent relationship of internal parts including human being. Light could be 'an object' and 'material' under 'Light and Space Art' artists' persistent efforts. They revealed another realm of spatial experiences such as extension-the metaphysical space, heterogeneous relationship-the complex space, and dematerialization-the illusionary space. The secondary and inclusive effects by 'Light and Space Art' can be found In the phenomenological architecture, the post-modern architecture, and the immaterial tendency of contemporary architecture. However, the more close connections between 'Light and Space Art' and the specific architectures are still left as a portion aside for the further research.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2726-2728
• /
• 2001

This paper describes an optimal synthesis method of binary neural network(BNN) for an approximation problem of a circular region using a newly proposed learning algorithm[7] Our object is to minimize the number of connections and neurons in hidden layer by using a Newly Expanded and Truncated Learning Algorithm(NETLA) for the multilayer BNN. The synthesis method in the NETLA is based on the extension principle of Expanded and Truncated Learning(ETL) and is based on Expanded Sum of Product (ESP) as one of the boolean expression techniques. And it has an ability to optimize the given BNN in the binary space without any iterative training as the conventional Error Back Propagation(EBP) algorithm[6] If all the true and false patterns are only given, the connection weights and the threshold values can be immediately determined by an optimal synthesis method of the NETLA without any tedious learning. Futhermore, the number of the required neurons in hidden layer can be reduced and the fast learning of BNN can be realized. The superiority of this NETLA to other algorithms was proved by the approximation problem of one circular region.

• Annals of Clinical Neurophysiology
• /
• v.23 no.2
• /
• pp.69-81
• /
• 2021

Cortico-cortical evoked potential (CCEP) mapping is a rapidly developing method for visualizing the brain network and estimating cortical excitability. The CCEP comprises the early N1 component the occurs at 10-30 ms poststimulation, indicating anatomic connectivity, and the late N2 component that appears at < 200 ms poststimulation, suggesting long-lasting effective connectivity. A later component at 200-1,000 ms poststimulation can also appear as a delayed response in some studied areas. Such delayed responses occur in areas with changed excitability, such as an epileptogenic zone. CCEP mapping has been used to examine the brain connections causally in functional systems such as the language, auditory, and visual systems as well as in anatomic regions including the frontoparietal neocortices and hippocampal limbic areas. Task-based CCEPs can be used to measure behavior. In addition to evaluations of the brain connectome, single-pulse electrical stimulation (SPES) can reflect cortical excitability, and so it could be used to predict a seizure onset zone. CCEP brain mapping and SPES investigations could be applied both extraoperatively and intraoperatively. These underused electrophysiologic tools in basic and clinical neuroscience might be powerful methods for providing insight into measures of brain connectivity and dynamics. Analyses of CCEPs might enable us to identify causal relationships between brain areas during cortical processing, and to develop a new paradigm of effective therapeutic neuromodulation in the future.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.993-996
• /
• 1993

This paper addresses the structure and its associated learning algorithms of a feedforward multi-layered connectionist network, which has distributed learning abilities, for realizing the basic elements and functions of a traditional fuzzy logic controller. The proposed neural-network-based fuzzy logic control system (NN-FLCS) can be contrasted with the traditional fuzzy logic control system in their network structure and learning ability. An on-line supervised structure/parameter learning algorithm dynamic learning algorithm can find proper fuzzy logic rules, membership functions, and the size of output fuzzy partitions simultaneously. Next, a Reinforcement Neural-Network-Based Fuzzy Logic Control System (RNN-FLCS) is proposed which consists of two closely integrated Neural-Network-Based Fuzzy Logic Controllers (NN-FLCS) for solving various reinforcement learning problems in fuzzy logic systems. One NN-FLC functions as a fuzzy predictor and the other as a fuzzy controller. As ociated with the proposed RNN-FLCS is the reinforcement structure/parameter learning algorithm which dynamically determines the proper network size, connections, and parameters of the RNN-FLCS through an external reinforcement signal. Furthermore, learning can proceed even in the period without any external reinforcement feedback.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.617-623
• /
• 2023

With the evolution of communication networks, there is a growing demand for stable high-speed data connections to support services relying on large-capacity data. The increasing volume of packet data aggregated from user devices underscores the significance of quality diagnostics for the backhaul network, an intermediate link transmitting data to the core network. This paper conducts empirical research on techniques to diagnose issues within the backhaul network through practical case studies, through diagnosing various factors such as circuit bandwidth, speed disparities within switches, network segment-specific buffer sizes, routing policies, among other factors that could potentially cause RTT (Round Trip Time) delays and performance degradation.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.5
• /
• pp.637-644
• /
• 2010

A vibration-powered piezoelectric energy harvester yields the maximum power output when its resonant frequency is made equal to the excitation frequency; however, the power output is dramatically decreased when the energy harvester is operated at off-resonance frequency. It has been observed that the resonant frequency of a piezoelectric energy harvester may change with time and that the excitation frequency often varies when the energy harvester is used in real applications. Hence, in this study, we propose a piezoelectric energy-harvesting module that is suitable for excitations in a certain frequency range. The frequency characteristics of the electrical output of the module are studied through analysis and experiment. A simple frequency tuning method is also suggested for the proposed energy-harvesting module; in this method, frequency tuning is achieved by changing the electrical connections between the constituent energy-harvesting units of the module.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.12
• /
• pp.2352-2360
• /
• 2011

In this paper, we introduce a comprehensive design methodology of Radial Basis Function Neural Networks (RBFNN) that is based on mechanism of clustering and optimization algorithm. We can divide some clusters based on similarity of input dataset by using clustering algorithm. As a result, the number of clusters is equal to the number of nodes in the hidden layer. Moreover, the centers of each cluster are used into the centers of each receptive field in the hidden layer. In this study, we have applied Fuzzy-C Means(FCM) and K-Means(KM) clustering algorithm, respectively and compared between them. The weight connections of model are expanded into the type of polynomial functions such as linear and quadratic. In this reason, the output of model consists of relation between input and output. In order to get the optimal structure and better performance, Particle Swarm Optimization(PSO) is used. We can obtain optimized parameters such as both the number of clusters and the polynomial order of weights connection through structural optimization as well as the widths of receptive fields through parametric optimization. To evaluate the performance of proposed model, NXT equipment offered by National Instrument(NI) is exploited. The situation awareness system-related intelligent model was built up by the experimental dataset of distance information measured between object and diverse sensor such as sound sensor, light sensor, and ultrasonic sensor of NXT equipment.

• Journal of the Korean Vacuum Society
• /
• v.18 no.3
• /
• pp.176-185
• /
• 2009

The realization and the performance of ICP source are strongly affected by its electrical impedance and the electric/magnetic field distribution. The ICP source impedance is determined by the antenna impedance and the plasma one. It is preferred to keep the imaginary impedance between -100 ohm to 100 ohm, since it should be avoided the high voltage formation on the antenna and abrupt impedance variation during the thin film process. The plasma uniformity is affected by the electric and magnetic field which is formed by the antenna current and voltage. The influence of azimuthal symmetry are shown by the electromagnetic simulation and the measurement result of plasma density. The radial uniformity can be controlled by locating the concentric antennas which have different diameters. The power distribution ratio and its control method are presented in the case of parallel antenna connections.

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.50 no.8
• /
• pp.387-393
• /
• 2001

This paper describes an advanced measuring method and precise evaluation of the ground resistance for the grounding system of energized substations and power equipments. A grounding system of substations consists of all interconnected grounding connections of grounded conductors, neutral ground wires, underground conductors of distribution lines, cable shields, grounding terminals of equipments, and etc. It is very difficult to measure the accurate ground resistance of the grounding terminals of equipments, and etc. It is very difficult to measure the accurate ground resistance of the grounding system of high voltage energized substations because of harmonic components caused by switched power supplies or overloads. The conventional fall-of-potential method may be subject to big error if stray ground currents and potentials are present. In this work, to improve the precision in measurements of the ground resistance by eliminating the effects of harmonic components and stray currents and potentials, the investigations of the ground resistance measurement by using a low pass filter in a model energized grounding system were conducted. The accuracy of ground resistance mesurements was evaluated as a function of the ratio of the test signal to noise (S/N). The errors due to the proposed ground resistance measurement method were decreased with increasing S/N and were less than 5[%] as S/N is 10. The proposed ground resistance measurement method appears to be considerably more accurate than the conventional fall-of -potential method. It is allows cancellation of the parasitic resistance of energized grounding systems, to employ the measurement method that allows cancellation of the parasitic effects due to other circulating ground currents and ground potential rises in practical situations.