• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.3
• /
• pp.238-244
• /
• 2008

Dynamic neural networks have been applied to diverse fields requiring temporal signal processing. This paper presents gamma neural network(GAM) to improve the dynamics of multilayer network. The GAM network uses the gamma memory kernel in the hidden layer of feedforword multilayer network. The GAM network is evaluated in linear and nonlinear system identification, and compared with feedforword(FNN) and recurrent neural networks(RNN) for the relative comparison of its performance. Experimental results show that the GAM network performs better with respect to the convergence and accuracy, indicating that it can be a more effective network than conventional multilayer networks in system identification.

• Speech Sciences
• /
• v.11 no.4
• /
• pp.53-66
• /
• 2004

The nonlinear speech enhancement method with interactive parallel-extended Kalman filter is applied to speech contaminated by additive white noise. To represent the nonlinear and nonstationary nature of speech. we assume that speech is the output of a nonlinear prediction HMM (NPHMM) combining both neural network and HMM. The NPHMM is a nonlinear autoregressive process whose time-varying parameters are controlled by a hidden Markov chain. The simulation results shows that the proposed method offers better performance gains relative to the previous results [6] with slightly increased complexity.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1398-1401
• /
• 1993

The computer users who desire the comprehensive use of an advanced network system which permits to link the diversified types of computer from one to others, still tend to increase in number. However, one of the ways to install a highly reliable facilities relative to the network system is to inherit the know-how preserved in the specific technology. Therefore, we will propose the solution of this problem. This paper describes COMNETS, an expert system for constructing distributed networks.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.81-84
• /
• 2007

This paper describes general procedure and results of the GPS 3rd odor network adjustment which has been carried out for determining coordinates sets with respect to new Korean Geodetic Datum, so-call Korean Geodetic Datum 2002 (KGD 2002). The adjustment begins with minimally constrained adjustments with respect to each of the 69 campaign networks. This was followed by constructing and adjusting sixteen block network. After detecting and removing outliers in the observation file, an attempt was made by applying the empirical stochastic modeling techniques used in the 2nd order network adjustment, so as to determine the magnitude of absolute and relative error for the estimated baseline vector from the GPS data processing. The over constrained adjustment were, in sequence, performed against each of the block network. In this adjustment, both of the 2nd order control points in the block network and the 3rd order control points overlapped with adjacent network whose coordinates were already determined from a preceding adjustment. The final adjustment results have shown that the accuracy of the 3rd order network adjustment was better than 1cm and 2cm in horizontal and vertical component, respectively.

• ETRI Journal
• /
• v.37 no.2
• /
• pp.262-272
• /
• 2015

In particular, for a practical mobile robot team to perform such a task as that of carrying out a search and rescue mission in a disaster area, the network connectivity and localization have to be guaranteed even in an environment where the network infrastructure is destroyed or a Global Positioning System is unavailable. This paper proposes the new collective intelligence network management architecture of multiple mobile robots supporting seamless network connectivity and cooperative localization. The proposed architecture includes a resource manager that makes the robots move around and not disconnect from the network link by considering the strength of the network signal and link quality. The location manager in the architecture supports localizing robots seamlessly by finding the relative locations of the robots as they move from a global outdoor environment to a local indoor position. The proposed schemes assuring network connectivity and localization were validated through numerical simulations and applied to a search and rescue robot team.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.9
• /
• pp.159-165
• /
• 1994

In this paper, we propose a multi-layer associative neural network structure suitable for hardware implementaion with the function of performance refinement and improved robutst capability. Unlike other methods which reduce network complexity by putting restrictions on synaptic weithts, we are imposing a requirement of hidden layer neurons for the function. The proposed network has synaptic weights obtainted by Hebbian rule between adjacent layer's memory patterns such as Kosko's BAM. This network can be extended to arbitary multi-layer network trainable with Genetic algorithm for getting hidden layer memory patterns starting with initial random binary patterns. Learning is done to minimize newly defined network error. The newly defined error is composed of the errors at input, hidden, and output layers. After learning, we have bidirectional recall process for performance improvement of the network with one-shot recall. Experimental results carried out on pattern recognition problems demonstrate its performace according to the parameter which represets relative significance of the hidden layer error over the sum of input and output layer errors, show that the proposed model has much better performance than that of Kosko's bidirectional associative memory (BAM), and show the performance increment due to the bidirectionality in recall process.

• Journal of Korea Multimedia Society
• /
• v.17 no.9
• /
• pp.1092-1097
• /
• 2014

It is difficult to perform automatic formation flight of UAV (Unmanned Aerial vehicle) when GPS (Global Positionig System) is out of order or has a system error, since the relative position estimation in the flight group is impossible in that case. In this paper, we design a relative localization system for the automatic formation flight of UAV. For this purpose, we adopt digital beam forming (DBF) to estimate the angle with the central controller of the flight group and Particle Filtering scheme to compensate the estimation error of ToA (time of arrival) method. Computer simulation results present a proper distance between the central controller and a following unit to maintain the automatic formation flight.

• Language and Information
• /
• v.5 no.1
• /
• pp.35-53
• /
• 2001

As a subtype of English relative clause constructions, free relative constructions like what John ate in I ate what John ate exhibit complicated syntactic and semantic properties. In particular, the constructions have mixed properties of nominal and verbal: they have the internal syntax of sentence and the external syntax of noun phrase. This paper provides a constraint-based approach to these mixed constructions, and shows that simple constructional constraints are enough to capture their complexities. The paper begins by surveying the properties of the constructions. In discusses two types(Specific and nonspecific) of free relatives, their ,lexical restrictions nominal properties and behavior with respect to extraposition, piped piping and stacking Following these it sketches the basic framework of the HPSG(Head-driven Phrase Structure Grammar) which is of relevance in this paper. As the main part, the paper presents a constraint- based analysis in which tight interactions between grammatical constructions and a rich network of inheritance relations play important roles in accounting for the basic as well as complex properties of the constructions is question.

• Korea-Australia Rheology Journal
• /
• v.15 no.1
• /
• pp.27-33
• /
• 2003

Associating polymers are hydrophilic long-chain molecules to which a small amount of hydrophobic groups (hydrophobes) is incorporated. In aqueous solution, the association interactions result in the formation of three-dimensional network through flowerlike micelles at high concentrations. In colloidal suspensions, the associating polymers act as flocculated by bridging mechanism. The rheological properties of suspensions flocculated by associating polymers end-capped with hydrophobes are studied in relation to the bridging conformation. At low polymer concentrations, the polymer chains effectively form bridges between particles by multichain association. The suspensions are highly flocculated and show typical viscoelastic responses. When the polymer concentration is increased above the absorbance at saturation, the excess polymer chains remaining in the solution phase build up three-dimensional network by associating interactions. Since the presence of particles does not significantly influence the network structures in the medium, the relative viscosity, which gives a measure of the degree of flocculation is decreased with increasing polymer concentration. The bridging conformation and flocculation level vary strongly depending on the polymer concentrations.

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 1996.11a
• /
• pp.65-74
• /
• 1996

Risk analysis is time-consuming and expensive process〔1〕〔6〕. Automated risk analysis tools have been widely used in industry and government to support decision making process and reduce cost. However, difficulties in materializing impact of threats and fast-changing network environments make analysis process more complicated and less trusted since impacts are relative in network environments. HAWK system is developed to improve the accuracy of analysis result in network-oriented environment. It provides user-friendly environments and considers network environments as primary assets.