• The Journal of the Acoustical Society of Korea
• /
• v.21 no.2E
• /
• pp.98-104
• /
• 2002

The present study describes a combination method to recognize the human affective states such as anger, happiness, sadness, or surprise. For this, we extracted emotional features from voice signals and facial expressions, and then trained them to recognize emotional states using hidden Markov model (HMM) and neural network (NN). For voices, we used prosodic parameters such as pitch signals, energy, and their derivatives, which were then trained by HMM for recognition. For facial expressions, on the other hands, we used feature parameters extracted from thermal and visible images, and these feature parameters were then trained by NN for recognition. The recognition rates for the combined parameters obtained from voice and facial expressions showed better performance than any of two isolated sets of parameters. The simulation results were also compared with human questionnaire results.

• International Journal of Precision Engineering and Manufacturing
• /
• v.3 no.1
• /
• pp.5-12
• /
• 2002

The grinding process has been mainly used fur finishing metal products as final machining stage. But chatter vibration and bum of a workpiece have a bad effect on the machined surface and should be detected in modern grinding process. This paper deals with a fault detection of the cylindrical plunge grinding process by power parameters. During the grinding process the power signals of an induced motor were sampled and used to determine the relationship between fault and change of power parameters. A neural network was used far detecting the grinding fault and an influence of power parameters to the grinding fault was analyzed.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.11
• /
• pp.89-98
• /
• 1998

The enhanced resource-allocating network(ERAN) that adaptively generates hidden units of radial basis function(RBF) network for systems modeling has been proposed. The ERAN is an improved version of the resource-allocating network(RAN) that allocates new hidden units based on the novelty of observation data. The learning process of the ERAN involves allocation of new hidden units and adjusting the network parameters. The network starts with no hidden units. As observation data are received, the network adds a hidden units only if the three network growth criteria are satisfied. The network parameters are adjusted by the LMS algorithm. The performance of the ERAN is compared with the RAN for nonlinear static systems modeling problem with sequential and random learning. For two simulations, the ERAN has been shown to realize RBF networks with better accuracy with fewer hidden units.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.583-599
• /
• 2022

In this paper, a multi-objective wireless sensor network configuration optimization method is proposed. The proposed method aims to determine the optimal information and lifespan wireless sensor network for structural health monitoring of large-scale infrastructures. In particular, cluster-based wireless sensor networks with multi-type of sensors are considered. To optimize the lifetime of the wireless sensor network, a cluster-based network optimization algorithm that optimizes the arrangement of cluster heads and base station is developed. On the other hand, based on the Bayesian inference, the uncertainty of the estimated parameters can be quantified. The coefficient of variance of the estimated parameters can be obtained, which is utilized as a holistic measure to evaluate the estimation accuracy of sensor configurations with multi-type of sensors. The proposed method provides the optimal wireless sensor network configuration that satisfies the required estimation accuracy with the longest lifetime. The proposed method is illustrated by designing the optimal wireless sensor network configuration of a cable-stayed bridge and a space truss.

• Proceedings of the KOSOMBE Conference
• /
• v.1995 no.11
• /
• pp.197-200
• /
• 1995

In this paper, we proposed the multi-step multi-layer artificial neural network(MMANN) to classify the chromosome, Which is used as a chromosome pattern classifier after learning. We extracted three chromosome morphological feature parameters such as centromeric index, relative length ratio, and relative area ratio by means of preprocessing method from ten chromosome images. The feature parameters of five chromosome images were used to learn neural network and the rest of them were used to classify the chromosome images. The experiment results show that the chromosome classification error is reduced much more, comparing with less feature parameters than that of the other researchers.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.3 s.174
• /
• pp.769-776
• /
• 2000

RP(Rapid Prototyping) technology is gaining its popularity in building a prototype in all industries. SLS(Slective Laser Sintering) is one of RP technologies, which is focused on tooling processes as well as three dimension solid model. There are several factors, the length and the cross-sectional area of a part, that have an effect on build setup in SLS process. In this paper, the computation on geometrical relationship is used to slice STL file and to estimate these factors. Based on these values, the build setup parameters such as the heating temperature, the laser power, and the powder cartridge feed rate are determined by neural network approaches. The test results show that the computation time is saved and the neural network approach is able to apply to get the optimal parameters of build process within an acceptable error rate.

• Journal of Mechanical Science and Technology
• /
• v.18 no.3
• /
• pp.443-452
• /
• 2004

For stereo lithography process, accuracy of prototypes is related to laser power, scan speed, scan width, scan pattern, layer thickness, resin characteristics and etc. An accurate prototype is obtained by using appropriate process parameters. In order to determine these parameters, the stereolithography (SLA) machine using neural network was developed and efficiency of the developed SLA machine was compared with that of the traditional SLA. Optimum values for scan speed, hatching spacing and layer thickness improved the surface roughness and build time for the developed SLA.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.972-974
• /
• 1993

This paper presents a new method to automatically design fuzzy logic controller(FLC). The main problems of designing FLC are how to optimally and automatically select the control rules and the parameters of membership function (MF). Cell state space algorithms (CSS), differential competitive learning (DCL) and multialyer neural network are combined in this paper to solve the problems. When the dynamical model of a control process is known. CSS can be used to generate a group of optimal input output pairs(X, Y) used by a controller. The(X, Y) then can be used to determine the FLC rules by DCL and to determine the optimal parameters of MF by DCL and to determine the optimal parameters of MF by multilayer neural network trained by BP algorithm.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.53 no.5
• /
• pp.332-337
• /
• 2004

A number of techniques have been developed for estimation of speed or position in motor drives. The accuracy of these techniques is affected by the variation of motor parameters such as the stator resistance, stator inductance or torque constant. This paper is proposed a neural network based estimator for torque and stator resistance in IPMSM Drives. The neural weights are initially chosen randomly and a model reference algorithm adjusts those weights to give the optimum estimations. The neural network estimator is able to track the varying. parameters quite accurately at different speeds with consistent performance. The neural network parameter estimator has been applied to slot and flux linkage torque ripple minimization of the IPMSM. The validity of the proposed parameter estimator is confirmed by the operating characteristics controlled by neural networks control.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.14 no.1
• /
• pp.84-92
• /
• 2001

In this papers, we proposed the new method in order to diagnosis aging state of transformers. For wavelet transform, Daubechies filter is used, we can obtain wavelet coefficients which is used to extract feature of statistical parameters (maximum value, average value, dispersion skewness, kurtosis) about each acoustic emission signal. Also, these coefficients are used to identify normal and fault signal of internal partial discharge in transformer. As improved method for classification use neural network. Extracted statistical parameters are input into an back-propagation neural network. The number of neurons of hidden layer are obtained through Result of Cross-Validation. The network, after training, can decide whether the test signal is early aging state, alst aging state or normal state. In quantity analysis, capability of proposed method is superior to compared that of classical method.