• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.1
• /
• pp.85-94
• /
• 2017

In this paper, I proposed a sound model generation and a most frequent model search algorithm for recognizing animal vocalization. The sound model generation algorithm generates a optimal set of models through repeating processes such as the training process, the Viterbi Search process, and the most frequent model search process while adjusting HMM(Hidden Markov Model) structure to improve global recognition rate. The most frequent model search algorithm searches the list of models produced by Viterbi Search Algorithm for the most frequent model and makes it be the final decision of recognition process. It is implemented using MFCC(Mel Frequency Cepstral Coefficient) for the sound feature, HMM for the model, and C# programming language. To evaluate the algorithm, a set of animal sounds for 27 species were prepared and the experiment showed that the sound model generation algorithm generates 27 HMM models with 97.29 percent of recognition rate.

• The Journal of the Korea Contents Association
• /
• v.8 no.7
• /
• pp.66-74
• /
• 2008

Criticality prediction models to identify most fault-prone modules in the system early in the software development process help in allocation of resources and foster software quality improvement. Many models for identifying fault-prone modules using design complexity metrics have been suggested, but most of them are training models that need training data set. Most organizations cannot use these models because very few organizations have their own training data. This paper builds a prediction model based on a well-known supervised learning model, error backpropagation neural net, using design metrics quantifying SDL system specifications. To solve the problem of other models, this model is trained by generated virtual training data set. Some simulation studies have been performed to investigate feasibility of this model, and the results show that suggested model can be an alternative for the organizations without real training data to predict their software qualities.

• Journal of KIISE:Software and Applications
• /
• v.33 no.2
• /
• pp.252-266
• /
• 2006

Many problems in computer vision are mainly based on mathematical models. Their optimal solutions can be found by estimating the parameters of each model. However, provided an input data set is involved outliers which are relative]V larger than normal noises, they lead to incorrect results. RANSAC is a representative robust algorithm which is used to resolve the problem. One major problem with RANSAC is that it needs priori knowledge(i.e. a percentage of outliers) of the distribution of data. To solve this problem, we propose a FRANSAC algorithm which improves the rejection rate of outliers and the accuracy of solutions. This is peformed by categorizing all data into good sample set, bad sample set and vague sample set using a fuzzy classification at each iteration and sampling in only good sample set. In the experimental results, we show that the performance of the proposed algorithm when it is applied to the linear regression and the calculation of a homography.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.7
• /
• pp.1751-1758
• /
• 1994

A new set of governing equations is derived for the dynamic analysis of the Free-Piston Stirling Engines(EPSE). Equations from the ideal adiabatic model for the thermodynamic analysis of the working fluid are incoporated with the equations of motion for the moving masses of the system, resulting in a set of nonlinear differential equations. The coupled set of equations are numerically integrated with proper intial conditions to obtain a steady state response of the engine. The proposed method is compared with the conventional method of analyzing EPSE based mainly on the ideal isothermal model. The results clearly shows the limitationsl of the conventional methods and the relative advantages of the method proposed in the present study.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.816-821
• /
• 2018

Recently, machine learning algorithms based on artificial neural networks started to be used widely as classifiers in the field of EEG research for emotion analysis and disease diagnosis. When a machine learning model is used to classify EEG data, if training data is composed of only data having similar characteristics, classification performance may be deteriorated when applied to data of another group. In this paper, we propose a method to construct training data set by selecting several groups of data using semi-supervised learning algorithm to improve these problems. We then compared the performance of the two models by training the model with a training data set consisting of data with similar characteristics to the training data set constructed using the proposed method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.1
• /
• pp.96-101
• /
• 2009

This paper presents a method for identifying the parameter set of inelastic constitutive equations, which is based on an Evolutionary Algorithm. The advantage of the method is that appropriate parameters can be identified even when the measured data are subject to considerable errors and the model equations are inaccurate. The design of experiments suited for the parameter identification of a material model by Chaboche under the uniaxial loading and stationary temperature conditions was first considered. Then the parameter set of the model was identified by the proposed method from a set of experimental data. In comparison to those by other methods, the resultant stress-strain curves by the proposed method correlated better to the actual material behaviors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.4
• /
• pp.967-975
• /
• 2010

Image segmentation is one of the first steps leading to image analysis and interpretation, which is to distinguish objects from background. However, the active contour model can't exactly extract the desired objects because the phase only is 2. In this paper, we propose the method which can find the desired contours by composing the initial curve near the objects which have intensities of special range. The initial curve is calculated by the histogram equalization, the Gaussian equalization, and the threshold. The proposed method reduce the calculation speed and exactly detect the wanted objects because the initial curve set near by interested area. The proposed method also shows more efficient than the active contour model in the results applied the CT and MR images.

• Spatial Information Research
• /
• v.21 no.2
• /
• pp.45-54
• /
• 2013

Analytical and simulation error models have the ability to describe (or realize) error-corrupted versions of spatial data. But the different approaches for modeling positional errors require an internal validation that ascertains whether the analytical and simulation error models predict correct positional errors in a defined set of conditions. This paper presents stochastic simulation models of a point and a line segm ent to be validated w ith analytical error models, which are an error ellipse and an error band model, respectively. The simulation error models populate positional errors by the Monte Carlo simulation, according to an assumed error distribution prescribed by given parameters of a variance-covariance matrix. In the validation process, a set of positional errors by the simulation models is compared to a theoretical description by the analytical error models. Results show that the proposed simulation models realize positional uncertainties of the same spatial data according to a defined level of positional quality.

• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.12
• /
• pp.641-655
• /
• 2007

Parameterization has been one of very important research subjects in several application areas including computer graphics. In the parameterization research, the problem of mapping 3D polygonal model to 2D plane has been studied frequently, but the previous methods often fail to handle complicated shapes of polygonal surfaces effectively as well as entail distortion between the 3D and 2D spaces. Several attempts have been made especially to reduce such distortion, but they often suffer from the problem when an arbitrary rectangular surface region on 3D model is locally parameterized. In this paper, we propose a new local parameterization scheme based on the projection level set method. This technique generates a series of equi-distanced curves on the surface region of interest, which are then used to generate effective local parameterization information. In this paper, we explain the new technique in detail and show its effectiveness by demonstrating experimental results.

• Journal of Radiation Protection and Research
• /
• v.19 no.2
• /
• pp.109-120
• /
• 1994

A method for estimating the effectiveness of each protective action against a nuclear accident has been proposed using the fuzzy set theory. In most of the existing countermeasure models in actions under radiological emergencies, the large variety of possible features is simplified by a number of rough assumptions. During this simplification procedure, a lot of information is lost which results in much uncertainty concerning the output of the countermeasure model. Furthermore, different assumptions should be used for different sites to consider the site specific conditions. Tn this study, the diversity of each variable related to protective action has been modelled by the linguistic variable. The effectiveness of sheltering and evacuation has been estimated using the proposed method. The potential advantage of the proposed method is in reducing the loss of information by incorporating the opinions of experts and by introducing the linguistic variables which represent the site specific conditions.