• Journal of Internet Computing and Services
• /
• v.15 no.6
• /
• pp.117-124
• /
• 2014

Cluttered background is a major obstacle in developing salient object detection and tracking system for mobile device captured natural scene video frames. In this paper we propose a context aware feature vector selection model to provide an efficient noise filtering by machine learning based classifiers. Since the context awareness for feature selection is achieved by searching nearest neighborhoods, known as NP hard problem, we apply a fast approximation method with complexity analysis in details. Separability enhancement in feature vector space by adding the context aware feature subsets is studied rigorously using principal component analysis (PCA). Overall performance enhancement is quantified by the statistical measures in terms of the various machine learning models including MLP, SVM, Naïve Bayesian, CART. Summary of computational costs and performance enhancement is also presented.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.8 no.3
• /
• pp.105-112
• /
• 1983

This paper discribes technique of the recursive restoration for the images degraded by linear space invariant blur and additive white Gaussian noise. The image is characterized statistically by tis mean and correlation function. An exponential autocorrelation function has been used to model neighborhood model. The vector model was used because of analytical simplicitly and capability to implement brightness correlation function. Base on the vector model, a two-dimensional discrete stochastic a 12 point neighborhood model for represeting images was developme and used the technique of moving window processing to restore blurred and noisy images without dimensionality increesing, It has been shown a 12 point neighborhood model was found to be more adequate than a 8 point pixel model to obtain optimum pixel estimated. If the image is highly correlated, it is necessary to use a large number of points in the neighborhood in order to have improvements in restoring image. It is believed that these result could be applied to a wide range of image processing problem. Because image processing thchniques normally required a 2-D linear filtering.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.41-47
• /
• 2008

Cluster based fuzzy model tree has certain drawbacks to decrease performance of testinB data when over-fitting of training data exists. To reduce the sensitivity of performance due to over-fitting problem, we proposed a modified cluster based fuzzy model tree with node information. To construct model tree, cluster centers are calculated by fuzzy clustering method using all input and output attributes in advance. And then, linear models are constructed at internal nodes with fuzzy membership values between centers and input attributes. In the prediction step, membership values are calculated by using fuzzy distance between input attributes and all centers that passing the nodes from root to leaf nodes. Finally, data prediction is performed by the weighted average method with the linear models and fuzzy membership values. To show the effectiveness of the proposed method, we have applied our method to various dataset. Under various experiments, our proposed method shows better performance than conventional cluster based fuzzy model tree.

• Journal of Digital Convergence
• /
• v.16 no.11
• /
• pp.335-340
• /
• 2018

Commercialized speech recognition systems that have an accuracy recognition rates are used a learning model from a type of speaker dependent isolated data. However, it has a problem that shows a decrease in the speech recognition performance according to the quantity of data in noise environments. In this paper, we proposed the vector quantization based speech recognition performance improvement using maximum log likelihood in Gaussian distribution. The proposed method is the best learning model configuration method for increasing the accuracy of speech recognition for similar speech using the vector quantization and Maximum Log Likelihood with speech characteristic extraction method. It is used a method of extracting a speech feature based on the hidden markov model. It can improve the accuracy of inaccurate speech model for speech models been produced at the existing system with the use of the proposed system may constitute a robust model for speech recognition. The proposed method shows the improved recognition accuracy in a speech recognition system.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_1
• /
• pp.763-774
• /
• 2020

Wind data forecasted from the numerical weather prediction (NWP) model is generally used as the first-guess of the target tracking process to obtain the atmospheric motion vectors(AMVs) because it increases tracking accuracy and reduce computational time. However, there is a contradiction that the NWP model used as the first-guess is used again as the reference in the AMVs verification process. To overcome this problem, model-independent first guesses are required. In this study, we propose the AMVs derivation from Lucas and Kanade optical flow method and then using it as the first guess. To retrieve AMVs, Himawari-8/AHI geostationary satellite level-1B data were used at 00, 06, 12, and 18 UTC from August 19 to September 5, 2015. To evaluate the impact of applying the optical flow method on the AMV derivation, cross-validation has been conducted in three ways as follows. (1) Without the first-guess, (2) NWP (KMA/UM) forecasted wind as the first-guess, and (3) Optical flow method based wind as the first-guess. As the results of verification using ECMWF ERA-Interim reanalysis data, the highest precision (RMSVD: 5.296-5.804 ms^-1) was obtained using optical flow based winds as the first-guess. In addition, the computation speed for AMVs derivation was the slowest without the first-guess test, but the other two had similar performance. Thus, applying the optical flow method in the target tracking process of AMVs algorithm, this study showed that the optical flow method is very effective as a first guess for model-independent AMVs derivation.

• Journal of the Korean Vacuum Society
• /
• v.21 no.2
• /
• pp.69-77
• /
• 2012

Visualization of the electromagnetic vector fields are presented and examined with Mathematica. Vector fields may be used to represent a great of many physical quantities in various area of physics, including electromagnetism with vector differential operators. Because they deal with abstract, three-dimensional fields that are some times very difficult to visualize, electromagnetism can be conceptually rather difficult. Visual representation of such an abstract vector fields is invaluable to student or researchers working in this field and also helps teaching electromagnetism to physics or engineering students. Mathematica provides a wider range of graphical tools including plot of vector fields and vector analysis, which can be applied to visualization of electromagnetic system. We have visualized the most fundamental concepts of the electromagnetic vector $\vec{E}=-\vec{\nabla}_{\varphi}$, $\vec{D}={\epsilon}\vec{E}$, $\vec{\nabla}{\times}\vec{A}$, $\vec{B}={\mu}\vec{H}$, $\vec{B}={\mu}_0(\vec{H}+\vec{M})$, which are confirmed with vector calculations and valid graphically with some presentations.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.2
• /
• pp.94-102
• /
• 2000

This paper presents a new FDI scheme based on dynamic fuzzy model(DFM) for the unknown nonlinear system, which can detect and isolate process faults continuously over all ranges of operating condition. The dynamic behavior of a nonlinear process is represented by a set of local linear models. The parameters of the DFM are identified by an on-line methods. The residual vector of the FDI system is consisted of the parameter deviations from nominal model and the set of grade of membership values indicating the operating condition of the nonlinear process. The detection and isolation of faults are performed via a neural network classifier that are learned the relationship between the residual vector and fault type. We apply the proposed FDI scheme to the FDI system design for a two-tank system and show the usefulness of the proposed scheme.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.1
• /
• pp.47-50
• /
• 2019

This paper proposes an acoustic model adaptation method for effective speech recognition in noisy environments. In the proposed algorithm, the noise corruption function is estimated employing DNN (Deep Neural Network), and the function is applied to the model parameter estimation. The experimental results using the Aurora 2.0 framework and database demonstrate that the proposed model adaptation method shows more effective in known and unknown noisy environments compared to the conventional methods. In particular, the experiments of the unknown environments show 15.87 % of relative improvement in the average of WER (Word Error Rate).

• Journal of the Korea Computer Graphics Society
• /
• v.4 no.2
• /
• pp.29-32
• /
• 1998

When rendering polyhedral models, normal vectors at polygon vertices are necessary for smooth shading. The most commonly used technique of approximating a vertex normal vector by averaging normal vectors of faces around the vertex yields, however, different results on different tessellations Further, continuous deformation of models may cause abrupt discontinuous changes in normal vector directions. In this paper, a variation of the above technique is proposed to avoid these problems. Specifically, it uses a weighted average of normal vectors of faces around the vertex, where the weight of a face being the angular span of the two edges incident on the vertex.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.563-568
• /
• 2016

The word sense disambiguation problem is to find the correct sense of an ambiguous word having multiple senses in a dictionary in a sentence. We regard this problem as a multi-class classification problem and classify the ambiguous word by using Support Vector Machines. Context words of the ambiguous word, which are extracted from Sejong sense tagged corpus, are represented to two kinds of vector space. One vector space is composed of context words vectors having binary weights. The other vector space has vectors where the context words are mapped by word embedding model. After experiments, we acquired accuracy of 87.0% with context word vectors and 86.0% with word embedding model.