• The Journal of the Acoustical Society of Korea
• /
• v.26 no.8
• /
• pp.390-396
• /
• 2007

In this letter, we propose a novel approach to improve the performance of speech/music classification for the selectable mode vocoder(SMV) of 3GPP2 using the Gaussian mixture model(GMM) which is based on the expectation-maximization(EM) algorithm. We first present an effective analysis of the features and the classification method adopted in the conventional SMV. And then feature vectors which are applied to the GMM are selected from relevant Parameters of the SMV for the efficient speech/music classification. The performance of the proposed algorithm is evaluated under various conditions and yields better results compared with the conventional scheme of the SMV.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.657-664
• /
• 2003

Reliable tracking of moving humans is essential to motion estimation, video surveillance and human-computer interface. This paper presents a new approach to human motion tracking that combines appearance-based and model-based techniques. Monocular color video is processed at both pixel level and object level. At the pixel level, a Gaussian mixture model is used to train and classily individual pixel colors. At the object level, a 3D human body model projected on a 2D image plane is used to fit the image data. Our method does not use inverse kinematics due to the singularity problem. While many others use stochastic sampling for model-based motion tracking, our method is purely dependent on nonlinear programming. We convert the human motion tracking problem into a nonlinear programming problem. A cost function for parameter optimization is used to estimate the degree of the overlapping between the foreground input image silhouette and a projected 3D model body silhouette. The overlapping is computed using computational geometry by converting a set of pixels from the image domain to a polygon in the real projection plane domain. Our method is used to recognize various human motions. Motion tracking results from video sequences are very encouraging.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.6
• /
• pp.571-576
• /
• 2002

There have been a lot of considerations dealing with improving the performance of neuro-fuzzy system. The studies on the neuro-fuzzy modeling have largely been devoted to two approaches. First is to improve performance index of system. The other is to reduce the structure size. In spite of its satisfactory result, it should be noted that these are difficult to extend to high dimensional input or to increase the membership functions. We propose a novel neuro-fuzzy system based on the efficient clustering method for initializing the parameters of the premise part. It is a very useful method that maintains a few number of rules and improves the performance. It combine the various algorithms to improve the performance. The Expectation-Maximization algorithm of Gaussian mixture model is an efficient estimation method for unknown parameter estimation of mirture model. The obtained parameters are used for fuzzy clustering method. The proposed method satisfies these two requirements using the Gaussian mixture model and neuro-fuzzy modeling. Experimental results indicate that the proposed method is capable of giving reliable performance.

• International Journal of Highway Engineering
• /
• v.4 no.1 s.11
• /
• pp.149-159
• /
• 2002

This study was performed to estimate the high-speed direct tensile strength(DTS1), low-speed direct tensile strength(DTS2) , indirect tensile strength(ITS) resilient modulus(MR) and stiffness index(SI) of sand asphalt mixture based on the absolute viscosity, kinematic viscosity, penetration, softening point and PG grade of binder. DTS2 showed higher correlation with the physical properties than other properties of mixture, and the next was DTS1, ITS, SI and MR in order. Among binder properties, PG grade showed the highest relation with DTS2. Therefore. it was found that the high DTS mixture could be made when the binder with a high PG grade was used. However, since the individual physical property showed a relatively low correlation, various properties were used together in regression analysis. The estimation models of DTS and ITS were over 0.99, respectively. R2 of MR and SI estimation models were over 0.91 and 0.93, respectively. It was concluded that mechanical properties could be estimated with a high coefficient of determination from those physical properties.

• International Journal of Highway Engineering
• /
• v.4 no.4 s.14
• /
• pp.41-52
• /
• 2002

This study dealt with analysis of size effect of testing apparatus for Kim test which measures rut resistance characteristics of asphalt mixture under static loading. Two columns in different diameter with each column having different radios of round cut (Curvature) at the bottom were used for testing asphalt mixture. Deformation load ($P_{max}$) and deformation strength ($K_D$) were found to have relatively high correlation with rut depth and dynamic stability of asphalt concrete. Diameter of specimen was not a significant factor in this test. From the statistical correlation analysis with rutting properties, the radius of curvature and diameter of loading column were found to be important factor affecting the results of the test. Among the radios (r) of curvatures, r=0.5cm and 1.0cm showed much higher correlation than the column without curvature, and r=1.0cm being better between the two. The column with diameter of 4cm showed better correlation than diameter of 3cm. Therefore, the column of 4cm diameter with r=1.0cm was found to be the best among various apparatus sizes. Prediction models for rut depth and dynamic stability were developed for each aggregate mixture based on Kim test variables using SAS STEPWISE procedure. Therefore, if this test method is validated through further study, Kim test can be used for selecting asphalt mixture with the highest resistance against permanent deformation.

• Economic and Environmental Geology
• /
• v.55 no.4
• /
• pp.353-366
• /
• 2022

Spatial estimation of geoscience data (geo-data) is challenging due to spatial heterogeneity, data scarcity, and high dimensionality. A novel spatial estimation method is needed to consider the characteristics of geo-data. In this study, we proposed the application of Gaussian Mixture Model (GMM) among machine learning algorithms with multivariate data for robust spatial predictions. The performance of the proposed approach was tested through soil chemical concentration data from a former smelting area. The concentrations of As and Pb determined by ex-situ ICP-AES were the primary variables to be interpolated, while the other metal concentrations by ICP-AES and all data determined by in-situ portable X-ray fluorescence (PXRF) were used as auxiliary variables in GMM and ordinary cokriging (OCK). Among the multidimensional auxiliary variables, important variables were selected using a variable selection method based on the random forest. The results of GMM with important multivariate auxiliary data decreased the root mean-squared error (RMSE) down to 0.11 for As and 0.33 for Pb and increased the correlations (r) up to 0.31 for As and 0.46 for Pb compared to those from ordinary kriging and OCK using univariate or bivariate data. The use of GMM improved the performance of spatial interpretation of anthropogenic metals in soil. The multivariate spatial approach can be applied to understand complex and heterogeneous geological and geochemical features.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.44 no.4
• /
• pp.497-505
• /
• 2015

Traditional herbs, such as Lonicera japonica, Arctii Fructus, and Scutellariae Radix have been used as traditional drug due to their anti-inflammatory and anti-oxidant activities. The aim of this study was to investigate the anti-inflammatory effects of extract mixture (YG-1) in a model of lipopolysaccharide (LPS)-induced acute inflammation in both macrophage (RAW 264.7) cells and Sprague-Dawley rats. YG-1 did not show specific cellular toxicity in RAW 264.7 cells until a concentration of $100{\mu}g/mL$. YG-1 reduced various markers related to inflammation such as IL-$1{\beta}$, COX-2, and iNOS caused by LPS in RAW 264.7 cells. Consistent with these results, YG-1 exerted significant anti-inflammatory effects in an acute inflammation rat model. Acute fever and high concentration of IL-$1{\beta}$ in serum induced by LPS were significantly reduced by YG-1. These results were similar to flubiprofen, a commercial anti-inflammatory and anti-febrile drug. Therefore, these results indicate that YG-1 has beneficial effects on LPS-induced acute inflammation and suggest that YG-1 can serve as an effective anti-inflammatory and anti-febrile drug.

• Korean Chemical Engineering Research
• /
• v.46 no.2
• /
• pp.233-247
• /
• 2008

Process monitoring technology is able to detect the faults and the process changes which occur in a process unpredictably, which makes it possible to find the reasons of the faults and get rid of them, resulting in a stable process operation, high-quality product. Statistical process monitoring method based on data set has a main merit to be a tool which can easily supervise a process with the statistics and can be used in the analysis of process data if a high quality of data is given. Because a real process has the inherent characteristics of nonlinearity, non-Gaussianity, multiple operation modes, sensor faults and process changes, however, the conventional multivariate statistical process monitoring method results in inefficient results, the degradation of the supervision performances, or often unreliable monitoring results. Because the conventional methods are not easy to properly supervise the process due to their disadvantages, several advanced monitoring methods are developed recently. This review introduces the theories and application results of several remarkable monitoring methods, which are a nonlinear monitoring with kernel principle component analysis (KPCA), an adaptive model for process change, a mixture model for multiple operation modes and a sensor fault detection and reconstruction, in order to tackle the weak points of the conventional methods.

• Journal of Korea Foresty Energy
• /
• v.20 no.1
• /
• pp.35-41
• /
• 2001

Lignin model compounds I-lV were pyrolyzed at 315$^{\circ}C$. The mixture compounds pyrolized were analyzed by GC-MS spectrometry. The results were summarized as follows : 1. From the pyrolysis of lignin model compound I and II, 0.45mo1 of guaiacol, 0.5mol of dimethoxyphenol(DMP), and 0.12 and 0.23mo1 of dimethoxyacetonphenone(DMAP) were produced respectively. 2. In the pyrolysis of lignin model compound III and IV, 0.26mol of guaiacol, 0.30mo1 of DMP, and 0.09 and 0.15mo1 of trimethoxyaretonphenone(TMAP) were produced respectively 3. Pyrolysis mechanism of lignin model compounds are dehydrated at first, and $\beta$-04 linkage cleavaged, and then guaiacol, DMP, DMAP and TMAP were produced. The above results show that lignin model compound I and II produce more aromatic compounds than lignin model compound III and IV. This is reason that veratryl unit structures may pyrolize easier than trimethoxyphenol unit structures. The closer research is proceeding.

• Journal of Broadcast Engineering
• /
• v.3 no.1
• /
• pp.50-60
• /
• 1998

This paper addresses a problem of extraction of parameteric motion estimation and structural motion segmentation for compact image sequence representation and object-based generic video coding. In order to extract meaningful motion structure from image sequences, a direct parameteric motion estimation based on a pre-segmentation is proposed. The pre-segmentation which considers the motion of the moving objects is canied out based on probabilistic clustering with mixture models using optical flow and image intensities. Parametric motion segmentation can be obtained by iterated estimation of motion model parameters and region reassignment according to a criterion using Gauss-Newton iterative optimization algorithm. The efficiency of the proposed methoo is verified with computer simulation using elF real image sequences.