• The Journal of the Acoustical Society of Korea
• /
• v.22 no.6
• /
• pp.457-462
• /
• 2003

In this paper, we propose a speaker pruning method for real-time processing and improving performance of speaker identification system based on GMM(Gaussian Mixture Model). Conventional speaker identification methods, such as ML (Maximum Likelihood), WMR(weighting Model Rank), and MWMR(Modified WMR) we that frame likelihoods are calculated using the whole frames of each input speech and all of the speaker models and then a speaker having the biggest accumulated likelihood is selected. However, in these methods, calculation cost and processing time become larger as the increase of the number of input frames and speakers. To solve this problem in the proposed method, only a part of speaker models that have higher likelihood are selected using only a part of input frames, and identified speaker is decided from evaluating the selected speaker models. In this method, fm can be applied for improving the identification performance in speaker identification even the number of speakers is changed. In several experiments, the proposed method showed a reduction of 65% on calculation cost and an increase of 2% on identification rate than conventional methods. These results means that the proposed method can be applied effectively for a real-time processing and for improvement of performance in speaker identification.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.3
• /
• pp.261-270
• /
• 2017

Bad sitting postures are known to cause for a variety of diseases or physical deformation. However, it is not easy to fit right sitting posture for long periods of time. Therefore, methods of distinguishing and inducing good sitting posture have been constantly proposed. Proposed methods were image processing, using pressure sensor attached to the chair, and using the IMU (Internal Measurement Unit). The method of using IMU has advantages of simple hardware configuration and free of various constraints in measurement. In this paper, we researched on distinguishing sitting postures with a small amount of data using just one IMU. Feature extraction method was used to find data which contribution is the least for classification. Machine learning algorithms were used to find the best position to classify and we found best machine learning algorithm. Used feature extraction method was PCA(Principal Component Analysis). Used Machine learning models were five : SVM(Support Vector Machine), KNN(K Nearest Neighbor), K-means (K-means Algorithm) GMM (Gaussian Mixture Model), and HMM (Hidden Marcov Model). As a result of research, back neck is suitable position for classification because classification rate of it was highest in every model. It was confirmed that Yaw data which is one of the IMU data has the smallest contribution to classification rate using PCA and there was no changes in classification rate after removal it. SVM, KNN are suitable for classification because their classification rate are higher than the others.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.703-709
• /
• 2019

This paper proposes speech recognition systems employing Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) structures combined with Hidden Markov Moldel (HMM) to effectively recognize the speech of VeloPharyngeal Insufficiency (VPI) patients, and compares the recognition performance of the systems to the Gaussian Mixture Model (GMM-HMM) and fully-connected Deep Neural Network (DNNHMM) based speech recognition systems. In this paper, the initial model is trained using normal speakers' speech and simulated VPI speech is used for generating a prior model for speaker adaptation. For VPI speaker adaptation, selected layers are trained in the CNN-HMM based model, and dropout regulatory technique is applied in the LSTM-HMM based model, showing 3.68 % improvement in recognition accuracy. The experimental results demonstrate that the proposed LSTM-HMM-based speech recognition system is effective for VPI speech with small-sized speech data, compared to conventional GMM-HMM and fully-connected DNN-HMM system.

• Journal of the Korean Institute of Gas
• /
• v.19 no.2
• /
• pp.37-44
• /
• 2015

We proposed the improved Langmuir adsorption relations considering volume change effect of coal matrix during primary production of CBM and Enhanced-CBM with injection of carbon dioxide or CCS in coalseam but also volumetric strain. To verify this model, experimental data of pure gas adsorption such as $CO_2$, $CH_4$, and $N_2$ on coals were used to compare conventional Langmuir model with this model. From the results, we obtained that the larger adsorption capacity of coal and the higher adsorption affinity of gas, the larger error occur with Langmuir model. Using this model, however, we found not only substantially better fit in all condition but also reasonable volumetric strain of the coal matrix. We also applied this volume modified pure gas adsorption model to the IAS model to describe gas adsorption and volumetric strain for mixed gas. This modified-IAS model fitting experimental data by Hall et al(1994) improved accuracy of mixed gas adsorption calculation compared with conventional model.

• Korean Journal of Food Science and Technology
• /
• v.42 no.1
• /
• pp.109-114
• /
• 2010

The in vivo and in vitro effects of oriental herb extracts of Cassia obtusifolia, Taraxacum platycarpum and Ulmusmacrocarpa on anti-atopic allergic reaction were evaluated in this study. A mixture of these extracts exhibited more potent anti-allergic activities in human mast cells than those from individual extracts. The herbal mixture significantly inhibited the release of compound 48/80-induced $\beta$-hexosaminidase release in the human mast cell line, HMC-1. The mixture also suppressed the production of PMA and A23187-induced inflammatory cytokines in HMC-1 cells. To further investigate the in vivo effects of the herbal mixture, a Dermatophagoides farinae (DF)-induced atopic dermatitis mouse model was utilized. Oral administration of the herbal mixture significantly decreased the ear thickness and swelling in DF treated NC/Nga mice in a dose dependent manner. Furthermore, serum levels of IgE and interleukin-4 (IL-4) were significantly decreased, whereas interferon-gamma (IFN-$\gamma$) levels were increased in the mixture administrated groups when compared to the control. Taken together, our data indicate the possibility of using a mixture of the oriental herb extract to relieve symptoms of atopic dermatitis.

• Journal of Energy Engineering
• /
• v.2 no.1
• /
• pp.54-67
• /
• 1993

Two turbulent reaction models of the premixed CC1$_4$/CH$_4$/air mixture are successfully incorporated in a 3-dimensional computer program and is applied for Dow Chemical incinerator equipped with two main off-center burners. The first reaction model is fast chemistry model(model 1), in which chemical reaction is governed by the turbulent mixing itself. And the second one is nonequilibrium model(model 2), where the effect of the chemical kinetics due to the presence of CC1$_4$is considered by the incorporation of the burning velocity data of CC1$_4$. The second model not only shows the flame inhibition trend due to the presence CC1$_4$compound, but also predicts qualitatively the vortical stratification of the CC1$_4$concentration appeared experimentally at the kiln exit. Other comparisions of two models are made in detail.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.2
• /
• pp.184-189
• /
• 2013

In this paper, we propose the injurious moving picture filtering system using certain sounds contained in the injurious moving picture to filter injurious moving picture which is distributed without limitation in internet and internet storage space. For this purpose, the Gaussian Mixture Model which can well represent the characteristics of the sound, is used and frame level likelihood estimation is used to calculate the likelihood between filtering target data and the sound models. Also, the pruning method which can real-time proceed by reducing the comparing number of data, is applied for real-time processing, and MWMR method which showed good performance from existing speaker identification, is applied for the distinguish performance of high precision. In the identification experiment result, in case of the frame rate which is the proportion of total frame to high likelihood frame, is set to 50%, identification error rate is 6.06%, and in case of frame rate is set to 60%, error rate is 3.03%. As the result, the proposed system can distinguish between general and injurious moving picture effectively.

• Journal of the Korean Chemical Society
• /
• v.37 no.6
• /
• pp.562-569
• /
• 1993

The pseudophase separation model is used to describe the effects of pH and n-propanol on the mixed micellar formation of protonated and unprotonated dimethyldodecylamine oxides. Dimethyl-dodecylamine oxide surfactant molecules may exist in aqueous solution in either nonionic (unprotonated) or cationic (protonated) form, and they can be modeled thermodynamically as a binary mixture of cationic and nonionic surfactants. The composition of the binary mixture is varied by adjusting the solution pH. And activities, micellar compositions, and monomeric compositions of two surfactant species can be calculated directly from the experimental titration data by applying pseudophase separation model to the micellar system of DDAO in water/n-propanol. The critical micellar concentrations and the p$K_a$ values of the binary mixture systems are dependent on the micellar composition of the protonated cationic surfactant (X); especially they show the minimum phenomena when they are plotted against the micellar composition of the protonated cationic surfactant (X). The critical micellar concentration of the binary mixed DDAO system is generally decreased when n-propanol is added to the binary mixture system, and the degree of decrease is dependent on the concentration of n-propanol.

• Smart Media Journal
• /
• v.4 no.3
• /
• pp.50-55
• /
• 2015

In this paper, we present background modeling method based on Gaussian mixture model to subtract background for night-time video surveillance. In night-time video, it is hard work to distinguish the object from the background because a background pixel is similar to a object pixel. To solve this problem, we change the pixel of input frame to more advantageous value to make the Gaussian mixture model using scaled histogram stretching in preprocessing step. Using scaled pixel value of input frame, we then exploit GMM to find the ideal background pixelwisely. In case that the pixel of next frame is not included in any Gaussian, the matching test in old GMM method ignores the information of stored background by eliminating the Gaussian distribution with low weight. Therefore we consider the stacked data by applying the difference between the old mean and new pixel intensity to new mean instead of removing the Gaussian with low weight. Some experiments demonstrate that the proposed background modeling method shows the superiority of our algorithm effectively.

• Journal of Advanced Navigation Technology
• /
• v.27 no.6
• /
• pp.888-896
• /
• 2023

When an aircraft is landing, it is expected that the aircraft will follow a specified approach procedure and then land at the airport. However, depending on the airport situation, neighbouring aircraft or the instructions of the air traffic controller, there can be a deviation from the specified approach. Detecting aircraft approach patterns is necessary for traffic flow and flight safety, and this paper suggests clustering techniques to identify aircraft patterns in the approach segment. The Gaussian Mixture Model (GMM), one of the machine learning techniques, is used to cluster the trajectories of aircraft, and ADS-B data from aircraft landing at the Gimhae airport in 2019 are used. The aircraft trajectories are clustered on the plane, and a total of 86 approach trajectory patterns are extracted using the centroid value of each cluster. Considering the correlation between the approach procedure pattern and overshoots, the distribution of overshoots is calculated.