• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.2
• /
• pp.116-127
• /
• 2002

A new approach to improve the speaker adaptation algorithm by means of the variable number of observation density functions for CDHMM speech recognizer has been proposed. The proposed method uses the observation density function with more than one mixture in each state to represent speech characteristics in detail. The number of mixtures in each state is determined by the number of frames and the determinant of the variance, respectively. The each MAP Parameter is extracted in every mixture determined by these two methods. In addition, the state segmentation method requiring speaker adaptation can segment the adapting speech more Precisely by using speaker-independent model trained from sufficient database as a priori knowledge. And the state duration distribution is used lot adapting the speech duration information owing to speaker's utterance habit and speed. The recognition rate of the proposed methods are significantly higher than that of the conventional method using one mixture in each state.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.9
• /
• pp.2153-2160
• /
• 2015

An analysis of hardware design conditions of moving object detection (MOD) algorithm is described, which is based on effective Gaussian mixture learning (EGML). A simulation model of EGML algorithm is implemented using OpenCV, and the effects of some parameter values on background learning time and MOD sensitivity are analyzed for various images. In addition, optimal design conditions for hardware implementation of EGML-based MOD algorithm are extracted from fixed-point simulations for various bit-widths of parameters. The proposed fixed-point model of the EGML-based MOD uses only half of the bit-width at the expense of the loss of MOD performance within 0.5% when compared with floating-point MOD results.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.1
• /
• pp.13-19
• /
• 2011

In this paper, a visual surveillance system using SOPC based NIOS II embedded processor and C2H compiler was implemented. In this system, the IP is constructed by C2H compiler for the output of the camera images, image processing, serial communication and network communication, then, it is implemented to effectively control each IP based on the SOPC and the NIOS II embedded processor. And, an algorithm which updates the background images for high speed and robust detection of the moving objects is proposed using the Adaptive Gaussian Mixture Model(AGMM). In results, it can detecte the moving objects(pedestrians and vehicles) under day-time and night-time. It is confirmed that the proposed AGMM algorithm has better performance than the Adaptive Threshold Method(ATM) and the Gaussian Mixture Model(GMM) from our experiments.

• Archives of Plastic Surgery
• /
• v.35 no.6
• /
• pp.631-636
• /
• 2008

Purpose: Adipose tissue-derived stem cells(ADSC) has an osteoconductive potential and demineralized bone matrix(DBM) is an osteoinductive material. A combination of DBM and ADSC wound probably create osteoinductive properties. The purpose of this study is to determine the effect of the combination of DBM and ADSC mixture on healing of rat calvarial defect. Methods: Thirty adult male Sprague-Dawley rats were randomized into 3 groups(n=10) as 1) Control, 2) DBM alone, 3) DBM with ADSC mixture. DBM with ADSC mixture group has had a 3-day preculture of ADSC from groin fat pad. An 6 mm critical size circular calvarial defect was made in each rat. Defect was implanted with DBM alone or DBM with ADSC mixture. Control defect was left unfilled. 6 and 12 weeks after the implantation, the rats were sacrificed and the defects were evaluated by histomorphometric and radiographical studies. Results: Histomorphometric analysis revealed that DBM with ADSC mixture group showed significantly higher bone formation than DBM alone group(p<0.05). Although radiographs from DBM alone group and DBM with ADSC group revealed similar diffuse radiopaque spots dispersed throughout the defect. Densitometric analysis of calvarial defect revealed DBM with ADSC mixture group significantly higher bone formation than DBM alone(p<0.05). There was correlation of densitometry with new bone formation(Spearman's correlation of coefficient=0.804, 6 weeks, 0.802, 12 weeks). Conclusion: The DBM with ADSC mixture group showed the best healing response and the osteoinductive properties of DBM were accelerated with ADSC mixture. It will be clinically applicable that DBM and ADSC mixture in plastic and reconstructive surgery, such as alveolar cleft and congenital facial deformities that bone graft should be required.

• Journal of KIISE:Software and Applications
• /
• v.32 no.8
• /
• pp.781-788
• /
• 2005

LDA (Linear Discriminant Analysis) is a data discrimination technique that seeks transformation to maximize the ratio of the between-class scatter and the within-class scatter While it has been successfully applied to several applications, it has two limitations, both concerning the underfitting problem. First, it fails to discriminate data with complex distributions since all data in each class are assumed to be distributed in the Gaussian manner; and second, it can lose class-wise information, since it produces only one transformation over the entire range of classes. We propose three extensions of LDA to overcome the above problems. The first extension overcomes the first problem by modeling the within-class scatter using a PCA mixture model that can represent more complex distribution. The second extension overcomes the second problem by taking different transformation for each class in order to provide class-wise features. The third extension combines these two modifications by representing each class in terms of the PCA mixture model and taking different transformation for each mixture component. It is shown that all our proposed extensions of LDA outperform LDA concerning classification errors for handwritten digit recognition and alphabet recognition.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.10C
• /
• pp.965-974
• /
• 2007

In this paper, we proposed the feature selection algorithm for multi-class genre classification. In our proposed algorithm, we developed GMM separation score based on Gaussian mixture model for measuring separability between two genres. Additionally, we improved feature subset selection algorithm based on sequential forward selection for multi-class genre classification. Instead of setting criterion as entire genre separability measures, we set criterion as worst genre separability measure for each sequential selection step. In order to assess the performance proposed algorithm, we extracted various features which represent characteristics such as timbre, rhythm, pitch and so on. Then, we investigate classification performance by GMM classifier and k-NN classifier for selected features using conventional algorithm and proposed algorithm. Proposed algorithm showed improved performance in classification accuracy up to 10 percent for classification experiments of low dimension feature vector especially.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.24 no.3
• /
• pp.26-38
• /
• 2020

Mixture design of self-compacting concrete is a typical multi-criteria decision making problem and conventional mixture designs are based on the low level engineering method like trials and errors through iteration method to satisfy the various requirements. This study concerns with performing the straightforward multiobjective design optimization of economic SCC mixture considering relative importances of the various requirements and cost-effectives of SCC. Total five requirements of 28day compressive strength, filling ability, segregation stability, material cost and mass were taken into consideration to prepare the objective function to be formulated in form of the weighted-multiobjective mixture design optimization problem. Economic SCC mixture computational design can be given in a rational way which considering material costs and the relative importances of the requiremets and from the result of this study it is expected that the development of SCC mixtue computational design and the consequent univeral concrete material design optimization methodology can be advanced.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.6
• /
• pp.506-511
• /
• 2018

This paper proposes an GMM(Gaussian Mixture Model)-DNN(Deep Neural Network) hybrid-based feature compensation method for effective speech recognition in noisy environments. In the proposed algorithm, the posterior probability for the conventional GMM-based feature compensation method is calculated using DNN. The experimental results using the Aurora 2.0 framework and database demonstrate that the proposed GMM-DNN hybrid-based feature compensation method shows more effective in Known and Unknown noisy environments compared to the GMM-based method. In particular, the experiments of the Unknown environments show 9.13 % of relative improvement in the average of WER (Word Error Rate) and considerable improvements in lower SNR (Signal to Noise Ratio) conditions such as 0 and 5 dB SNR.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.4
• /
• pp.401-407
• /
• 2009

In this paper, we propose a novel method for the cross-correlation based double-talk detection (DTD), which employing the Gaussian Mixture Model (GMM) in the frequency domain. The proposed algorithm transforms the cross correlation coefficient used in the time domain into 16 channels in the frequency domain using the discrete fourier transform (DFT). The channels are then selected into seven feature vectors for GMM and we identify three different regions such as far-end, double-talk and near-end speech using the likelihood comparison based on those feature vectors. The presented DTD algorithm detects efficiently the double-talk regions without Voice Activity Detector which has been used in conventional cross correlation based double-talk detection. The performance of the proposed algorithm is evaluated under various conditions and yields better results compared with the conventional schemes. especially, show the robustness against detection errors resulting from the background noises or echo path change which one of the key issues in practical DTD.

• Journal of Global Scholars of Marketing Science
• /
• v.13
• /
• pp.209-229
• /
• 2004

Although the site evaluation factors that affect the navigation pattern are well documented, the attempt to explore the difference in the relationship between navigation pattern and site evaluation factors by post hoc segmentation approach has been relatively rare. For this purpose, this study constructs the structure equation model using web-evaluation data and log file of a community site with 300,000 members. And then it applies the structure equation model to each segment. Each segment is identified by mixture model. Mixture model is to unmix the sample, to identify the segments, and to estimate the parameters of the density function underlying the observed data within each segment. The study examines the opportunity to increase GFI, using mixture model which supposes heterogeneous groups in the users, not through specification search by modification index from structure equation model. This study finds out that AGFI increases from 0.819 at total sample to 0.927, 0.930, 0.928, 0.929 for each 4 segments in the case of the community site. The results confirm that segment level approach is more effective than model modification when model is robust in terms of theoretical background. Furthermore, we can identify a heterogeneous navigation pattern and site evaluation variation in the community website at segment level.