• The Journal of the Acoustical Society of Korea
• /
• v.30 no.2
• /
• pp.100-106
• /
• 2011

Music recordings have been digitalized such that huge size of music database is available to the public. Thus, the automatic classification system of music genres is required to effectively manage the growing music database. Mel-Frequency Cepstral Coefficient (MFCC) is a popular feature vector for genre classification. In this paper, the combined super-vector with Decorrelated Filter Bank (DFB) and Octave-based Spectral Contrast (OSC) using texture windows is processed by Support Vector Machine (SVM) for genre classification. Even with the lower order of the feature vector, the proposed super-vector produces 4.2 % improved classification accuracy compared with the conventional Marsyas system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.11a
• /
• pp.193-198
• /
• 1999

In the 21th century, everyone feels that the multimedia system is close at hand in real life due to the rapid advance of the computer processing ability and high speed and high guality of communication services. Also the limited frequencies resource will be optimized due to rapid advances in digital video technology which is believed superior to analogue technology in information engineering. MEPG-2 has been introduced for broadcasting use such as digital TV Thus it features the high-definition and hyper-low bit rate. But, because of much throughput it has been implemented by high-priced private ASIC chip and is not in general use yet. But in this research, noticing the rapid enhancement of PC processor performance comparing with the price. MPEG-2 was developed by real time software MPEG-2 had been known impossible to implement with S/W, but the research proved the possibility of the S/W implementation and below are the pictures also in the research was improved 'Motion Vector and Compensation' Algorithm which requires the most operations and UT was made possible real time process. Multimedia Info Society has settled and accompanied by the rapid advance of image-processing technology and lots of standards.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.7
• /
• pp.119-124
• /
• 2015

Speech enhancement has been required as a preprocessor for a noise robust speech recognition system. Codebook-based Speech Enhancement (CBSE) is highly robust in nonstationary noise environments compared with conventional noise estimation algorithms. However, its performance is severely degraded for the codevector combinations that have lower correlation with the input signal since CBSE depends on the trained codebook information. To overcome this problem, only the reliable codevector combinations are selected to be used to remove the codevector combinations that have lower correlation with input signal. The proposed method produces the improved performance compared to the conventional CBSE in terms of Log-Spectral Distortion (LSD) and Perceptual Evaluation of Speech Quality (PESQ).

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.4
• /
• pp.286-293
• /
• 2010

There are two major conventional quantization algorithms: resolution-constrained quantization (RCQ) and entropy-constrained quantization (ECQ). Although RCQ works well for fixed transmission-rate, it produces the distortion outliers since the cell sizes are different. Compared with RCQ, ECQ has the constraints on the cell size but it produces the rate outliers. We propose the cell-size constrained vector quantization (CCVQ) that improves the generalized Lloyd algorithm (GLA). The CCVQ algorithm is able to make a soft-decision between RCQ and ECQ by using the flexible penalty measure according to the cell size. Although the proposed method increases the small amount of overall mean-distortion, it can reduce the distortion outliers.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.3
• /
• pp.74-80
• /
• 2012

In resolution-constrained quantization, the size of Voronoi cell varies depending on probability density function of the input data, which causes large amount of distortion outliers. We propose a vector quantization method that reduces distortion outliers by combining the generalized Lloyd algorithm (GLA) and the cell-size constrained vector quantization (CCVQ) scheme. The training data are divided into the inside and outside regions according to the size of Voronoi cell, and consequently CCVQ and GLA are applied to each region, respectively. As CCVQ is applied to the densely populated region of the source instead of GLA, the number of centroids for the outside region can be increased such that distortion outliers can be decreased. In real-world environment, source mismatch between training and test data is inevitable. For the source mismatch case, the proposed algorithm improves performance in terms of average distortion and distortion outliers.

• The Korean Journal of Health Service Management
• /
• v.9 no.3
• /
• pp.175-185
• /
• 2015

Objectives : This study was did a meta-analysis of emergency room visits decreased effectiveness of self management education interventions in asthma among adult patients with asthma. Methods : A search of the database PubMed resulted in identifying 8,619 studies done between January 1990 and November 2012. STATA version 10.0 was used to analyze the effect size, explore possible causes of heterogeneity, and determine publication bias with a funnel plot. Results : We included 7 cases on emergency room visits decreased effectiveness of self management and education. Asthmatic patients experienced fewer attacks (summary effect size, 0.75; 95% confidence interval [CI], 0.65-0.95). We found that emergency room visits decreased effectiveness of self management and education were associated with statistically significant effects. Conclusions : Based on these finding, self management and education on interventions are necessary to prevent asthmatic attacks in patients and to reduce the severity of the attacks, and self management and education programs are needed in Korea.

• Korean Journal of Materials Research
• /
• v.19 no.9
• /
• pp.510-515
• /
• 2009

The compound of 2,6-Bis[(9-phenylcarbazolyl)ethenyl]naphthalene (BPCEN-1), 2-[6-{1-Cyano-2-(9-phenylcarbazoly)vinyl}naphthyl]-3-(9-phenylcarbazolyl)acrylonitrile (BPCEN-2), 2,6-Bis[{4-(1-naphthy l)phenylamino} styrenyl] naphthalene (BNPASN-1), 2-[6-{1-Cyano-2-(naphthylphenylaminophenyl) vinyl}naphthyl]-3-(naphthylphenylaminophenyl)acrylonitrile (BNPASN-2) was analyzed electrochemically and spectroscopically and can be obtained by bonding phenylcarbazolyl, naphthylphenylaminophenyl and -CN ligands to 2,7-naphthalene. The electrochemical and spectroscopic study resulted in the P-type (BPCEN-1, BNPASN-1) being changed to N-type (BPCEN-2, BNPASN-2) according to -CN bonding despite having the same structure. The value of band gap(Eg) was revealed to be small as HOMO had shifted higher and LUMO lower. The Eg value for naphthylphenylaminophenyl ligand was reduced because it has a smaller HOMO/LUMO value than that of phenylcarbazolyl from a structural perspective. The electrochemical HOMO/LUMO values for BPCEN-1, BPCEN-2, BNPASN-1, BNPASN-2 were measured to be 5.55eV / 2.83eV, 5.73eV / 3.06eV, 5.48eV / 2.78eV, and 5.53eV / 2.98eV, respectively. By -CN ligand, the UV max, Eg and PL max were shifted to longer wavelength in their spectra and the luminescence band could be also confirmed to be broad in the photoluminescence (PL) spectrum.

• Korean Journal of Applied Biomechanics
• /
• v.13 no.3
• /
• pp.163-180
• /
• 2003

This paper aims at collecting the guantitative data of kenematic variables by analysing the gait patterns of the normal adult men and the handicapped. The gait motions were taped with 4 video cameras, the cinematographic analyses were performed by the DLT technique of three dimensional image treatment. The following results were obtained in the analysis of the variables: 1. The ratio of stance time and swing time did not show any significant difference in the groups of the normal men and the handicapped when both foot of the former and the right feet of the latter were compared. The stride peeriod time of these two groups were 1.12 and 1.11 second, respectively. 2. In the handicapped group, the step width was wider, the step length and stride length were shorter, and especially, the step length of the right foot was shorter, 3. The small vertical displacement of left toes of the handicapped group showed that the heal contact and the left midstance are almost simultaneous. 4. The two groups have almost the same horizontal displacement of the center of gravity and the same vertical rate of extension. In view of the velocity of the center of gravity the normal adults showed the constant speed of movement. However, the handicapped adults were reduced from the right midstance to the right toe-off. 5. The handicapped showed prominently low angle on the left toe-off in the ankle joint angle, they also had the tendency to walk in the patterns of extended knee in the knee joint angle. Both the handicapped and the normal had the hyperextension on the toe-off in the hip joint angle. In the back and front angle of body, both showed the slightly back-sided walking positions. 6. Both groups had the abduction of both feet in foot placement angle, but the handicapped did not show serious abduction of left midstance.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.5
• /
• pp.31-36
• /
• 2011

In this paper, Mel-Frequency Cepstral Coefficient (MFCC), Decorrelated Filter Bank (DFB), Octave-based Spectral Contrast (OSC), Zero-Crossing Rate (ZCR), and Spectral Contract/Roll-Off are combined as a set of multiple feature-vectors for the music genre classification system based on the Support Vector Machine (SVM) classifier. In the conventional system, feature vectors for the entire genre classes are normalized for the SVM model training and classification. However, in this paper, selected feature vectors that are compared based on the One-Against-One (OAO) SVM classifier are only used for normalization. Using OSC as a single feature-vector and the multiple feature-vectors, we obtain the genre classification rates of 60.8% and 77.4%, respectively, with the conventional normalization method. Using the proposed normalization method, we obtain the increased classification rates by 8.2% and 3.3% for OSC and the multiple feature-vectors, respectively.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.5
• /
• pp.100-108
• /
• 2010

An autocorrelation method is used in pitch estimation. Autocorrelation values in time and frequency domains, which have different characteristics, correspond to the pitch period and fundamental frequency, respectively. We utilize an integrated autocorrelation method in time and frequency domains. It can remove the errors of pitch doubling and having. In the time and frequency domains, pitch period and fundamental frequency have reciprocal relation to each other. Especially, fundamental frequency estimation ends up as an error because of the resolution of FFT. To reduce these artifacts, interpolation methods are applied in the integrated autocorrelation domain, which decreases pitch errors. Moreover, only for the pitch candidates found in a time domain, the corresponding frequency-domain autocorrelation values are calculated with reduced computational complexity. Using linear interpolation, we can decrease the required number of FFT coefficients by 8 times. Thus, compared to the conventional methods, computational complexity can be reduced by 9.5 times.