• The Journal of the Acoustical Society of Korea
• /
• v.22 no.1
• /
• pp.42-47
• /
• 2003

This paper proposes the method to generate new test data using the sample shift of the start frame for SPRT(sequential probability ratio test) in speaker verification. The SPRT method is a effective algorithm that can reduce the test computational complexity. However, in making the decision procedure, SPRT can be executed on the assumption that the input samples are usually to be i.i.d. (Independent and Identically Distributed) samples from a probability density function (pdf), also it's not suitable method to apply for the short utterance. The proposed method can achieve SPRT regardless of the utterance length of the test data because it is method to generate the new test data through the sample shift of start frame. Also, the correlation property of data to be considered in the SPRT method can be effectively removed by employing the principal component analysis. Experimental results show that the proposed method increased the computational complexity of data for sample shift a little, but it has a good performance result more than a conventional method above the average 0.7% in EER (equal error rate).

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.2
• /
• pp.5-11
• /
• 1996

The purpose of this paper is to propose a method improving the performance of a semi-continuous hidden Markov model(SCHMM) speaker adaptation system which uses Bayesian Parameter reestimation approach. The performance of Bayesian speaker adaptation could be degraded in case that the features of a new speaker are severely different from those of a reference codebook. The excessive codewords of the reference codebook still remain after adaptation proess. which cause confusion in recognition process. To solve such problems, the proposed method uses formant information which is extracted from the cepstral coefficients of the reference codebook and adaptation data. The reference codebook is adapted to represent the formant distribution of a new speaker and it is used for Bayesian speaker adaptation as an initial codebook. The proposed method provides accurate correspondence between reference codebook and adaptation data. It was observed that the excessive codewords were not selected during recognition process. The experimental results showed that the proposed method improved the recognition performance.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.6
• /
• pp.427-431
• /
• 2007

In this paper we describe a Korean part-of-speech tagging approach using resolution rules for individual ambiguous word and statistical information. Our tagging approach resolves lexical ambiguities by common rules, rules for individual ambiguous word, and statistical approach. Common rules are ones for idioms and phrases of common use including phrases composed of main and auxiliary verbs. We built resolution rules for each word which has several distinct morphological analysis results to enhance tagging accuracy. Each rule may have morphemes, morphological tags, and/or word senses of not only an ambiguous word itself but also words around it. Statistical approach based on HMM is then applied for ambiguous words which are not resolved by rules. Experiment shows that the part-of-speech tagging approach has high accuracy and broad coverage.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.11
• /
• pp.222-227
• /
• 1997

To diagnose cardiac arrhythmia owing to reentry mechanism, cardiac conduction system was modeled by modified Hidden Markov modeled by evaluated. First, simulation of transient conduction states and output waves were made with initially assumed parametric values of cardiac muscle repolariztion time, conduction velocity and its automaticity. The output was a series of onset time and the name of the wave. Parameters determined the rate of beating, lengths of wave intervals, rate of abnormal beats, and the like. Several parameter sets were found to simulate normal sinus rhythm, supraventricular /ventricular tachycardia, atrial /vetricular extrasystole, etc. Then, utilizing the estimation theorems of Hidden Markov Model, the best conduction path was estimated given the previous output. With this modified estimation method, close matching between the simulated conduction path and the estimated one was confirmed.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.39 no.9
• /
• pp.848-857
• /
• 2011

Vision-based collision avoidance system for air traffic management requires a excellent multiple target detection algorithm under low signal-to-noise ratio (SNR) levels. The track-before-detect (TBD) approaches have significant applications such as detection of small and dim targets from an image sequence. In this paper, two detection algorithms with the TBD approaches are proposed to satisfy the multiple target detection requirements. The first algorithm, based on a dynamic programming approach, is designed to classify multiple targets by using a k-means clustering algorithm. In the second approach, a hidden Markov model (HMM) is slightly modified for detecting multiple targets sequentially. Both of the proposed approaches are used in numerical simulations with variations in target appearance properties to provide satisfactory performance as multiple target detection methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.9
• /
• pp.2285-2301
• /
• 2012

Peer-to-Peer (P2P) networks are becoming more and more popular in video content delivery services, such as Video on Demand (VoD). Scalability feature of P2P allows a higher number of simultaneous users at a given server load and bandwidth to use stream service. However, the quality of service (QoS) in these networks is difficult to be guaranteed because of the free-riding problem that nodes download the recourses while never uploading recourses, which degrades the performance of P2P VoD networks. In this paper, a distributed trust model is designed to reduce node's free-riding phenomenon in P2P VoD networks. In this model, the P2P network is abstracted to be a super node hierarchical structure to monitor the reputation of nodes. In order to calculate the reputation of nodes, the Hidden Markov Model (HMM) is introduced in this paper. Besides, a distinction algorithm is proposed to distinguish the free-riders and malicious nodes. The free-riders are the nodes which have a low frequency to free-ride. And the malicious nodes have a high frequency to free-ride. The distinction algorithm takes different measures to response to the request of these two kinds of free-riders. The simulation results demonstrate that this proposed trust model can improve QoS effectively in P2P VoD networks.

• Development and Reproduction
• /
• v.6 no.1
• /
• pp.45-54
• /
• 2002

Reproductive activity of golden hamsters(Mesocricetus auratus) is regulated by the photoperiod. They are sexually active in summer and inactive in winter. Melatonin, a pineal hormone, has been known to mediate sexual activities in seasonal breeding animals. Melatonin receptor was recently identified in several animal species including hmm. But little has been known about it in relation to the reproductive activities of golden hamsters. By using reverse transcription polymerase chain reaction(RT-PCR) methods, a portion of the melatonin receptor gene(309 nucleotides) was identified in golden hamsters. The nucleotide sequence of the melatonin receptor and the amino acid sequence deduced were compared to those reported in other animals. Melatonin receptors were obviously detected in hypothalamus, pituitary containing pars tuberalis, blood, and spleen. Although the testicular weights and the levels of reproductive hormones were dramatically affected by photoperiods, the expression of melatonin receptor was not markedly changed by them. These results suggest that the action of melatonin in regulating reproduction might be mainly due to the affinity of melatonin receptor rather than the density fi melatonin receptor.

• Health Policy and Management
• /
• v.15 no.3
• /
• pp.1-16
• /
• 2005

This study was planned to investigate the relationship between development levels of learning organization and organization effectiveness in Hospital. Data were collected from 285 respondents who have participated in 'Learning Organization Project'(response rate =$50.5\%$). Structured questionnaire were applied by self administrated survey for two weeks since 2003 May. Main results were as follows; In the result of factor analysis, four factor were created and almost questionnaire items were classified into as same categories as theoretical concepts. Cronbach's a coefficient also showed over 0.7 in all categories. This result means that measurement tool to evaluate the development level of learning organization is valid and reliable. In the comparison of the development level of learning organization by participants' specialties, managerial workers perceived the lowest construction level, while medical technicians evaluated it as the highest level. In regression analysis, the perception levels of work environment, task and human aspect showed positive relationship with job competency significantly. For job satisfaction, levels of task and human aspects had positive relationship significantly. In addition, for organizational commitement, levels of organization and human aspect were positive predictors. Finally, for the satisfaction about experience of learning organization project, levels of environment, task and hmm aspects were related positively. We concluded from these result that the positive relationship between construction levels of learning organization and organization effectiveness was extended to hospital, besides industrial fields. We recommend the introduction and facilitation of learning organization project in various settings to improve the competency of knowledge management in individual and organizational levels.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.15 no.6
• /
• pp.579-589
• /
• 2004

The radar signals are generally very sensitive to relative orientations between radar and target. Thus, the performance of a target recognition system significantly deteriorates as the region of aspect angles becomes broader. To address this difficulty, in this paper, we propose a method based on the multi-aspect information in order to improve the classification capability ever for a wide angular region. First, range profiles are used to extract feature vectors based on the central moments and principal component analysis(PCA). Then, a classifier with the use of multi-aspect information is applied to them, yielding an additional improvement of target recognition capability. There are two different strategies among the classifiers that can fuse the information from multi-aspect radar signals: independent methodology and dependent methodology. In this study, the performances of the two strategies are compared within the frame work of target recognition. The radar cross section(RCS) data of six aircraft models measured at compact range of Pohang University of Science and Technology are used to demonstrate and compare the performances of the two strategies.

• Journal of KIISE:Software and Applications
• /
• v.32 no.6
• /
• pp.570-579
• /
• 2005

Facial expression recognition technology that has potentialities for applying various fields is appling on the man-machine interface development, human identification test, and restoration of facial expression by virtual model etc. Using sequential facial images, this study proposes a simpler method for detecting human facial expressions such as happiness, anger, surprise, and sadness. Moreover the proposed method can detect the facial expressions in the conditions of the sequential facial images which is not rigid motion. We identify the determinant face and elements of facial expressions and then estimates the feature regions of the elements by using information about color, size, and position. In the next step, the direction patterns of feature regions of each element are determined by using optical flows estimated gradient methods. Using the direction model proposed by this study, we match each direction patterns. The method identifies a facial expression based on the least minimum score of combination values between direction model and pattern matching for presenting each facial expression. In the experiments, this study verifies the validity of the Proposed methods.