• Speech Sciences
• /
• v.11 no.2
• /
• pp.237-245
• /
• 2004

In general, Gaussian mixture model(GMM) is used to estimate the speaker model for speaker identification. The parameter estimates of the GMM are obtained by using the expectation-maximization (EM) algorithm for the maximum likelihood(ML) estimation. However, if the number of mixtures isn't defined well in the GMM, those parameters are obtained inappropriately. The problem to find the number of components is significant to estimate the optimal parameter in mixture model. In this paper, to estimate the optimal number of mixtures, we propose the method that starts from the sufficient mixtures, after, the number is reduced by investigating the mutual information between mixtures for GMM. In result, we can estimate the optimal number of mixtures. The effectiveness of the proposed method is shown by the experiment using artificial data. Also, we performed the speaker identification applying the proposed method comparing with other approaches.

• International journal of advanced smart convergence
• /
• v.11 no.4
• /
• pp.47-56
• /
• 2022

Recently bank card number recognition plays an important role in improving payment efficiency. In this paper we propose a new bank-card number identification algorithm. The proposed algorithm consists of three modules which include edge detection, candidate region generation, and recognition. The module of 'edge detection' is used to obtain the possible digital region. The module of 'candidate region generation' has the role to expand the length of the digital region to obtain the candidate card number regions, i.e. to obtain the final bank card number location. And the module of 'recognition' has Convolutional deep learning Neural Network (CNN) to identify the final bank card numbers. Experimental results show that the identification rate of the proposed algorithm is 95% for the card numbers, which shows 20% better than that of conventional algorithm or method.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.2
• /
• pp.1-7
• /
• 2017

Recently, NAND flash memory, which is used as a storage medium, is replacing HDD (Hard Disk Drive) at a high speed due to various advantages such as fast access speed, low power, and easy portability. In order to apply NAND flash memory to a computer system, a Flash Translation Layer (FTL) is indispensably required. FTL provides a number of features such as address mapping, garbage collection, wear leveling, and hot data identification. In particular, hot data identification is an algorithm that identifies specific pages where data updates frequently occur. Hot data identification helps to improve overall performance by identifying and managing hot data separately. MHF (Multi hash framework) technique, known as hot data identification technique, records the number of write operations in memory. The recorded value is evaluated and judged as hot data. However, the method of counting the number of times in a write request is not enough to judge a page as a hot data page. In this paper, we propose hot data identification which considers not only the number of write requests but also the persistence of write requests.

• The KIPS Transactions:PartC
• /
• v.12C no.3 s.99
• /
• pp.317-322
• /
• 2005

The existing certificate based authentication or identification just verifies whether the owner of private key corresponding to public key of certificate is the DN user set in the user field in the certificate or not, then we cannot find out who is the actual private key owner in a real world. To make up for this weak points, the method to insert the identification number like the resident registration number into the certificate extension field is applied as a technical standard to current domestic PKI system. In this paper, we propose the ECC based integrated identification, identification number checking and key management protocol providing user validation during the login.

• Spatial Information Research
• /
• v.2 no.1
• /
• pp.85-92
• /
• 1994

This study examines the unique characteristics of the parcel identification number especially in developing the Korean land information system(KLIS). There are several limitations in establishing KLIS in terms of the location identification. Therefore, it is necessary to develop the appropriate parcel identification number system in Korea including the road identification systym and the three dimensional parcel identification system. The exact parcel bounary also needs accurate surveying and registration.

• The Journal of Society for e-Business Studies
• /
• v.19 no.4
• /
• pp.151-168
• /
• 2014

UCI (Universal Content Identifier) as a national digital content identification system for identifying digital content and ICN (Integrated Copyright Number) for copyright management are operated by Korea copyright commission. However, They are not interoperable with international standard identification system such as ISRC (International Standard Recording Code), ISWC (International Standard Works Code), and ISAN (International Standard Audiovisual Number) due to lack of linkage system. Hence, extra works with international standard identification system are needed for international market entry and integrated management of statistical information including content settlement in international market is impossible. In this paper, the domestic/international identification systems are surveyed, and by metadata analysis of identification systems, linkage method with UCI/ICN is proposed. And also by developing the prototype model, research direction to UCI/ICN with international standard identification system is proposed.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2538-2541
• /
• 2005

This paper deals one of the methods of system identification, especially on-line system identification in time-domain. The algorithm in this study needs all states of the system as well input to it for system identification. In this reason, Kalman filter is used for state estimation. But in order to implement a state estimator, the fact that a system model must be known is logical contradiction. To overcome this, state estimation and system parameter estimation are performed simultaneously in one sample. And the result of the system parameter estimation is used as basis to state estimation in next sample. On-line system identification comes, in every sample by performing both processes of state estimation and parameter estimation that are related mutually and recursively. This paper demonstrates the validity of proposed algorithm through an example of an unstable inverted pendulum system. This algorithm can be useful for on-line system identification of a system that has fewer number of measurable output than system order or number of states.

• Speech Sciences
• /
• v.8 no.3
• /
• pp.93-104
• /
• 2001

The author analyzed acoustic parameters of ten Korean numbers produced by ten male students using Praat. Variations of f0, F1, F2 and F3 within and between speakers were examined by determining an average and standard deviation of the parameters of each number and by comparing the acoustic values with one another. Results showed that each subject produced the numbers within a certain range of variation across time. Thus, speaker identification can be more certain using dynamic information of the acoustic parameters within each vocalic segment. Also, percent difference of within-subjects' variation to that of between-subjects can be utilized to determine which sounds would be better stimuli for speaker identification. According to the criteria, the number '2' proved the best stimulus while the number '7' was the worst. Future studies will be necessary to explore robust methods of speaker identification under noisy conditions.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.4 no.3
• /
• pp.45-53
• /
• 2008

As internet is wide spread, the number of internet service provider is increased. Internet service providers gather the personnel information with inhabitants registration identification number for the user management and the adult authentication. The personnel information is spreaded thorough the Internet by the system hacking, mismanagement and malicious resale. And the personnel information is used for spam email, phishing scams, etc. by malicious others. So the Ministry of Information and Communication Republic of Korea developments I-PIN system of the personnel identification. But, I-PIN has some problem the guideline for it and the method of 5 I-PIN services. In this paper, we analyze the problem about the guideline for I-PIN and the method of 5 I-PIN services. And we propose the countermeasure about the problem.

• Computational Structural Engineering : An International Journal
• /
• v.3 no.1
• /
• pp.1-7
• /
• 2003

For system identification of large structures, it is not practical to identify the entire structure due to the prohibitive computational time and difficulty in numerical convergence. This paper explores the possibility of performing system identification at substructure level, taking advantage of reduction in both the number of unknowns and the number of degrees of freedom involved. Another advantage is that different portions (substructures) of a structural system can be identified independently and even concurrently with parallel computing. Two substructural identification methods are formulated on the basis whether substructural approach is used to obtain first-order or second-order model. For substructural first-order model, identification at the substructure level will be performed by means of the Observer/Kalman filter Identification (OKID) and the Eigensystem Realization Algorithm (ERA) whereas identification at the global level will be performed to obtain second-order model in order to evaluate the system's stiffness and mass parameters. In the case of substructural second-order model, identification will be performed at the substructure level throughout the identification process. The efficiency of the proposed technique is shown by numerical examples for multi-storey shear buildings subjected to random forces, taking into consideration the effects of noisy measurement data. The results indicate that both the proposed methods are effective and efficient for damage identification of large structures.