• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.8
• /
• pp.958-964
• /
• 2016

In this paper, we propose an i-vector based language recognition system to identify the spoken language of the speaker, which uses multiple discriminative deep neural network (DNN) models analogous to the multi-class support vector machine (SVM) classification system. The proposed model was trained and tested using the i-vectors included in the NIST 2015 i-vector Machine Learning Challenge database, and shown to outperform the conventional language recognition methods such as cosine distance, SVM and softmax NN classifier in open-set experiments.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.10
• /
• pp.397-404
• /
• 2018

Various applications are widely developed for smartphones to meet customer's needs. In many companies, messenger's typed interactive systems have been studied for business marketing, advertising and promotion to provide useful services for the customers. Such interactive systems are usually called as "Chatbot". In Chatbot, duplicated responses from Chatbot could occur frequently, and these make one lose interest. In this paper, we define a case that the response of Chatbot is duplicated according to the user's input, and propose a method to reduce duplicated responses of Chatbot. In the proposed method, we try to reduce duplication responses through a new duplication avoidance algorithm by building multiple tables in a database and by making combinations of user's input and its response in each table. In our experiments, the proposed method shows that duplicated responses are reduced by an average of 70%, compared with the existing method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.3 s.303
• /
• pp.73-80
• /
• 2005

Recently there have been many efforts to support searching and browsing based on the visual content of image and multimedia data. Most existing approaches to content-based image retrieval rely on query by example or user based low-level features such as color, shape, texture. But these methods of query are not easy to use and restrict. In this paper we propose a method for automatic color object extraction and labelling to support multiple queries of content-based image retrieval system. These approaches simplify the regions within images using single colorizing algorithm and extract color object using proposed Color and Spatial based Binary tree map(CSB tree map). And by searching over a large of number of processed regions, a index for the database is created by using proposed labelling method. This allows very fast indexing of the image by color contents of the images and spatial attributes. Futhermore, information about the labelled regions, such as the color set, size, and location, enables variable multiple queries that combine both color content and spatial relationships of regions. We proved our proposed system to be high performance through experiment comparable with another algorithm using 'Washington' image database.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.4
• /
• pp.521-526
• /
• 2015

Research on how to use the biological characteristics of human to confirm the identity of the individual is being actively conducted. Electrocardiogram(: ECG) based biometric system is difficult to counterfeit and does not cause skin irritation on the subject. It can be easily combined with conventional biometrics such as fingerprint and face recognition to give multimodal biometric systems. In this thesis, biometric identification method analysing ECG waveform characteristics from Discrete Wavelet Transform(DWT) coefficients is suggested. Feature selection is performed on the 9 coefficients of DWT using the correlation analysis. The verification is achieved by using the error back propagation neural networks. Using the proposed approach on 24 subjects of MIT-BIH QT Database, 98.88% verification rate has been obtained.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.4 no.2
• /
• pp.103-110
• /
• 2011

It is necessary to accurate and efficient management for measured digital data from sensors in u-health system. It is not efficient that sensor network process input stream data of mass storage stored in database the same time. We propose to improve the processing performance of multidimensional stream data continuous incoming from multiple sensor. We propose process query based on sliding window for efficient input stream and found multiple query plan to Mjoin method and we reduce stored data using backpropagation algorithm. As a result, we obtained to efficient result about 18.3% reduction rate of database using 14,324 data sets.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.11
• /
• pp.2889-2899
• /
• 1999

To maintain the traditional notion of global serializability in multidatabase systems has been recognized as one of difficult problems due to the autonomy of participating local database systems. In this paper, we propose a global concurrency control algorithm based on the relaxed concurrency control criterion in distributed MDBs, which can be applied to applications in which the database integration has no effect on the integrity constraints. In the proposed algorithm, the process to determine whether a global transaction can be executed or not consists of intra-validation phase and inter-validation phase.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.461-463
• /
• 2003

휴먼지놈프로젝트이후 컴퓨터를 이용한 연구는 점차로 활발하게 진행되고 있는데 그 중 단백질의 기능예측과 관련하여 보다 많은 연구가 이루어지고 있다. 단백질의 기능예측을 위해서는 3차원 구조정보가 많이 이용된다. 3차원 구조를 형성하는 것은 주로 아미노산 서열이나 1차, 2차 구조 정보가 보다 구체적인 단백질 구조예측을 위해 이용되고 있다. 전세계적으로 다량의 단백질 구조정보 및 예측을 위한 방법들이 소개되고 있지만 각 자원들마다 저장, 관리 형식이 다를 뿐만 아니라, 정보를 이용하는 방법도 어렵다. 본 논문에서는 다양하게 존재하는 단백질 구조 데이터베이스 자원들을 에이전트화여 통합성과 재사용성을 지향하였고, 에이전트시티 네트워크에 연결함으로써 개방성과 확장성, 분산성을 높이도록 하였다.

• Journal of the Korea Society for Simulation
• /
• v.3 no.1
• /
• pp.125-134
• /
• 1994

In real-time database systems, transactions's commitment done before the given deadlines is more important than just getting the maximum throughput. Transactions missing the given deadlines are no longer meaningful in real-time applications. Therefore, there is a need for new transaction processing models to meet the given deadlines in real-time database applications, because moat conventional transaction models are not designed to meet deadlines. In this paper we propose a new transaction models which uses multiple versions of a data item. The model uses read-from graphs and dynamic reorder of transactions to meet deadlines. A read-from graph contains the past read semantics of read operations and support the model to decide which database operation to be taken. Then, we show simulation results comparing the proposed model with other transaction models such as two phase locking model and the optimistic concurrency control model.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10a
• /
• pp.121-124
• /
• 2000

DAC 정책을 기반으로 하는 DBMS에서 데이터에 대한 사용자의 접근 통제는 접근 규칙 데이터베이스에 저장된 접근 규칙을 바탕으로 이 사용자가 접근하려는 데이터에 접근 권리가 명시적으로 기술되었는지를 확인하므로 써 수행된다. MAC 정책은 각 시스템의 주체와 객체에게 보안 등급을 부여하고, 등급별로 분리된 정보의 보안을 유지하기 위해서 다중 보안 단계에서 정보를 처리하는 강제적 접근 권한을 제공한다. 본 논문에서는 실제 MAC 정책을 기업 환경에 적용시키는데 있어서는 많은 제약사항이 존재하고 있으며, 이러한 제약사항 중에 레벨별로 정보의 공유가 필요할 경우에 레벨간에 최대, 최소를 둠으로써 레벨간의 정보 공유를 가능하게 만들고자 하는 모델을 제안하고자 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.229-231
• /
• 2001

공간 데이터베이스 시스템에서의 질의처리 과정 중 질의 재작성 과정에 의해 다중 블록 질의가 단일 블록으로 변환되면 공간 서술자와 비공간 서술자가 OR와 AND에 의해 연결되어있는 복잡한 CNF가 생성된다. CNF 내의 공간 서술자는 공간연산의 정제단계의 수행 비용이 비공간 연산에 비해 상당히 많이 들기 때문에 비공간 서술자와는 다른 최적화 기법이 필요하다. 본 논문에서는 공간 서술자가 포함된 복잡한 CNF를 수평적으로 분리하여 질의를 재작성하고 수행순서를 재조정하는 기법을 제안한다. 제안하는 기법은 원시 CNF를 수행 비용이 상대적으로 적은 전처리 단계의 CNF와 이에 비해 수행비용이 많이 드는 후처리 단계의 CNF로 분리하고 질의를 재작성 한 후 비용 모델에 의거해서 실행 트리를 최적화 한다. 본 논문에서 제시하는 기법은 질의 최적화 단계에서 공간연산의 단계별 실행특성을 감안한 효율적인 실행 계획 생성이 가능하다는 장점이 있다.