• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.2
• /
• pp.150-155
• /
• 2004

In this paper, an emotion recognition method using speech signal is presented. Six basic human emotions including happiness, sadness, anger, surprise, fear and dislike are investigated. The proposed recognizer have each codebook constructed by using the wavelet transform for the emotional state. Here, we first verify the emotional state at each filterbank and then the final recognition is obtained from a multi-decision method scheme. The database consists of 360 emotional utterances from twenty person who talk a sentence three times for six emotional states. The proposed method showed more 5% improvement of the recognition rate than previous works.

• Journal of KIISE
• /
• v.43 no.11
• /
• pp.1216-1222
• /
• 2016

The advent of large-scale web services has resulted in gradual increase in the amount of data used in those services. These big data are managed efficiently by DBMS such as MySQL and MariaDB, which use InnoDB engine as their storage engine, since InnoDB guarantees ACID and is suitable for handling large-scale data. To improve I/O performance, InnoDB caches data and index of its database through a buffer pool. It also supports multiple buffer pools to mitigate lock contentions. However, the multiple buffer pool scheme leads to the additional data consistency overhead. In this paper, we analyze the overhead of the multiple buffer pool scheme. In our experimental results, although multiple buffer pool scheme mitigates the lock contention by up to 46.3%, throughput of DMBS is significantly degraded by up to 50.6% due to increased disk I/O and fsync calls.

• Journal of KIISE:Databases
• /
• v.34 no.4
• /
• pp.315-327
• /
• 2007

The performance of database applications with large sets of multidimensional data depends on the performance of its access methods and the underlying disk system. In modeling the disk system, even though modem disks are manufactured with multiple physical zones, conventional access methods have been developed based on a traditional disk model with many simplifying assumptions. Thus, there is a marked lack of investigation on how to enhance the performance of access methods given a zoned disk model. The paper proposes novel zoning techniques that can be applied to any multidimensional access methods, both static and dynamic, enhancing the effective data transfer rate of underlying disk system by fully utilizing its zone characteristics. Our zoning techniques include data placement algorithms for multidimensional index structures and accompanying localized query processing algorithms for range queries. The experimental results show that our zoning techniques significantly improve the query performance.

• Journal of Korea Multimedia Society
• /
• v.6 no.1
• /
• pp.148-160
• /
• 2003

TMA(Tissue Mineral Analysis) is very popular method in hair mineral analysis for health care professionals in over 48 countries medical center. Assesment of nutritional minerals and toxic elements in the hair is very important not only for determining adequacy, deficiencies and unbalance, but also for assessing their relative relationships in a body. In Korea, there are some problems in TMA method. Because of not haying a medical information database which is suitable for korean to do analyze, the requested TMA has to send to TEI-USA. However, as the TMA results from TEI-USA is composed of English documents and graphic files prohibited to open, its usability is very low and a lot of dollars has to be payed. Also, it can make some problems in the reliability of the TMA results, since the TMA results are based on the database of western health and mineral standards, To solve these problems, I developed the first Medical Information System of TMA in Korea here. The system can analyze the complex tissue mineral data with multiple stage decision tree classifier. It is also constructed with multiple fuzzy database and hence analyze the TMA data by fuzzy inference methods. The effectiveness test of this systems can be shown the increased business efficiency and satisfaction rate 86% and 92% respectively.

• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1627-1633
• /
• 2017

Human dance is difficult to learn since there is no effective way to imitate an expert's motion, a sequence of complicated body movements, without taking an actual class. In this paper, we propose a dance learning system using human depth information. In the proposed system, a set of example motions are captured from various expert dancers through a marker-free motion capture and archived into a motion database server for online dance lessons. Given the end-user devices such as tablet and kiosk PCs, a student can learn a desired motion selected from the database and send one's own motion to an instructor for online feedback. During this learning process, our system provides a posture-based motion search and multi-mode views to support the efficient exchange of motion data between the student and instructor under a networked environment. The experimental results demonstrate that our system is capable to improve the student's dance skills over a given period of time.

• Journal of KIISE:Databases
• /
• v.31 no.4
• /
• pp.432-443
• /
• 2004

As the XML data has been widely used in the Internet, it is necessary to store and retrieve the XML data by using DBMSs. However, relational DBMSs suffer from the model difference between graph structure of the XML data and table forms in relational databases. We propose an ORDBMS-based DTD-dependent XML data management system Xing. Xing stores XML data in a DTD-dependent form in an object database. Since the object database schema has a graph structure and supports multi-valued attributes, mapping from an XML data model and queries into an object data model and OQLs is a simple problem. For rapid storing of large quantities of the XML data, we use SAX parser with customized Xing-tree which requires a small memory space compared with the DOM-tree. Xing also returns the query result in an XML document form. We have implemented the Xing system on top of UniSQL object-relational DBMS for the validity checking and performance comparison. For XML genome data from GenBank, and experimental evaluation shows that Xing can provide significant performance improvement (maximum 10 times) compared with the relational approach.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.4
• /
• pp.136-147
• /
• 2021

Autonomous driving-related technologies are developing step by step by applying the degree of driving. It is essential that operational management technology for roads where autonomous vehicles move should also develop in line with autonomous driving technology. However, in the case of road operation management, it is currently managed using only two-dimensional information, showing limitations in the systematic operation management of lane and facility information and maintenance. This study proposed a plan to construct an operation management system architecture capable of 3D spatial information-based operation management by designing a convergence database that can process real-time big data with high-definition road map data. Through this study, when using a high-definition road map based operation management system for lane and facility maintenance in the future, it is possible to visualize and manage facilities, edit and analyze data of multiple users, link various GIS S/W and efficiently process large scale of real-time data.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.401-404
• /
• 2007

본 논문은 거울 투영을 이용하여 2D의 감정인식 데이터베이스를 3D에 적용 가능하다는 것을 증명한다. 또한, 감정 확률을 이용하여 퍼지 모델링을 기반으로한 얼굴표정을 생성하고, 표정을 움직이는 3가지 기본 움직임에 대한 퍼지이론을 적용하여 얼굴표현함수를 제안한다. 제안된 방법은 거울 투영을 통한 다중 이미지를 이용하여 2D에서 사용되는 감정인식에 대한 특징벡터를 3D에 적용한다. 이로 인해, 2D의 모델링 대상이 되는 실제 모델의 기본감정에 대한 비선형적인 얼굴표정을 퍼지를 기반으로 모델링한다. 그리고 얼굴표정을 표현하는데 기본 감정 6가지인 행복, 슬픔, 혐오, 화남, 놀람, 무서움으로 표현되며 기본 감정의 확률에 대해서 각 감정의 평균값을 사용하고, 6가지 감정 확률을 이용하여 동적 얼굴표정을 생성한다. 제안된 방법을 3D 인간형 아바타에 적용하여 실제 모델의 표정 벡터와 비교 분석한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10a
• /
• pp.222-224
• /
• 2000

본 논문은 객체 관계형 실시간 DBMS인 Tachyon의 특성 및 구조에 관한여 기술한다. Tachyon은 전전자 교환기용 관계형 DBMS인 DREAM-S의 개발 경험을 바탕으로 개발된 객체 관계형 DBMA이고, 고성능 데이터 처리를 위한 주기억 장치 상주 DBMS이며, 우선순위 기반의 스케쥴링과 연성 데드라인(soft-deadline) 트랜잭션을 처리하는 실시간 DBMS이다. Tachyon은 객체지향 질의를 통한 융통성 있는 데이터 조작이 가능하며, 다중 사용자 환경에서 항상 데이터의 일관성을 유지하고, 고신뢰 시스템을 위한 이중화 구조의 지원 및 데이터 백업/복구 등의 종합적인 데이터베이스 관리를 제공한다. 현재 Tachyon은 DREAM-S와 더불어 초고속정보통신망에서의 백본 교환기 시스템의 DBMS로 활용될 예정이다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.27-31
• /
• 2008

많은 바이오인포매틱스 관련 데이터베이스와 도구가 네트워크를 통해서 제공되고 있고, 이들을 효과적으로 활용하면 생물학적 분석을 적은 비용으로 우수한 결과를 얻을 수 있다. 이 논문에서는 주어진 질의에 대해서 잠재적으로 관련된 DNA 서열 정보를 획득하고, 분석자가 관심 있는 항목을 선택하면, 선택된 항목에 대한 모든 DNA 서열 정보를 확보하고, 이들에 대해서 아미노산 서열로 자동변환하여 ORF라는 정보를 활용하여 가장 가능성이 큰 것을 추천하는 도구를 소개한다. 해당 도구에는 웹 로봇 기법과 ORF 검색등을 위한 생물학적 지식을 활용한다.