• 전기학회논문지
• /
• 제64권9호
• /
• pp.1347-1355
• /
• 2015

In this study, we compare the recognition performance using PCA and RBFNNs for introducing robust face recognition system to pose variations based on pose estimation. proposed face recognition system uses Honda/UCSD database for comparing recognition performance. Honda/UCSD database consists of 20 people, with 5 poses per person for a total of 500 face images. Extracted image consists of 5 poses using Multiple-Space PCA and each pose is performed by using (2D)²PCA for performing pose classification. Linear polynomial function is used as connection weight of RBFNNs Pattern Classifier and parameter coefficient is set by using Particle Swarm Optimization for model optimization. Proposed (2D)²PCA-based face pose classification performs recognition performance with PCA, (2D)²PCA and RBFNNs.

• 한국국방경영분석학회지
• /
• 제34권1호
• /
• pp.13-30
• /
• 2008

본 연구에서는 외국의 국방표준화 정보관리 발전동향을 살펴보고 우리나라 현 실태를 분석한 후 민수-국방분야에 공통 적용가능한 규격/표준 공통 분류목록의 제정과 이를 바탕으로 한 표준화 정보기반 통합DB의 구축 및 국방표준화 정보체계의 구축방안을 제시하였다. 규격/표준 공통 분류목록은 국방규격과 한국산업표준의 그룹핑을 통해 표준화 대상식별에 관한 보다 효과적인 방법을 제시하였으며, 표준화 정보기반 통합DB 구축을 통해 규격/표준과 다양한 정보들과의 상호참조 기반을 제공하였고, 표준화 정보체계를 통해 민수-국방분야 전반에 걸친 규격/표준정보 활용의 토대를 제시하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 A
• /
• pp.416-418
• /
• 2001

This Paper presents the 2-step load cycle of daily load curve for representative load pattern of power distribution transformer. We decide the representative load pattern of distribution transformer in domestic using the pattern classification algorithm. The K-mean method is used for the pattern classification algorithm. The acquisition equipment of field load data is utilized for 96-sample distribution transformers and the field data is used in the construction of the database for the creation of daily load pattern.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2000년도 춘계학술대회 논문집
• /
• pp.503-510
• /
• 2000

Recently, many kinds of research has been actively developing for a standardization and information related to the construction works. These works include the general field of design, construction, supervision, maintenance and management on facilities. The works of database construction for a standardization and information were chiefly propelled centering around the present conditions related to the design, construction work. The field related to maintenance and management on facilities lags behind in the works of database construction. The establishment of standard classification system(SCS) on facilities and inspection data is most important among the things related to maintenance and management to have a efficiently maintenance and management. This paper suggests SCS on facilities and inspection data according to that of facilities. On the basis of SCS of facilities and inspection data, code work with classification system and input work for a data of maintenance and management was practised. The purpose of this paper is to suggest a kind of statistics data and investigate a characteristics of inspection using statistic data on tunnel structures

• 정보기술과데이타베이스저널
• /
• 제2권2호
• /
• pp.71-85
• /
• 1995

Many research results conducted by neural network researchers have claimed that the classification accuracy of neural networks is superior to, or at least equal to that of conventional methods. However, in series of neural network classifications, it was found that the classification accuracy strongly depends on the characteristics of training data set. Even though there are many research reports that the classification accuracy of neural networks can be different, depending on the composition and architecture of the networks, training algorithm, and test data set, very few research addressed the problem of classification accuracy when the basic assumption of data monotonicity is violated, In this research, development project of automated credit evaluation system is described. The finding was that arrangement of training data is critical to successful implementation of neural training to maintain monotonicity of the data set, for enhancing classification accuracy of neural networks.

• 대한음성학회지:말소리
• /
• 제68권
• /
• pp.75-93
• /
• 2008

An example-based dialogue system tries to utilize many pairs which are stored in a dialogue database. The most important part of the example-based dialogue system is to find the most similar utterance to user's input utterance. Modality, which is characterized as conveying the speaker's involvement in the propositional content of a given utterance, is one of the core sentence features. For example, the sentence "I want to go to school." has a modality of hope. In this paper, we have proposed a modality classification system which can predict sentence modality in order to improve the performance of example-based dialogue systems. We also define a modality tag set for a dialogue system, and validate this tag set using a rule-based modality classification system. Experimental results show that our modality tag set and modality classification system improve the performance of an example-based dialogue system.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.767-772
• /
• 2005

The Internet is a packet switched network which offers best-effort service, but current IP network provide enhanced services such Quality of Services, Virtual Private Network (VPN) services, Distribute Firewall and IP Security Gateways. All such services need packet classification for determining the flow. The problem is performing scalable packet classification at wire speeds even as rule databases increase in size. Therefore, this research offer packet classification algorithm that increase classifier performance when working with enlarge rules database by rearrange rule structure into Bitmap Intersection Lookup (BIL) tables. It will use packet's header field for looking up BIL tables and take the result with intersection operation by logical AND. This approach will use simple algorithm and rule structure, it make classifier have high search speed and fast updates.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 춘계학술대회 논문집 전력기술부문
• /
• pp.89-91
• /
• 2001

This paper presents the result of pattern classification of load demand for distribution transformer in domestic. The field data of load demand is measured using the load acquisition device and the measurement data is used for the database system for load management of distribution transformed. For the pattern classification, the load data and the customer information data are also used. The K-MEAN method is used for the pattern classification algorithm. The result of pattern classification is used for the 2-step format of load demand curve.

• 한국건설관리학회:학술대회논문집
• /
• 한국건설관리학회 2003년도 학술대회지
• /
• pp.589-592
• /
• 2003

국내에서는 건설공사지원정보체계의 활용을 촉진하고, 건설공사의 제반 단계에서 발생하는 정보의 상호교류를 촉진하기 위하여 통합건설정보 분류체계를 제안하고 있으나 효율적인 활용방안에 대한 연구의 미흡과 건설공사의 중요한 정보인 설계도서의 체계적인 통합관리를 위한 데이터베이스 (Database : DB) 중심의 전산관리시스템의 구축미비로 인하여 많은 문제점을 야기하고 있다. 이에 본 연구에서는 건설정보 분류체계의 활용과 설계도서의 체계적인 통합관리를 위한 방안으로 데이터베이스 설계하고 이를 웹(Web)기반에서 관리할 수 있는 설계도서 통합관리 시스템을 구축 하였다.

• 터널과지하공간
• /
• 제9권3호
• /
• pp.214-220
• /
• 1999

본 연구에서는 RMR system항목들의 타당성을 평가하였고 국내현장에서 측정한 데이터에 대한 적용성을 검토하였다. 데이터베이스는 전국에 걸쳐 지하철, 철도, 도로 터널로 구분하여 139개 현장으로부터 작성하였다. Bieniawsk의 원분류는 경험적으로 도출되었지만 비교적 타당한 것으로 분석되었다. 그러나 국내 현장에 적용할 때에는 상당한 차이가 있어서 국내의 데이터베이스로 추론한 새로운 암반분류 시스템 KRMR1과 KRMR2를 제안하였다. KRMR1에서는 인자들의 등 급비중을 조정하였으며 KRMR2에는 2개의 인자를 추가하였다. 이 과정에서 암반의 성질을 평가하는 ‘특성치’의 선택이 어려워 인공신경 망을 이용하여 추론하였다.