• Journal of IKEEE
• /
• v.6 no.2 s.11
• /
• pp.152-160
• /
• 2002

This paper is the realization of the face recognition system for multimedia application. This system is focused on the design concerning the improvement of recognition rate and the reduction of processing time for face recognition. The non-modificated application of typical RGB color system enables the reduction of time required for color system transform. The neural network and the application of algorithm using face characteristic improves the recognition rate. After mosaicking an image, a face-color block has been selected through the color analysis of mosaic block. The characteristic of the face removes the mis-checked face-color candidate block. Finally, from the face color block, four special values are obtained. These values are processed to the neural network using the back propagation algorithm. The output values are the touchstone to decide the genuineness of face field. The realized system showed 90% of face recognition rate with less than 0.1 second of processing time. This result can be understood as sufficient processing time and recognition rate to find out the face block for multimedia application in dynamic image.

• Proceedings of the KOSOMBE Conference
• /
• v.1992 no.11
• /
• pp.83-85
• /
• 1992

In this paper, the Infant Incubator Consisting of amp lifer, A/D Convert, I/O Expand, Watchdog Timer, Alarm Circuit. Display, and mirco-Computer part was developed. The care of Premature new borns of the required that they be in an environment in which temperature is elevaled and Controlled, because they are unable to regulated their own temperature. The central and processing methods based on micro-processor employ the flexibility, and economy over other conventional system. The system characteristic were as follows 1) system based on micro-processor. 2) Easy-to read, touch-Operate control panel all displays and indicators 3) System flexibility.

• Journal of Welding and Joining
• /
• v.9 no.2
• /
• pp.20-28
• /
• 1991

The main subject of this study is the construction of an automatic welding system that has the capability to trace the weld seam in GMA welding of lap joints. The system was composed of a vision sensor, moving torch, and personal computer(IBM-PC). In the developed vision sensor, an image was captured by the frame grabber at the time of short circuit during welding. The threshold method was adopted for determining the structured light and the central difference method for detecting the weld joint. And the seam tracing of the torch was performed by using the data regeneration algorithm. In this system using the image at the time of short circuit, weld seam tracking was performed without any relations to arc light and spatters.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.5
• /
• pp.1198-1206
• /
• 1996

This paper proposes the functionality of communication network management which operates in central control station of satellite communication network, which will be constructed to DAMA-SCPC ground station using KORE ASAT. And communication network configuration components are classified with hierarchical structure in order to efficiently maintain communication network operation management, and configuration components that are classified into graphic objects and this graphic objects are visualized with tree structure which can be handled uniformally and efficiently. In addition to that, this paper proposes expression method of graphic object to implement our real time communication network management system, and the real time communication net-work management composed as client-server system. The performance of the proposed algorithm is analyzed through the computer simulation.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.20 no.4
• /
• pp.39-44
• /
• 2012

This paper propose a transmission method for "Transportation system" that can decide precise position under wide area road traffic environment. For precise position detecting, central station collect multiple receiver station's satellite navigation data and generate correction information. In this process, we need efficient real time transmission method for satellite navigation message that has variable data size. We propose real time data transmission method. This real time transmission method offer efficient processing structure for multiple receiver station's satellite navigation message. This paper explains proposed real time transmission method and proofs this transmission method.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.11a
• /
• pp.233-238
• /
• 2000

CNC machine tool is assembled by central processor, PLC(Programmable Logic Controller), and actuator. The sequential control of machine generally controlled by a PLC. The main fault occured at PLC in 3 control parts. In LC faults, operational fault is charged over 70%. This paper describes diagnosis model and data processing for remote monitoring and diagnosis system in machine tools with open architecture controller. Two diagnostic models based on the ladder diagram. Logical Diagnosis Model(LDM), Sequential Diagnosis Model(SDM), are proposed. Data processing structure is proposed ST(Structured Text) based on IEC1131-3. The faults from CNC are received message form open architecture controller and faults from PLC are gathered by sequential data.. To do this, CNC and PLC's logical and sequential data is constructed database.

• Annual Conference on Human and Language Technology
• /
• 2011.10a
• /
• pp.83-84
• /
• 2011

정보 검색 시스템에서 사용되고 있는 벡터 공간 모델은 벡터 유사도 계산 속도에 따라 전체 시스템의 성능에 많은 영향을 미친다. 본 논문에서는 문서 유사도 계산 성능을 향상시키기 위하여 GPU(Graphic Processing Unit)를 이용하는 CUDA프레임워크에서 병렬처리 연산을 구현하였으며, CPU(Central Processing Unit) 환경에서의 연산 속도와 비교했을 때 최대 15배의 성능 향상 효과가 있음을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.04a
• /
• pp.1116-1122
• /
• 2000

네트워크 상에 다수의 방화벽이 설치되어 있을 경우, 각각의 방화벽에 대한 정책을 설정하고 관리하는 데 있어서 각 방화벽의 정책이 서로 충돌하거나, 하나의 방화벽에 설정된 정책이 다른 방화벽에 영향을 줄 수 있다. 이의 결과로, 네트워크 방화벽의 존재가 무의미해 지거나 네트워크의 정상적인 동작을 방해할 가능성도 존재한다. 따라서, 네트워크 방화벽 정책의 중앙 집중적인 관리가 필요한데, 각 방화벽이 서로 다른 제품일 경우, 각 방화벽의 중앙 집중적인 정책 관리는 더더욱 어려우며, 보안 관리자의 업무를 가중시키고 혼란을 초래하여 문제 발생의 소지를 내포한다. 본 논문에서는 이러한 문제점을 해결하고자 이질적인 방화벽을 중앙 관리하기 위한 시스템의 전체적인 구조를 제시하고 관리자의 요구를 처리하며, 중앙 정책 데이터베이스를 통해 네트워크 상의 각 방화벽 정책을 조정하고 유지하는 네트워크 방화벽 통합 관리 시스템의 핵심 부분인 관리 엔진의 구현 기술에 대해 설명하고자 한다.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.2
• /
• pp.93-99
• /
• 2011

In this paper, an ATSC(Advanced Television Standard Committee)-M/H(Mobile/Handheld) multiplexer is designed and implemented using an embedded Linux based hardware platform. The ATSC-M/H multiplexer is composed of a CPU(Central Processor Unit), an FPGA(Field-Programmable Gate Array), ASI(Asynchronous Serial Interface)/SMPTE310(Society of Motion Picture and Television Engineers310) interface board, and a GPS(Global Position System) clock processing block. The main functions of the ATSC-M/H multiplexer executed in the CPU and FPGA are described. The operation of the ATSC-M/H multiplexer is verified by processing its broadcast signal on a commercial receiver analyzer.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.204-207
• /
• 2013

Music genre classification is an essential component for music information retrieval system. There are two important components to be considered for better genre classification, which are audio feature extraction and classifier. This paper incorporates two different kinds of features for genre classification, timbral texture and rhythmic content features. Timbral texture contains several spectral and Mel-frequency Cepstral Coefficient (MFCC) features. Before choosing a timbral feature we explore which feature contributes less significant role on genre discrimination. This facilitates the reduction of feature dimension. For the timbral features up to the 4-th order central moments and the covariance components of mutual features are considered to improve the overall classification result. For the rhythmic content the features extracted from beat histogram are selected. In the paper Extreme Learning Machine (ELM) with bagging is used as classifier for classifying the genres. Based on the proposed feature sets and classifier, experiment is performed with well-known datasets: GTZAN databases with ten different music genres, respectively. The proposed method acquires the better classification accuracy than the existing approaches.