• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.543-545
• /
• 1999

In this paper, the composition method of global and local fuzzy reasoning concepts is researched for reducing the number of rules, not losing the performance for fuzzy controller. A new method is proposed in details that controls the interaction between global reasoning and local reasoning. In order to automatically acquire and optimize the method, the DNA coding algorithm is introduced to the local fuzzy reasoning of the proposed composition fuzzy reasoning method. The method is applied to the real liquid level control system for the purpose of evaluating the Performance. The simulation results show that the proposed technique can produce the fuzzy rules with higher accuracy and feasibility than the conventional methods.

• 전자통신동향분석
• /
• 제35권7호
• /
• pp.23-35
• /
• 2020

In this paper, we introduce ETRI AI Strategy #3, "Leading Future Technologies of Network, Media, and Content." Its first goal is "to innovate AI service technology to overcome the current limitations of AI technologies." Artificial intelligence (AI) services, such as self-driving cars and robots, are combinations of computing, network, AI algorithms, and other technologies. To develop AI services, we need to develop different types of network, media coding, and content creation technologies. Moreover, AI technologies are adopted in ICT technologies. Self-planning and self-managing networks and automatic content creation technologies using AI are being developed. This paper introduces the two directions of ETRI's ICT technology development plan for AI: ICT for AI and ICT by AI. The area of ICT for AI has only recently begun to develop. ETRI, the ICT leader, hopes to have opportunities for leadership in the second wave of AI services.

• 한국콘텐츠학회논문지
• /
• 제13권2호
• /
• pp.19-31
• /
• 2013

가독성 있는 소스코드는 이해하기 쉽고 수정하기 편하기 때문에 손쉽게 유지보수할 수 있다. 소스코드의 가독성은 프로그램의 제어 구조와 같은 알고리즘의 복잡도뿐만 아니라 함수명, 들여쓰기 등과 같은 코딩스타일에 의해서도 많은 영향을 받는다. 지금까지 소스코드의 가독성을 높이기 위해 다양한 코딩 표준들이 제안되었으나 프로그래밍 교과목에서는 코딩스타일을 다루지 않거나 무시하는 경우가 많았다. 그 이유는 코딩스타일이 프로그램의 효율에는 영향을 주지 않기 때문에 강제하기 어렵기 때문이다. 이 논문에서는 프로그램 소스코드의 코딩스타일을 분석하고 그 결과를 시각화하는 스타일직소(StyleJigsaw) 시스템을 제안한다. 스타일직소 시스템은 C/C++나 Java 언어로 작성된 소스코드의 코딩스타일을 분석하여 이를 정량화하고 그 결과를 퍼즐화된 이미지로 시각화한다. 스타일직소 시스템의 교육적 효과를 입증하기 위해 C++프로그래밍 수업을 듣는 학생들을 대상으로 스타일직소 사용 실험을 진행하였다. 실험 결과 스타일직소 시스템을 사용한 경우 코딩스타일 평균 점수가 약 8.0점(10.9%) 가량 향상된 것으로 나타났다. 또한, 프로그래밍 수업의 수강생들을 대상으로 한 설문조사에서 약 88.5%의 학생이 스타일직소 시스템이 코딩스타일 학습에 도움이 되었다고 응답하였다. 프로그래밍 수업에서 스타일직소 시스템을 활용함으로써 학생들이 가독성 있는 프로그램 작성 능력을 기르는 데 도움을 줄 수 있을 것이다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 추계학술대회 논문집 전기기기 및 에너지변환시스템부문
• /
• pp.219-223
• /
• 2001

This paper proposed the Automatic defect testing technology which used in the defect test of printed things and external shapes in the precision industry. According to adapting the very high speed image processor called ASIC for high resolution. This system also realized that the System being able to perform the very high speed resolution testing. As the image processing algorithm, Run-length coding, Multi-level threshold and fast-adaptive line matching were applied.

• Journal of Communications and Networks
• /
• 제14권5호
• /
• pp.510-517
• /
• 2012

This paper analyzes the performance of voice-over-Internet protocol (VoIP) services in terms of the system throughput, the packet delay, and the signaling overhead in a mobile WiMAX system with a hybrid automatic repeat request (HARQ) mechanism. Furthermore, a queueing analytical model is developed with due consideration of adaptive modulation and coding, the signaling overhead, and the retransmissions of erroneous packets. The arrival process is modeled as the sum of the arrival rate at the initial transmission queue and the retransmission queue, respectively. The service rate is calculated by taking the HARQ retransmissions into consideration. This paper also evaluates the performance of VoIP services in a mobile WiMAX system with and without persistent allocation; persistent allocation is a technique used to reduce the signaling overhead for connections with a periodic traffic pattern and a relatively fixed payload. As shown in the simulation results, the HARQ mechanism increases the system throughput as well as the signaling overhead and the packet delay.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.119-119
• /
• 2000

In this research an induction motor vector control system was developed using Simulink and RTW(Real Time Workshop). On the Simulink window, control system is designed in the form of block diagrams, program codes are produced automatically with the RTW, then c compiler compiles the program codes. With this automatic real time program producing mechanism rapid prototyping is realized without the time-consuming manual program coding procedures. To show effectiveness of the proposed designing scheme a DSP-based induction motor vector control system was constructed and implemented

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.1043-1044
• /
• 2006

In a packet based wireless system, an adaptive modulation and coding (AMC) scheme is often employed with the use of channel quality information (CQI). However, the AMC can be operated improperly due to delayed CQI, causing performance degradation. In this paper, we consider the use of predicted CQI for the AMC considering the feedback delay and channel characteristics. We also consider the use of a hybrid automatic repeat request scheme with the proposed AMC for further improvement in high mobility environments.

• 생물환경조절학회지
• /
• 제1권1호
• /
• pp.37-51
• /
• 1992

Quantizing and extracting visual features of mushroom(Lentinus edodes L.) are crucial to the sorting and grading automation, the growth state measurement, and the dried performance indexing. A computer image processing system was utilized for the extraction and measurement of visual features of front and back sides of the mushroom. The image processing system is composed of the IBM PC compatible 386DK, ITEX PCVISION Plus frame grabber, B/W CCD camera, VGA color graphic monitor, and image output RGB monitor. In this paper, an automatic thresholding algorithm was developed to yield the segmented binary image representing skin states of the front and back sides. An eight directional Freeman's chain coding was modified to solve the edge disconnectivity by gradually expanding the mask size of 3$\times$3 to 9$\times$9. A real scaled geometric quantity of the object was directly extracted from the 8-directional chain element. The external shape of the mushroom was analyzed and converted to the quantitative feature patterns. Efficient algorithms for the extraction of the selected feature patterns and the recognition of the front and back side were developed. The developed algorithms were coded in a menu driven way using MS_C language Ver.6.0, PC VISION PLUS library fuctions, and VGA graphic functions.

• 한국멀티미디어학회논문지
• /
• 제21권11호
• /
• pp.1305-1316
• /
• 2018

Graphical user interface(GUI) has a very important role to interact with software users. However, designing and coding of GUI are tedious and pain taking processes. In many studies, the researchers are trying to convert GUI elements or widgets to code or describe formally their structures by help of domain knowledge of stochastic methods. In this paper, we propose the GUI elements detection approach based on object detection strategy using deep neural networks(DNN). Object detection with DNN is the approach that integrates localization and classification techniques. From the experimental result, if we selected the appropriate object detection model, the results can be used for automatic code generation from the sketch or capture images. The successful GUI elements detection can describe the objects as hierarchical structures of elements and transform their information to appropriate code by object description translator that will be studied at future.

• 한국통신학회논문지
• /
• 제33권6C호
• /
• pp.471-479
• /
• 2008

본 논문에서는 인터넷과 같은 IP망에서 SVC 비디오를 RTP 패킷화하여 전송할 때 RTP 패킷의 헤더에 기록될 타임스탬프 정보를 자동으로 생성할 수 있는 새로운 알고리듬을 제안한다. H.263, MPEG-4, H.264 등의 단일 계층 비디오 압축 방식과는 달리 SVC는 하나의 비트스트림으로 시간적, 공간적, SNR 스케일러빌리티를 동시에 제공하기 위해 다중 계층 부호화에 의해 SVC 비트스트림을 생성하게 된다. 특히, 시간적 스케일러빌리티 제공을 위해 계층적 B-픽처 (hierarchical B-picture) 예측 구조를 채택하는 관계로 화면의 부호화 (또는 전송) 순서와 디스플레이 순서가 서로 일치하지 않는다. 따라서, 각 화면에 대한 RTP 패킷 헤더에 기록될 타임스탬프 값의 증가치가 불규칙적으로 나타나게 된다. SVC 비디오 전송 찬경에서 RTP 타임스탬프 값을 실시간으로 효과적으로 생성해 줄 수 있는 방법이 현재까지 제안된 적이 없다. 따라서, 본 논문에서는 SVC 비디오 전송 환경에서 NAL unit 헤더에 기록되는 TID (Temporal ID) 필드를 이용하여 RTP 타임스탬프 값을 자동적으로 생성하는 방법을 제안한다.