• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2008.06a
• /
• pp.75-76
• /
• 2008

• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.6
• /
• pp.339-347
• /
• 2010

Inter-process communication (IPC), which is a technique that enables exchanging data among multiple processes, is commonly used not only in user applications but also in system processes. For this reason, the performance of IPC highly influences the performance of whole computer system. Especially, heavy overload on a single server process caused by IPC requests from multiple client processes, easily results overall slowdown of IPC response time. Here, to deal with the problem stated above, the time-slice donation technique which is adapted in L4 microkernel is analyzed and enhanced for reducing latency of IPC response time and implemented on linux kernel for actual performance evaluation. While trying to maintain the additional overhead as least as possible, the experiment shows that the use of this technique enhances the performance of IPC multiple times of existing technique under certain circumstances.

• Journal of Biomedical Engineering Research
• /
• v.18 no.3
• /
• pp.223-231
• /
• 1997

In this paper, an interframe coding method for volumetric medical images is proposed. By treating interslice variations as the motion of bones or tissues, we use the motion compensation (MC) technique to predict the current frame from the previous frame. Instead of a block matching algorithm (BMA), which is the most common motion estimation (ME) algorithm in video coding, image warping with biolinear transformation has been suggested to predict complex interslice object variation in medical images. When an object disappears between slices, however, warping prediction has poor performance. In order to overcome this drawback, an overlapped block motion compensation (OBMC) technique is combined with carping prediction. Motion compensated residual images are then encoded by using an embedded zerotree wavelet (EZW) coder with small modification for consistent quality of reconstructed images. The experimental results show that the interframe coding suing warping prediction provides better performance compared with interframe coding, and the OBMC scheme gives some additional improvement over the warping-only MC method.

• Food Science and Preservation
• /
• v.19 no.5
• /
• pp.626-632
• /
• 2012

In this study, the changes that occurred in the quality of minimally processed sliced Deodeok (Codonopsis lanceolata) in relation to the packing method during storage at $7^{\circ}C$ were investigated. The storage tests were conducted for seven days using PE sealing, but PP sealing and vacuum packaging preserved the Deodeok for 14 days. On the seventh day, the vinyl-packaged Deodeok showed a remarkable fall in quality with 4.5 °Brix, but the PP-sealed and vacuum-packaged Deodeok showed slight falls with 6.4 and $6.8^{\circ}Brix$, respectively. The PE- and PP-sealed Deodeok did not show significant differences in texture and moisture content for two days, and the moisture content was highest in the vacuum-packaged Deodeok during storage. In relation to the total viable cell and the coliform count, the vacuum-packaged Deodeok showed the lowest rate of increment during storage, followed by the others. Thus, the bubble-washed and vacuum-packaged minimally processed sliced Deodeok was found to have the best quality.

• Journal of Broadcast Engineering
• /
• v.22 no.4
• /
• pp.484-495
• /
• 2017

The development of display devices and the increase of network transmission bandwidth bring demands for over 2K high resolution video such as panorama video, 4K ultra-high definition commercial broadcasting, and ultra-wide viewing video. To compress these image sequences with significant amount of data, High Efficiency Video Coding (HEVC) standard with the highest coding efficiency is a promising solution. HEVC, the latest video coding standard, provides high encoding efficiency using various advanced encoding tools, but it also requires significant amounts of computation complexity compared to previous coding standards. In particular, the complexity of HEVC decoding process is a imposing challenges on real-time playback of ultra-high resolution video. To accelerate the HEVC decoding process for ultra high resolution video, this paper introduces a data-level parallel video decoding method using slice and/or tile supported by HEVC. Moreover, deblocking filter process is further parallelized. The proposed method distributes independent decoding operations of each tile and/or each slice to multiple threads as well as deblocking filter operations. The experimental results show that the proposed method facilitates executions up to 2.0 times faster than the HEVC reference software for 4K videos.

• Progress in Medical Physics
• /
• v.17 no.2
• /
• pp.67-76
• /
• 2006

We evaluated the accuracy of a patient setup error correction due to reference image quality for a 2D-2D matching process. Digitally reconstructed radiographs (DRRs) generated by use of the Pinnacle3 and the Eclipse for various regions of a humanoid phantom and a patient for different CT slice thickness were employed as a reference images and kV X-ray Images from the On-Board Imager were registered to the reference DRRs. In comparison of the DRRs and profiles, DRR image quality was getting worse with an increase of CT image slice thickness. However there were only slight differences of setup errors evaluation between matching results for good and poor reference DRRs. Although DRR image quality did not strongly affect to the 2D-2D matching accuracy, there are still potential errors for matching procedure, therefore we recommend that DRR images are needed to be generated with less than 3mm slice thickness for 2D-2D matching.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.20 no.6
• /
• pp.6-10
• /
• 1983

In this paper, an implementation method for digital filters using the residue arithmetic is proposed. This method can be used for processing digital signals with larger number of bits by applying the idea of the bit-slice algorithm, while previous residue digital filters can process digital signals with only a small number of bits. Furthermore, high-speed residue addition, subtrac-tion, and multiplication using look-up tables make it possible to get more flexible filters. Everything that is mentioned above is proved by implementing a cascade fourth-order Butterworth lowpass digital filter using this method.

• The Magazine of the IEIE
• /
• v.23 no.11
• /
• pp.89-100
• /
• 1996

A new stage-sliced pipiline structure is presented to design a high speed real time Global Positional Systems(GPS) applications. The CORDIC algorothm was revised to generate a pipeline structure, which will be used to produce a large amount of trigonometric computations rapidly. A stage-sliced approach was introduced to adjust the number of interative processes, and thereby to control the precision of computation results. Both the computation and the control circuits of the proposed architecture are included in a pipeline stage, which are intergrated into a stage slice. The circuit was prototyped using six FPGA chips : one is used for glue logics and five of the chips are used for pipeline slice implementation. A single FPGA chip comprising 7 pipeline stages provides one pipeline slice. To compensate and inter-slice time delay, dummy cycles are introduced in inter-slice signal exchanges.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.697-699
• /
• 2005

본 논문에서는 그래픽 하드웨어를 이용한 텍스처기반 볼륨렌더링으로 DRR 영상을 고속으로 생성하는 방법을 제안한다. 제안방법은 크게 세단계로 구성된다. 첫째, CT 영상 슬라이스 데이터에서 각 슬라이스를 최인접보간법으로 보간함으로써 등방해상도의 볼륨데이터를 생성한다. 둘째, 그래픽 하드웨어의 메모리용량 때문에 발생하는 문제를 해결하기 위해 텍스처 메모리의 효율적 관리방법을 제시한다. 셋째, 텍스처기반 볼륨렌더링을 이용해서 X-ray 영상과 유사한 투시투영한 DRR 영상을 생성한다. 본 논문에서 제안한 방법을 평가하기 위해서 인공 심장 데이터를 사용한다. 제안방법의 수행시간과 화질을 평가하기 위해서 기존 광선추적법, 복셀투영법을 적용한 DRR 영상과 비교 분석하였다. 실험결과 제안 방법은 기존 방법에 비해서 빠르게 DRR 영상을 생성하였고, 영상의 화질 또한 광선추적법의 결과 영상의 화질만큼 좋은 영상을 생성하였기 때문에 실시간 정합에 적합하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.763-765
• /
• 2005

DVS(dynamic voltage sealing)은 이동형 프로세서에서 에너지 효율을 높이기 위한 필수 요소로 자리 잡고있다. DVS를 효과적으로 사용하기 위해선 대상 태스크의 특성과 하드웨어 특성에 맞는 DVS 알고리즘이 필요하다. 상품화 수준의 않은 운영체계들이 일정한 인터벌(interval)을 바탕으로 시스템 사용 상황을 분석하여 목표 성능을 결정하는 방식을 사용하고 있다. 이러한 방식은 태스크의 특성이 갑자기 변하여 성능을 요구할 경우 인터벌만큼의 시간이 진행된 후에야 반응 한다는 단점이 있다. 또한, 태스크 별 특성이 아닌 시스템 전체의 특성을 따르므로 이질적인 성격의 태스크들이 동시에 실행 되는 환경에는 적합하지 않다. 최근의 모바일 프로세서들은 수 마이크로초 수준의 성능 전환 시간을 제공하고 있으며 이 속도는 계속 줄어들고 있다. 프로세서의 고성능화로 인해 I/O 작업의 경우 프로세서 성능에 따른 실행 시간의 차이가 존재 하지 않는다. 이러한 두 가지 특성을 바탕으로 우리는 TIB(timer interrupt based) 알고리즘을 제안한다. TIB 알고리즘은 일정한 길이의 인터벌 대신 타임 슬라이스(time slice)를 성능 결정의 단위로 삼는다. 성능의 결정은 태스크 별로 이루어지며 각 태스크가 사용했던 이전 타임 슬라이스가 타이머 인터룹트(timer interrupt)에 의해 끝났다면 최대의 성능을 그 외의 경우는 최저의 성능으로 실행하게 된다. 이러한 접근 방식을 통해 I/O 작업이나 이벤트를 기다리는 태스크에 대해 최저 성능을 제공함으로써 실행 시간의 적은 손해를 대가로 많은 에너지 절감을 이룰 수 있다. 또한, 태스크의 속성이 변한 경우 타임 슬라이스 길이 만큼의 지체만을 허용하게 된다. 이러한 TIB 인터벌에 기반한 알고리즘에 비해 개별 태스크의 특성에 따른 성능 조절과 태스크의 변화에 따른 빠른 반응을 자랑으로 한다. 본 논문에선 TIB 알고리즘을 리눅스 커널에 구현하여 성능을 평가하였고 그 결과 리눅스에서 사용되는 기존 인터벌 기반의 알고리즘들에 비해 좋은 전력 절감 효과를 얻을 수 있었다.