• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.23-26
• /
• 2013

최근 모바일 장치의 영상 데이터 처리 능력 확대와 더불어 사용자가 요구하는 다양한 영상 데이터의 효율적인 인식 기술 연구가 요구되어지고 있다. 모바일 환경은 고성능 PC 환경과 달리 저사양의 CPU와 메모리를 탑재하고 있어, 영상에서 원하는 객체를 인식하기 위한 기존의 방법론으로는 사용자 요구를 실시간으로 충족하기 어려운 부분이 존재한다. 이에 모바일 환경에 맞는 객체 인식 방법론의 개발이 요구된다. 모바일 환경에서 실시간으로 객체 인식을 하기 위하여, 본 논문에서는 객체 코너 정보를 이용한 Harris corner detector[1]로부터 객체의 특징점을 추출하고, 이를 바탕으로 하여 영상내의 객체 정보 인식 방법을 제안한다. 제안하는 방법에 의해, 입력 영상에서 객체의 코너 정보를 빠르게 추출, 기존 특징점과의 비교를 통하여 영상 내부의 객체 인식을 진행한다. 일반적으로, 회전된 특징점 객체의 정보는 객체의 회전 정도에 따라 코너 픽셀 색상 정보의 변화가 발생하게 된다. 특징점의 색상값은 객체의 회전 정도에 영향을 받아 주변의 픽셀값과 혼합되는 특성이 존재한다. 본 논문에서는 회전 변경된 픽셀 색상값의 영향을 분석하여, 회전된 객체의 특징점 추출 및 객체 검출에 반영하도록 하여, 영상 내부의 회전된 객체 검출의 수행에 효과적으로 이용될 수 있도록 한다. 특징점의 코너 정보를 이용하여 객체를 인식하는 것은, 객체의 인식률은 다소 감소하더라도 모바일 환경에서 계산량의 감소를 통한 실시간 활용이 가능하도록 한다. 이러한 특성은 저성능 CPU와 메모리에서도 회전된 객체의 인식을 수행할 수 있게 하는데 상당히 효과적이다.

• Journal of Energy Engineering
• /
• v.9 no.1
• /
• pp.54-59
• /
• 2000

전자부품 및 시스템의 고속/고밀도화 추세에 따라 발열밀도가 계속증가하고 있다. 최근 팬티엄 II 급이상의 노트북 컴퓨터의 CPU에서는 칩당 발열량이 10W 이상으로 증가하고 있고 패키징 공간의 제한 때문에 소형히트파이프를 이용한 냉각이 많이 적용되고 있다. 본 연구에서는 모세압구동력이 크고 생산성등이 고려된 편조 형태의 새로운 윅을 개발하였으며 , 노트북 컴퓨터의 CPU 등 소형 전자부품냉ㄱ가에 적용가능한 직경 3, 4 mm 히트파이프를 설계 및 제작하였다. 직경 3, 4 mm Miniature Heat Pipe (이하 MHP) 의 작동특성은 일반적인 중형히트파이프와 다르므로 MHP 의 열전달 특성 및 작동성능에 미치는 각종 인자들의 영향을 파악하고자 성능시험을 수행하였다. 고려된 작동인자로는 작동유체 충전률, 전체 파이프길이 및 증발부, 응축부길이, 설치 경사각, 윅의 가닥수, 열부하 등이다. 작동인자의 영향과 관련된 연구결과는 향후 패키징을 위한 응용연구의 기초자료로 활용할 수 있을 것이다.

• Journal of the Korea Computer Graphics Society
• /
• v.13 no.1
• /
• pp.1-6
• /
• 2007

Although free-form surfaces can represent smooth shapes with only a few control points contrary to polygonal meshes, graphics hardware does not support surface rendering currently. Since modern programmable graphics pipeline can be used to accelerate various kinds of existing graphics algorithms, this paper presents a method that utilizes the graphics processing unit (GPU) to render blending surfaces with arbitrary topology fast. Surface parameters sampled on the control mesh and geometric data for local surfaces are sent to the graphics pipeline, and then the vertex processor evaluates the surface positions and normals with these data. This method can achieve very high performance rather than CPU-based rendering.

• Journal of the Korea Computer Graphics Society
• /
• v.16 no.4
• /
• pp.11-16
• /
• 2010

We present an efficient algorithm for rendering sweep surfaces using programmable graphics hardware. A sweep surface can be represented by a cross-section curve undergoing a spline motion. This representation has a simple matrix-vector multiplication structure that can easily be adapted to programmable graphics hardware. The data for the motion and cross-section curves are stored in texture memory. The vertex processor considers a pair of surface parameters as a vertex and evaluates its coordinates and normal vector with a single matrix multiplication. Using the GPU in this way is between 10 and 40 times as fast as CPU-based rendering.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.18-25
• /
• 2022

Neuromorphic computing generally shows significantly better power, area, and speed performance than neural network computation using CPU and GPU. These characteristics are suitable for resource-constrained IoT environments where energy consumption is important. However, there is a problem in that it is necessary to modify the source code for environment setting and application operation according to heterogeneous IoT devices that support neuromorphic computing. To solve these problems, NAAL was proposed and implemented in this paper. NAAL provides functions necessary for IoT device control and neuromorphic architecture abstraction and inference model operation in various heterogeneous IoT device environments based on common APIs of NAAL. NAAL has the advantage of enabling additional support for new heterogeneous IoT devices and neuromorphic architectures and computing devices in the future.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.113-118
• /
• 2021

In this paper, we propose an efficient dynamic workload balancing strategy which improves the performance of high-performance computing system. The key idea of this dynamic workload balancing strategy is to minimize execution time of each job and to maximize the system throughput by effectively using system resource such as CPU, memory. Also, this strategy dynamically allocates job by considering demanded memory size of executing job and workload status of each node. If an overload node occurs due to allocated job, the proposed scheme migrates job, executing in overload nodes, to another free nodes and reduces the waiting time and execution time of job by balancing workload of each node. Through simulation, we show that the proposed dynamic workload balancing strategy based on CPU, memory improves the performance of high-performance computing system compared to previous strategies.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.2
• /
• pp.191-199
• /
• 2009

In this paper we present a light weighted robust Korean morphological analyzer for mobile devices such as mobile phones, smart phones, and PDA phones. Such mobile devices are not suitable for natural language interfaces for their low CPU performance and memory restriction. In order to overcome the difficulties we propose 1) an online analysis by using Key Event Handler mechanism, 2) and a robust analysis of the Korean sentences with spacing errors without its correction pre-processing. We adapt the proposed Korean analyzer to a Korean-English mobile translator, which shows 5.8% memory usage reduction and 19.0% enhancement of average response time.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.32 no.10
• /
• pp.776-783
• /
• 2008

The object of this paper is to study on the thermal performance of a micro channel water block for computer CPU cooling. The effects of liquid flow rate, micro channel width and height on the thermal performances of water block are investigated experimentally. The water block was fabricated Al and machined with a micro milling. The water block consisted of rectangular micro channels 0.5 to 0.9 mm width and 1.5 to 4.5 mm height. The experiments were conducted using deionized water, over a liquid flow rate ranging from 0.2 to 2.0 kg/min. The base temperature and thermal resistance decrease with increasing of liquid flow rate. The increase of a channel height is more effective on the thermal resistance than the decrease of a channel width. At the flow rate of 0.7 kg/min, input power of 100 W, the base temperature and thermal resistance of sample 6 is $33^{\circ}C$ and $0.13\;^{\circ}C/W$ respectively.

• Proceedings of the SAREK Conference
• /
• 2007.11a
• /
• pp.264-269
• /
• 2007

The microchannel waterblock has a good capability in the cooling of electronic devices. The object of this paper is to study on thermal performance of microchannel water block for cooling of CPU in desktop. The effects of header shape, liquid flow rate, and inlet temperature on the thermal performances of microchannel waterblock are investigated experimentally. Three types of waterblock with different header shape are manufactured from the micro milling and brazing processing. The experiments are conducted using water, over a liquid flow rate ranging from 0.7 to 2.0 LPM and inlet temperature ranging from 20 to $35^{\circ}C$. Waterblocks are attached both horizontally and vertically on the test section to anticipate a performance of waterblock under the actual state in computer. The base temperature and thermal resistance decrease with increasing of liquid flow rate. It was found that the sample #1 was appropriate for the prototype of liquid cooling system.

• Korean Journal of Remote Sensing
• /
• v.5 no.1
• /
• pp.41-56
• /
• 1989

Improvement of the multichannel sea surface temperature(MCSST) software, which had been developed for the purpose of operating under mainframe computer system, was seeked in order to operate effectively in a mini computer system. CPU time and processing time, which is not a major factor under mainframe computer system, become a critical factor in real time image processing under mini computer system. Due to fixed kernel size(3$\times$4) of the old MCSST software, high spatial resolution characteristics of the original image received from satellites were apparently degraded when images are transformed into a cartesian coordinate system after geometrical distortions of the image due to earth curvature are removed. CPU and processing time were reduced to 0.13 and 0.15~0.22 comparing with the old MCSST's, respectively, by applying disk block I/O and M/T queue I/O method under VAX-11/750 computer. The high resolution quality (1.1km in AVHRR) of the processed image was guaranted using 2$\times$2 kernel size and applying moving window techniques without sacrificing CPU and processing time much.