• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.6
• /
• pp.78-85
• /
• 2009

In time-varying multipath fading channels, orthogonal frequency division multiple access (OFDMA) uplink systems suffer severe performance degradation caused by inter-channel interference (ICI). In this paper, we propose a hybrid interference cancellation (HIC) for suppressing the degradation effect of ICI. The proposed HIC can achieve both exact interference cancellation and low detection complexity through efficient combination of parallel detection and serial cancellation. Simulation results show that, as the effect of Doppler increases, the proposed HIC achieves bit error rate (BER) performance enhancement in compared with severe performance degradation of conventional OFDMA receivers. In addition, both the computational complexity and total detection time are reduced.

• International Journal of Aeronautical and Space Sciences
• /
• v.18 no.1
• /
• pp.91-98
• /
• 2017

Performance of a low speed axial compressor is enhanced through a proper configuration of blade row tip injection and casing treatment of groove type. Air injectors were mounted evenly spaced upstream of the blade row within the casing groove and were all aligned parallel to the compressor axis. The groove, which covers all the blade tip chord length, extends all-round the casing circumference. Method of investigation is based on solution of the unsteady form of the Navier-Stokes equations utilizing $k-{\omega}$ SST turbulence model. Extensive parametric studies have been carried out to explore effects of injectors' flow momentums and yaw angles on compressor performance, while being run at different throttle valve setting. Emphasis has been focused on situations near to stall condition. Unsteady numerical analyses for untreated casing and no-injection case for near stall condition provided to discover two well-known criteria for spike stall inception, i.e., blade leading edge spillage and trailing edge back-flow. Final results showed that with only 6 injectors mounted axially in the casing groove and at yaw angle of 15 degrees opposite the direction of the blade row rotation, with a total mass flow rate of only 0.5% of the compressor main flow, surprisingly, the stall margin improves by 15.5%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.321-324
• /
• 2010

There have been lots of researches on a multi-core processor. The enhancement has been performed through parallelization method. Multi-core architecture in the mobile environment has emerged. But, there is a limit to a mobile CPU's performance. GP-GPU(General-Purpose computing on Graphics Processing Units) can improve performance without adding other dedicated hardware. This paper presents the implementation of Inverse Quantization, Inverse DCT and Color Space Conversion module in H.264/AVC decoder using Multi-Core GP-GPU for a mobile environments. The proposed architecture improves approximately 50% of performance when it use all the features.

• Nuclear Medicine and Molecular Imaging
• /
• v.43 no.5
• /
• pp.443-450
• /
• 2009

Purpose: Conventional image reconstruction uses simplified physical models of projection. However, real physics, for example 3D reconstruction, takes too long time to process all the data in clinic and is unable in a common reconstruction machine because of the large memory for complex physical models. We suggest the realistic distributed memory model of fast-reconstruction using parallel processing on personal computers to enable large-scale technologies. Materials and Methods: The preliminary tests for the possibility on virtual manchines and various performance test on commercial super computer, Tachyon were performed. Expectation maximization algorithm with common 2D projection and realistic 3D line of response were tested. Since the process time was getting slower (max 6 times) after a certain iteration, optimization for compiler was performed to maximize the efficiency of parallelization. Results: Parallel processing of a program on multiple computers was available on Linux with MPICH and NFS. We verified that differences between parallel processed image and single processed image at the same iterations were under the significant digits of floating point number, about 6 bit. Double processors showed good efficiency (1.96 times) of parallel computing. Delay phenomenon was solved by vectorization method using SSE. Conclusion: Through the study, realistic parallel computing system in clinic was established to be able to reconstruct by plenty of memory using the realistic physical models which was impossible to simplify.

• Journal of ILASS-Korea
• /
• v.13 no.1
• /
• pp.9-15
• /
• 2008

This experimental study was carried out to examine the heat transfer characteristics of impinging air jet on a flat plate with a set of right angled triangle rods. Each right angled triangle rod in the array was positioned normal to the flow direction and parallel to the flat plate surface. The clearances from a right angled triangle rod to flat plate surface (C=1, 2 and 4 mm) and the distance from nozzle exit to flat plate (H=100 and 500 mm) were changed for the pitch between each right angled triangle rods (P=40 mm). As a result, heat transfer shows best performance at the clearance of C=1 mm, in case clearance changed, and the average heat transfer enhancement rate increased up to 47% compared to the result of a flat plate without a right angled triangle rod.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.169-172
• /
• 2010

최근 플래시 메모리뿐만 아니라 SSD 를 활용한 데이터베이스의 사용이 점차 늘어나고 있다. 대용량의 데이터를 처리하는 데이터베이스에서는 삽입, 삭제, 검색을 빠르게 하기 위해 다양한 색인기법을 사용하는데 그 중 B-트리 구조가 대표적인 기법이다. B-트리는 삽입, 삭제, 검색을 할 때 더 나은 성능을 갖도록 도와주지만 그 구조를 유지하기 위한 비용이 많이 들어간다는 단점이 있다. 그 중 하나로 삽입 시 키가 삽입된 단말노드뿐만 아니라 그 부모노드까지 수정이 되어 한 번의 삽입에 여러 노드가 여러 페이지에 씌어져서 삽입시간이 길어지는 단점이 있다. 본 논문에서는 이러한 단점을 개선하기 위하여 SSD 에서 데이터베이스를 사용할 때 SSD 의 병렬 접근(parallel access) 방식을 사용해서 수정된 단말노드부터 루트노드까지의 경로에 있는 모든 노드들을 연속한 논리 주소 공간에 쓰는 방식을 적용하였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.1-6
• /
• 2020

Road movement pollutant air environment big data is a link between real-time traffic data such as vehicle type, speed, and load using AVC, VDS, WIM, and DTG, which are always traffic volume survey equipment, and road shape (uphill, downhill, turning section) data using GIS. It consists of traffic flow data. Also, unlike general data, a lot of data per unit time is generated and has various formats. In particular, since about 7.4 million cases/hour or more of large-scale real-time data collected as detailed traffic flow information are collected, stored and processed, a system that can efficiently process data is required. Therefore, in this study, an open source-based data parallel processing performance optimization study is conducted for the visualization of big data in the air environment of road transport pollution.

• The KIPS Transactions:PartB
• /
• v.11B no.6
• /
• pp.735-742
• /
• 2004

We present a new use of common graphics hardware to perform a faster artificial neural network. And we examine the use of GPU enhances the time performance of the image processing system using neural network, In the case of parallel computation of multiple input sets, the vector-matrix products become matrix-matrix multiplications. As a result, we can fully utilize the parallelism of GPU. Sigmoid operation and bias term addition are also implemented using pixel shader on GPU. Our preliminary result shows a performance enhancement of about thirty times faster using ATI RADEON 9800 XT board.

• The KIPS Transactions:PartD
• /
• v.19D no.2
• /
• pp.151-160
• /
• 2012

Most of the distributed high-dimensional indexing structures provide a reasonable search performance especially when the dataset is uniformly distributed. However, in case when the dataset is clustered or skewed, the search performances gradually degrade as compared with the uniformly distributed dataset. We propose a method of improving the k-nearest neighbor search performance for the distributed vector approximation-tree based on the strongly clustered or skewed dataset. The basic idea is to compute volumes of the leaf nodes on the top-tree of a distributed vector approximation-tree and to assign different number of bits to them in order to assure an identification performance of vector approximation. In other words, it can be done by assigning more bits to the high-density clusters. We conducted experiments to compare the search performance with the distributed hybrid spill-tree and distributed vector approximation-tree by using the synthetic and real data sets. The experimental results show that our proposed scheme provides consistent results with significant performance improvements of the distributed vector approximation-tree for strongly clustered or skewed datasets.

• Journal of IKEEE
• /
• v.20 no.1
• /
• pp.89-93
• /
• 2016

In this paper, we proposed SIMT based Image Signal Processor which can apply various image preprocessing algorithms and allow parallel processing of application programs such as image recognition. Conventional ISP has the hard-wired image enhancement algorithm of which the processing speed is fast, but there was difficult to optimize performance depending on various image processing algorithms. The proposed ISP improved the processing time applying SIMT architecture and processed a variety of image processing algorithms as an instruction based processor. We used Xilinx Virtex-7 board and the processing time compared to cell multicore processor, ARM Cortex-A9, ARM Cortex-A15 was reduced by about 71 percent, 63 percent and 33 percent, respectively.