• Database Research
• /
• v.34 no.3
• /
• pp.28-44
• /
• 2018

In a database system, the most expensive operation among relational operations is a join operation. Generally, CPU-based join operations uses parallel processing with either 1 core or 16 cores at most, which does not significantly improve the function. On the other hand, GPGPU(General-Purpose computing on Graphics Processing Units) allows parallel processing through thousands of processing units, greatly reducing the time required to perform join operations. Parallelization of the operation using GPGPU uses NVIDIA's CUDA SDK. In this paper, we implement parallelization of the join operation using GPGPU and compare the performances. The used join operations are Nested Loop Join (NLJ), Sort Merge Join (SMJ) and Hash Join (HJ), and GPGPU equipment uses TITAN Xp, GTX 1080 Ti and GTX 1080. We measure and compare the performance of join operations based on CPU and GPGPU. We compare this performance with the performance of the previous study on the join operation based on GPGPU. The results of experiment show that the performance based on GPGPU is 6~328 times faster than the one based on CPU.

• Journal of The Korean Society of Clinical Toxicology
• /
• v.10 no.1
• /
• pp.37-40
• /
• 2012

Honey is produced by bees from nectar collected from nearby flowers. Sometimes, honey produced from the Rhododendron species is contaminated by Grayanotoxin (GTX) in Nepal and other countries. There have been reports of GTX intoxication, also known as 'mad honey disease', from honey produced in countries other than Korea. The importation of wild honey has been prohibited by the Korean Food and Drug Administration since 2005, yet it is still distributed within Korea by the occasional tourist. We report a case of GTX intoxication from contaminated honey which included the symptoms of nausea, vomiting, general weakness, dizziness, blurred vision, hypotension and sinus bradycardia. By means of infusion with normal saline and atropine sulfate, the patient's condition fully recovered within 8 hours of hospital admission, and she was discharged without any complications.

• Journal of Food Hygiene and Safety
• /
• v.15 no.4
• /
• pp.287-292
• /
• 2000

The toxicity and toxin composition between blue mussel, Mytilus edulis and oyster, Crassostrea gigas collected at Woepori in Ko je island in South Coast of Korea in 1996 and 1997 were compared. The highest toxicity score was about 10 times higher in blue mussel than oyster (blue mussel, 8,670 $\mu\textrm{g}$; oyster, 860$\mu\textrm{g}$ in 1996, blue mussel, 5,657 $\mu\textrm{g}$/100g in 1997). The blue mussel also retained its toxicity for slightly longer period than oyster. In the both shellfish, PSP was composed almost exclusively of C toxicity (Cl and C2, 20~65%) and gonyautoxins (GTXl, 2, 3, and 4, 38~78%). In the early period of toxin accumulation, the ratio of 11$\beta$-epimer toxins (C2, GTX4) whose amount was 25~56 mole% (5th March to 12th April in 1996) and 25~80 mole% (18th March to 7th April in 1997), were higher than that of 11-epimer toxins (Cl, GTX2) whose amount was 41~57 mol%(27th May to 3rd June in 1996) and 25~56 mole% (29th April to 12th May in 1997), became higher than that of 11-epimer toxins. The toxin compositions in the both samples changed on a daily basis, presumably owing to metabolism of the toxin in the bivalves.

• Journal of Korea Game Society
• /
• v.10 no.5
• /
• pp.95-102
• /
• 2010

This paper proposes a parallel algorithm of the flocking behaviors using GPU. To do this, we used CUDA as the parallel processing architecture of GPU and then analyzed its characteristics and constraints. Based on them, the paper improved the performance by parallelizing to find the neighbors for an agent which requires the largest cost in the flocking behaviors. We implemented the proposed algorithm on GTX 285 GPU and compared experimentally its performance with the original spatial partitioning method. The results of the comparison showed that the proposed algorithm outperformed the original method up to 9 times with respect to the execution time.

• International Journal of Internet, Broadcasting and Communication
• /
• v.7 no.2
• /
• pp.105-108
• /
• 2015

There are a lot of traffic jams in the metropolitan area and the commuting time has been longer nowadays. So the urban people has been interested in the GTX(Great Train Express) project in Korea. The GTX is the train which runs at 200km/h speed in underground tunnels. If the train also operates at high speed in tunnel section, the pressure wave will happen and the uplift force of pantograph may vary abruptly. If the rigid trolley bar system is used in tunnel section, it is difficult to improve the commercial speed of train. In order to improve the train speed in tunnel section, this paper presents the new pantograph concepts which can change the suspension stiffness and deals with the dynamic behavior characteristics of pantograph according to the parameter variation.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.591-596
• /
• 2019

In this paper, we implemented a deep learning operation structure with less influence of local PC performance. In general, the deep learning model has a large amount of computation and is heavily influenced by the performance of the processing PC. In this paper, we implemented deep learning operation using AWS and streaming server to reduce this limitation. First, deep learning operations were performed on AWS so that deep learning operation would work even if the performance of the local PC decreased. However, with AWS, the output is less real-time relative to the input when computed. Second, we use streaming server to increase the real-time of deep learning model. If the streaming server is not used, the real-time performance is poor because the images must be processed one by one or by stacking the images. We used the YOLO v3 model as a deep learning model for performance comparison experiments, and compared the performance of local PCs with instances of AWS and GTX1080, a high-performance GPU. The simulation results show that the test time per image is 0.023444 seconds when using the p3 instance of AWS, which is similar to the test time per image of 0.027099 seconds on a local PC with the high-performance GPU GTX1080.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.25 no.2
• /
• pp.144-150
• /
• 1992

Paralytic shellfish toxins in mussels Mytilus edulis and dinoflagellate Alexandrium tamarene from Jinhae Bay, south coast of Korea were investigated. The mussels collected in March-April, 1989 showed toxicities of 7.5 MU/g of whole meat(31-88 MU/g of the digestive gland) , and those collected in 1990 showed toxicity level of 1.9-9.9 MU/g of whole meat by the standard mouse bioassay. Analysis of toxins by high performance liquid chromatography revealed the presence of gonyautoxin 1-4$(48-76\%)$ gonyautoxin 8 and epi-gonyautoxin $8(C1-C2,\;14-39\%)$, saxitoxin$(1-10\%)$, neosaxitoxin$(l-7\%)$ and trace amount of decarbamoylgonyautoxin 2 and 3(dcGTX2, dcGTX3) in the mussels of 1989. While, Mussels collected in 1990 contained a significantly larger proportion of neosaxitoxin $(44-50\%)$ than did those of 1989. A. tamarense isolated in April 1989 produced the same toxins in culture with slightly higher proportion of Cl, C2, dcGTX2 and dcGTX3 than in the mussels. The difference was within a range of toxin change during accumulation by shellfish and during sample preparation for analysis. It was thus concluded that the dinoflagellate was the cause of toxins in the mussels.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.538-540
• /
• 2021

In this paper, we proposed a smart target detection system that detects and recognizes a designated target to provide relative motion information when performing a target detection mission of a drone. The proposed system focused on developing an algorithm that can secure adequate accuracy (i.e. mAP, IoU) and high real-time at the same time. The proposed system showed an accuracy of close to 1.0 after 100k learning of the Google Inception V2 deep learning model, and the inference speed was about 60-80[Hz] when using a high-performance laptop based on the real-time performance Nvidia GTX 2070 Max-Q. The proposed smart target detection system will be operated like a drone and will be helpful in successfully performing surveillance and reconnaissance missions by automatically recognizing the target using computer image processing and following the target.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.3
• /
• pp.583-588
• /
• 2011

In this paper, we propose an adaptive variable-sized matching window method using the characteristic points of the image and a method to increase the reliability of the cross-consistency check to raise the correctness of the final disparity image. The proposed adaptive variable-sized window method segments the image with the color information, finds the characteristic points inside the window. Also the proposed algorithm implement using a graphic processing unit(GPU). The GPU, we used in this paper is GeForce GTX296 (NVIDIA) and we can use programming based on CUDA. The calculation speed realizes a speed approximately 128 times faster than that of a CPU.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.5
• /
• pp.1177-1186
• /
• 2014

Computer-generated hologram (CGH) is to mathematically model optical phenomenon with digital computer. Because it requires huge amount of computational power, a fast and high performance technique is needed. In this paper, we proposed two parallelizations for CGH calculation. The first is to parallelize CGH algorithm in a GPU (general processing unit) and the second is to parallelize multiple GPUs. The proposed algorithm was implemented in GTX780 Ti GPU. It calculates a $1,024{\times}1,024$ hologram with 10K object points for about 24ms.