• Journal of the Semiconductor & Display Technology
• /
• v.9 no.2
• /
• pp.67-72
• /
• 2010

Recently increasing application of flash memory in mobile and ubiquitous related devices is due to its non-volatility, fast response time, shock resistance and low power consumption. Following this trend, SSD(Solid State Disk) using multiple flash chips, instead of hard-drive based storage system, started to widely used for its advantageous features. However, flash memory based storage subsystem should resolve the performance bottleneck for writing in perspective of speed and lifetime according to its disadvantageous physical property. In order to provide tangible performance, solutions are studied in aspect of reclaiming of invalid regions by decreasing the number of erasures and distributing the erasures uniformly over the whole memory space as much as possible. In this paper, we study flash memory recycling algorithms with multiple management units and demonstrate that the proposed algorithm provides feasible performance. The proposed method utilizes the partitions of the memory space by utilizing threshold values and reconfigures the management units if necessary. The performance of the proposed policies is evaluated through a number of simulation based experiments.

• Journal of information and communication convergence engineering
• /
• v.21 no.1
• /
• pp.24-31
• /
• 2023

The solid-state drive (SSD) possesses higher input and output speeds, more resistance to physical shock, and lower latency compared with regular hard disks; hence, it is an increasingly popular storage device. However, tiny components on an internal printed circuit board (PCB) hinder the manual detection of malfunctioning components. With the rapid development of artificial intelligence technologies, automatic detection of components through convolutional neural networks (CNN) can provide a sound solution for this area. This study proposes applying the YOLOv5 model to SSD PCB component detection, which is the first step in detecting defective components. It achieves pioneering state-of-the-art results on the SSD PCB dataset. Contrast experiments are conducted with YOLOX, a neck-and-neck model with YOLOv5; evidently, YOLOv5 obtains an mAP@0.5 of 99.0%, essentially outperforming YOLOX. These experiments prove that the YOLOv5 model is effective for tiny object detection and can be used to study the second step of detecting defective components in the future.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.1291-1293
• /
• 2011

OLTP(online transaction processing) 환경은 다수의 사용자의 질의 및 요청을 처리하기 위한 데이터베이스 환경으로서 신속하고 정확한 질의 처리가 요구된다. 조인 연산은 이러한 데이터베이스 관리 시스템에서 자주 처리하게 되는 질의 가운데 하나이며, 그 중에서도 해시 조인은 현재 가장 좋은 성능을 보인다고 알려진 조인 알고리즘이다. 이 논문에서는 직접 해시 조인을 구현하여 읽기 및 쓰기 버퍼의 크기가 제한되었을 때 SSD와 하드디스크에서 해시 조인의 성능을 비교하고, 나아가 다수의 사용자가 동시에 여러 개의 조인 연산을 요청했을 때의 상황을 시뮬레이션 하여 SSD에서의 최적화 방안을 생각해본다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.1379-1380
• /
• 2011

• Journal of KIISE
• /
• v.44 no.2
• /
• pp.208-212
• /
• 2017

Flash SSDs have many advantages over the existing hard disks such as energy efficiency, shock resistance, and high I/O throughput. For these reasons, in combination with the emergence of innovative technologies such as 3D-NAND and V-NAND for cheaper cost-per-byte, flash SSDs have been rapidly replacing hard disks in many areas. However, the existing database engines, which have been developed mainly assuming hard disks as the storage, could not fully exploit the characteristics of flash SSDs (e.g. internal parallelism). In this paper, in order to utilize the internal parallelism intrinsic to modern flash SSDs for faster query processing, we implemented a prefetching method using asynchronous input/output as a new functionality for secondary index scans in MySQL InnoDB engine. Compared to the original InnoDB engine, the proposed prefetching-based scan scheme shows three-fold higher performance in the case of 16KB-page sizes, and about 4.2-fold higher performance in the case of 4KB-page sizes.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.361-368
• /
• 2018

As autonomous driving research is rapidly developing, pedestrian detection study is also successfully investigated. However, most of the study utilizes color image datasets and those are relatively easy to detect the pedestrian. In case of color images, the scene should be exposed by enough light in order to capture the pedestrian and it is not easy for the conventional methods to detect the pedestrian if it is the other case. Therefore, in this paper, we propose deep neural network (DNN)-based multi-spectrum pedestrian detection method using color and thermal images. Based on single-shot multibox detector (SSD), we propose fusion network structures which simultaneously employ color and thermal images. In the experiment, we used KAIST dataset. We showed that proposed SSD-H (SSD-Halfway fusion) technique shows 18.18% lower miss rate compared to the KAIST pedestrian detection baseline. In addition, the proposed method shows at least 2.1% lower miss rate compared to the conventional halfway fusion method.

• The Journal of Korean Society for Radiation Therapy
• /
• v.11 no.1
• /
• pp.73-78
• /
• 1999

In general, the patients of the head and neck cancer are treated with 4MV photon beam up to prescribed dose, but spinal cord should be excluded in the treatment field. When its absorbed dose is limited at the tolerance dose. In case of the patients who has the positive posterior neck nodes need a boost electron beam treatment to the prescribed dose. In that case, the anatomical structure of the neck and the physical structure of the standard electron cone interrupt to allow proper access to the disease site. Therefore, we extended treatment SSD for the remove of the those hindrances. In this study, we evaluated the dosimetric variation of the standard electron cone for the extended SSD, from 100cm to 120cm, 5 cm increment, and compare to the custom-made electron cone. As a result, the $\%$ depth dose, the point of maximum dose and the range of maximum were changed within the $2\%$. The penumbra width was increased from 1.0cm to 2.0cm. However, the dosimetric characteristics of the custom-made electron cone was very similar to that of the 100cm SSD standard electron cone and due to its characteristic of physical structure, patients didn't need re-positioning after photon beam treatment, therefore accurate treatment was possible, we conclude that the custom-made electron cone was very useful for the clinical practice.

• Journal of KIISE
• /
• v.44 no.8
• /
• pp.767-773
• /
• 2017

In a distributed system environment, such as a cloud database, the tail latency needs to be kept short to ensure uniform quality of service. In this paper, through experiments on a Cassandra database, we show that long tail latency is caused by a lack of memory space because the database cannot receive any request until free space is reclaimed by writing the buffered data to the storage device. We observed that, since the performance of the storage device determines the amount of time required for writing the buffered data, the performance degradation of Solid State Drive (SSD) due to garbage collection results in a longer tail latency. We propose a garbage collection synchronization technique, called SyncGC, that simultaneously performs garbage collection in the java virtual machine and in the garbage collection in SSD concurrently, thus hiding garbage collection overheads in the SSD. Our evaluations on real SSDs show that SyncGC reduces the tail latency of $99.9^{th}$ and, $99.9^{th}-percentile$ by 31% and 36%, respectively.

• Korean Chemical Engineering Research
• /
• v.47 no.2
• /
• pp.179-184
• /
• 2009

Recent evolution of computer technology enhances the effectiveness of CFD(Computational Fluid Dynamics) analysis for the 3-dimensional complex transport phenomena including turbulent flows. Cheaper and easier than laser and ultra-sonic methods, the windows simulator name by CAMSI(Computer-Aided Management of Stereo Images) has been developed in order to implement the 3-dimensional image using a disparity histogram extracted from left and right stereo images. In our program using the area-based method, the matching pixel finding methods consist of SSD(Sum of Squared Distance), SAD(Sum of Absolute Distance), NCC(Normalized Correlation Coefficient) and MPC(Matching Pixel Count). On performing the program, stereo images on different window sizes for various matching pixel finding methods are compared reasonably. When the image has a small noise, SSD on small window size is more effective. Whereas there is much noise, NCC or MPC is more effective than SSD. CAMSI from the present study will be much helpful to implement the complex objects and to analyze 3-dimensional CFD around them.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.48 no.6
• /
• pp.857-863
• /
• 2015

This study characterized the nutrition and taste of commercial salted semi-dried brown croaker Miichthys miiuy (SSD-BC). The mean crude protein content of the commercial SSD-BC was $19.8{\pm}1.7%$ (range, 17.7-23.2%), and the mean crude lipid content was $0.6{\pm}0.3%$ (range, 0.3-1.1%). The total amino acid content ranged from 17.08 to 18.56 g/100 g, except for sample code 5, which was 22.24 mg/100 g and differed significantly from the other samples. The major amino acids in the commercial SSD-BC were aspartic acid, glutamic acid, leucine, and lysine. In the commercial SSD-BC, the calcium ranged from 11.1-21.4 mg/100 g, phosphorus from 148.4-209.2 mg/100 g, and magnesium from 12.2-48.2 mg/100 g. Monoenoic acid (37.1-40.3%) was the most common fatty acid, followed by saturated acid (33.9-36.3%) and polyenoic acid (25.1-29.2%). The prominent fatty acids in the commercial SSD-BC were 16:0 (23.9-26.5%), 16:1n-7 (11.3-13.0%), 18:1n-9 (19.7-21.5%), and 22:6n-3 (6.9-10.7%). The mean trichloroacetic acidsoluble nitrogen content was 248.1 (range, 137.2-334.2) mg/100 g. The evaluation demonstrated that the commercial SSD-BC is rich in nutrition and taste.