• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.81-89
• /
• 2021

Under natural conditions, Apple detection has the problems of occlusion and small object detection difficulties. This paper proposes an improved model based on SSD. The SSD backbone network VGG16 is replaced with the ResNet50 network model, and the receptive field structure RFB structure is introduced. The RFB model amplifies the feature information of small objects and improves the detection accuracy of small objects. Combined with the attention mechanism (SE) to filter out the information that needs to be retained, the semantic information of the detection objectis enhanced. An improved SSD algorithm is trained on the VOC2007 data set. Compared with SSD, the improved algorithm has increased the accuracy of occlusion and small object detection by 3.4% and 3.9%. The algorithm has improved the false detection rate and missed detection rate. The improved algorithm proposed in this paper has higher efficiency.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.25 no.3
• /
• pp.176-183
• /
• 2015

This research proposes a method to estimate the fatigue life of SSD(solid-state drive) due to the effect of dummy solder ball under forced vibration. A finite element model of the SSD was developed to simulate the forced vibration and a modal testing was performed to verify the developed finite element model. Fatigue life of the SSD under vibration was experimentally determined according to JEDEC standard in which the SSD was excited by a sinusoidal sweep vibration within the narrow frequency band around the first natural frequency until the SSD fails. Basquin's equation was introduced to estimate the fatigue life of the SSD due to the effect of dummy solder balls. It shows that the dummy solder balls are effective elements of the SSD to increase the fatigue life of an SSD by increasing 700 times of the fatigue life of the given SSD.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.15 no.5
• /
• pp.511-518
• /
• 2015

As the cost-per-byte of SSDs dramatically decreases, the introduction of SSDs to Hadoop becomes an attractive choice for high performance data processing. In this paper the cost-per-performance of SSD-based Hadoop cluster (SSD-Hadoop) and HDD-based Hadoop cluster (HDD-Hadoop) are evaluated. For this, we propose a MapReduce performance model using queuing network to simulate the execution time of MapReduce job with varying cluster size. To achieve an accurate model, the execution time distribution of MapReduce job is carefully profiled. The developed model can precisely predict the execution time of MapReduce jobs with less than 7% difference for most cases. It is also found that SSD-Hadoop is 20% more cost efficient than HDD-Hadoop because SSD-Hadoop needs a smaller number of nodes than HDD-Hadoop to achieve a comparable performance, according to the results of simulation with varying the number of cluster nodes.

• 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 Korean Society for Noise and Vibration Engineering Conference
• /
• 2014.10a
• /
• pp.978-983
• /
• 2014

This research proposes a method to estimate the fatigue life of solid-state drive(SSD) due to the effect of dummy solder ball under forced vibration. Mechanical jig is developed to describe the SSD in laptop computer. The jig with SSD is mounted on a shaker, and excited by a sinusoidal sweep vibration within the narrow frequency band around the first resonant frequency until the SSD fails. A finite element model of SSD is also developed to simulate the forced vibration. It shows that the solder joints at the corners of controller package are most vulnerable components and that placing dummy solder balls at those area is effective method to increase fatigue life of SSD.

• Journal of IKEEE
• /
• v.23 no.3
• /
• pp.777-784
• /
• 2019

A pre-fire awareness and automatic notification system are required because it is possible to minimize the damage if the fire situation is precisely detected after a fire occurs in a place where people are unusual or in a mountainous area. In this study, we developed a RaspberryPi-based fire recognition system using Faster-recurrent convolutional neural network (F-RCNN) and single shot multibox detector (SSD) and demonstrated a fire alarm system that works with power line communication. Image recognition was performed with a pie camera of RaspberryPi, and the detected fire image was transmitted to a monitoring PC through an inductive power line communication network. The frame rate per second (fps) for each learning model was 0.05 fps for Faster-RCNN and 1.4 fps for SSD. SSD was 28 times faster than F-RCNN.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.838-846
• /
• 2004

In the case where both a camera and a target are moving at the same time, the image background is successively changed, and the overlap with other moving objects is apt to be generated. The snake algorithms have been variously used in tracking the object, but it is difficult to be applied in the excessive overlap with other objects and the large bias between the snake and the target. To solve this problem, this paper presents an extended snake model. It includes an additional energy function which considers the temporal variation rate of the snake's area and a SSD algorithm which generates the template adaptive to the snake detected in the previous frame. The new energy function prevents the snake from over-shrinking or stretching and the SSD algorithm with adaptively changing template allows the prediction of the target's position in the next frame. The experimental results have shown that the proposed algorithm successfully tracks the target even when the target is temporarily occluded by other objects.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.348-350
• /
• 2021

The core technology of augmented reality is object recognition technology. Recently, due to the development of various artificial intelligence algorithms such as CNN, it has become possible to effectively distinguish specific objects from images. It is possible to realize more realistic and immersive augmented reality contents only when technology for recognizing objects quickly and accurately is secured. In this study, an object recognition model using SSD (single shot multibox detector) and an object recognition model using YOLO were compared and evaluated.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.1-23
• /
• 2018

From the 21st century, various high-quality services have come up with the growth of the internet or 'Information and Communication Technologies'. Especially, the scale of E-commerce industry in which Amazon and E-bay are standing out is exploding in a large way. As E-commerce grows, Customers could get what they want to buy easily while comparing various products because more products have been registered at online shopping malls. However, a problem has arisen with the growth of E-commerce. As too many products have been registered, it has become difficult for customers to search what they really need in the flood of products. When customers search for desired products with a generalized keyword, too many products have come out as a result. On the contrary, few products have been searched if customers type in details of products because concrete product-attributes have been registered rarely. In this situation, recognizing texts in images automatically with a machine can be a solution. Because bulk of product details are written in catalogs as image format, most of product information are not searched with text inputs in the current text-based searching system. It means if information in images can be converted to text format, customers can search products with product-details, which make them shop more conveniently. There are various existing OCR(Optical Character Recognition) programs which can recognize texts in images. But existing OCR programs are hard to be applied to catalog because they have problems in recognizing texts in certain circumstances, like texts are not big enough or fonts are not consistent. Therefore, this research suggests the way to recognize keywords in catalog with the Deep Learning algorithm which is state of the art in image-recognition area from 2010s. Single Shot Multibox Detector(SSD), which is a credited model for object-detection performance, can be used with structures re-designed to take into account the difference of text from object. But there is an issue that SSD model needs a lot of labeled-train data to be trained, because of the characteristic of deep learning algorithms, that it should be trained by supervised-learning. To collect data, we can try labelling location and classification information to texts in catalog manually. But if data are collected manually, many problems would come up. Some keywords would be missed because human can make mistakes while labelling train data. And it becomes too time-consuming to collect train data considering the scale of data needed or costly if a lot of workers are hired to shorten the time. Furthermore, if some specific keywords are needed to be trained, searching images that have the words would be difficult, as well. To solve the data issue, this research developed a program which create train data automatically. This program can make images which have various keywords and pictures like catalog and save location-information of keywords at the same time. With this program, not only data can be collected efficiently, but also the performance of SSD model becomes better. The SSD model recorded 81.99% of recognition rate with 20,000 data created by the program. Moreover, this research had an efficiency test of SSD model according to data differences to analyze what feature of data exert influence upon the performance of recognizing texts in images. As a result, it is figured out that the number of labeled keywords, the addition of overlapped keyword label, the existence of keywords that is not labeled, the spaces among keywords and the differences of background images are related to the performance of SSD model. This test can lead performance improvement of SSD model or other text-recognizing machine based on deep learning algorithm with high-quality data. SSD model which is re-designed to recognize texts in images and the program developed for creating train data are expected to contribute to improvement of searching system in E-commerce. Suppliers can put less time to register keywords for products and customers can search products with product-details which is written on the catalog.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.5
• /
• pp.2449-2456
• /
• 2013

The column-oriented database storage is a very advanced model for large-volume data analysis systems because of its superior I/O performance. Traditional data storages exploit row-oriented storage where the attributes of a record are placed contiguously in hard disk for fast write operations. However, for search-mostly datawarehouse systems, column-oriented storage has become a more proper model because of its superior read performance. Recently, solid state drive using MLC flash memory is largely recognized as the preferred storage media for high-speed data analysis systems. In this paper, we introduce fast column-oriented data storage model and then propose a new storage management scheme using a cross compressed replication for the high-speed column-oriented datawarehouse system. Our storage management scheme which is based on two MLC SSD achieves superior performance and reliability by the cross replication of the uncompressed segment and the compressed segment under high workloads of CPU and I/O. Based on the results of the performance evaluation, we conclude that our storage management scheme outperforms the traditional scheme in the respect of update throughput and response time of the column segments.