• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1187-1194
• /
• 2020

We presented a method of deep quiz cropping for automatic construction of quiz pool in online quiz systems. The method detects question boxes and sunda boxes in images captured from test papers by a deep learning-based object detector, and makes pairs of question box and sunda box by the box coupling. We applied the deep quiz cropping to images captured from test papers and achieved successful results.

• Communications for Statistical Applications and Methods
• /
• v.30 no.2
• /
• pp.215-226
• /
• 2023

Deep learning has made great strides in the field of unstructured data such as text, images, and audio. However, in the case of tabular data analysis, machine learning algorithms such as ensemble methods are still better than deep learning. To keep up with the performance of machine learning algorithms with good predictive power, several deep learning methods for tabular data have been proposed recently. In this paper, we review the latest deep learning models for tabular data and compare the performances of these models using several datasets. In addition, we also compare the latest boosting methods to these deep learning methods and suggest the guidelines to the users, who analyze tabular datasets. In regression, machine learning methods are better than deep learning methods. But for the classification problems, deep learning methods perform better than the machine learning methods in some cases.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.2
• /
• pp.46.2-46.2
• /
• 2021

We present solar event auto detection using deep-learning-based object detection algorithms and DeepSDO event dataset. DeepSDO event dataset is a new detection dataset with bounding boxed as ground-truth for three solar event (coronal holes, sunspots and prominences) features using Solar Dynamics Observatory data. To access the reliability of DeepSDO event dataset, we compared to HEK data. We train two representative object detection models, the Single Shot MultiBox Detector (SSD) and the Faster Region-based Convolutional Neural Network (R-CNN) with DeepSDO event dataset. We compared the performance of the two models for three solar events and this study demonstrates that deep learning-based object detection can successfully detect multiple types of solar events. In addition, we provide DeepSDO event dataset for further achievements event detection in solar physics.

• Korean Journal of Metals and Materials
• /
• v.47 no.5
• /
• pp.274-282
• /
• 2009

To investigate the evolution of deformation texture in dual phase (DP) steels during deep-drawing deformation, deep-drawing experiments were performed. Microtexture measurements were conducted using electron backscattered diffraction (EBSD) to analyze texture evolution. A rate-sensitive polycrystal model was used to predict texture evolution during deep-drawing deformation. In order to evaluate the strain path during deep-drawing deformation, a steady state was assumed in the flange part of a deep-drawn cup. A ratesensitive polycrystal model successfully predicted the texture evolution in DP steels during deep-drawing deformation. The final stable orientations were found to be strongly dependent on the initial location in the blank. Texture analysis revealed that the deep drawability of DP steels decreases as the true strain in the radial direction of the deep-drawn cup increases during deep-drawing deformation.

• Korean Journal of Radiology
• /
• v.24 no.7
• /
• pp.698-714
• /
• 2023

In recent years, artificial intelligence, especially object detection-based deep learning in computer vision, has made significant advancements, driven by the development of computing power and the widespread use of graphic processor units. Object detection-based deep learning techniques have been applied in various fields, including the medical imaging domain, where remarkable achievements have been reported in disease detection. However, the application of deep learning does not always guarantee satisfactory performance, and researchers have been employing trial-and-error to identify the factors contributing to performance degradation and enhance their models. Moreover, due to the black-box problem, the intermediate processes of a deep learning network cannot be comprehended by humans; as a result, identifying problems in a deep learning model that exhibits poor performance can be challenging. This article highlights potential issues that may cause performance degradation at each deep learning step in the medical imaging domain and discusses factors that must be considered to improve the performance of deep learning models. Researchers who wish to begin deep learning research can reduce the required amount of trial-and-error by understanding the issues discussed in this study.

• KIISE Transactions on Computing Practices
• /
• v.23 no.5
• /
• pp.299-303
• /
• 2017

By piling up hidden layers in artificial neural networks, deep learning is delivering outstanding performances for high-level abstraction problems such as object/speech recognition and natural language processing. Alternatively, deep-learning users often struggle with the tremendous amounts of time and resources that are required to train deep neural networks. To alleviate this computational challenge, many approaches have been proposed in a diversity of areas. In this work, two of the existing Apache Spark-based acceleration frameworks for deep learning (SparkNet and DeepSpark) are compared and analyzed in terms of the training accuracy and the time demands. In the authors' experiments with the CIFAR-10 and CIFAR-100 benchmark datasets, SparkNet showed a more stable convergence behavior than DeepSpark; but in terms of the training accuracy, DeepSpark delivered a higher classification accuracy of approximately 15%. For some of the cases, DeepSpark also outperformed the sequential implementation running on a single machine in terms of both the accuracy and the running time.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.43-50
• /
• 2021

Recently, researches and projects of companies based on artificial intelligence have been actively carried out. Various services and systems are being grafted with artificial intelligence technology. They become more intelligent. Accordingly, interest in deep learning, one of the techniques of artificial intelligence, and people who want to learn it have increased. In order to learn deep learning, deep learning theory with a lot of knowledge such as computer programming and mathematics is required. That is a high barrier to entry to beginners. Therefore, in this study, we designed and implemented a web-based deep learning platform called DeepBlock, which enables beginners to implement basic models of deep learning such as DNN and CNN without considering programming and mathematics. The proposed DeepBlock can be used for the education of students or beginners interested in deep learning.

• Korean journal of food and cookery science
• /
• v.17 no.6
• /
• pp.533-541
• /
• 2001

This research was carried out to obtain the information about the use of deep-fat-fried foods and treatment of oils used for deep-fat-frying at home. Data were obtained through questionnaires from 442 housewives in Chonbuk area. The frequency of taking deep-fat-fried foods was affected by ages and residential area. Average score for the preference of deep-fat-fried foods was 3.60 in the 5 point scale. Fifty three percent of the respondents prepared deep-fat-fried foods by themselves at home. The oil most commonly used for deep-fat-frying was soybean oil followed by com oil. Proper frying temperature was determined by dropping salt or food coating materials into the oil. Oil color was used as a parameter for determining the life of frying oils by 81.2% of the respondents. Most of the respondents appealed to use oils one more time after filtering. For the disposal of used frying oil, 65.7% of the respondents used some kinds of absorbing papers; 16.1% made soaps and 10.7% discarded into a sink. According to correlation analysis, the frequency of taking deep-fat-fried food had positive relationships with housewives's health status, preference for foods prepared with oil and fats and family's preference for deep-fat-fried foods.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2009.06a
• /
• pp.118-119
• /
• 2009

This paper presents the feature profile evolution silicon deep trench etching, which is very crucial for the commercial wafer process application. The silicon deep trenches were etched with the SF6 gas & Hbr gas based process recipe. The optimized silicon deep trench process resulted in vertical profiles (87o~90o) with loading effect of < 1%. The process recipes were developed for the silicon deep trench etching applications. This scheme provides vertically profiles without notching of top corner was observed. In this study, the production of SF6 gas based silicon deep trench etch process much more strongly than expected on the basis of Hbr gas trench process that have been investigated by scanning electron microscope (SEM). Based on the test results, it is concluded that the silicon deep trench etching shows the sufficient profile for practical MOS FET silicon deep trench technology process.

• Food Science and Preservation
• /
• v.10 no.3
• /
• pp.326-332
• /
• 2003

Deep seawater is pumped up about 200 m water depth, which has characteristics of rich nutrients, low temperature and cleanness. This study was performed to investigate the effect of deep seawater and deep seawater salt on the yeast growth of fermented bread. The rate of increase in volume of groups added with deep seawater and deep seawater salt was higher than that of groups added with distilled water. The pore pattern of groups added with deep seawater was more regular than that of groups added with distilled water. In sensory property, the bread added with distilled water and deep seawater salt has the highest score (6.56) in overall acceptability.