• 한국전자통신학회논문지
• /
• 제15권6호
• /
• pp.1187-1194
• /
• 2020

본 논문은 온라인 퀴즈 시스템에서 핵심인 문제은행 구축 자동화를 위한 Deep Quiz Cropping 기법을 제시했다. 이것은 문제지를 스캔한 그림 파일에서 개별문제에 대한 질의영역과 선다영역을 딥러닝 기반 검출기를 통해 검출하는 것과, 문제생성을 위해 질의영역과 선다영역을 짝지우고 영역오류를 수정하는 Box Coupling으로 이루어졌다. 문제지 및 시험지를 스캔한 영상파일에 Deep Quiz Coupling 기법을 적용한 다수의 실험에서 질의영역과 선다영역을 검출하는데 있어서 성공적인 결과를 도출했다.

• Communications for Statistical Applications and Methods
• /
• 제30권2호
• /
• 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.

• 천문학회보
• /
• 제46권2호
• /
• 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.

• 대한금속재료학회지
• /
• 제47권5호
• /
• 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
• /
• 제24권7호
• /
• 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.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제23권5호
• /
• pp.299-303
• /
• 2017

딥 러닝(Deep learning)은 기존 인공 신경망 내 계층 수를 증가시킴과 동시에 효과적인 학습 방법론을 제시함으로써 객체/음성 인식 및 자연어 처리 등 고수준 문제 해결에 있어 괄목할만한 성과를 보이고 있다. 그러나 학습에 필요한 시간과 리소스가 크다는 한계를 지니고 있어, 이를 줄이기 위한 연구가 활발히 진행되고 있다. 본 연구에서는 아파치 스파크 기반 클러스터 컴퓨팅 프레임워크 상에서 딥 러닝을 분산화하는 두 가지 툴(DeepSpark, SparkNet)의 성능을 학습 정확도와 속도 측면에서 측정하고 분석하였다. CIFAR-10/CIFAR-100 데이터를 사용한 실험에서 SparkNet은 학습 과정의 정확도 변동 폭이 적은 반면 DeepSpark는 학습 초기 정확도는 변동 폭이 크지만 점차 변동 폭이 줄어들면서 SparkNet 대비 약 15% 높은 정확도를 보였고, 조건에 따라 단일 머신보다도 높은 정확도로 보다 빠르게 수렴하는 양상을 확인할 수 있었다.

• 한국인터넷방송통신학회논문지
• /
• 제21권3호
• /
• pp.43-50
• /
• 2021

최근 인공지능을 사용한 연구나 기업의 프로젝트가 활발하게 이루어지고 다양한 서비스나 시스템이 인공지능 기술과 접목되어 점점 더 지능화되고 있다. 이에 따라 인공지능의 기법 중 하나인 딥러닝에 대한 관심과 이를 학습하려는 사람들이 증가했다. 딥러닝을 학습하기 위해서는 딥러닝 이론 이외에도 컴퓨터 프로그래밍, 수식 등 많은 지식들이 요구된다. 이는 초심자에게 높은 진입장벽으로 작용한다. 따라서 본 연구에서는 초심자가 프로그래밍 및 수식 등을 고려하지 않고 DNN, CNN 등과 같은 딥러닝의 기본적인 모델을 구현할 수 있는 DeepBlock이라는 웹 기반 교육용 딥러닝 플랫폼을 설계 및 구현하였다. 제안한 DeepBlock을 이용하여 딥러닝에 관심을 가진 학생들이나 초심자들의 교육에 활용이 가능하다.

• 한국식품조리과학회지
• /
• 제17권6호
• /
• 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.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2009년도 하계학술대회 논문집
• /
• 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.

• 한국식품저장유통학회지
• /
• 제10권3호
• /
• pp.326-332
• /
• 2003

해양 심층수는 일본, 미국 등에서 200 m 이하의 심해에서 취수되고 있으며, 물의 특성으로 부영양성, 저온안정성 및 청정성을 들 수 있다. 본 연구에서는 발효빵의 효모증식에 대한 해양 심층수와 그 염의 효과에 대해 조사하였다. 해양 심층수와 심층수염을 첨가하여 발효한 빵의 부피증가율은 증류수만을 사용한 빵보다 높게 나타났다. 또한 해양 심층수를 이용한 식빵의 기공 형태는 증류수로 제조된 식빵의 기공보다 둥글고 일정하였다. 한편, 식빵의 전반적인 기호도에서 증류수와 심층수염을 혼합하여 첨가한 식빵이 6.56으로 가장 높은 관능평점을 나타내었다.