이슈논문

Data Report>이슈논문

이슈 키워드 논문 TOP10

이슈논문
| | | | 다운로드

KCI등재

1딥러닝(Deep learning) 기반 미술 학습 지원도구 개발: 생성 모델링(Generative modeling)을 활용하여

저자 : 이웅기 ( Ung-gi Lee ) , 강상희 ( Sang-hee Kang ) , 이종찬 ( Jong-chan Lee ) , 최서연 ( Seo-yeon Choi ) , 최욱명 ( Ukmyung Choi ) , 임철일 ( Cheol-il Lim )

발행기관 : 한국교육정보미디어학회(구 한국교육정보방송학회) 간행물 : 교육정보미디어연구 26권 1호 발행 연도 : 2020 페이지 : pp. 207-236 (30 pages)

다운로드

(기관인증 필요)

초록보기

4차 산업혁명 시대 인공지능의 발달과 함께 여러 산업 분야에 인공지능을 활용한 변화가 일어나고 있다. 교육 분야에서도 인공지능의 기술을 활용하기 위한 시도가 이루어지고 있다. 본 연구에서는 인공지능의 한 분야인 딥러닝(Deep learning)을 기반으로 한 미술 학습 지원도구를 개발하여 학생들의 미술교육활동을 지원하였다. 본 연구의 미술 학습 지원도구는 딥러닝의 생성 모델(Generative model) 중 뉴럴 트랜스퍼(Neural Transfer) 알고리즘을 이용하였다. 뉴럴 트랜스퍼 알고리즘은 두 가지 이미지를 조합하여 새로운 이미지를 창조할 수 있다. 미술 학습 지원도구 개발을 위해 연구자들은 설계개발연구 방법론에 따라 문헌조사와 요구분석을 통해 초기 프로토타입을 개발하였다. 이후 2번의 전문가 타당화 과정과 학습자 사용성 평가를 거쳐 미술 학습 지원도구의 프로토타입을 개발하였다. 미술 표현 활동관련 수업 시연을 통해 학습자들은 본 교구를 체험한 후, 도구의 효과성과 인식에 대한 의견을 제시하였다. 딥러닝을 활용한 미술 학습지원도구에 대한 효과 및 인식 조사에서 만족도, 편리성, 교구사용 용이성 등 대다수의 문항에 학습자들은 전반적으로 만족하였다고 응답하였다. 추후 사용자 중심의 도구사용 지침과 관련 소프트웨어를 다루는 능력과 제반시설의 향상이 함께 이루어진다면 다양한 미술 표현 영역에서 사용될 수 있는 학습 지원도구가 될 것으로 기대한다.


With the development of artificial intelligence in the 4th Industrial Revolution, changes are being made by applying artificial intelligence to various industrial fields. In the contemporary art world, there is an active consideration about the location of the art field in which artificial intelligence is involved. Since education is an open reflection in the demands and transition of the times, it can be seen that art education is naturally affected by the modern art world. Therefore, according to the change of the modern art world, art education using artificial intelligence is needed in schools. In this study, the art learning support tool based on deep learning were developed to support students’ art education activities. The art learning support tool used the neural transfer algorithm in deep learning generative models. The neural transfer algorithm can combine two images to create a single image. In order to develop the art learning support tool, researchers developed initial prototypes through literature research and needs analysis according to the design and development research methodology. The students’ satisfaction level with the tool was analyzed through class demonstrations. In the survey of the effects and perceptions of art learning support tools, learners were generally satisfied with it. In the future, it will be used in various expression education fields when the tool offers the user-centered guideline and students have a higher-ability for dealing with related software.

KCI후보SCOUPUS

2Is it possible to forecast KOSPI direction using deep learning methods?

저자 : Songa Choi , Jongwoo Song

발행기관 : 한국통계학회 간행물 : CSAM(Communications for Statistical Applications and Methods) 28권 4호 발행 연도 : 2021 페이지 : pp. 329-338 (10 pages)

다운로드

(기관인증 필요)

초록보기

Deep learning methods have been developed, used in various fields, and they have shown outstanding performances in many cases. Many studies predicted a daily stock return, a classic example of time-series data, using deep learning methods. We also tried to apply deep learning methods to Korea’s stock market data. We used Korea’s stock market index (KOSPI) and several individual stocks to forecast daily returns and directions. We compared several deep learning models with other machine learning methods, including random forest and XGBoost. In regression, long short term memory (LSTM) and gated recurrent unit (GRU) models are better than other prediction models. For the classification applications, there is no clear winner. However, even the best deep learning models cannot predict significantly better than the simple base model. We believe that it is challenging to predict daily stock return data even if we use the latest deep learning methods.

KCI등재SCISCOUPUS

3Multi Label Deep Learning classification approach for False Data Injection Attacks in Smart Grid

저자 : Prasanna Srinivasan. V , Balasubadra. K , Saravanan. K , Arjun. V. S , Malarkodi. S

발행기관 : 한국인터넷정보학회 간행물 : KSII Transactions on Internet and Information Systems (TIIS) 15권 6호 발행 연도 : 2021 페이지 : pp. 2168-2187 (20 pages)

다운로드

(기관인증 필요)

초록보기

The smart grid replaces the traditional power structure with information inventiveness that contributes to a new physical structure. In such a field, malicious information injection can potentially lead to extreme results. Incorrect, FDI attacks will never be identified by typical residual techniques for false data identification. Most of the work on the detection of FDI attacks is based on the linearized power system model DC and does not detect attacks from the AC model. Also, the overwhelming majority of current FDIA recognition approaches focus on FDIA, whilst significant injection location data cannot be achieved. Building on the continuous developments in deep learning, we propose a Deep Learning based Locational Detection technique to continuously recognize the specific areas of FDIA. In the development area solver gap happiness is a False Data Detector (FDD) that incorporates a Convolutional Neural Network (CNN). The FDD is established enough to catch the fake information. As a multi-label classifier, the following CNN is utilized to evaluate the irregularity and cooccurrence dependency of power flow calculations due to the possible attacks. There are no earlier statistical assumptions in the architecture proposed, as they are "model-free." It is also "cost-accommodating" since it does not alter the current FDD framework and it is only several microseconds on a household computer during the identification procedure. We have shown that ANN-MLP, SVM-RBF, and CNN can conduct locational detection under different noise and attack circumstances through broad experience in IEEE 14, 30, 57, and 118 bus systems. Moreover, the multi-name classification method used successfully improves the precision of the present identification.

KCI등재

4대장 종양의 현미부수체 불안정성 검사에서 딥러닝의 유용성

저자 : 김재현 ( Jae Hyun Kim )

발행기관 : 대한소화기학회 간행물 : 대한소화기학회지 77권 1호 발행 연도 : 2021 페이지 : pp. 54-55 (2 pages)

다운로드

(기관인증 필요)

키워드 보기
초록보기

대장 종양의 현미부수체 불안정성(microsatellite instability, MSI)과 부적합 결합 DNA 교정 기능 소실(mismatch repair deficiency, dMMR) 검사는 대장암 환자 치료제 선택의 중요한 고려 요소이다. MSI 검사는 Bethesda 패널 polymerase chain reaction (PCR)을 이용하며, MMR 검사는 MLH1, MSH2, MSH6, PMS2를 포함한 immunohistochemistry 패널을 이용한다. 이러한 검사를 위해서는 추가적인 조직 샘플 획득이 필요하며, 기존의 조직 슬라이드 검사 비용 외에 추가적인 비용이 발생하게 된다. 이 연구에서는 딥러닝 기법을 이용하여 일반적인 조직 슬라이드에서 MSI와 dMMR의 분석을 가능하게 하였고, 추가 분석에 따로 필요한 비용과 시간을 절약할 수 있게 하였다. 저자들은 독일, 네덜란드, 영국, 미국의 MSDETECT 컨소시엄 스터디에서 총 8,836개 대장 종양의 헤마톡실린/에오진 염색 슬라이드와 분자 분석 결과를 수집하였고, 모든 슬라이드를 리뷰하여 슬라이드의 종양 조직 포함 유무 및 이미지 퀄리티를 확인하였다. 딥러닝 시스템이 헤마톡실린/에오진 염색 슬라이드에서 MSI 또는 dMMR 결과를 예측하도록 학습시켰고, 예측 정확도를 다기관 코호트를 이용하여 검증하였다. 그 결과 평균 area under the receiver operating characteristics 값이 0.92, 민감도가 95%, 특이도가 67%로 확인 되었다. 특히 슬라이드 이미지의 색 보정(color normalization) 후의 dMMR 예측에 대한 area under the receiver operating characteristics 값은 0.96이었다. 저자들은 이러한 시스템이 실제 임상에서 대장암 조직 검체를 분석을 위한 비용 절감 및 효율 증대 효과를 보일 것으로 기대하였다.

KCI등재SCOUPUS

5Secure Ob ject Detection Based on Deep Learning

저자 : Keonhyeong Kim , Im Young Jung

발행기관 : 한국정보처리학회 간행물 : JIPS(Journal of Information Processing Systems) 17권 3호 발행 연도 : 2021 페이지 : pp. 571-585 (15 pages)

다운로드

(기관인증 필요)

초록보기

Applications for object detection are expanding as it is automated through artificial intelligence-based processing, such as deep learning, on a large volume of images and videos. High dependence on training data and a non-transparent way to find answers are the common characteristics of deep learning. Attacks on training data and training models have emerged, which are closely related to the nature of deep learning. Privacy, integrity, and robustness for the extracted information are important security issues because deep learning enables object recognition in images and videos. This paper summarizes the security issues that need to be addressed for future applications and analyzes the state-of-the-art security studies related to robustness, privacy, and integrity of object detection for images and videos.

KCI등재

6Deep Learning Machine Vision System with High Object Recognition Rate using Multiple-Exposure Image Sensing Method

저자 : Min-jun Park , Hyeon-june Kim

발행기관 : 한국센서학회 간행물 : 센서학회지 30권 2호 발행 연도 : 2021 페이지 : pp. 76-81 (6 pages)

다운로드

(기관인증 필요)

초록보기

In this study, we propose a machine vision system with a high object recognition rate. By utilizing a multiple-exposure image sensing technique, the proposed deep learning-based machine vision system can cover a wide light intensity range without further learning processes on the various light intensity range. If the proposed machine vision system fails to recognize object features, the system operates in a multiple-exposure sensing mode and detects the target object that is blocked in the near dark or bright region. Furthermore, shortand long-exposure images from the multiple-exposure sensing mode are synthesized to obtain accurate object feature information. That results in the generation of a wide dynamic range of image information. Even with the object recognition resources for the deep learning process with a light intensity range of only 23 dB, the prototype machine vision system with the multiple-exposure imaging method demonstrated an object recognition performance with a light intensity range of up to 96 dB.

KCI등재SCISCOUPUS

7Deep Learning Assisted Differential Cryptanalysis for the Lightweight Cipher SIMON

저자 : Wenqiang Tian , Bin Hu

발행기관 : 한국인터넷정보학회 간행물 : KSII Transactions on Internet and Information Systems (TIIS) 15권 2호 발행 연도 : 2021 페이지 : pp. 600-616 (17 pages)

다운로드

(기관인증 필요)

초록보기

SIMON and SPECK are two families of lightweight block ciphers that have excellent performance on hardware and software platforms. At CRYPTO 2019, Gohr first introduces the differential cryptanalysis based deep learning on round-reduced SPECK32/64, and finally reduces the remaining security of 11-round SPECK32/64 to roughly 38 bits. In this paper, we are committed to evaluating the safety of SIMON cipher under the neural differential cryptanalysis. We firstly prove theoretically that SIMON is a non-Markov cipher, which means that the results based on conventional differential cryptanalysis may be inaccurate. Then we train a residual neural network to get the 7-, 8-, 9-round neural distinguishers for SIMON32/64. To prove the effectiveness for our distinguishers, we perform the distinguishing attack and key-recovery attack against 15-round SIMON32/64. The results show that the real ciphertexts can be distinguished from random ciphertexts with a probability close to 1 only by 28.7 chosen-plaintext pairs. For the key-recovery attack, the correct key was recovered with a success rate of 23%, and the data complexity and computation complexity are as low as 28 and 220.1 respectively. All the results are better than the existing literature. Furthermore, we briefly discussed the effect of different residual network structures on the training results of neural distinguishers. It is hoped that our findings will provide some reference for future research.

KCI등재SCOUPUS

8해수 이용 LNG 재기화 공정의 딥러닝과 AutoML을 이용한 동적모델링

저자 : 신용범 ( Yongbeom Shin ) , 유상우 ( Sangwoo Yoo ) , 곽동호 ( Dongho Kwak ) , 이나경 ( Nagyeong Lee ) , 신동일 ( Dongil Shin )

발행기관 : 한국화학공학회 간행물 : 화학공학 59권 2호 발행 연도 : 2021 페이지 : pp. 209-218 (10 pages)

다운로드

(기관인증 필요)

초록보기

ORV의 열교환 효율 향상 및 운전 최적화를 위한, first principle 기반 모델링 연구들이 수행되어왔지만, ORV의 열전달 계수는 시간, 위치에 따라 불규칙한 시스템으로, 복잡한 모델링 과정을 거친다. 본 연구는 복잡한 시스템에 대한 데이터 기반 모델링의 실효성을 확인하고자, LNG 재기화 공정의 실제 운전데이터를 이용해, ORV의 해수 유량, 해수 온도, LNG 유량 변화에 따른 토출 NG 온도 및 토출 해수 온도의 동적 변화 예측이 가능한, FNN, LSTM 및 AutoML 기반 모델링을 진행하였다. 예측 정확도는 MSE 기준 LSTM > AutoML > FNN 순으로 좋은 성능을 보였다. 기계학습 모델의 자동설계 방법인 AutoML의 성능은 개발된 FNN보다 뛰어났으며, 모델 개발 전체소요시간은 복잡한 모델인 LSTM 대비 1/15로 크게 차이를 보여 AutoML의 활용 가능성을 보였다. LSTM과 AutoML을 이용한 토출 NG 및 토출 해수 온도의 예측은 0.5 K 미만의 오차를 보였다. 예측모델을 활용해, 겨울철 ORV를 이용해 처리 가능한 LNG 기화량의 실시간 최적화를 수행하여, 기존 대비 최대 23.5%의 LNG를 추가 처리 가능함을 확인하였고, 개발된 동적 예측모델 기반의 ORV 최적 운전 가이드라인을 제시하였다.


First principle-based modeling studies have been performed to improve the heat exchange efficiency of ORV and optimize operation, but the heat transfer coefficient of ORV is an irregular system according to time and location, and it undergoes a complex modeling process. In this study, FNN, LSTM, and AutoML-based modeling were performed to confirm the effectiveness of data-based modeling for complex systems. The prediction accuracy indicated high performance in the order of LSTM > AutoML > FNN in MSE. The performance of AutoML, an automatic design method for machine learning models, was superior to developed FNN, and the total time required for model development was 1/15 compared to LSTM, showing the possibility of using AutoML. The prediction of NG and seawater discharged temperatures using LSTM and AutoML showed an error of less than 0.5K. Using the predictive model, real-time optimization of the amount of LNG vaporized that can be processed using ORV in winter is performed, confirming that up to 23.5% of LNG can be additionally processed, and an ORV optimal operation guideline based on the developed dynamic prediction model was presented.

KCI등재SCOUPUS

9Deep learning can contrast the minimal pairs of syntactic data

저자 : Kwonsik Park , Myung-kwan Park , Sanghoun Song

발행기관 : 경희대학교 언어정보연구소 간행물 : 언어연구 38권 2호 발행 연도 : 2021 페이지 : pp. 395-424 (30 pages)

다운로드

(기관인증 필요)

초록보기

The present work aims to assess the feasibility of using deep learning as a useful tool to investigate syntactic phenomena. To this end, the present study concerns three research questions: (i) whether deep learning can detect syntactically inappropriate constructions, (ii) whether deep learning’s acceptability judgments are accountable, and (iii) whether deep learning’s aspects of acceptability judgments are similar to human judgments. As a proxy for a deep learning language model, this study chooses BERT. The current paper comprises syntactically contrasted pairs of English sentences which come from the three test suites already available. The first one is 196 grammatical -ungrammatical minimal pairs from DeKeyser (2000). The second one is examples in four published syntax textbooks excerpted from Warstadt et al. (2019). The last one is extracted from Sprouse et al. (2013), which collects the examples reported in a theoretical linguistics journal, Linguistic Inquiry. The BERT models, base BERT and large BERT, are assessed by judging acceptability of items in the test suites with an evaluation metric, surprisal, which is used to measure how ‘surprised’ a model is when encountering a word in a sequence of words, i.e., a sentence. The results are analyzed in the two frameworks: directionality and repulsion. The results of directionality reveals that the two versions of BERT are overall competent at distinguishing ungrammatical sentences from grammatical ones. The statistical results of both repulsion and directionality also reveal that the two variants of BERT do not differ significantly. Regarding repulsion, correct judgments and incorrect ones are significantly different. Additionally, the repulsion of the first test suite, which is excerpted from the items for testing learners’ grammaticality judgments, is higher than the other test suites, which are excerpted from the syntax textbooks and published literature. This study compares BERT’s acceptability judgments with magnitude estimation results reported in Sprouse et al. (2013) in order to examine if deep learning’s syntactic knowledge is akin to human knowledge. The error analyses on incorrectly judged items reveal that there are some syntactic constructions that the two BERTs have trouble learning, which indicates that BERT’s acceptability judgments are distributed not randomly. (Korea University · Dongguk University)

KCI등재

10딥러닝 사물 인식 알고리즘(YOLOv3)을 이용한 미세조류 인식 연구

저자 : 박정수 ( Jungsu Park ) , 백지원 ( Jiwon Baek ) , 유광태 ( Kwangtae You ) , 남승원 ( Seung Won Nam ) , 김종락 ( Jongrack Kim )

발행기관 : 한국물환경학회 간행물 : 한국물환경학회지 37권 4호 발행 연도 : 2021 페이지 : pp. 275-285 (11 pages)

다운로드

(기관인증 필요)

초록보기

Algal bloom is an important issue in maintaining the safety of the drinking water supply system. Fast detection and classification of algae images are essential for the management of algal blooms. Conventional visual identification using a microscope is a labor-intensive and time-consuming method that often requires several hours to several days in order to obtain analysis results from field water samples. In recent decades, various deep learning algorithms have been developed and widely used in object detection studies. YOLO is a state-of-the-art deep learning algorithm. In this study the third version of the YOLO algorithm, namely, YOLOv3, was used to develop an algae image detection model. YOLOv3 is one of the most representative one-stage object detection algorithms with faster inference time, which is an important benefit of YOLO. A total of 1,114 algae images for 30 genera collected by microscope were used to develop the YOLOv3 algae image detection model. The algae images were divided into four groups with five, 10, 20, and 30 genera for training and testing the model. The mean average precision (mAP) was 81, 70, 52, and 41 for data sets with five, 10, 20, and 30 genera, respectively. The precision was higher than 0.8 for all four image groups. These results show the practical applicability of the deep learning algorithm, YOLOv3, for algae image detection.

내가 찾은 최근 검색어

최근 열람 자료

맞춤 논문

보관함

내 보관함
공유한 보관함

1:1문의

닫기