• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.245-246
• /
• 2020

본 논문에서는 블록형 코딩 방식을 통해 비전공자가 스스로 머신러닝의 쉽게 원리를 구현해 볼 수 있는 딥아이( D.I.Y, Deep AI Yourself) 플랫폼을 제안하였다. 딥아이는 구글의 오픈 소스 블록형 코딩 툴 개발 라이브러리인 Blockly를 기반으로 머신러닝 알고리즘을 쉽게 구현할 수 다양한 블록으로 구성되어 있다. Blockly는 CSR 기반이며 사용자가 개발한 블록 코드는 내부적으로 코드 생성기에 의해 파이썬 코드 등으로 변환되어 백엔드 서버에서 처리를 하며 결과를 사용자에게 제공한다.

• Journal of Practical Engineering Education
• /
• v.9 no.1
• /
• pp.23-30
• /
• 2017

This is a study on a case applying flipped learning to coding classes that is a college liberal arts course. A required coding class for the students who do not major in computers needs a teaching method differentiated from a coding education for training experts. The present study presented a flipped learning teaching model for the coding education of non-major students, and observed its effect and possibility. Flipped learning enables learners to learn with on-line contents anywhere and anytime they want and concentrate on practice education based on what they learned during class. Accordingly, the study sought for the solution to maximize the efficiency of teaching and learning through flipped learning. A pre and post surveys after applying a flipped learning to a practical class confirmed that the students taught using flipped learning were more positively assessed in learning satisfaction than those taught using a traditional method, and that in academic achievement as well, flipped learning was more effective.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.143-144
• /
• 2020

VVC (Versatile Video Coding)는 HEVC이후 차세대 표준 비디오 코딩으로 JVET(Joint Video Exploration)에 의해 2018년 표준화를 시작하였다. VVC에는 복원픽쳐의 변환-양자화에러에 의해 발생한 블로어, 블로킹, 링잉 아티팩트를 감소시키기 위하여 deblocking filter (DF), sample adaptive offset (SAO), adaptive loop filter(ALF)와 같은 모듈을 사용한다. 한편 CNN (Convolutional Neural Network)은 최근 이미지와 비디오 복원에 높은 성능을 보이고 있다. VVC에서 픽쳐는 CTU (Coding Tree Unit)으로 분할되고 각 CTU는 다시 CU (Coding Unit)으로 분할된다. 그리고 인코딩을 위한 중요한 정보들이 Picture, CTU, CU단위로 디코더에 전송된다. 이 논문에서는 화면 간 예측으로 인코딩 된 픽처에서 블록과 픽처정보를 이용한 딥러닝 기반의 인루프 필터 모델을 제안한다. 제안하는 모델은 화면 간 예측에서 QP, 4×4 블록단위의 모션벡터, 참조블록과의 시간적거리, CU의 깊이를 모델에 추가적인 정보로 이용한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.461-470
• /
• 2023

While speech animation generation employing deep learning has been actively researched for English, there has been no prior work for Korean. Given the fact, this paper for the very first time employs supervised deep learning to generate Korean speech animation. By doing so, we find out the significant effect of deep learning being able to make speech animation research come down to speech recognition research which is the predominating technique. Also, we study the way to make best use of the effect for Korean speech animation generation. The effect can contribute to efficiently and efficaciously revitalizing the recently inactive Korean speech animation research, by clarifying the top priority research target. This paper performs this process: (i) it chooses blendshape animation technique, (ii) implements the deep-learning model in the master-servant pipeline of the automatic speech recognition (ASR) module and the facial action coding (FAC) module, (iii) makes Korean speech facial motion capture dataset, (iv) prepares two comparison deep learning models (one model adopts the English ASR module, the other model adopts the Korean ASR module, however both models adopt the same basic structure for their FAC modules), and (v) train the FAC modules of both models dependently on their ASR modules. The user study demonstrates that the model which adopts the Korean ASR module and dependently trains its FAC module (getting 4.2/5.0 points) generates decisively much more natural Korean speech animations than the model which adopts the English ASR module and dependently trains its FAC module (getting 2.7/5.0 points). The result confirms the aforementioned effect showing that the quality of the Korean speech animation comes down to the accuracy of Korean ASR.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.5
• /
• pp.124-130
• /
• 2017

Character encoding is the method used to represent characters or symbols on a computer, and there are many encoding detection software tools. For the widely used encoding detection software"uchardet", the accuracy of encoding detection of unmodified normal text document is 91.39%, but the accuracy of language detection is only 32.09%. Also, if a text document is encrypted by substitution, the accuracy of encoding detection is 3.55% and the accuracy of language detection is 0.06%. Therefore, in this paper, we propose encoding and language detection of text document using the deep learning algorithm called LSTM(Long Short-Term Memory). The results of LSTM are better than encoding detection software"uchardet". The accuracy of encoding detection of normal text document using the LSTM is 99.89% and the accuracy of language detection is 99.92%. Also, if a text document is encrypted by substitution, the accuracy of encoding detection is 99.26%, the accuracy of language detection is 99.77%.

• Journal of the Korea Convergence Society
• /
• v.12 no.4
• /
• pp.23-30
• /
• 2021

An Automated Industry and Occupation Coding System assigns statistical classification code to the enormous amount of natural language data collected from people who write about their industry and occupation. Unlike previous studies that applied information retrieval, we propose a system that does not need an index database and gives proper code regardless of the level of classification. Also, we show our model, which utilized KoBERT that achieves high performance in natural language downstream tasks with deep learning, outperforms baseline. Our method achieves 95.65%, 91.51%, and 97.66% in Occupation/Industry Code Classification of Population and Housing Census, and Industry Code Classification of Census on Basic Characteristics of Establishments. Moreover, we also demonstrate future improvements through error analysis in the respect of data and modeling.

• Journal of Digital Convergence
• /
• v.14 no.10
• /
• pp.1-8
• /
• 2016

Coding education is an effective convergence type educational tool. While solving problems and designing programs, students can enhance problem solving ability, logical reasoning ability and creative thinking. Researches on coding education are done primarily for elementary school and middle school students. However, researches on college students are lacking. Today, educating college students about coding is in dire need. Although there are efforts to promote the importance of coding education and make it requirements. People find it difficult to find ways to provide training. There is a need for researches on coding as universal education. Therefore, this research proposed educational training using app inventor based on flipped running in order to effectively promote coding education. This study conducted the survey and the personal interview to measure the effectiveness of coding education. It is hoped that, through coding education, students who do not major in coding could combined their knowledge of their major with coding to improve their problem solving ability to solve various problems based on computing knowledge and approach.

• Journal of The Korean Association For Science Education
• /
• v.38 no.2
• /
• pp.219-234
• /
• 2018

In this study, we explored the possibility of automating the process of analyzing elements of scientific argument in the context of a Korean classroom. To gather training data, we collected 990 sentences from science education journals that illustrate the results of coding elements of argumentation according to Toulmin's argumentation structure framework. We extracted 483 sentences as a test data set from the transcription of students' discourse in scientific argumentation activities. The words and morphemes of each argument were analyzed using the Python 'KoNLPy' package and the 'Kkma' module for Korean Natural Language Processing. After constructing the 'argument-morpheme:class' matrix for 1,473 sentences, five machine learning techniques were applied to generate predictive models relating each sentences to the element of argument with which it corresponded. The accuracy of the predictive models was investigated by comparing them with the results of pre-coding by researchers and confirming the degree of agreement. The predictive model generated by the k-nearest neighbor algorithm (KNN) demonstrated the highest degree of agreement [54.04% (${\kappa}=0.22$)] when machine learning was performed with the consideration of morpheme of each sentence. The predictive model generated by the KNN exhibited higher agreement [55.07% (${\kappa}=0.24$)] when the coding results of the previous sentence were added to the prediction process. In addition, the results indicated importance of considering context of discourse by reflecting the codes of previous sentences to the analysis. The results have significance in that, it showed the possibility of automating the analysis of students' argumentation activities in Korean language by applying machine learning.

• Review of KIISC
• /
• v.30 no.1
• /
• pp.43-53
• /
• 2020

딥러닝 기술의 발달로 인해 다양한 응용 분야에서 해당 기술 활용 시 좋은 성능을 보임에 따라 부채널 분석 분야에서도 딥러닝 기술을 적용하는 연구들이 활발히 진행되고 있다. 초기 딥러닝 기술은 데이터 분류 문제를 해결해야 하는 템플릿 공격과 같은 프로파일링 기반의 부채널 공격에 집중되어 적용되었지만 최근에는 프로파일링 기반의 부채널 분석 뿐만 아니라 상관 전력 분석 등과 같은 논프로파일링 기반 부채널 공격, 파형 인코딩 및 전처리, 부채널 누출신호 탐색 등으로 연구범위가 확대되어지고 있다. 본 논문에서는 딥러닝을 이용한 부채널 분석 기술의 최신 연구 동향을 분야별로 체계적으로 정리 및 분석하고자 한다.

• Journal of the Korea Convergence Society
• /
• v.9 no.2
• /
• pp.7-12
• /
• 2018

With our society entering the Fourth Industrial Revolution, there has been heightened interest in coding education, which has led to an increased number of coding classes offered in schools. Once catered to degree holders only, coding courses are now being offered as liberal arts courses to even non-majors. As the importance of computing abilities and creativity-oriented education through software learning becomes increasingly pronounced, the need for research on effective coding learning is growing more urgent. The present study sought an effective coding education model that would encourage and enhance learners' participation and interest in coding. The proposed learning model is designed to invoke learner's recognition of various coding grammars and data search in the process of designing and performing their own unique project. Application of the proposed learning model and analysis of such case studies showed improvement in learning outcomes. One can expect improved performance among learners if the proposed learning model is applied to various coding courses.