• 한국빅데이터학회지
• /
• 제6권2호
• /
• pp.169-179
• /
• 2021

소비자의 식품소비행동은 소비자 패널 데이터와 같은 정형 데이터 뿐 아니라 매스미디어와 소셜미디어(SNS) 등 비정형 데이터로부터 영향을 받을 가능성이 높아지고 있다. 본 연구에서는 식품소비 관련된 정형 데이터와 비정형 데이터를 연계한 융합데이터 셋에 대하여 딥러닝 기반의 소비예측 모델을 생성하고 이를 검증한다. 연구의 결과는 정형 데이터와 비정형 데이터를 결합할 때 모델 정확도가 향상되었음을 보여주었다. 또한 비정형 데이터가 모델 예측 가능성을 향상시키는 것으로 나타났다. 변수들의 중요도를 식별하기 위해 SHAP 기법을 사용한 결과 블로그 및 비디오 데이터 관련 변수가 상위 목록에 있었고, 파프리카 구매 금액과 양의 상관관계가 있음을 알 수 있었다. 또한 실험 결과에 따르면 머신러닝 모델이 딥러닝 모델보다 높은 정확도를 보였고, 기존의 시계열 분석 모델링에 대한 효율적인 대안이 될 수 있음을 확인하였다.

• 한국수학교육학회지시리즈E:수학교육논문집
• /
• 제23권2호
• /
• pp.461-481
• /
• 2009

최근 20여 년 동안 국제적으로 기호학의 관점에서 수학교육에 대한 다양한 연구와 실천이 진행되어 오고 있다. 멀티미디어는 표현 매체이며 기호로서 수학 및 수학교육과 다양한 관계를 가지고 상호 작용한다. 수학 및 수학교육의 활동은 기호학의 관점에서 기호적 활동으로 영향력, 역할 그리고 범위가 확대될 것으로 예상된다. 본 논문에서는 기호학의 기본 개념을 소개하고 수학교육에서의 적용 가능성을 제안하였다. 개념, 표상, 사회적 구성주의, 문화와의 맥락에 관한 수학교육의 기존 연구와 기호학관점의 연구는 유사성을 갖는다. 기호학의 관점에서 산술학습, 연역법, 귀납법, 가추법과 퍼스의 기호-삼항틀 적용 사례, 기하의 명제들 사이의 퍼스-삼항틀 관계, 대칭과 증명을 다루는 기하학습 등을 제시하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2017년도 춘계학술대회
• /
• pp.543-546
• /
• 2017

최근, 데이터 분석을 통해 새로운 이슈를 선제적으로 확인하고 이를 통해 기술 발전을 이끌어 내고 있다. 이러한 새로운 이슈에 대해서 미디어 보도가 결정적인 역할을 하며, 특히 과학 기술에 대한 사회적 인식 형성에 큰 영향을 끼치고 있다. 이에 따라 200여개의 뉴스 기사를 중심으로 키워드 분석과 감성 분석, 2가지 데이터 분석을 바탕으로 미래 정보통신의 주요 기술(Machine Learning & Blockchains)을 확인한다. 본 분석 결과를 바탕으로 향후 정보통신 주요 기술을 지속적으로 발전하는데 길잡이 역할을 할 것으로 예상한다.

• International Journal of Advanced Culture Technology
• /
• 제7권4호
• /
• pp.289-294
• /
• 2019

As social network service platforms grow and one-person media market expands, people upload their own photos and/or videos through multiple open platforms. However, it can be illegal to upload the digital contents containing the faces of others on the public sites without their permission. Therefore, many people are spending much time and effort in editing such digital contents so that the faces of others should not be exposed to the public. In this paper, we propose an automatic face hiding system called 'autoblur', which detects all the unregistered faces and mosaic them automatically. The system has been implemented using the GitHub MIT open-source 'Face Recognition' which is based on deep learning technology. In this system, two dozens of face images of the user are taken from different angles to register his/her own face. Once the face of the user is learned and registered, the system detects all the other faces for the given photo or video and then blurs them out. Our experiments show that it produces quick and correct results for the sample photos.

• 대한통합의학회지
• /
• 제9권3호
• /
• pp.59-68
• /
• 2021

Purpose : The purpose of this study was to investigate the lecture method and physical activity level of Korean university students during the COVID-19 pandemic to determine their effect on the students' mental health, self-efficacy, and learning motivation. Methods : A total of 203 participants (53 male, 150 female) completed the study. An online survey was distributed through a social media platform between March 24 and April 7, 2021. Participants completed the international physical activity questionnaire-short form (IPAQ-SF), COVID-19 stress scale for Korean people (CSSK), the Korean version of the general health questionnaire (KGHQ-30), and self-efficacy and learning motivation scales. Results : Among the general characteristics of the study subjects, there were statistically significant differences in the IPAQ-SF, CSSK, KGHQ, self-efficacy, and learning motivation measures by sex. There were no significant differences in the degree of IPAQ-SF, CSSK, KGHQ, self-efficacy, and learning motivation among any of the lecture method and university area groups. The level of physical activity corresponded with significant differences in KGHQ, self-efficacy, and learning motivation, excluding CSSK. There was a statistically significant positive correlation between IPAQ and self-efficacy (r=.273, p<.001), IPAQ-SF and learning motivation (r=.201, p<.01), CSSK and KGHQ (r=.271, p<.001), self-efficacy and learning motivation measures (r=.506, p<.001). There was a statistically significant negative correlation between IPAQ-SF and KGHQ (r=-.203, p<.01) and between KGHQ and self-efficacy (r=-.558, p<.001). Conclusion : CSSK and KGHQ measures were significantly higher in female students than in male students. Therefore, it is important to consider sex as a protective factor in the mental health management of university students in the context of an infectious disease pandemic. The results of this study suggest that university students should continue to engage in physical activities, even during a pandemic, and that it is necessary to prepare health management to improve mental health in such situations.

• International Journal of Computer Science & Network Security
• /
• 제22권9호
• /
• pp.353-357
• /
• 2022

This article identifies the problems and substantiates the directions for the development of distance learning technologies in the training of personnel. An example of using digital media to create a remote access laboratory is given. The article is devoted to the definition of the main aspects of the organization of distance education. Rapid digitization, economic, political and social changes taking place in Ukraine necessitate the reform of the education system. First of all, it concerns meeting the educational needs of citizens throughout their lives, providing access to educational and professional training for all who have the necessary abilities and adequate training. The most effective solution to the above-mentioned problems is facilitated by distance learning. The article analyzes the essence and methods of distance learning organization, reveals the features of the use of electronic platforms for the organization of this form of education in different countries of the world. The positive characteristics of distance learning are identified, namely: extraterritoriality; savings on transport costs; the interest of modern youth in the use of information tools in everyday life; increase in the number of students; simplicity and accessibility of training; convenient consultation system; democratic relations between the student and the teacher; convenience for organizations in training their employees without interrupting their regular work; low level of payment for distance education compared to traditional education; individual learning pace; new teacher status. Among the negative features of online education, the author refers to the following problems: authentication of users during knowledge verification, calculation of the teacher's methodological load and copyright of educational materials; the high labor intensity of developing high-quality educational content and the high cost of distance learning equipment; the need to provide users with a personal computer and access to the Internet; the need to find and use effective motivation mechanisms for education seekers.

• International Journal of Computer Science & Network Security
• /
• 제24권8호
• /
• pp.179-183
• /
• 2024

This article identifies the problems and substantiates the directions for the development of distance learning technologies in the training of personnel. An example of using digital media to create a remote access laboratory is given. The article is devoted to the definition of the main aspects of the organization of distance education. Rapid digitization, economic, political and social changes taking place in Ukraine necessitate the reform of the education system. First of all, it concerns meeting the educational needs of citizens throughout their lives, providing access to educational and professional training for all who have the necessary abilities and adequate training. The most effective solution to the above-mentioned problems is facilitated by distance learning. The article analyzes the essence and methods of distance learning organization, reveals the features of the use of electronic platforms for the organization of this form of education in different countries of the world. The positive characteristics of distance learning are identified, namely: extraterritoriality; savings on transport costs; the interest of modern youth in the use of information tools in everyday life; increase in the number of students; simplicity and accessibility of training; convenient consultation system; democratic relations between the student and the teacher; convenience for organizations in training their employees without interrupting their regular work; low level of payment for distance education compared to traditional education; individual learning pace; new teacher status. Among the negative features of online education, the author refers to the following problems: authentication of users during knowledge verification, calculation of the teacher's methodological load and copyright of educational materials; the high labor intensity of developing high-quality educational content and the high cost of distance learning equipment; the need to provide users with a personal computer and access to the Internet; the need to find and use effective motivation mechanisms for education seekers.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제6권5호
• /
• pp.279-284
• /
• 2017

빅데이터 시대를 맞이하여 텍스트마이닝과 오피니언마이닝의 활용도가 커지고 있는 시점에서 소셜 네트워크 서비스로부터 유용한 정보를 추출하는 작업은 매우 중요한 연구 주제 중 하나이다. 이에 본 논문은 블로그 HTML 문서에서 주요 본문을 찾는 로지스틱 회귀 앙상블 기법을 제안한다. 먼저, 블로그 HTML 태그에서 구조적 특징, 텍스트 특징을 추출한다. 그 다음, 블로그 HTML 문서에서 추출한 태그 특징에 로지스틱 회귀 및 앙상블 기법을 적용하여 본문을 포함하는 태그를 분류하는 모델을 구성한다. 본 연구의 중요한 발견 중 하나는 태그의 깊이 특징을 이용하여 주요 본문을 찾을 수 있다는 점이다. 다양한 주제의 국내 블로그 데이터를 이용한 실험에서 태그 분류 정확도가 99%, 본문을 찾아낸 문서의 비율이 80.5%로 평가되었다.

• 한국전자통신학회논문지
• /
• 제15권4호
• /
• pp.709-716
• /
• 2020

소셜 미디어에서 일반적으로 게시물을 올릴 때 이미지의 태그 정보를 사용하는데, 태그를 이용하여 주로 검색이 이루어지기 때문이다. 사용자는 태그를 게시물에 붙임으로써 게시물을 많은 사람들에게 노출시키길 원한다. 또한, 사용자는 게시물과 함께 태깅될 태그를 붙이는 행위를 번거롭게 여겨 태깅하지 않은 게시물도 올리게 된다. 본 논문에서는 입력 이미지와 유사한 이미지를 찾아 해당 이미지에 부착된 레이블을 추출하여 그 레이블이 태그로 존재하는 인스타그램의 게시물들을 찾아 게시물 속 존재하는 다른 태그들을 추천해주는 방법을 제안한다. 제안하는 방법에서는 CNN(Convolutional Neural Network) 딥러닝 기법의 모델을 통하여 이미지로 부터 레이블을 추출하여 추출된 레이블로 인스타그램을 크롤링하여 레이블 외의 태그를 정렬하여 추천해준다. 추천된 태그를 이용하여 이미지를 게시하기도 편해지고, 검색의 노출을 높일 수 있고, 검색오류가 적어 높은 정확도를 도출할 수 있음을 알 수 있다.

• International Journal of Knowledge Content Development & Technology
• /
• 제12권4호
• /
• pp.41-65
• /
• 2022

This study would understand the overall perception of our society about public libraries, analyzing the texts related to public libraries, utilizing the semantic connection network & sentiment analysis. For this purpose, this study collected data from the last five years with keywords, 'Library' and 'Lifelong Learning Center' from January 1, 2016 through November 30, 2020 through the blogs and cafés of major domestic portal sites. With the collected data, text mining, centrality of keywords, network structure, structural equipotentiality, and sensitivity analyses were conducted. As a result of the analysis, First, 'reading' and 'book' were identified as representative keywords that form the social perception of public libraries. Second, it turned out that there were keywords related to the use of the library and the untact service due to the recent spread of COVID-19. Third, in seeking a plan for the development of public libraries through the keywords drawn to have positive meanings, it is necessary to create continuous services that can form a new image of the library, breaking away from the existing fixed role and image of the library and increase the convenience of use. Fourth, facilities and facilities for library services were recognized from a neutral point of view. Fifth, the spread of infectious diseases, social distancing, and temporary closure and closure of libraries are negatively related to public libraries, and awareness of librarians has been identified as negative keywords.