• 한국컴퓨터정보학회논문지
• /
• 제24권9호
• /
• pp.77-82
• /
• 2019

Collaborative filtering is a popular technique for recommender systems and used in many practical commercial systems. Its basic principle is select similar neighbors of a current user and from their past preference information on items the system makes recommendations for the current user. One of the major problems inherent in this type of system is data sparsity of ratings. This is mainly caused from the underlying similarity measures which produce neighbors based on the ratings records. This paper handles this problem and suggests a new similarity measure. The proposed method takes users rating patterns into account for computing similarity, without just relying on the commonly rated items as in previous measures. Performance experiments of various existing measures are conducted and their performance is compared in terms of major performance metrics. As a result, the proposed measure reveals better or comparable achievements in all the metrics considered.

• Journal of Multimedia Information System
• /
• 제6권3호
• /
• pp.147-154
• /
• 2019

In a variety of fields, highly developed technology is being combined to create a lot of value. In order to keep up with this global trend, the Ministry of Education, which is in charge of national education, continuously develops and applies content for creative education to textbooks. The continuous development of content for creative education is not only related to national interests, but also to the continued development of mankind. Today, the succession and development of human knowledge is in charge of the education system. Research into an effective educational system is necessary for effective succession of rapidly developing science and technology and building up technical personnel with such skills. In particular, the computer science field is faster in development than other scientific fields and has accumulated many technologies, indicating that it takes a lot of time and good teaching to foster talent that can effectively utilize the technology. In this paper, elementary school subjects were analyzed to achieve the purpose of cultivating talent in the field of computer science. In addition, we have investigated techniques related to computer programming learning not covered in elementary school subjects. So we developed content that students need to practice. Next, we taught the content to randomly selected elementary school students and assessed their educational effectiveness. As a result of training using the content we developed, 55.37% increased academic performance.

• ETRI Journal
• /
• 제46권4호
• /
• pp.660-670
• /
• 2024

The performance of face recognition (FR) has reached a plateau for public benchmark datasets, such as labeled faces in the wild (LFW), celebrities in frontal-profile in the wild (CFP-FP), and the first manually collected, in-the-wild age database (AgeDB), owing to the rapid advances in convolutional neural networks (CNNs). However, the effects of faces under various fine-grained conditions on FR models have not been investigated, owing to the absence of relevant datasets. This paper analyzes their effects under different conditions and loss functions using K-FACE, a recently introduced FR dataset with fine-grained conditions. We propose a novel loss function called MixFace, which combines classification and metric losses. The superiority of MixFace in terms of effectiveness and robustness was experimentally demonstrated using various benchmark datasets.

• 디지털콘텐츠학회 논문지
• /
• 제19권5호
• /
• pp.1021-1026
• /
• 2018

국내에서는 계산과학이라는 학문이 초기단계로 아직 활성화되지 못하고 있으며 고성능컴퓨팅을 기초부터 고급 과정까지 체계적으로 배울 수 있는 교육체계가 미비하다. 본 논문에서는 계산과학 전공자들이 배워야 할 컴퓨터과학에 대한 기본 연구로 고성능컴퓨팅을 배우기 위해 필요한 지식 단위을 도출하였다. ACM의 Computer Science 커리큘럼(CS2013)을 기초로 하여 89개의 지식 단위들에 대해 타당성과 신뢰성을 조사하였으며 검증된 11개의 지식단위에 대해 전문가를 통해 6개의 핵심 지식 단위와 2개의 선택 지식 단위를 제안되었다. 제안된 지식단위들은 계산과학 전공들에게 필요한 고성능컴퓨팅 교육과정 개발에 기여할 것으로 기대된다.

• 한국컴퓨터정보학회논문지
• /
• 제20권12호
• /
• pp.107-113
• /
• 2015

This study analyzed the effect of the factors of introducing information technology(organizational and environmental characteristics) on non-financial performance. As detailed variables of each characteristic, the technical support/task force, users' IT capability, and education/training were used for the organizational characteristics while the degree of competition, external pressure, and uncertainty of environment were used for the environmental characteristics. In the results of the analysis, such factors like technical support/task force, users' IT capability, and education/training of the organizational characteristics had significant influence on non-financial performance. Also, factors such as degree of competition, external pressure, and uncertainty of environment of the environmental characteristics had significant influence on non-financial performance.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.246-256
• /
• 2022

Recently, parents and teachers consider physical education as a minor subject for students in elementary and secondary schools. Physical education performance has become increasingly significant as parents and schools pay more attention to physical schooling. The sports mining with distribution analysis model considers different factors, including the games, comments, conversations, and connection made on numerous sports interests. Using different machine learning/deep learning approach, children's athletic and academic interests can be tracked over the course of their academic lives. There have been a number of studies that have focused on predicting the success of students in higher education. Sports interest prediction research at the secondary level is uncommon, but the secondary level is often used as a benchmark to describe students' educational development at higher levels. An Automated Student Interest Prediction on Sports Mining using DL Based Bi-directional Long Short-Term Memory model (BiLSTM) is presented in this article. Pre-processing of data, interest classification, and parameter tweaking are all the essential operations of the proposed model. Initially, data augmentation is used to expand the dataset's size. Secondly, a BiLSTM model is used to predict and classify user interests. Adagrad optimizer is employed for hyperparameter optimization. In order to test the model's performance, a dataset is used and the results are analysed using precision, recall, accuracy and F-measure. The proposed model achieved 95% accuracy on 400^th instances, where the existing techniques achieved 93.20% accuracy for the same. The proposed model achieved 95% of accuracy and precision for 60%-40% data, where the existing models achieved 93% for accuracy and precision.

• 방송공학회논문지
• /
• 제25권6호
• /
• pp.911-921
• /
• 2020

최근 MPEG-I (Immersive) 그룹에서는 몰입형 비디오(Immersive Video)에 대한 표준화 프로젝트를 통해 압축 성능 탐색을 진행하고 있다. MIV(MPEG Immersive Video) 표준 기술은 다수의 시점 영상과 깊이 맵을 통한 깊이 맵 기반 이미지 렌더링(DIBR)을 바탕으로 제한적인 6DoF을 제공하고자 하는 기술이다. 현재 MIV에서는 바탕 시점(Basic View)과 각 시점의 고유한 영상 정보를 패치 단위로 모아둔 추가 시점(Additional View)으로 처리하는 모델을 채택하고 있다. MIV에서 생성된 아틀라스는 포함되는 시점의 성격에 따라 다른 영상의 특성을 나타내어 비디오 코덱의 압축 효율에 대한 고찰이 필요하다. 따라서 본 논문에서는 다양한 시점과 패치들이 반복되는 패턴에 착안하여 화면 내 블록 카피(IBC: intra block copy) 등의 압축 기법이 포함된 스크린 콘텐츠 코딩 툴에 대한 성능 비교 분석을 진행하여 복원 영상에서 최대 -15.74% Peak Signal-to-Noise Ratio (PSNR) 관점에서의 부호화 성능 향상을 제공하였다.

• 디지털융복합연구
• /
• 제19권10호
• /
• pp.95-104
• /
• 2021

소프트웨어 교육은 4차 산업혁명을 이끌 미래인재 양성을 위한 교육으로 주목받고 있다. 유아부터 성인까지 모두를 위한 소프트웨어 교육의 목적은 단순히 프로그래밍 능력을 기르는 것이 아닌, 컴퓨팅을 기반으로 현실 세계의 문제를 효과적으로 해결해 나가는 문제 해결 능력인 '컴퓨팅 사고력'을 기르는 것이다. 따라서 어떻게 컴퓨팅 사고력을 함양하고 평가할 것인가는 매우 중요한 사안이다. 본 논문은 학습자가 문제를 해결하는 과정에서 과정중심 수행평가 방식을 적용하여 컴퓨팅 사고력을 평가하는 방식을 제안하였다. 개발된 내용은 컴퓨터과학·컴퓨터교육 전공의 대학 교수 5인, 컴퓨터과학·컴퓨터교육 전공 현직 정보교사 5인으로 구성된 전문가 집단의 2차에 걸친 델파이 조사를 통해 수정·보완하여 최종 모델의 타당성을 검증하였다. 본 논문이 문제 해결 관점에서 컴퓨팅 사고력을 평가하기 위한 연구에 기여할 수 있기를 기대한다.

• 한국컴퓨터정보학회논문지
• /
• 제23권1호
• /
• pp.103-109
• /
• 2018

The purpose of the study is to investigate the effect of a simulation training of BLS in paramedics in pre-hospital situation. This a nonequivalence control quasi-experimental study. The study subjects were 8 paramedics of experimental group and 8 paramedics of control group in K fire department. An informed consent was written by the subjects after explaining of the purpose of the study. The study methods consisted of conventional education and practice training. The conventional education was done for 30 minutes and the practice training was taken by four trainees of one group and the instructor demonstrated Basic Iife Support (BLS) performance for three minutes. Each trainer peformed BLS for ten minutes. In the beginning of the course, two paramedics got off from the ambulance and performed BLS including 5 cycles of Cardiopulmonary Resuscitation (CPR). Soon after the BLS, another two paramedics performed pre-hospital BLS survey. The education was guided by two professors of emergency medical technology, two Basic Iife Support instructors, and two emergency rescue directors. Pre-hospital BLS was measured by a 5-point Likert scale. Higher score means higher performance skills. The data were analyzed using SPSS/WIN 22.0 program set at significance level of p<05. The effect of simulation education was much more significant than the conventional education in BLS. The simulation education is very important and effective in improving the clinical performance skills of paramedics than the conventional education. The simulation education can provide the virtual environment of cardiac arrest to the paramedics. In conclusion, the simulation education can provide the effective teaching methods for various practice performance skills and solution by critical thinking in the paramedics and healthcare providers in the future.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2018년도 춘계학술발표대회
• /
• pp.297-299
• /
• 2018

IT기업뿐만 아니라 다양한 기업들이 빅데이터, 인공지능, 블록체인 등 많은 양의 컴퓨터 자원 (CPU, RAM 등)을 요구하는 기술들을 서비스화 하고 있다. 따라서 한정된 차원으로 효율적인 서비스를 운영하는 것도 주요 이슈가 되고 있다. 본 논문에서는 오픈소스 RDBMS 인 MariaDB와 PostgreSQL을 프로파일링하여 CPU 자원 효율성 관점에서 비교한다. 연구 결과 인터넷 서비스 환경에서 MariaDB가 PostgreSQL보다 버퍼 풀로 인해 페이지 캐시 참조율이 낮고, page fault 수가 적어 CPU 오버헤드가 더 작다는 것을 입증하였다.