• Proceedings of The KACE
• /
• 2017.08a
• /
• pp.221-224
• /
• 2017

본 논문은 사용자 수준에 적합한 맞춤형 학습코스를 추천하여 학습효과를 향상시킬 수 있는 추천모델을 개발하고, 효과분석을 위한 방안을 제시한다. 학습자 개개인의 학습수준이나 학습내용 등에 따라 적합한 학습주제를 선정하여 제공하는 것은 중요하나, 일반적인 추천은 전문가 그룹을 활용한 사람중심의 추천으로 시간이 오래 걸리는 등 자원의 비효율적 한계점[1]을 가지고 있다. 이를 극복하기 위해, TF-IDF를 이용해 단어별 가중치를 계산하여 고빈도 단어를 추출하여 벡터 공간에 배치시키고, Cosine Similarity 기법을 이용해 벡터간의 유사도를 측정하였다. 학습자 프로파일을 분석하고, 학습스킬간의 연관성을 고려하여 맞춤형 학습코스를 추천하기 위해, 워드 임베딩 기법을 적용하였고, 이를 위해 오픈소스 Gensim[2]을 이용하였다. 맞춤형 학습코스 추천 모델의 효과를 분석하기 위한 실험을 설계하고 평가 문항지를 개발하였다.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1467-1472
• /
• 2018

For the problem that the face image of surveillance video cannot be accurately identified due to the low resolution, this paper proposes a low resolution face recognition solution based on convolutional neural network model. Convolutional Neural Networks (CNN) model for multi-scale input The CNN model for multi-scale input is an improvement over the existing "two-step method" in which low-resolution images are up-sampled using a simple bi-cubic interpolation method. Then, the up sampled image and the high-resolution image are mixed as a model training sample. The CNN model learns the common feature space of the high- and low-resolution images, and then measures the feature similarity through the cosine distance. Finally, the recognition result is given. The experiments on the CMU PIE and Extended Yale B datasets show that the accuracy of the model is better than other comparison methods. Compared with the CMDA_BGE algorithm with the highest recognition rate, the accuracy rate is 2.5%~9.9%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.962-963
• /
• 2013

트위터 해시태그(#, HashTag)는 트윗(Tweets)에서 특정 키워드나 내용을 주제별로 분류하고 검색을 보다 효율적으로 사용하기 위한 사용자 정의 태그이다. 사용자가 정의하기에 따라 다양한 형태로 작성되기 때문에 오히려 검색의 효율성이 떨어질 수 있으며, 사용자는 자신이 작성한 트윗에 어떤 해시태그를 추가해야 하는지에 대한 궁금증이 생기는 경우가 발생한다. 본 논문에서는 이러한 문제를 해결하기 위해 사용자가 작성한 트윗에 적합한 해시태그를 추천하는 기법을 제안한다. 수집한 트윗과 해시태그의 키워드를 추출하고 트윗의 유사도를 계산하기 위해 TF-IDF와 Cosine Similarity를 적용하여 유사한 트윗을 갖는 해시태그를 추천한다. 본 논문에서 제안된 기법을 검증하기 위한 실험으로 추천의 정확성을 평가했다.

• Journal of information and communication convergence engineering
• /
• v.21 no.2
• /
• pp.159-166
• /
• 2023

The COI gene is a sequence of approximately 650 bp at the 5' terminal of the mitochondrial Cytochrome c Oxidase subunit I (COI) gene. As an effective DeoxyriboNucleic Acid (DNA) barcode, it is widely used for the taxonomic identification and evolutionary analysis of species. We created a CNN-LSTM hybrid model by combining the gene features partially extracted by the Long Short-Term Memory ( LSTM ) network with the feature maps obtained by the CNN. Compared to K-Means Clustering, Support Vector Machines (SVM), and a single CNN classification model, after training 278 samples in a training set that included 15 genera from two orders, the CNN-LSTM hybrid model achieved 94% accuracy in the test set, which contained 118 samples. We augmented the training set samples and four genera into four orders, and the classification accuracy of the test set reached 100%. This study also proposes calculating the cosine similarity between the training and test sets to initially assess the reliability of the predicted results and discover new species.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.624-629
• /
• 2020

최근 온라인 쇼핑 시장이 커지면서 소비자들은 다양한 물건을 온라인에서 쉽게 접근하고 구매할 수 있게 되었다. 이와 함께 인터파크의 '톡집사', 네이버 쇼핑 등에서는 다양한 쇼핑몰의 가격 정보를 모아서 소비자들이 합리적인 가격에 상품을 구매할 수 있도록 도와주고 있다. 이에 본 논문에서는 이러한 가격 비교 시스템을 활용하여 판매자들을 대상으로 서비스하는 시스템을 제안한다. 문서 유사도를 비교하기 위하여 쓰이던 코사인 유사도 분석 기법을 쇼핑몰 상품명 분석에 이용할 수 있도록 한다. 실제 상품명 정보를 이용해 코사인 유사도 분석을 실행하고 코사인 유사도 분석 결괏값으로 관련성이 낮은 상품을 배제한다. 나머지 상품의 정보를 바탕으로 최저가 분석을 수행하여 적정 판매가격을 추출하여 제시한다. 따라서 제안하는 방식을 적용하여 상품 분석을 시행하면 비슷한 범주에 있는 상품들을 추출한 뒤 최적의 가격을 제시할 수 있을 것이다.

• Korean Journal of Occupational Health Nursing
• /
• v.24 no.2
• /
• pp.76-85
• /
• 2015

Purpose: The purpose of this study was to identify knowledge structure of the Korean Journal of Occupational Health Nursing from 1991 to 2014. Methods: 400 articles between 1991 and 2014 were collected. 1,369 keywords as noun phrases were extracted from articles and standardized for analysis. Co-occurrence matrix was generated via a cosine similarity measure, then the network was analyzed and visualized using PFNet. Also NodeXL was applied to visualize intellectual interchanges among keywords. Results: According to the results of the content analysis and the cluster analysis of author keywords from the Korean Journal of Occupational Health Nursing articles, 7 most important research topics of the journal were 'Workers & Work-related Health Problem', 'Recognition & Preventive Health Behaviors', 'Health Promotion & Quality of Life', 'Occupational Health Nursing & Management', 'Clinical Nursing Environment', 'Caregivers and Social Support', and 'Job Satisfaction, Stress & Performance'. Newly emerging topics for 4-year period units were observed as research trends. Conclusion: Through this study, the knowledge structure of the Korean Journal of Occupational Health Nursing was identified. The network analysis of this study will be useful for identifying the knowledge structure as well as finding general view and current research trends. Furthermore, The results of this study could be utilized to seek the research direction in the Korean Journal of Occupational Health Nursing.

• The Journal of Society for e-Business Studies
• /
• v.24 no.2
• /
• pp.1-14
• /
• 2019

Because of the characteristics of game software, it is important to quickly identify and reflect users' needs into game software after its launch. However, most sites such as the Google Play Store, where users can download games and post reviews, provide only very limited and ambiguous classification categories for game reviews. Therefore, in this paper, we develop an automatic classification system for game reviews that categorizes reviews into categories that are clearer and more useful for game providers. The developed system converts words in reviews into vectors using word2vec, which is a representative word embedding model, and classifies reviews into the most relevant categories by measuring the similarity between those vectors and each category. Especially, in order to choose the best similarity measure that directly affects the classification performance of the system, we have compared the performance of three representative similarity measures, the Euclidean similarity, cosine similarity, and the extended Jaccard similarity, in a real environment. Furthermore, to allow a review to be classified into multiple categories, we use a threshold-based multi-category classification method. Through experiments on real reviews collected from Google Play Store, we have confirmed that the system achieved up to 95% accuracy.

• Journal of Korean Academy of Nursing
• /
• v.46 no.1
• /
• pp.50-58
• /
• 2016

Purpose: The purpose of this study was to identify the knowledge structure of cancer survivors. Methods: For data, 1099 articles were collected, with 365 keywords as a Noun phrase extracted from the articles and standardized for analyzing. Co-occurrence matrix were generated via a cosine similarity measure, and then the network analysis and visualization using PFNet and NodeXL were applied to visualize intellectual interchanges among keywords. Results: According to the result of the content analysis and the cluster analysis of author keywords from cancer survivors articles, keywords such as 'quality of life', 'breast neoplasms', 'cancer survivors', 'neoplasms', 'exercise' had a high degree centrality. The 9 most important research topics concerning cancer survivors were 'cancer-related symptoms and nursing', 'cancer treatment-related issues', 'late effects', 'psychosocial issues', 'healthy living managements', 'social supports', 'palliative cares', 'research methodology', and 'research participants'. Conclusion: Through this study, the knowledge structure of cancer survivors was identified. The 9 topics identified in this study can provide useful research direction for the development of nursing in cancer survivor research areas. The Network analysis used in this study will be useful for identifying the knowledge structure and identifying general views and current cancer survivor research trends.

• The Journal of the Korea Contents Association
• /
• v.8 no.1
• /
• pp.282-289
• /
• 2008

Although there were some technological developments in improving the collaborative filtering, they have yet to fully reflect the actual relation of the items. In this paper, we propose the recommendation system using associative web document classification by word frequency and ${\alpha}$-cut to address the short comings of the collaborative filtering. The proposed method extracts words from web documents through the morpheme analysis and accumulates the weight of term frequency. It makes associative rules and applies the weight of term frequency to its confidence by using Apriori algorithm. And it calculates the similarity among the words using the hypergraph partition. Lastly, it classifies related web document by using ${\alpha}$-cut and calculates similarity by using adjusted cosine similarity. The results show that the proposed method significantly outperforms the existing methods.

• Journal of Digital Convergence
• /
• v.17 no.8
• /
• pp.95-104
• /
• 2019

Recently, software education has been emphasized as a key element of the fourth industrial revolution. Many universities are strengthening the software education for all students according to the needs of the times. The use of online content is an effective way to introduce SW education for all students. However, the provision of uniform online contents has limitations in that it does not consider individual characteristics(major, sw interest, comprehension, interests, etc.) of students. In this study, we propose a recommendation method that utilizes the directional similarity between contents in the boolean view history data environment. We propose a new item-based recommendation formula that uses the confidence value of association rule analysis as the similarity level and apply it to the data of domestic paid contents site. Experimental results show that the recommendation accuracy is improved than when using the traditional collaborative recommendation using cosine or jaccard for similarity measurements.