• 한국멀티미디어학회논문지
• /
• 제22권2호
• /
• pp.250-259
• /
• 2019

Big data processing technology and artificial intelligence (AI) are increasingly attracting attention. Natural language processing is an important research area of artificial intelligence. In this paper, we use Korean news articles to extract topic distributions in documents and word distribution vectors in topics through LDA-based Topic Modeling. Then, we use Word2vec to vector words, and generate a weight matrix to derive the relevance SCORE considering the semantic relationship between the words. We propose a way to recommend documents in order of high score.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2154-2168
• /
• 2022

Our work addresses the issues associated with usage of the semantic features by Bag of Words model, which requires construction of the dictionary. Extracting the relevant features and clustering them into code book or dictionary is computationally intensive and requires large storage area. Hence we propose to use a simple distribution of multiple shape based features, which is a mixture of gradients, radius and slope angles requiring very less computational cost and storage requirements but can serve as an equivalent image representative. The experimental work conducted on PASCAL VOC 2007 dataset exhibits marginally closer performance in terms of accuracy with the Bag of Word model using Self Organizing Map for clustering and very significant computational gain.

• 한국수학교육학회지시리즈B:순수및응용수학
• /
• 제30권3호
• /
• pp.309-336
• /
• 2023

We establish some common fixed point theorems satisfying weak ψ - ϕ contraction on partially ordered non-Archimedean fuzzy metric spaces. By using this results we show the existence of fixed point on the domain of words and apply this approach to deduce the existence of solution for some recurrence equations associated to the analysis of Quicksort algorithms and divide and Conquer algorithms, respectively and also give an example to show the usefulness of our hypothesis. Our results generalize, extend and improve several well-known results of the existing literature in fixed point theory.

• 한국안전학회지
• /
• 제36권5호
• /
• pp.61-70
• /
• 2021

This study aimed to analyze the research trends of the abstract data of ergonomic studies registered in MEDLINE, a medical bibliographic database, using word embedding. Medical-related ergonomic studies mainly focus on work-related musculoskeletal disorders, and there are no studies on the analysis of words as data using natural language processing techniques, such as word embedding. In this study, the abstract data of ergonomic studies were extracted with a program written with selenium and BeutifulSoup modules using python. The word embedding of the abstract data was performed using the word2vec model, after which the data found in the abstract were vectorized. The vectorized data were visualized in two dimensions using t-Distributed Stochastic Neighbor Embedding (t-SNE). The word "ergonomics" and ten of the most frequently used words in the abstract were selected as keywords. The results revealed that the most frequently used words in the abstract of ergonomics studies include "use", "work", and "task". In addition, the t-SNE technique revealed that words, such as "workplace", "design", and "engineering," exhibited the highest relevance to ergonomics. The keywords observed in the abstract of ergonomic studies using t-SNE were classified into four groups. Ergonomics studies registered with MEDLINE have investigated the risk factors associated with workers performing an operation or task using tools, and in this study, ergonomics studies were identified by the relationship between keywords using word embedding. The results of this study will provide useful and diverse insights on future research direction on ergonomic studies.

• 대한간호학회지
• /
• 제10권2호
• /
• pp.21-40
• /
• 1980

In order to take cue of the dying persons and their survivors in a more positive and affirmative atti-tube. and to understand the valuable meaning of and dying. a survey was performed to 550 cases of health care personnels including 116 nursing students. 238 medical students. 137 nurses. and 59 doctors. Samplings were made through census Procedure from the entire group of medical and nursing students in College of Medicine. Chung-Ang University. and of licenced nurses and doctors in Chung-Ang University Hospital. and in Han-Gang Sacred Heart Hospital from the first to the end of march. 1980. These collected data were computerized at KIST by SPSS programming and were statistically analyzed by chi-square test. Through content analysis of the word associated with death and descriptive analysis of the death-re-lated variables. the following conclusion in is reached. First. Total numbers of death-word percieved by health care personnels were 198 kinds. Among them, 40 kinds of words associated with death were responded from than 1% of the total. As to the 10 death related word responded by free word association method. it was revealed that individual average number of death related word was 7.70 word. which came from higher number of words in the senior students (8.96 word) or the graduates (8.10 word) compared with the freshman (6.84 word). Second. In Content specific analysis of the death related word. more frequently perceived types summarized as the following order; the affective context of death. the diseases. the disasters. the religion, the funeral ceremonies. the separation, the drakness. and the life. Third. The most prevalent 10 words associated with death which the the respondents gave response to the the first recalling word. were as following o order； the dieases. the sadness, the vanity. the darkness, the frustration. the suicide. the incurable dieases, the graves. the dead. and the catastrophes. By sex, the diease is outstanding in females, but the vanity is in males. By occupation. the vanity and the dead was frequently observed in student group including senior students. while the incurable dieases presented by doctors. Fourth. In health care personnels. the first perceived ages of death were 11.47 $\pm$3.33 years (8.14- 15.80 years). Among them. senior students were inclined to percept death at the earliest age of life (11.28years). while doctors and nurses perceived death later in their life (12.98 years). Fifth, It is revealed in this survey that the most frequently responded death perceiving motives by health care personnels ar“psychological conflict”and“death of those around them”. Death perceiving motives can be classified in two factors; personality and life circumstances. Sixth It is of interest that only 11.3% health care personnels was found to feel death as inevitable or acceptable event. whereas 58.3% deny or reject it.

• 수산해양교육연구
• /
• 제29권2호
• /
• pp.593-606
• /
• 2017

This study aims to provide preliminary data capable of suggesting directivity of an initiating start by understanding consumer awareness through analysis of SNS social big data on marine sports. This study selected windsurfing, yacht, jet ski, scuba diving and sea fishing as research subjects, and produced following results by setting period of total 1 month from January 22 through February 22, 2017 on the SNS (twitter, blog) through the Social MatrixTM service of Daumsoft Co., Ltd., and analyzing frequency of mention, associated words etc. First, sports that was mentioned the most out of marine sports was yacht, which was 3,273 cases on twitter and 2,199 on blog respectively. Second, the word which was shown the most associated with marine sports was the attribute showing unique characteristic of marine sports, which was 6,261 cases in total.

• 한국콘텐츠학회논문지
• /
• 제10권11호
• /
• pp.125-135
• /
• 2010

본 연구는 애니메이션에 등장하는 의인화된 동물캐릭터를 표현하는데 있어서 인간의 성격과 관상이 의인화 캐릭터에 미치는 영향을 분석하고, 의인화된 동물캐릭터에서 나타나는 성격과 인상이 실제 동물의 연상 이미지와의 관련성을 분석하였다. 먼저 애니메이션에 등장 빈도수가 높은 동물들을 분류하여 각 동물의 특징을 가장 잘 표현한 대표적인 캐릭터를 추출 후 시각화하여 캐릭터의 인상을 성격단어로 평정하고, 각 동물의 이름(단어)을 연상할 때 떠오르는 성격을 성격단어로 평정하여 이미지와 단어 연상 간의 관련성을 분석하였다. 분석결과 두 실험은 유사성이 매우 높았으며, 인간이 잠재적으로 인식하는 동물의 이미지가 인간에게 친숙한 이미지로 의인화되어 표현되는 것을 알 수 있었다. 본 연구는 애니메이션에 등장하는 의인화된 동물캐릭터를 표현하는데 있어서 적절한 성격의 캐릭터 표현을 제안하고자 한다.

• 한국환경보건학회지
• /
• 제47권6호
• /
• pp.513-520
• /
• 2021

Background: Benzalkonium chloride (BKC) has been extensively used as a preservative in industrial products and in hygiene, medical, and cosmetic applications. Humidifier disinfectant (HD) products containing BKC have been used in South Korea. Objectives: This study was aimed to review types of products containing BKC, to summarize the regulations in the US, EU, Japan, and South Korea, and to review the health effects associated with the use of HD. Methods: We reviewed and summarized documents which were searched through PubMed and Google Scholar with the key words: BKC and asthma/contact dermatitis, humidifier disinfectant-associated lung injury (HDLI), and more. Results: Regulations in most countries including South Korea do not allow its use as disinfectants in spray-type of products for medicine, cosmetics, and household products. Two types of HD containing BKC (800~1,270 ppm) were marketed in South Korea from 1996~2003. Health effects reported from people who used products containing BKC were allergic contact dermatitis, erythema, and respiratory disease, including asthma. Two people who responded as HD users containing BKC only were confirmed to have developed asthma. HD-associated lung injury (HDLI) was reported by consumers who used both HD containing polyhexamethylene guanidine (PHMG) and HD containing BKC. Conclusions: In conclusion, the use of BKC as a biocide has to be controlled considering the route and pattern of exposure. Products containing BKC as preservatives were reviewed with exposure routes and sites in the human body such as skin, eyes, and the respiratory tract. HD containing BKC was clinically evaluated to be associated with asthma.

• Genomics & Informatics
• /
• 제2권3호
• /
• pp.131-133
• /
• 2004

MediScore is an information retrieval system, which helps to search for the set of genes associated with a specific disease or the set of diseases associated with a specific gene. Despite recent improvement of natural language processing (NLP) and other text mining approaches to search for disease associated genes, many false positive results come out due to diversity of exceptional cases as well as ambiguities in gene names. In order to overcome the weak points of current text mining approaches, MediScore introduces statistical normalization based on binomial to normal distribution approximation which corrects inaccurate scores caused by common words not representing genes and interactive rescoring by the user to remove the false positive results. Interactive rescoring includes individual alias scoring for each gene to remove false gene synonyms, referring MEDLINE abstracts, and cross referencing between OMIM and other related information.

• 한국콘텐츠학회논문지
• /
• 제20권3호
• /
• pp.223-234
• /
• 2020

본 연구는 Hong(2019)의 연구에서 도출된 한국 노인의 성공적인 노후에 영향을 주는 예측 키워드 32개를 중심으로 데이터마이닝의 Apriori 알고리즘을 활용하여 연관관계 규칙을 분석하였다. 그리고 한국 노인의 성공적 노후에 영향을 주는 예측변수들의 규칙 및 패턴을 파악하기 위한 지표로 지지도, 신뢰도, 향상도를 활용하였다. 본 연구의 분석은 R version 3. 5. 1 프로그램으로 분석을 실시하였으며, arulesViz 패기지와 visNetwork 패키지로 시각화하였다. 연구결과 한국 노인들의 성공적인 노후와 연관성이 높은 예측변수는 '취미', '봉사', '준비', '운동'으로 나타났다. 그리고 한국 노인의 성공적 노후를 고려할 때 가장 우선적으로 고려해야 할 변수는 '취미' 이며 그 다음 '봉사', 준비', 운동'의 순으로 고려해야 한다는 결과를 얻었다.