폴리케톤/천연섬유 복합재료에 대한 연구

유성환(Sunghwan Ryu),윤정환(Junghwan Yoon),윤주호(Ju-ho Yun),유승을(Seung-eul Yoo) 한국자동차공학회 2017 한국자동차공학회 부문종합 학술대회 Vol.2017 No.5

Automobile interior products are researching and developing automobile parts in three directions of high quality, environment friendly and light weight. As the living standard is improved and passengers stay in the automobile, research on environmentally friendly materials is studied in various aspects In fact. Eco-friendly materials are currently being applied to press forming other than extrusion and injection, and since the natural fiber composite material through injection molding has not been used as an automotive interior product up to now, the test piece is molded through extrusion and injection molding The matrix polymer used in this study was Polyketone (PK or POK) developed by Hyosung. The natural fiber used in this study was Kenaf (lignin removal, lignin The test specimens were prepared by extrusion molding and injection molding using fibers and Sisal (lignin-removing) fibers. The recipe was made before and after the addition of additives (antioxidants, radical formation inhibitors, UV stabilizers) After the optimized mixing ratio was selected, the test specimens were molded for each fiber content, and then the mechanical properties and chemical properties were changed through UTM, FT-IR, DSC, TGA, GCMS and FE-SEM The morphology at the interface between matrix polymer and fiber was analyzed. As a result of the study, it has been studied that the dispersion of physical properties decreases as the additives are added. As the content of fibers increases, the tensile-related properties decrease and flexural-related properties increase. As the content of fibers increases, In order to increase the dispersibility of fiber, it was confirmed by analyzing that fiber is dispersed evenly on the outer surface of specimen when glass bubble is added..

흡연상태에 관한 자가보고 설문의 타당도 평가: 제1기(2009-2011) 국민환경보건기초조사 자료 분석

최욱희,박경화,김현정,류정민,유승도,최경희,김수진,Choi, Wookhee,Park, Kyung Hwa,Kim, Hyun Jeong,Ryu, Jungmin,Yu, Seung Do,Choi, Kyunghee,Kim, Suejin 한국환경보건학회 2014 한국환경보건학회지 Vol.40 No.6

Objectives: The purpose of this study was to assess the validity of self-reported cigarette smoking status and investigate factors associated with the accuracy self-reported and measured urinary cotinine in Korean adults. Methods: We used data from the $1^{st}$ Korean National Environmental Health Survey (2009-2011) among adults aged ${\geq}19$ years (N=6,246). The survey examined self-reported smoking status, and urinary cotinine was regarded as the biomarker of exposure to tobacco smoke. Urinary cotinine was analyzed using a gas chromatography-mass spectrometry (GC/MS) and data analysis was conducted using IBM SPSS version 20.0, which uses the sample weight and calculates variance estimates to adjust for the unequal probability of selection into the survey. Results: We calculated a cut-off point (53.3 ug/L) by using a ROC (Receiver Operating Characteristic) curve. The smoking prevalence was 24.6% based on self-reported data and 28.2% based on urinary cotinine concentrations. When we assessed the agreement between self-reported and urinary cotinine, we found an average agreement of 97.7% among self-reported smokers and 94.5% among self-reported non-smokers. Among self-reported smokers, factors affected the discrepancy were age, household economic status and average number of cigarettes smoked per day. On the other hand, gender, former smoking experience, and exposure to SHS (second hand smoke) were associated with discrepancies among self-reported non-smokers. Conclusion: These results suggest that self-reported data on smoking status provide a valid estimate of actual smoking status. In future research, we will conduct a continuous monitoring study for reliability verification of the data to reduce potential interpretation errors.

비산단지역 환경오염 수준 및 주민의 생체지표 모니터링

김대선,안승철,류정민,유승도,Kim, Dae-Seon,Ahn, Seung Chul,Ryu, Jung Min,Yu, Seung Do 한국환경보건학회 2012 한국환경보건학회지 Vol.38 No.6

Objectives: The main purpose of this study is to produce background data which can be compared with data on vulnerable areas such as industrial complexes in Ulsan, SihwaBanwol, Gwangyang, Yeosu, Pohang, Cheongju and Daesan in Korea. Methods: This study was performed on 1,007 local residents in Gangneung using personal questionnaires and medical check-up. Environmental pollutants including heavy metals in blood and urine were analyzed and the results are as follows. Results: According to the results of medical check-up, 705 subjects were "Normal (A and B)", 232 subjects were "Disease doubtful (R1)" and 70 subjects were "High blood pressure or Diabetes doubtful (R2)". Regarding geometric mean concentration, blood lead was 1.57 ${\mu}g/dL$, urine cadmium was 0.82 ${\mu}g/g-cr$, urine mercury was 0.98 ${\mu}g/g-cr$ and urine arsenic was 15.78 ${\mu}g/g-cr$. In the analysis of 11 kinds of VOCs in blood, vinyl chloride, 1,3-butadiene and dichloroethylene were not detected, while the detection rate of other chemicals was above 70% except chloroform(49.7%) and trichloroethylene(19.0%). In analysis of 16 kinds of PAHs in blood, 10 kinds showed more than 80% in detection rate. Also, detection rate of 4 kinds of PCBs in blood ranged 52 to 78%. Conclusions: Compared with industrial compelxes, the concentration of blood lead was lower, while urine cadmium and mercury levels were similar. Also, urine arsenic ranged at a significant level. Further study is required to find the cause of regional differences in concentrations of environmental pollutants.

전이학습을 활용한 소규모 비정형 정책데이터 감성분석 모델

안순재(Soonjae Ahn),유승의(Seungui Ryu),홍순구(Soongoo Hong) 한국데이터정보과학회 2020 한국데이터정보과학회지 Vol.31 No.2

최근 빅데이터 기술의 발전에도 불구하고 정책분야에서는 텍스트 등 비정형 데이터의 부족으로 감성분석 연구에 제한이 많았다. 이에 본 연구에서는 전이학습을 기반으로 소규모 비정형 정책 데이터를 활용한 감성분석 모델을 제안한다. 이를 위해 네이버 영화리뷰 20만 건의 댓글로 CNN 모델을 생성하고 지역 리뷰 1만 건의 댓글을 이용하여 전이학습을 수행하였다. 분석결과 본 연구에서 제안한 전이학습 모델은 소규모 데이터만으로 생성된 모델보다 약 10%의 정확도 향상과 1epoch당 1000ms의 학습지간 단축을 보였다. 본 연구의 공헌도로 학술적으로는 한글 텍스트 감성분석에 전이학습을 처음으로 적용하여 향후 소규모 데이터의 감성분석 연구에 활용할 수 있는 이론적 기반을 제공하였다는 점이다. 실무적으로는 데이터가 부족하여 시도하기 어려웠던 정책 분야의 감성분석을 통해 정부사업의 성공여부를 판별할 수 있는 기초자료로 활용할 수 있다. Despite the recent development in big data technologies, the research on sentiment analysis is still facing many limitations due to the lack of unstructured data, including texts, in the policy field. Thus, this study proposes a sentiment analysis model for small-scale unstructured policy data based on transfer learning. As a result, the proposed transfer learning model achieved about 10% better accuracy and a shorter training time of 1000 ms per epoch than the model generated only by using small-scale data. As an academic contribution, this study, which is the first application of transfer learning to Korean text sentiment analysis, provides a theoretical basis for future research on sentiment analysis using small-scale data. For practicality, this study can serve as basic data in determining the success or failure of government projects through sentiment analysis in the policy field, which was difficult to determine previously given the lack of data. the detailed feature of sea/land breeze at each site is closely associated with the local shape of coastline.

비지도학습 기반의 행정부서별 신문기사 자동분류 연구

김현종(Hyun-Jong Kim),유승의(Seung-Eui Ryu),이철호(Chul-Ho Lee),남광우(Kwang Woo Nam) 한국산학기술학회 2020 한국산학기술학회논문지 Vol.21 No.9

행정기관은 정책 대응성을 제고하기 위해 빅데이터 분석에 관심을 기울이고 있다. 빅데이터 중 뉴스 기사는 정책이슈와 정책에 대한 여론을 파악하는데 중요한 자료로 활용될 수 있다. 한편으로 새로운 온라인 매체의 등장으로 뉴스기사의 생산은 급격히 증가하고 있어 문서 자동분류를 통해 기사를 수집할 필요가 있다. 그러나 기존 뉴스 기사의 범주와 키워드 검색방법으로는 특정 행정기관 및 부서별로 업무에 관련된 기사를 자동적으로 수집하는 것에 한계가 있었다. 또한 기존의 지도학습 기반의 분류 기법은 다량의 학습 데이터가 필요한 단점을 가지고 있다. 이에 본 연구에서는 행정부서의 업무특징을 포함한 분류사전을 활용하여 기사의 분류를 효과적으로 처리하기 위한 방법을 제안한다. 이를 위해 행정기관의 업무와 신문기사를 Word2Vec와 토픽모델링 기법으로 부서별 특징을 추출하여 분류사전을 생성하고, 행정 부서별로 신문기사를 자동분류 한 결과 71%정도의 정확도를 얻었다. 본 연구는 행정부서별 신문기사를 자동분류하기 위해 부서별 업무 특징 추출 방법과 비지도학습 기반의 자동분류 방법을 제시하였다는 학문적 · 실무적 기여점이 있다. Administrative agencies today are paying keen attention to big data analysis to improve their policy responsiveness. Of all the big data, news articles can be used to understand public opinion regarding policy and policy issues. The amount of news output has increased rapidly because of the emergence of new online media outlets, which calls for the use of automated bots or automatic document classification tools. There are, however, limits to the automatic collection of news articles related to specific agencies or departments based on the existing news article categories and keyword search queries. Thus, this paper proposes a method to process articles using classification glossaries that take into account each agency"s different work features. To this end, classification glossaries were developed by extracting the work features of different departments using Word2Vec and topic modeling techniques from news articles related to different agencies. As a result, the automatic classification of newspaper articles for each department yielded approximately 71% accuracy. This study is meaningful in making academic and practical contributions because it presents a method of extracting the work features for each department, and it is an unsupervised learning-based automatic classification method for automatically classifying news articles relevant to each agency.

온라인 리뷰 빅데이터 분석을 통한 흰여울문화마을 관광 활성화 방안 연구

이새미 ( Lee Sae-mi ),유승의 ( Ryu Seung-eui ) 한국호텔리조트학회(구 한국호텔리조트카지노산학학회) 2020 호텔리조트연구 Vol.19 No.1

The purpose of this study is to investigate tourists' perceptions by analyzing tourism-related data among social big data, and to derive ideas for using social big data in tourism and promoting the tourism industry. To this end, 1162 tourists' online reviews were collected and analyzed by LDA, a representative topic modeling technique among text mining techniques, and extracted into 7 topics(sightseeing, emotional image 1, purpose of travel, parking dis­comfort, recommendation, architecture, emotional image 2). Topic 7 had the highest weight and consisted of keywords showing the emotional image of tourists. Topic 4 of the seven themes showed tourists' negative feelings about the parking problem. The meaning of this study is as follows. First, by analyzing the comments of tourists, authors suggest ideas for tourism based on the main issues. Second, text mining, which is one of the big data analysis technologies that can quantify reviews, which is unstructured data, is employed to analyze tourist opinions. Third, theoretical and practical implications are suggested based on the analy­sis results of tourist opinions.

민원 분석을 위한 텍스트 마이닝 기법 연구

김현종(Kim HyunJong),이태헌(Lee TaiHun),유승의(Ryu SeungEui),김나랑(Kim NaRang) 한국산업정보학회 2018 한국산업정보학회논문지 Vol.23 No.3

정부 및 공공기관에 있어 시민의 직접적인 요구사항이 담겨 있는 민원은 정책 개발을 위한 중요한 데이터로 활용이 가능하다. 그러나 민원 데이터는 비정형 텍스트로 작성되어 있는 특성으로 인해 일반적인 텍스트 마이닝 기법으로는 시민의 요구사항을 정확히 도출하기 어려웠다. 이에 본 연구에서는 민원 데이터 분석을 위한 텍스트 마이닝 기법을 개선하여, 시민의 요구사항을 도출할 수 있는 방법을 제시하고자 하였다. 새로운 텍스트 마이닝 기법은 공기어구조맵의 원리에 착안하여 연관성 분석을 2단계로 실시하여 핵심주제어를 기반으로 1차 연관 단어 와 2차 연관 단어로 구조화하였다. 분석을 위해 2016년 1년간 부산시 민원게시판에 올라온 3004건을 활용하였다. 분석 결과는 빈도수와 핵심주제어를 가지고 연관성 분석만으로는 찾을 수 없었던 민원 상의 문제를 본연구에서 제시한 계층적 연관성 분석을 이용하여 시민의 요구사항을 더욱 정확하게 파악할 수 있었다. 본 연구는 민원 데이터에서 시민의 요구사항을 도출하기 용이한 방법을 제안하였다는 학문적 기여점이 있으며, 행정기관에서 민원 데이터를 통해 정책 개발에 활용할 수 있다는 실무적 기여점이 있다. For government and public institutions, civil complaints containing direct requirements of citizens can be utilized as important data in developing policies. However, it is difficult to draw accurate requirements using text mining methods since the nature of the complaint text is unstructured. In this study, a new method is proposed that draws the exact requirements of citizens, improving the previous text mining in analyzing the data of civil complaints. The new text-mining method is based on the principle of Co-Occurrences Structure Map, and it is structured by two-step association analysis, so that it consists of the first-order related word and a second-order related word based on the core subject word. For the analysis, 3,004 cases posted on the electronic bulletin board of Busan City for the year 2016 are used. This study’s academic contribution suggests a method deriving the requirements of citizens from the civil affairs data. As a practical contribution, it also enables policy development using civil service data.

지역사회 통합돌봄(Community Care) 지원을 위한 생활권역 구축 연구

이태헌(Lee, Taihun),정하영(Jeong, Hayeong),유승의(Ryu, Seungeui),김현종(Kim, Hyunjong) 한국지역개발학회 2021 한국지역개발학회 학술대회 Vol.2021 No.11

The Integrated Community Care Leading Project is to create an environment in which individuals in need of care can receive continuous medical care and help for all aspects of life while living in the familiar environment they used to live in. The aim of this study is to define a concept of living zone of urban planning in accordance with ‘integrated community care’ and apply to meet the minimum physical conditions that enable daily community care. In order to apply the concept of ‘living zone for integrated community care ’ to concrete reality, GIS analysis was conducted to identify the current related facilities in Busanjin-gu and examine the formation of the living zone. Based on the results of the GIS analysis, this study proposed a baseline of formation of a living zone and presented policy implications by indicating a guideline for facilities that were insufficiently identified within the living zone.

레이블이 없는 문서 자동분류를 위한 분류체계 생성에 관한 연구

김현종(Hyun-Jong Kim),이강배(Kang-Bae Lee),유승의(Seung-Eui Ryu),홍순구(Soon-Goo Hong) 한국디지털콘텐츠학회 2020 한국디지털콘텐츠학회논문지 Vol.21 No.12

Since most unstructured data does not have labels, it is necessary to write ones on the data before performing supervised learning, which takes a lot of labor and time. This study proposed a method of generating and utilizing a classification scheme to classify unlabeled documents automatically. Consisting of multiple layers and including the characteristics of categories that provide classification criteria, the classification scheme provides a weighted value for document classification. Such concept of a classification scheme and classification criteria were extracted in this study to suggest a method of generating a classification scheme. The method and procedure proposed in this study were explained in detail by carrying out automatic classification tests with the civil complaint data of each administrative department of Busan City, and the effect was verified through the classification results. This study has significance in providing a theoretical basis for the generation of a classification scheme for the automatic classification of unlabeled documents.

비산단 지역주민들의 Skin Prick Test를 통한 알레르기 반응률 조사

김대선(Dae Seon Kim),안승철(Seung Chul Ahn),류정민(Jung Min Ryu),남상훈(Sang Hoon Nam),유승도(Seung Do Yu) 환경독성보건학회 2013 한국독성학회 심포지움 및 학술발표회 Vol.2013 No.5