• Journal of Korea Multimedia Society
• /
• v.6 no.6
• /
• pp.1111-1119
• /
• 2003

The research of science and engineering needs the latest information from internet resources. But it is a complex and repeated procedure to search and filter web documents from the huge Internet resources. In this paper, we propose the PREA system, which can organize the research paper databases and search World Wide Web documents that the user is interested in. It observes the usage of the local Paper databases and presented web documents and then constructs a profile intelligently. However, to make a profile, we used the modified spreading activation network(MSAN) so that the PREA can search and filter web documents by semantic meaning of user's interest in realtime. The system constructed in multi-agents manner that can cooperate together effectively. The results show the effectiveness of our system to search web documents compared with a commercial search engine.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.3
• /
• pp.35-46
• /
• 2016

Social network services (SNS) that help to build relationship network and share a particular interest or activity freely according to their interests by posting comments, photos, videos,${\ldots}$ on online communities such as blogs have adopted and developed widely as a social phenomenon. Several researches have been done to explore the pattern and valuable information in social networks data via text mining such as opinion mining and semantic analysis. For improving the efficiency of text mining, keyword-based approach have been applied but most of researchers argued the limitations of the rules of Korean orthography. This research aims to construct a database of non-standard Korean words which are difficulty in data mining such abbreviations, slangs, strange expressions, emoticons in order to improve the limitations in keyword-based text mining techniques. Based on the study of subjective opinions about specific topics on blogs, this research extracted non-standard words that were found useful in text mining process.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.5
• /
• pp.492-501
• /
• 2019

To use the system safely in cyberspace, you need to use a security solution that is appropriate for your situation. In order to strengthen cyber security, it is necessary to accurately understand the flow of security from past to present and to prepare for various future threats. In this study, information security words of security/hacking news of Naver News which is reliable by using text mining were collected and analyzed. First, we checked the number of security news articles for the past seven years and analyzed the trends. Second, after confirming the security/hacking word rankings, we identified major concerns each year. Third, we analyzed the word of each security solution to see which security group is interested. Fourth, after separating the title and the body of the security news, security related words were extracted and analyzed. The fifth confirms trends and trends by detailed security solutions. Lastly, annual revenue and security word frequencies were analyzed. Through this big data news analysis, we will conduct an overall awareness survey on security solutions and analyze many unstructured data to analyze current market trends and provide information that can predict the future.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.11a
• /
• pp.475-480
• /
• 2005

인터넷상에 존재하는 수 많은 웹 페이지들에는 정형화되지 않은 각종 정보들이 이종의 형태로 산재되어 있다. 현재의 검색 기술을 통하여 필요한 정보를 찾아내는 것은 시간과 비용이 많이 소요되는 비효율적인 방법으로 이뤄지고 있다. 이러한 상황에서 사용자가 원하는 정보를 검색 및 추출해내어 정형화시키는 것은 매우 중요하다. 전자상거래의 폭발적 성장에도 불구하고 전자상거래 표준 활용 및 적용이 미비하여 e- Procurement, e-Marketplace, on-Line Shopping Mall 등에서 소비자가 원하는 상품 정보를 손쉽게 획득하지 못하고 있다. 이는 공급자에게는 보다 많은 매출의 기회를 구매자에게는 보다 좋은 자재 및 상품을 저렴한 가격에 소싱 할 수 있는 기회를 제공하지 못하는 문제점이 발생한다. 본 연구에서 제안하고자 하는 지능형 상품 에이전트는 소비자가 구매하고자 하는 특정 상품에 대한 공급자 검색 문제를 해결하기 위하여, 시스템 내부 정보의 확장 및 지식화 뿐만 아니라 웹 상의 다양한 상품 정보를 자동적으로 수집 및 가공하여 저장하는 역할을 수행한다. 이러한 연구를 위해서 사용한 기술은 우선 database 의 schema 를 읽어 들일 수 있는 DB schema reader, 인터넷 웹 페이지(웹문서)를 방문해서 다양한 정보들의 URL을 수집하는 일을 하는 Meta Search Engine 과 Focused Crawler, 그리고 다른 형태의 데이터 구조를 특정 목적에 따라 표준화된 형태로 바꾸는 Wrapper가 있다. 이러한 기술들을 연동하여 필요한 정보들을 추출 공급자 검색 문제를 해결하고자 하는 것이 연구의 목적이다. 정보추출은 사용자의 관심사에 적합한 문서들로부터 어떤 구체적인 사실이나 관계를 정확히 추출하는 작업을 가리킨다.앞으로 e-메일, 매신저, 전자결재, 지식관리시스템, 인터넷 방송 시스템의 기반 구조 역할을 할 수 있다. 현재 오픈웨어에 적용하기 위한 P2P 기반의 지능형 BPM(Business Process Management)에 관한 연구와 X인터넷 기술을 이용한 RIA (Rich Internet Application) 기반 웹인터페이스 연구를 진행하고 있다.태도와 유아의 창의성간에는 상관이 없는 것으로 나타났고, 일반 유아의 아버지 양육태도와 유아의 창의성간의 상관에서는 아버지 양육태도의 성취-비성취 요인에서와 창의성제목의 추상성요인에서 상관이 있는 것으로 나타났다. 따라서 창의성이 높은 아동의 아버지의 양육태도는 일반 유아의 아버지와 보다 더 애정적이며 자율성이 높지만 창의성이 높은 아동의 집단내에서 창의성에 특별한 영향을 더 미치는 아버지의 양육방식은 발견되지 않았다. 반면 일반 유아의 경우 아버지의 성취지향성이 낮을 때 자녀의 창의성을 향상시킬 수 있는 것으로 나타났다. 이상에서 자녀의 창의성을 향상시키는 중요한 양육차원은 애정성이나 비성취지향성으로 나타나고 있어 정서적인 측면의 지원인 것으로 밝혀졌다.징에서 나타나는 AD-SR맥락의 반성적 탐구가 자주 나타났다. 반성적 탐구 척도 두 그룹을 비교 했을 때 CON 상호작용의 특징이 낮게 나타나는 N그룹이 양적으로 그리고 내용적으로 더 의미 있는 반성적 탐구를 했다용을 지원하는 홈페이지를 만들어 자료 제공 사이트에 대한 메타 자료를 데이터베이스화했으며 이를 통해 학생들이 원하는 실시간 자료를 검색하여 찾을 수 있고 홈페이지를 방분했을 때 이해하기 어려운 그래프나 각 홈페이지가 제공하는 자료들에 대한 처리 방법을 도움말로 제공받을 수 있게 했다. 실시간 자료들을 이용한 학습은 학생들의 학습 의욕과 탐구 능력을 향상시켰으

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.1-25
• /
• 2020

In this paper, we suggest an application system architecture which provides accurate, fast and efficient automatic gasometer reading function. The system captures gasometer image using mobile device camera, transmits the image to a cloud server on top of private LTE network, and analyzes the image to extract character information of device ID and gas usage amount by selective optical character recognition based on deep learning technology. In general, there are many types of character in an image and optical character recognition technology extracts all character information in an image. But some applications need to ignore non-of-interest types of character and only have to focus on some specific types of characters. For an example of the application, automatic gasometer reading system only need to extract device ID and gas usage amount character information from gasometer images to send bill to users. Non-of-interest character strings, such as device type, manufacturer, manufacturing date, specification and etc., are not valuable information to the application. Thus, the application have to analyze point of interest region and specific types of characters to extract valuable information only. We adopted CNN (Convolutional Neural Network) based object detection and CRNN (Convolutional Recurrent Neural Network) technology for selective optical character recognition which only analyze point of interest region for selective character information extraction. We build up 3 neural networks for the application system. The first is a convolutional neural network which detects point of interest region of gas usage amount and device ID information character strings, the second is another convolutional neural network which transforms spatial information of point of interest region to spatial sequential feature vectors, and the third is bi-directional long short term memory network which converts spatial sequential information to character strings using time-series analysis mapping from feature vectors to character strings. In this research, point of interest character strings are device ID and gas usage amount. Device ID consists of 12 arabic character strings and gas usage amount consists of 4 ~ 5 arabic character strings. All system components are implemented in Amazon Web Service Cloud with Intel Zeon E5-2686 v4 CPU and NVidia TESLA V100 GPU. The system architecture adopts master-lave processing structure for efficient and fast parallel processing coping with about 700,000 requests per day. Mobile device captures gasometer image and transmits to master process in AWS cloud. Master process runs on Intel Zeon CPU and pushes reading request from mobile device to an input queue with FIFO (First In First Out) structure. Slave process consists of 3 types of deep neural networks which conduct character recognition process and runs on NVidia GPU module. Slave process is always polling the input queue to get recognition request. If there are some requests from master process in the input queue, slave process converts the image in the input queue to device ID character string, gas usage amount character string and position information of the strings, returns the information to output queue, and switch to idle mode to poll the input queue. Master process gets final information form the output queue and delivers the information to the mobile device. We used total 27,120 gasometer images for training, validation and testing of 3 types of deep neural network. 22,985 images were used for training and validation, 4,135 images were used for testing. We randomly splitted 22,985 images with 8:2 ratio for training and validation respectively for each training epoch. 4,135 test image were categorized into 5 types (Normal, noise, reflex, scale and slant). Normal data is clean image data, noise means image with noise signal, relfex means image with light reflection in gasometer region, scale means images with small object size due to long-distance capturing and slant means images which is not horizontally flat. Final character string recognition accuracies for device ID and gas usage amount of normal data are 0.960 and 0.864 respectively.

• Proceedings of the Korean Society of Dyers and Finishers Conference
• /
• 2012.03a
• /
• pp.62-62
• /
• 2012

지구온난화 및 환경오염의 영향으로 선진국을 중심으로한 환경규제가 심해지면서, 홈 텍스타일 분야에서는 세계 패션 트렌드 및 소비자 선호에 부응한 친환경 섬유소재 개발, 웰빙 시대에 적합한 기능성 및 고감성 제품개발을 통한 차별화가 요구되고 있다. 최근의 섬유산업의 동향도 인체에 무해한 천연적인 섬유소재에 많은 관심이 증대됨에 따라 개인의 건강 뿐만 아니라 환경을 생각하는 생활패턴인 친환경섬유의 개발이 새로운 트렌드로 떠오르고 있는 실정이다. 헴프는 일년생 식물로서 학명은 Cannabis sativa L.이다. 헴프섬유의 장점으로 내구성 및 내수성, 항균성 등이 우수한 것으로 보고되고 있으나 양질의 원료 확보, 세섬도 추출 기술 및 combing 기술 등의 부족으로 100% 헴프 세 번수 방적사의 제조가 어려워 주로 면섬유와의 혼합소재로 제조되어 왔다. 최근 들어, 친환경 소재로서 박테리아 성장 억제 기능을 가진 재생섬유인 Tencel 소재를 이용하여 stiff한 Hemp의 성질에 유연성을 추가하여 촉감을 개선함과 동시에, Tencel과 Hemp를 혼용함으로써 soft touch부터 harsh touch까지 혼용율에 의한 다양한 감성을 느끼게 함으로써 용도의 다양화 추구가 시도되어 왔다. Hemp의 거친 느낌을 완화시키고 Tencel의 박테리아 억제 기능과 Hemp의 항균기능, 방충, 탈취기능이 상호 보완되어 친환경적이고 위생적인 다용도 홈 인테리어 및 가구용 직물 등의 제품으로 Hemp/Tencel 복합사가 많이 사용되고 있다. 본 연구는 Hemp와 Tencel의 혼용율의 변화에 따른 복합사의 물리적 특성을 확인하기 위하여 천연복합 태번수 방적사 최적 사설계 이론을 적용하여 Hemp 섬유 혼용율에 따른 사의 물성분석을 함으로써 Hemp/Tencel 방적사 최적 공정 조건을 결정하기 위한 사설계 이론 결과와 실험결과를 비교 분석하고자 한다. 최적 천연 Hemp복합방적사 사설계의 이론화 및 사 물성 DB화 그리고 태번수 Hemp사의 물성분석 및 이들을 DB화 함으로써 가구용 직물로 많이 사용되는 친환경 Hemp 소재사의 방적성 향상을 꾀하고자 한다. 이를 위해서 제조한 방적사의 Dry heat shrinkage와 Wet heat shrinkage를 측정하여 확인하였고 인장시험기를 이용하여 Tenacity, Initial Modulus, breaking strain을 측정 분석하였다. 방적사의 표면 특성은 영상 현미경 시스템을 사용하여 ${\times}40$ 배율로 측정하여 확인하였다.

• Journal of Conservation Science
• /
• v.23
• /
• pp.81-93
• /
• 2008

The analysis of ancient DNA (aDNA) in paleogenetics has become an increasingly important subject of archaeological, anthropological, biological as well as public interest. In this study, paleogenetic analyses were carried out on the human skeletal remains from a historical cemetery site in Myeongam-ri, Asan, Korea. Archaeological records show that this particular location had been used as a habitation or mortuary site as early as the Bronze Age and up until the Joseon Dynasty. Human remains of twenty individuals out of forty-nine tombs from the Goryeo to Joseon Dynasty were selected for the analysis of this study. In order to identify the genealogy of the population and traditional burial pattern of the cemetery, we conducted comparative analyses of the hyper variable regions (HVRs) in mitochondrial DNA (mtDNA) of each sample. A number of cautious steps were taken at all experimental stages in order to avoid erroneous recombination by the segmental and modern contaminations derived from the researchers. We sequenced segmental amplicons of HVRs andassigned relevant haplogroups according to the sequence polymorphism on the basis of the known mtDNA database. The result shows that diverse haplogroups were unexpectedly present in the small population group of the Myeongam-ri site. This diversity appears to be related to the geographical conditions and archaeological properties of the Myeongam-ri site.

• Journal of Periodontal and Implant Science
• /
• v.29 no.2
• /
• pp.289-297
• /
• 1999

최근 생약 추출물의 항균, 항염효과에 관한 관심이 증대되고 있으며 이를 이용한 치주질환의 예방 및 억제효과에 관한 연구들이진행되고 있다. 이 연구의 목적은 시험관 실험을 통하여 이미 밝혀진 후박 및 대조추출물의 치주질환 원인 균에 대한 항균, 항염효과를 성견에서 인위적으로 치주질환을 일으킨 후 실험 약제의 경구투여를 통하여 질환의 진행에 미치는 영향을 알아보는 것이다. 실험동물은 생후 18개월된 비글견 6마리를 이용하였다. 상악은 제2,3 소구치 및 제4소구치에 하악은 제2, 3, 4 소구치 및 제1 대구치를 실험대상 치아로 하였으며 교정용 철사와 봉합사를 이용하여 치경부주위에 결찰하여 인위적 치주질환을 일으켰다. 염증 유발 8주 후에 결찰을 풀고 실험동물을 아무 것도 투여하지 않은 군(음성대조군, 3마리), 후박 및 대조 추출혼합물 투여군(실험군, 3마리)으로 나누었다. 실험 시작 (-8주), 약제 투여 시작(0주), 투여 후 2, 4, 6, 8주째에 치태지수, 치은지수, Florida Probe를 이용한 치주낭깊이 및 치은열구액 등의 임상지수를 측정하였다. 염증유발 8주동안에 치태지수, 치은지수, 치주낭깊이, 치은열구액은 급속히 증가하였다. 결찰은 제거하고, 약제를 투여한 이후 실험군에서 치은지수, 치주낭깊이, 치은열구액은 가장 높은 값을 나타내고 있었다. 실험군에서는 8주가 될때까지 임상지수 수치가 낮아지고 있었으며, 8주째에는 대부분의 지수에서 음성대조군과 유의성 있는 차이를 보이고 있었다. 양성대조군에서 비해서 실험군은 대부분의 경우에 임상지수가 나이지고 있었지만 6주 또는 8주째의 치은지수, 치주낭깊이 중 일부만을 제외하고는 유의성 있는 차이를 보이지는 않았다. 이 연구결과 후박 및 대조 추출혼합물이 in vitro뿐만 아니라 in vivo 상태에서도 치주염의 치료 및 골재생의 효과가 있음을 알 수 있었으며, 이와 같은 동물실험의 결과를 바탕으로 임상시험을 거쳐 향후 사람에게 유용한 치주염치료제로 개발, 사용될 수 있을 것으로 여겨진다.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.57-71
• /
• 2013

Over a billion people in the world generate new news minute by minute. People forecasts some news but most news are from unexpected events such as natural disasters, accidents, crimes. People spend much time to watch a huge amount of news delivered from many media because they want to understand what is happening now, to predict what might happen in the near future, and to share and discuss on the news. People make better daily decisions through watching and obtaining useful information from news they saw. However, it is difficult that people choose news suitable to them and obtain useful information from the news because there are so many news media such as portal sites, broadcasters, and most news articles consist of gossipy news and breaking news. User interest changes over time and many people have no interest in outdated news. From this fact, applying users' recent interest to personalized news service is also required in news service. It means that personalized news service should dynamically manage user profiles. In this paper, a content-based news recommendation system is proposed to provide the personalized news service. For a personalized service, user's personal information is requisitely required. Social network service is used to extract user information for personalization service. The proposed system constructs dynamic user profile based on recent user information of Facebook, which is one of social network services. User information contains personal information, recent articles, and Facebook Page information. Facebook Pages are used for businesses, organizations and brands to share their contents and connect with people. Facebook users can add Facebook Page to specify their interest in the Page. The proposed system uses this Page information to create user profile, and to match user preferences to news topics. However, some Pages are not directly matched to news topic because Page deals with individual objects and do not provide topic information suitable to news. Freebase, which is a large collaborative database of well-known people, places, things, is used to match Page to news topic by using hierarchy information of its objects. By using recent Page information and articles of Facebook users, the proposed systems can own dynamic user profile. The generated user profile is used to measure user preferences on news. To generate news profile, news category predefined by news media is used and keywords of news articles are extracted after analysis of news contents including title, category, and scripts. TF-IDF technique, which reflects how important a word is to a document in a corpus, is used to identify keywords of each news article. For user profile and news profile, same format is used to efficiently measure similarity between user preferences and news. The proposed system calculates all similarity values between user profiles and news profiles. Existing methods of similarity calculation in vector space model do not cover synonym, hypernym and hyponym because they only handle given words in vector space model. The proposed system applies WordNet to similarity calculation to overcome the limitation. Top-N news articles, which have high similarity value for a target user, are recommended to the user. To evaluate the proposed news recommendation system, user profiles are generated using Facebook account with participants consent, and we implement a Web crawler to extract news information from PBS, which is non-profit public broadcasting television network in the United States, and construct news profiles. We compare the performance of the proposed method with that of benchmark algorithms. One is a traditional method based on TF-IDF. Another is 6Sub-Vectors method that divides the points to get keywords into six parts. Experimental results demonstrate that the proposed system provide useful news to users by applying user's social network information and WordNet functions, in terms of prediction error of recommended news.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.2
• /
• pp.142-149
• /
• 2004

It is important to retrieve exact information coinciding with user's need from lots of Usenet news and filter desired information quickly. Differently from email system, we must previously register our interesting news group if we want to get the news information. However, it is not easy for a novice to decide which news group is relevant to his or her interests. In this work, we present a service classifying user preferred news groups among various news groups by the use of Kohonen network. We first extract candidate terms from example documents and then choose a number of representative keywords to be used in Kohonen network from them through fuzzy inference. From the observation of training patterns, we could find the sparsity problem that lots of keywords in training patterns are empty. Thus, a new method to train neural network through reduction of unnecessary dimensions by the statistical coefficient of determination is proposed in this paper. Experimental results show that the proposed method is superior to the method using every dimension in terms of cluster overlap defined by using within cluster distance and between cluster distance.