• Title/Summary/Keyword: Document research

Search Result 1,342, Processing Time 0.031 seconds

Impact of Word Embedding Methods on Performance of Sentiment Analysis with Machine Learning Techniques

  • Park, Hoyeon;Kim, Kyoung-jae
    • Journal of the Korea Society of Computer and Information
    • /
    • v.25 no.8
    • /
    • pp.181-188
    • /
    • 2020
  • In this study, we propose a comparative study to confirm the impact of various word embedding techniques on the performance of sentiment analysis. Sentiment analysis is one of opinion mining techniques to identify and extract subjective information from text using natural language processing and can be used to classify the sentiment of product reviews or comments. Since sentiment can be classified as either positive or negative, it can be considered one of the general classification problems. For sentiment analysis, the text must be converted into a language that can be recognized by a computer. Therefore, text such as a word or document is transformed into a vector in natural language processing called word embedding. Various techniques, such as Bag of Words, TF-IDF, and Word2Vec are used as word embedding techniques. Until now, there have not been many studies on word embedding techniques suitable for emotional analysis. In this study, among various word embedding techniques, Bag of Words, TF-IDF, and Word2Vec are used to compare and analyze the performance of movie review sentiment analysis. The research data set for this study is the IMDB data set, which is widely used in text mining. As a result, it was found that the performance of TF-IDF and Bag of Words was superior to that of Word2Vec and TF-IDF performed better than Bag of Words, but the difference was not very significant.

Differences in Breeding Bird Communities by Post-fire Restoration Methods (산불 후 복원방법의 차이가 번식기 조류 군집에 미치는 영향)

  • Kim, Jin-Yong;Lee, Eun-Jae;Choi, Chang-Yong;Lee, Woo-Shin;Lim, Joo-Hoon
    • Korean Journal of Environment and Ecology
    • /
    • v.29 no.4
    • /
    • pp.508-515
    • /
    • 2015
  • Post-fire restoration can affect breeding bird communities and species compositions over a long-term period by determining pot-fire succession, and a long-term monitoring is therefore required to understand its impacts on forest birds. This study aimed to document the effects of post-fire restoration methods on breeding bird communities in three areas: unburned and two burned (nonintervention and intervention with clear-cut logging and planting) stands 13 years after the stand-replacing Samcheok forest fire at Mt. Geombong in Samcheok, South Korea. According to 108 point counts during the breeding season from April to June 2013, we found that the number of individuals, observed bird species, and species diversity index in intervention stands with clear-cut logging and planting were lower than that in nonintervention and unburned control stands. Foraging and nesting guild analysis also showed a lower abundance of foliage searchers, timber drillers, primary cavity nesters and secondary cavity nesters in intervention stands than in the other stands, while no significant difference was detected between the nonintervention and unburned stands. These results imply that an interventional restoration method may deter the recovery of avian breeding communities after forest fires, and also suggest that non-interventional restoration methods may be an effective way to benefit the species diversity and density of breeding bird communities.

Study of the Risk of Ignition due to Internal Combustion Engines in Areas with Potentially Explosive Gas Atmospheres (잠재적 폭발위험장소에서 내연기관에 의한 점화 위험성에 관한 연구)

  • Kim, Yun Seok;Rie, Dong Ho
    • Fire Science and Engineering
    • /
    • v.30 no.5
    • /
    • pp.1-8
    • /
    • 2016
  • Safety management in hazardous areas with potentially explosive gas atmospheres (here in after referred to as hazardous areas) in large scale facilities dealing with combustible or flammable materials at home and abroad is very important (significant) for the coexistence of the company and local society based on business continuity management (BCM) and reliance. For the safety management in hazardous areas, two systems are mainly used: (1) the control system for the prevention of combustible or flammable substances and (2) the explosion proof system for the elimination of ignition sources when flammable gases are leaked to inhibit the transition to fire or explosion accidents. While technology and regulations on explosion proof facilities or devices for electrical ignition sources are well developed and defined, those for thermal ignition sources need to be more developed and established. In this study, the internal combustion engine in hazardous areas was investigated to determine the risk of ignition. For this purpose, document searches were conducted on the relevant international standards and accidents cases and risk analysis reports. In addition, this study assessed the application cases of the diesel engine's safety equipment, such as spark arresters regarding the site of process safety management (PSM) system in central Korea. To practically apply these results to the hydrocarbon industry, the safety management method for explosion prevention in hazardous areas was provided by risk identification for ignition sources of internal combustion engines, such as diesel engines.

A Study on the Development of GIS based Integrated Information System for Water Quality Management of Yeongsan River Estuary (영산강 하구역 수질환경 관리를 위한 GIS기반 통합정보시스템 개발에 관한 연구)

  • Lee, Sung Joo;Kim, Kye Hyun;Park, Young Gil;Lee, Geon Hwi;Yoo, Jea Hyun
    • Journal of Wetlands Research
    • /
    • v.16 no.1
    • /
    • pp.73-83
    • /
    • 2014
  • The government has recently carried out monitoring to attain a better understanding of the current situation and model for prediction of future events pertaining to water quality in the estuarine area of Yeongsan River. But many users have noted difficulties to understand and utilize the results because most monitoring and model data consist of figures and text. The aim of this study is to develop a GIS-based integrated information system to support the understanding of the current situation and prediction of future events about water quality in the estuarine area of Yeongsan River. To achieve this, a monitoring DB is assembled, a linkages model is defined, a GUI is composed, and the system development environment and system composition are defined. The monitoring data consisted of observation data from 2010 ~ 2012 in the estuarine area of Yeongsan River. The models used in the study are HSPF (Hydrological Simulation Program-Fortran) for simulation of the basin and EFDC (Environmental Fluid Dynamics Code) for simulation of the estuary and river. Ultimately, a GIS based system was presented for utilization and expression using monitoring and model data. The system supports prediction of the estuarine area ecological environment quantitatively and displays document type model simulation results in a map-based environment to enhance the user's spatial understanding. In future study, the system will be updated to include a decision making support system that is capable of handling estuary environment issues and support environmental assessment and development of related policies.

A Study on the Application of River Surveying by Airborne LiDAR (항공라이다의 하천측량 적용 방안 연구)

  • Choi, Byoung Gil;Na, Young Woo;Choo, Ki Hwan;Lee, Jung Il
    • Journal of Korean Society for Geospatial Information Science
    • /
    • v.22 no.2
    • /
    • pp.25-32
    • /
    • 2014
  • The river plan executes the role for prevention of disaster and protection of environment, and requires the surveying results with high accuracies for managing river, dam, reservoir which will be the major infrastructures. The purpose of this study is for comparing and analyzing the results of river surveying which is used widely for disaster management and construction industry support. The results are gathered by using LiDAR which is being used in Korea recently and by using Total station. Study area is chosen at upper area of Bukhan River which is located at Gangwon-do. Total 2 cross-sections of the two methods are extracted from the study area. The standard deviation of land part is about 0.017m which shows little difference between two methods, but the Airborne LiDAR results cannot survey the heights of the points accurately at the singular points with vertical structure and water body part. To overcome the problems through this study, there should be ways to survey the bottom river through transmission of water level within the same margin scope as land part and to survey detailed facilities used by laser exactly through continuous research and experiment. When implementation stage comes, this study expect that this document will be utilized variously for making decision in the area of planning and drawing of business and engineering not just for river regarding the major area or the area that people cannot access.

Discipline Bias of Document Citation Impact Indicators: Analyzing Articles in Korean Citation Index (논문 인용 영향력 측정 지수의 편향성에 대한 연구: KCI 수록 논문을 대상으로)

  • Lee, Jae Yun;Choi, Sanghee
    • Journal of the Korean Society for information Management
    • /
    • v.32 no.4
    • /
    • pp.205-221
    • /
    • 2015
  • The impact of a journal is commonly used as the impact of an individual paper within that journal. It is problematic to interpret a journal's impact as a single paper's impact of the journal, so there are several researches to measure a single paper's impact with its own citation counts. This study applied 8 impact indicators to Korean Citation Index database and examined discipline bias of each indicator. Analyzed indicators are simple citation counts, PageRank, f-value, CCI, c-index, single publication h-index, single publication hs-index, and cl-index. PageRank has the least discipline bias at highly ranked papers and journal bias in a discipline. On the contrary, simple citation counts showed strongly biased results toward a certain discipline or a journal. KCI database provides only simple citation counts. It needs to show PageRank (global indicator) to discover influential papers in diverse areas. Furthermore it needs to consider to provide the best of local indicators. Local indicators can be calculated only with papers in users' search results because they uses citation counts of citing papers and the number of references. They are more efficient than global indicators which explore the whole database. KCI should also consider to provide Cl-index (local indicator).

Quilitative certificational plan of heshouwu (하수오(何首烏)의 품질인증(品質認證) 방안(方案))

  • Shin, Mi-Kyung;Roh, Seong-Soo;Kil, Ki-Jeong;Seo, Bu-il;Seo, Young-Bae
    • Journal of Haehwa Medicine
    • /
    • v.13 no.2
    • /
    • pp.205-212
    • /
    • 2004
  • Now many sustitution and false articles is used in korea instead of heshouwu. To use heshouwu correctly, we will make a quilitative certificational plan of heshouwu to investigate all of lieraturea, records and documents. And we could reach conclusions as folloews. 1) Source of plant Heshouwu is a root tuber of a perennial herb Polygonum multiflorum Thunberg(Family : Polygonaceae). 2) Harvest After planting 3-5 yaers, harvesting in an autumn, washin clean the mud, a big heshouwu cut off a half or section, dry in sunny place or at a little fire. When harvesting, we harvest only a big thing, a small thing transfer a field, after culturing of 1-2 years, harvest at big roots. Harvesting is done usually in an autumn after 3 years. When collecting a seed, we must harvest a heshouwu the next year. 3) Process We must process heshouwu at the decoction of black beans, heshouwu suck in the decoction of black beans, heat with steam in an iron pot. Black beans is used every 100 kg of heshouwu. 4) Quility (1) Funstional standards It is good that weight is heavy and outer skin is yellow-brown, section surface is light red color, powdery and has a figure such as clouds in section. (2) Physicochemical standards Heshouwu expesses a various chang of components in process of working. We think that it need to add a standard of detection about 2,3,5,4'-tetrahrdroxystilbene-2-O-${\beta}$ -D-glucoside in a current authentic document which is a water-soluble component of heshouwu. It must that Dry on loss is less than 14.0%, content of ash is less than 5.0%, Content of acid-nonsoluble ash is less than 1.5%, Content of extract is more than 17.0%. A fixed quantity of 2,3,5,4'-tetrahrdroxystilbene-2-O-${\beta}$ -D-glucoside is more than 1.0%. Contens of heavy metal has to detect less than 30 ppm and there is no reminding agriculural medince.

  • PDF

A Study of e-Textbook Format Standardization Scheme for Smart Education Circumstance (스마트 교육환경을 위한 e-교과서 포맷 표준화 방안 연구)

  • Sohn, Won-Sung;Lim, Soon-Bum;Kim, Jae-Kyung
    • Journal of The Korean Association of Information Education
    • /
    • v.16 no.3
    • /
    • pp.327-336
    • /
    • 2012
  • The Korea government has recently announced "A Master Plan for Smart Education", including application of digital textbooks and composition of education system using cloud computing. Our education system in future circumstance, over the conventional e-learning methods, needs the smart education solutions which enable students to study and communicate on various types of devices. The ongoing government project related with the digital textbook has been performed as mid- and long-term goals, whereas PDF-based e-textbook project, similar to e-book model and, has been already completed for the short-term goal. For the purpose of improved future smart education circumstance, however, a specific strategy is required in the following areas: flexibility of format conversion and independency of original text sources among the multiple device platforms. Therefore, in this paper, we propose a standardization scheme for e-textbook format based on e-book structure. To do this, we survey trends in e-book technologies, and research on standardization of e-book format for digitalization of textbooks, based on the analysis of existing textbooks. Moreover, we produce an example e-book content using our proposed standard method. As a result, our approach can be applied to the future smart education circumstance, and we may say that it will be efficiently applicable to the long-term digital textbook project.

  • PDF

Change Reconciliation on XML Repetitive Data (XML 반복부 데이터의 변경 협상 방법)

  • Lee Eunjung
    • The KIPS Transactions:PartA
    • /
    • v.11A no.6
    • /
    • pp.459-468
    • /
    • 2004
  • Sharing XML trees on mobile devices has become more and more popular. Optimistic replication of XML trees for mobile devices raises the need for reconciliation of concurrently modified data. Especially for reconciling the modified tree structures, we have to compare trees by node mapping which takes O($n^2$) time. Also, using semantic based conflict resolving policy is often discussed in the literature. In this research, we focused on an efficient reconciliation method for mobile environments, using edit scripts of XML data sent from each device. To get a simple model for mobile devices, we use the XML list data sharing model, which allows inserting/deleting subtrees only for the repetitive parts of the tree, based on the document type. Also, we use keys for repetitive part subtrees, keys are unique between nodes with a same parent. This model not only guarantees that the edit action always results a valid tree but also allows a linear time reconciliation algorithm due to key based list reconciliation. The algorithm proposed in this paper takes linear time to the length of edit scripts, if we can assume that there is no insertion key conflict. Since the previous methods take a linear time to the size of the tree, the proposed method is expected to provide a more efficient reconciliation model in the mobile environment.

Primary Management Factors for Collaboration among Participants in Technical Proposal Tendering (기술제안입찰 참여자간의 협업지원을 위한 중점협업관리요소 도출)

  • Koo, Seonkeun;Lim, Susang;Yoon, Yousang;Han, Sangwon;Hyun, Changtaek
    • Korean Journal of Construction Engineering and Management
    • /
    • v.17 no.5
    • /
    • pp.3-12
    • /
    • 2016
  • Recently government is set to expand its policy to promote technical proposal tendering in a dimension of technical competitiveness reinforcement. Because a variety of complicated techniques are applied in technical proposal tendering and variables could be occurred in terms of cost, schedule, constructability and others when techniques are reflected on design document collaboration management among participants is considered insignificantly. So the research would determine primary management factors and presents management direction for collaboration among participants. First action for this is categorization of hindrance factors to collaboration into five factors as 'Poor work processing', 'Communication cap among participants', 'Lack of understanding about technical proposal tendering', 'Difficulty of decision making' and 'Insufficiency in managing the work data'. Second correlation analysis is conducted between the categorized factors and participants according to tasks in technical proposal tendering to figure out the correlation degree of variables. If there is a strong correlation between variables, hindrance factor in that case regarded primary management factor to collaboration and finally management direction is presented at each task.