• Title/Summary/Keyword: 단어 인식

Search Result 926, Processing Time 0.025 seconds

Usability Analysis of Structured Abstracts in Journal Articles for Document Clustering (문서 클러스터링을 위한 학술지 논문의 구조적 초록 활용성 연구)

  • Choi, Sang-Hee;Lee, Jae-Yun
    • Journal of the Korean Society for information Management
    • /
    • v.29 no.1
    • /
    • pp.331-349
    • /
    • 2012
  • Structured abstracts have been regarded as an essential information factor to represent topics of journal articles. This study aims to provide an unconventional view to utilize structured abstracts with the analysis on sub fields of a structured abstract in depth. In this study, a structured abstract was segmented into four fields, namely, purpose, design, findings, and values/implications. Each field was compared in the performance analysis of document clustering. In result, the purpose statement of an abstract affected on the performance of journal article clustering more than any other fields. Furthermore, certain types of keywords were identified to be excluded in the document clustering to improve clustering performance, especially by Within group average clustering method. These keywords had stronger relationship to a specific abstract field such as research design than the topic of an article.

Analysis and Recognition of Depressive Emotion through NLP and Machine Learning (자연어처리와 기계학습을 통한 우울 감정 분석과 인식)

  • Kim, Kyuri;Moon, Jihyun;Oh, Uran
    • The Journal of the Convergence on Culture Technology
    • /
    • v.6 no.2
    • /
    • pp.449-454
    • /
    • 2020
  • This paper proposes a machine learning-based emotion analysis system that detects a user's depression through their SNS posts. We first made a list of keywords related to depression in Korean, then used these to create a training data by crawling Twitter data - 1,297 positive and 1,032 negative tweets in total. Lastly, to identify the best machine learning model for text-based depression detection purposes, we compared RNN, LSTM, and GRU in terms of performance. Our experiment results verified that the GRU model had the accuracy of 92.2%, which is 2~4% higher than other models. We expect that the finding of this paper can be used to prevent depression by analyzing the users' SNS posts.

Design of Integration Process for JIT System in Construction Schedule Management (건설 공정관리에서의 적시생산을 위한 통합 프로세스 설계)

  • Jin You-Na;Lee Sang-Beom
    • Korean Journal of Construction Engineering and Management
    • /
    • v.5 no.5 s.21
    • /
    • pp.117-125
    • /
    • 2004
  • Recently, the word 'outsourcing' is used frequently in the corporation circumstance. Continuous recession with IMF caused restructuring measures which made unnecessary organization be downsized, and offered opportunity to breakup structure of $^{\circ}A$EHigh cost and Low efficiency, which is inefficient and uneconomic production method' in our corporation. Due to the effect of such circumstance change, the construction industry have already introduced and implemented outsourcing in many parts. For successful outsourcing in the construction industry, close relation and mutual cooperation should be preceded and JIT system is needed to improve the relation. In this study, the importance and proportion in which outsourcing is occupied in the construction industry are recognized, and the method for improving the productivity is suggested through evaluating the factors and usefulness of JIT system which can be applied to the construction industry.

Character Segmentation on Printed Korean Document Images Using a Simplification of Projection Profiles (투영 프로파일의 간략화 방법을 이용한 인쇄체 한글 문서 영상에서의 문자 분할)

  • Park Sang-Cheol;Kim Soo-Hyung
    • The KIPS Transactions:PartB
    • /
    • v.13B no.2 s.105
    • /
    • pp.89-96
    • /
    • 2006
  • In this paper, we propose two approaches for the character segmentation on Korean document images. One is an improved version of a projection profile-based algorithm. It involves estimating the number of characters, obtaining the split points and then searching for each character's boundary, and selecting the best segmentation result. The other is developed for low quality document images where adjacent characters are connected. In this case, parts of the projection profile are cut to resolve the connection between the characters. This is called ${\alpha}$-cut. Afterwards, the revised former segmentation procedure is conducted. The two approaches have been tested with 43,572 low-quality Korean word images punted in various font styles. The segmentation accuracies of the former and the latter are 91.81% and 99.57%, respectively. This result shows that the proposed algorithm using a ${\alpha}$-cut is effective for low-quality Korean document images.

Video Compression Standard Prediction using Attention-based Bidirectional LSTM (어텐션 알고리듬 기반 양방향성 LSTM을 이용한 동영상의 압축 표준 예측)

  • Kim, Sangmin;Park, Bumjun;Jeong, Jechang
    • Journal of Broadcast Engineering
    • /
    • v.24 no.5
    • /
    • pp.870-878
    • /
    • 2019
  • In this paper, we propose an Attention-based BLSTM for predicting the video compression standard of a video. Recently, in NLP, many researches have been studied to predict the next word of sentences, classify and translate sentences by their semantics using the structure of RNN, and they were commercialized as chatbots, AI speakers and translator applications, etc. LSTM is designed to solve the gradient vanishing problem in RNN, and is used in NLP. The proposed algorithm makes video compression standard prediction possible by applying BLSTM and Attention algorithm which focuses on the most important word in a sentence to a bitstream of a video, not an sentence of a natural language.

Analysis of changes in artificial intelligence image of elementary school students applying cognitive modeling-based artificial intelligence education program (인지 모델링기반 인공지능 교육 프로그램을 적용한 초등학생의 인공지능 이미지 변화 분석)

  • Kim, Tae-ryeong;Han, Sun-gwan
    • Journal of The Korean Association of Information Education
    • /
    • v.24 no.6
    • /
    • pp.573-584
    • /
    • 2020
  • This study is about the development of AI algorithm education program using cognition modeling to positively improve students' image on AI. First, we analyzed the concept of user-based collaborative filtering and developed the education program using the cognition modeling method. We checked the adequacy of program through the expert validity test. Both CVR values for the content development method of cognitive modeling and the developed program showed validity above .80. We applied the developed program to elementary school students in class. The test was conducted using a semantic discrimination to examine changes in students' perception of artificial intelligence before and after. We were able to confirm that the students' AI images were significant positive change in 12 of the 23 words in the adjective pair.

A Study on Change in Domestic Eco-friendly Consumption Issues - Applying LDA Topic Modeling Analysis - (친환경 소비 이슈 변화에 관한 연구 - LDA 토픽모델링 분석을 적용하여 -)

  • Song, Eugene;Kwon, Seol-A
    • The Journal of the Korea Contents Association
    • /
    • v.22 no.6
    • /
    • pp.45-55
    • /
    • 2022
  • This study explores the issues of "eco-friendly consumption" through online media posts, and aims to identify changes in it. Total 6,812 blog posts on Naver, that included the words "eco-friendly consumption" and "eco-friendly lifestyle," published between 2005 and 2020, in five-year intervals, were analyzed. The results illustrated that consumption issues began with the identification of the causes of environmental problems however, "eco-friendly consumption" gradually gained importance, until it developed into preparing standards and alternatives for proper "eco-friendly consumption." In 2020, "eco-friendly consumption" values and ideal consumption practices were expanded into social movements. However, there is relatively little discussion on controlled and modest spending. Therefore, for the future direction of "eco-friendly consumption," it is necessary to thoroughly examine and highlight the agenda of controlled and modest living from a higher perspective.

Analysis of Research Trends in Social Responsibility Education of Chinese University Students (중국 대학생 사회적책임 교육 연구동향 분석)

  • ZHAI, LIXIA;Park, Changun
    • Journal of the International Relations & Interdisciplinary Education
    • /
    • v.2 no.1
    • /
    • pp.15-28
    • /
    • 2022
  • College students' perception of social responsibility is directly related to the development of the country. With the development of society, the social responsibility of university students is becoming more important, so research on it is being actively conducted in China. In order to understand the current research status of social responsibility education for Chinese university students, this study analyzed the research trends of the top 22 language networks among the key words that appeared in related studies from January 2015 to December 2021. As a result, many key words such as college student social responsibility (563), social responsibility education (340 times), college students (191), social responsibility (197 times), and responsibility (133 times) appeared a lot. In the case of connection centrality, the connection centrality of social responsibility education, college student social responsibility, college students, and social responsibility was high. In the case of proximity centrality, the proximity centrality of college students' social responsibility, social responsibility education, college students, and social responsibility was high.

Forming and Changing the Concept of 'Cultural Property' before the Enactment of the Cultural Heritage Protection Act (문화재보호법 제정 이전 '문화재' 개념의 형성과 변화)

  • OH Chunyoung
    • Korean Journal of Heritage: History & Science
    • /
    • v.56 no.4
    • /
    • pp.288-318
    • /
    • 2023
  • This work began with the aim of examining the history of the concept "cultural property" that is expected to disappear, and the main subject of research was the history that preceded the spread of this notion throughout society. The phrase "cultural property" first appeared in the 1920s, and was used in various fields such as literature, history, music, and philosophy in the context of cultural resources. Until immediately following liberation from the Japanese colonial era, the meaning of cultural assets was widely applied in the range of "cultural resources," and during this period, it was often used to help supplant the reality and history of Japanese occupation. Immediately after the Korean War, it was also employed for the purpose of 'restoration of cultural resources through war'. Recognition of cultural property directly influenced by Japan's Cultural Heritage Protection Act has occurred since 1950s. In the early 1960s, the enactment of various laws related to cultural properties and the establishment of the Cultural Heritage Administration caused the meaning of cultural property to be limited to 'cultural heritage'. In this way, the definition of state-led cultural property has continued to apply to this day. It has not been clearly confirmed whether the concept of cultural properties was imported from Japan through means such as the Cultural Heritage Protection Act. Cases in which several Japanese students endorsed the concept of cultural property within Korea serve to increase the likelihood that the concept was indeed imported from Japan. However, "coined language using multiple Chinese characters," "the phenomenon of cultural complex words in the 1920s,", and "cases of non-Japanese international students using the concept of cultural property" also open up the possibility of their own occurrence. Apart from the general importance of the concept of cultural property, intellectuals at the time used this concept to promote internal development and the overcoming of colonial Joseon. In this research, it was confirmed that the conceptual word cultural property was older and had a wider history than the general perception had indicated previously. The history of the conceptual term "cultural property" may appear to be more than 60 years old based on the enactment of the Cultural Heritage Protection Act, but in fact it is nearly 100 years old when traced back to on 1925, as established here. In general, the creation and disappearance of terms may proceed naturally with social change, but such terms may alternatively be created or erased through national policy. Identifying the origins of a phrase that is about to disappear represents a significant task for purposes of establishing its historical meaning.

An Analysis on Elementary Pre-service Teachers' Perception of Science Using the Photo-narrative Method (포토 내러티브 방법을 이용한 초등 예비교사들의 과학에 대한 인식 분석)

  • Lim, Sung-man
    • Journal of the Korean Society of Earth Science Education
    • /
    • v.13 no.2
    • /
    • pp.134-146
    • /
    • 2020
  • The purpose of this study is to examine how elementary pre-service teachers have a perception of 'science'. Especially, this study used photo-narrative method to analysis pre-service teachers' perception of 'science'. Photo-narrative is a way of describing what a study participant wants to say by taking a picture. Participants were 66 elementary pre-service teachers. The results of this study were as follows: First, elementary pre-service teachers used many words such as people, life, everyday as well as scientific terms such as phenomena and principles to explain science. Secondly, the pictures used by elementary pre-service teachers to explain science included household goods, natural phenomena, advanced devices, and living things. Third, elementary pre-service teachers explained science with knowledge of science, knowledge, convenience, and nature of science. As a result of this study, it was found that elementary pre-service teachers recognized that science is closely related to life and that it is necessary for learning. The results of this study can contribute not only to curriculum composition and curriculum content of elementary and middle school science education but also to curriculum development for teacher training.