• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.4
• /
• pp.71-79
• /
• 2019

By using convolutional neural networks (CNNs) based on semantic segmentation, road surface damage detection has being studied. In order to generate the CNN model, it is essential to collect the input and the corresponding labeled images. Unfortunately, such collecting pairs of the dataset requires a great deal of time and costs. In this paper, we proposed a road surface damage detection technique based on semi-supervised learning using pseudo labels to mitigate such problem. The model is updated by properly mixing labeled and unlabeled datasets, and compares the performance against existing model using only labeled dataset. As a subjective result, it was confirmed that the recall was slightly degraded, but the precision was considerably improved. In addition, the $F_1-score$ was also evaluated as a high value.

• Journal of the Korean Society for Library and Information Science
• /
• v.53 no.3
• /
• pp.247-271
• /
• 2019

Uncertainty in scientific knowledge means an uncertain state where propositions are neither true or false at present. The existing studies have analyzed the propositions written in the academic literature, and have conducted the performance evaluation based on the rule based and machine learning based approaches by using the corpus. Although they recognized that the importance of word construction, there are insufficient attempts to expand the word by analyzing the meaning of uncertainty words. On the other hand, studies for analyzing the structure of networks by using bibliometrics and text mining techniques are widely used as methods for understanding intellectual structure and relationship in various disciplines. Therefore, in this study, semantic relations were analyzed by applying Word2Vec to existing uncertainty words. In addition, WordNet, which is an English vocabulary database and thesaurus, was applied to perform a network analysis based on hypernyms, hyponyms, and synonyms relations linked to uncertainty words. The semantic and lexical relationships of uncertainty words were structurally identified. As a result, we identified the possibility of automatically expanding uncertainty words.

• The Research Journal of the Costume Culture
• /
• v.27 no.3
• /
• pp.193-205
• /
• 2019

A trend analysis of research articles in a field of knowledge is significant because it can help in finding out the structural characteristics of the field and the future direction of research through observing change in a time series. We identified the structural characteristics and trends in text data (keywords) gathered from research articles which in itself is an important task in various research areas. The titles and keywords were crawled from research articles published from 2016 to 2018 in the Research Journal of the Costume Culture (RJCC), one of the representative Korean journal in the field of clothing and textile. After we extracted data comprising English titles and keywords from 195 published articles, we transformed it into a 1-mode matrix. We used measures from network analysis (i.e., link, strength, and degree centrality) for evaluating meaningful patterns and trends in the research on clothing and textile. NodeXL was used for visualizing the semantic network. This study observed change in the clothing and textile research trend. In addition to covering the core areas of the field, the subjects of research have been diversifying with every passing year and have evolved onto a developmental direction. The most studied area in articles published by the RJCC was fashion retailing/consumer psychology while aesthetic/historic and fashion industry/policy studies were covered to a more limited extent. We observed that most of the studies reflecting the identity of RJCC share subject keywords to a significant extent.

• Journal of Digital Convergence
• /
• v.19 no.11
• /
• pp.1-10
• /
• 2021

This paper aimed to look at the awareness of foreign workers in social platforms by using text mining, one of the big data techniques and draw suggestions for foreign workers. To achieve this purpose, data collection was conducted with search keyword 'Foreign Worker' from Jan. 1, to Dec. 31, 2020, and frequency analysis, TF-IDF analysis, and degree centrality analysis and 100 parent keywords were drawn for comparison. Furthermore, Ucinet6.0 and Netdraw were used to analyze semantic networks, and through CONCOR analysis, data were clustered into the following eight groups: foreigner policy issue, regional community issue, business owner's perspective issue, employment issue, working environment issue, legal issue, immigration issue, and human rights issue. Based on such analyzed results, it identified national awareness of foreign workers and main issues and provided the basic data on policy proposals for foreign workers and related researches.

• The KIPS Transactions:PartB
• /
• v.14B no.1 s.111
• /
• pp.51-58
• /
• 2007

This paper suggests prototype of dialog system combining VXML(VoiceXML) that is the W3C's standard XML format for specifying interactive voice dialogues between human and computer, and RSS(RDF Site Summary or Really Simple Syndication) that is representative technology of semantic web for syndication and subscription of updated web-contents. Merits of the proposed system are as following: 1) It is a new method that recognize spoken contents using ire and wireless telephone networks and then provide contents to user via STT(Speech-to-Text) and TTS(Text-to-Speech) instead of traditional method using web only. 2) It can apply advantage of RSS that subscription of updated contents is converted to VXML without modifying traditional method to provide RSS service, 3) In terms of users, it can reduce restriction on time-spate in search of contents that is provided by RSS because it uses ire and wireless telephone networks, not internet environment. 4) In terms of information provider, it does not need special component for syndication of the newest contents using speech recognition and synthesis technology. We implemented a news service system using VXML and RSS for performance evaluation of the proposed system. In experiment results, we estimated the response time and the speech recognition rate in subscription and search of actuality contents, and confirmed that the proposed system can provide contents those are provided using RSS Feed.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.1
• /
• pp.23-33
• /
• 2020

Recently, high-resolution images can be easily acquired using UAV (Unmanned Aerial Vehicle), so that it is possible to produce small area observation and spatial information at low cost. In particular, research on the generation of cover maps in crop production areas is being actively conducted for monitoring the agricultural environment. As a result of comparing classification performance by applying RF(Random Forest), SVM(Support Vector Machine) and CNN(Convolutional Neural Network), deep learning classification method has many advantages in image classification. In particular, land cover classification using satellite images has the advantage of accuracy and time of classification using satellite image data set and pre-trained parameters. However, UAV images have different characteristics such as satellite images and spatial resolution, which makes it difficult to apply them. In order to solve this problem, we conducted a study on the application of deep learning algorithms that can be used for analyzing agricultural lands where UAV data sets and small-scale composite cover exist in Korea. In this study, we applied DeepLab V3 +, FC-DenseNet (Fully Convolutional DenseNets) and FRRN-B (Full-Resolution Residual Networks), the semantic image classification of the state-of-art algorithm, to UAV data set. As a result, DeepLab V3 + and FC-DenseNet have an overall accuracy of 97% and a Kappa coefficient of 0.92, which is higher than the conventional classification. The applicability of the cover classification using UAV images of small areas is shown.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.42 no.2
• /
• pp.65-76
• /
• 2014

Green Infrastructure(GI) is suggested to recover urban water circulation system as a newly conceptual alternative methodology by Korean landscape field in recent years. In this context, the study considers the essential meaning of GI. The methodology of this study is literature review with 47 published papers which were peer-reviewed in international journals in the recent 5 years. These papers were collected from online database and academic archives. The main analysis targets are definition sentences about GI. The each sentences were interpreted by semantic structure between verbs and objects in the definition sentences. As the results, it figured out 5 aims('Provide', 'Improve', 'Produce', 'Conserve', 'Reduce'), 4 objects('Humanistic', 'Environmental', 'Ecological', 'Hydrological') and 3 spaces('Object space', 'Technically available spaces', 'Object or technically available spaces'). The '5 aims' connected with the elements of '4 objects' based on the '3 spaces'. The elements was connected to the '5 aims' via single form or 2~3 forms of the essential meaning networks of GI. The study provides 83 meaning networks to use landscape architecture planning and urban planning.

• Korean journal of communication and information
• /
• v.45
• /
• pp.220-254
• /
• 2009

Presidential TV debates serve as an important instrument for the general viewers to evaluate the candidates’ character, to examine their policy, and finally to make an important political decisions to cast ballots. Every words candidates utter in the course of entire election campaign exert influence of a certain significance by delivering their ideas and by creating clashes with their respective opponents. This study focuses on the conceptual venue, coined as ‘stasis’ by ancient rhetoricians, in which the clashes take place, and examines the words selection made by each candidates, the manners in which they form stasis, call for evidence, educate the public, and finally create a legitimate form of political argumentation. The study applied computer based content analysis using KrKwic and UCINET software to analyze semantic networks among the candidates. The results showed three major candidates, namely Lee Myung Bak, Jung Dong Young, and Lee Hoi Chang, displayed separate patterns in their use of language, by selecting the words that are often neglected by their opponents. Apparently, the absence of stasis and the lack of speaking mutual language significantly undermined the effects of debates. Central questions regarding issues of North Korea failed to meet basic requirements, and the respondents failed to engage in effective argumentation process.

• Journal of The Korean Association For Science Education
• /
• v.35 no.6
• /
• pp.997-1006
• /
• 2015

Perception of the experiment is one of the most important factors of students' understanding of scientific inquiry and the nature of science. This study examined the perception of middle and high school students of the meaning of 'experiment' in the biological sciences. Semantic network analysis (SNA) was especially used to visualize students' perception structure in this study. One hundred and ninety middle school students and 200 high school students participated in this study. Students responded to two questions on the meaning of 'experiment' in science and biology. This study constructed four semantic networks based on the collected response. As a result, middle school students about the 'experiment' in science are 'we', 'direct', 'principle' of such words was aware of the experiments from the center to the active side. The high school students' 'theory', 'true', 'information' were recognized as an experiment that explores the process of creating a knowledge center including the word. In addition, middle school students relative to 'experiment' of the creature around the 'dissection', 'body', high school students were recognized as 'life', 'observation' observation activities dealing with the living organisms and recognized as a core. The results of this study will be used as important evidence in the future to map out an experiment in biological science curriculum.

• Korean Journal of Cognitive Science
• /
• v.19 no.2
• /
• pp.143-161
• /
• 2008

The goal of this paper is to extract the hyponymy relation between words in the corpus. Adopting the basic algorithm of Hearst (1992), I propose a method of pattern-based extraction of semantic relations from the corpus. To this end, I set up a list of hypernym-hyponym pairs from Sejong Electronic Dictionary. This list is supplemented with the superordinate-subordinate terms of CoroNet. Then, I extracted all the sentences from the corpus that include hypemym-hyponym pairs of the list. From these extracted sentences, I collected all the sentences that contain meaningful constructions that occur systematically in the corpus. As a result, we could obtain 21 generalized patterns. Using the PERL program, we collected sentences of each of the 21 patterns. 57% of the sentences are turned out to have hyponymy relation. The proposed method in this paper is simpler and more advanced than that in Cederberg and Widdows (2003), in that using a word net or an electronic dictionary is generally considered to be efficient for information retrieval. The patterns extracted by this method are helpful when we look fer appropriate documents during information retrieval, and they are used to expand the concept networks like ontologies or thesauruses. However, the word order of Korean is relatively free and it is difficult to capture various expressions of a fired pattern. In the future, we should investigate more semantic relations than hyponymy, so that we can extract various patterns from the corpus.