• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1925-1934
• /
• 2022

Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.792-799
• /
• 2022

Building Information Modeling (BIM) technology is a key component of modern construction engineering and project management workflows. As-is BIM models that represent the spatial reality of a project site can offer crucial information to stakeholders for construction progress monitoring, error checking, and building maintenance purposes. Geometric methods for automatically converting raw scan data into BIM models (Scan-to-BIM) often fail to make use of higher-level semantic information in the data. Whereas, semantic segmentation methods only output labels at the point level without creating object level models that is necessary for BIM. To address these issues, this research proposes a hybrid semantic-geometric approach for clutter-resistant floorplan generation from laser-scanned building point clouds. The input point clouds are first pre-processed by normalizing the coordinate system and removing outliers. Then, a semantic segmentation network based on PointNet++ is used to label each point as ceiling, floor, wall, door, stair, and clutter. The clutter points are removed whereas the wall, door, and stair points are used for 2D floorplan generation. A region-growing segmentation algorithm paired with geometric reasoning rules is applied to group the points together into individual building elements. Finally, a 2-fold Random Sample Consensus (RANSAC) algorithm is applied to parameterize the building elements into 2D lines which are used to create the output floorplan. The proposed method is evaluated using the metrics of precision, recall, Intersection-over-Union (IOU), Betti error, and warping error.

• Culinary science and hospitality research
• /
• v.24 no.3
• /
• pp.167-176
• /
• 2018

In this study, Big Data was used to collect the information related to 'Cooking Academy' keywords. After collecting all the data, we calculated the frequency through the text mining and selected the main words for future data analysis. Data collection was conducted from Google Web and News during the period from January 1, 2013 to December 31, 2017. The selected 64 words were analyzed by using UCINET 6.0 program, and the analysis results were visualized with NetDraw in order to present the relationship of main words. As a result, it was found that the most important goal for the students from cooking school is to work as a cook, likewise to have practical classes. In addition, we obtained the result that SNS marketing system that the social sites, such as Facebook, Twitter, and Instagram are actively utilized as a marketing strategy of the institute. Therefore, the results can be helpful in searching for the method of utilizing big data and can bring brand-new ideas for the follow-up studies. In practical terms, it will be remarkable material about the future marketing directions and various programs that are improved by the detailed curriculums through semantic network of cooking school by using big data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.2
• /
• pp.347-354
• /
• 2013

In this paper, we propose a enhancing document clustering method using term re-weighting by the expanded term. The proposed method extracts the important terms of documents in cluster using semantic features, which it can well represent the topics of document to expand term using WordNet. Besides, the method can improve the performance of document clustering using re-weighting terms based on the expanded terms. The experimental results demonstrate appling the proposed method to document clustering methods achieves better performance than the normal document clustering methods.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.6
• /
• pp.737-744
• /
• 2004

Retrieving relevant information well corresponding to the user`s request from web is a crucial task of search engines. However, most of conventional search engines based on pattern matching schemes to queries have a limitation that is not easy to provide results corresponding to the user`s request due to the uncertainty of queries. To overcome the limitation in this paper, we propose a framework for knowledge-based semantic meta-search engines with the following five processes: (i) Query formation, (ii) Query expansion, (iii) Searching, (iv) Ranking recreation, and (v) Knowledge base. From simulation results on english-based web documents, we can see that the Proposed knowledge-based semantic meta-search engine provides more correct and better searching results than those obtained by using the Google.

• Language and Information
• /
• v.10 no.1
• /
• pp.47-69
• /
• 2006

Recently, there has been a surge of interests concerning the construction and utilization of a Korean thesaurus. In this paper, a semi-automatic method for generating a lexical-semantic network of Korean '-ha' verbs is presented through an analysis of the lexical definitions of these verbs. Initially, through the use of several tools that can filter out and coordinate lexical data, pairs constituting a word and a definition were prepared for treatment in a subsequent step. While inspecting the various definitions of each verb, we extracted and coordinated the head words from the sentences that constitute the definition of each word. These words are thought to be the main conceptual words that represent the sense of the current verb. Using these head words and related information, this paper shows that the creation of a thesaurus could be achieved without any difficulty in a semi-automatic fashion.

• Culinary science and hospitality research
• /
• v.23 no.3
• /
• pp.257-270
• /
• 2017

The purpose of this study was to visualize the semantic network with big data related to food exhibition at convention center. For this, this study collected data containing 'coex food exhibition/bexco food exhibition' keywords from web pages and news on Google during one year from January 1 to December 31, 2016. Data were collected by using TEXTOM, a data collecting and processing program. From those data, degree centrality, closeness centrality, betweenness centrality and eigenvector centrality were analyzed by utilizing packaged NetDraw along with UCINET 6. The result showed that the web visibility of hospitality and destinations was high. In addition, the web visibility was also high for convention center programs, such as festival, exhibition, k-pop and event; hospitality related words, such as tourists, service, hotel, cruise, cuisine, travel. Convergence of iterated correlations showed 4 clustered named "Coex", "Bexco", "Nations" and "Hospitality". It is expected that this diagnosis on food exhibition at convention center according to changes in domestic environment by using these web information will be a foundation of baseline data useful for establishing convention marketing strategies.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.5
• /
• pp.1019-1035
• /
• 2020

This study examines the millennial generation, who express themselves and share information on social media after experiencing constantly changing 'hot places' (places of interest) in contemporary cities, with the goal of analyzing space consumption behaviors. Data were collected via an Instagram crawler application developed with Python 3.4 administered to 19,262 posts using the term 'hot places' from November 1 and December 15, 2019. Issues were derived from a text mining technique using Textom 2.0; in addition, semantic network analysis using Ucinet6 and the NetDraw program were also conducted. The results are as follows. First, a frequency analysis of keywords for hot places indicated words frequently found in nouns were related to food, local names, SNS and timing. Words related to positive emotions felt in experience, and words related to behavior in hot places appeared in predicate. Based on importance, communication is the most important keyword and influenced all issues. Second, the results of visualization of semantic network analysis revealed four categories in the scope of the definition of "hot place": (1) culinary exploration, (2) atmosphere of cafés, (3) happy daily life of 'me' expressed in images, (4) emotional photos.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2458-2482
• /
• 2023

Medical image segmentation techniques based on convolution neural networks indulge in feature extraction triggering redundancy of parameters and unsatisfactory target localization, which outcomes in less accurate segmentation results to assist doctors in diagnosis. In this paper, we propose a multi-level semantic-rich encoding-decoding network, which consists of a Pooling-Conv-Former (PCFormer) module and a Cbam-Dilated-Transformer (CDT) module. In the PCFormer module, it is used to tackle the issue of parameter explosion in the conservative transformer and to compensate for the feature loss in the down-sampling process. In the CDT module, the Cbam attention module is adopted to highlight the feature regions by blending the intersection of attention mechanisms implicitly, and the Dilated convolution-Concat (DCC) module is designed as a parallel concatenation of multiple atrous convolution blocks to display the expanded perceptual field explicitly. In addition, MultiHead Attention-DwConv-Transformer (MDTransformer) module is utilized to evidently distinguish the target region from the background region. Extensive experiments on medical image segmentation from Glas, SIIM-ACR, ISIC and LGG demonstrated that our proposed network outperforms existing advanced methods in terms of both objective evaluation and subjective visual performance.

• 한국디지털정책학회:학술대회논문집
• /
• 2004.11a
• /
• pp.111-127
• /
• 2004

In this paper we describe an application of the lexical resource JurWordNet and of the Core Legal Ontology as a descriptive vocabulary for modeling legal domains. It can be viewed as the semantic component of a global standardisation framework for digital governments. A content description model provides a repository of structured knowledge aimed at supporting the semantic interoperability between sectors of Public Administration and the communication processes towards citizen. Specific conceptual models built from this base will act as a cognitive interface able to cope with specific digital government issues and to improve the interaction between citizen and Public Bodies. As a Case study, the representation of the click-on licences for re-using Public Sector Information is presented.