• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.221-235
• /
• 2022

Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.

• Women's Health Nursing
• /
• v.29 no.2
• /
• pp.128-136
• /
• 2023

Purpose: Topic modeling is a text mining technique that extracts concepts from textual data and uncovers semantic structures and potential knowledge frameworks within context. This study aimed to identify major keywords and network structures for each major topic to discern research trends in women's health nursing published in the Korean Journal of Women Health Nursing (KJWHN) using text network analysis and topic modeling. Methods: The study targeted papers with English abstracts among 373 articles published in KJWHN from January 2011 to December 2021. Text network analysis and topic modeling were employed, and the analysis consisted of five steps: (1) data collection, (2) word extraction and refinement, (3) extraction of keywords and creation of networks, (4) network centrality analysis and key topic selection, and (5) topic modeling. Results: Six major keywords, each corresponding to a topic, were extracted through topic modeling analysis: "gynecologic neoplasms," "menopausal health," "health behavior," "infertility," "women's health in transition," and "nursing education for women." Conclusion: The latent topics from the target studies primarily focused on the health of women across all age groups. Research related to women's health is evolving with changing times and warrants further progress in the future. Future research on women's health nursing should explore various topics that reflect changes in social trends, and research methods should be diversified accordingly.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.437-438
• /
• 2023

This paper takes the Pingjiang historical and cultural district of Suzhou city as an example, collects 1439 visitor review data from Ctrip.com with the help of Python technology, and uses web text analysis to conduct research on high-frequency words, semantic networks and emotional tendencies to comprehensively assess the tourist perception of the Grand Canal heritage. The study found that: natural and humanistic landscape, historical and cultural accumulation, and the style of Jiangnan Canal are fully reflected in the tourists' perception of Pingjiang historical and cultural district; tourists hold strong positive emotion towards Pingjiang Road, however, there is still more room for renovation and improvement of the historical and cultural district. Finally, countermeasure suggestions for improving the tourist perception of the Grand Canal heritage are given in terms of protection first, cultural integration and innovative utilization.

• International journal of advanced smart convergence
• /
• v.13 no.1
• /
• pp.108-113
• /
• 2024

The purpose of this study is to analyze user perceptions of tourism platforms through big data. Data were collected from Naver, Daum, and Google as big data analysis channels. Using semantic network analysis with the keyword 'tourism platform,' a total of 29,265 words were collected. The collection period was set for two years, from August 31, 2021, to August 31, 2023. Keywords were analyzed for connected networks using TexTom and Ucinet programs for social network analysis. Keywords perceived by tourism platform users include 'travel,' 'diverse,' 'online,' 'service,' 'tourists,' 'reservation,' 'provision,' and 'region.' CONCOR analysis revealed four groups: 'platform information,' 'tourism information and products,' 'activation strategies for tourism platforms,' and 'tourism destination market.' This study aims to expand and activate services that meet the needs and preferences of users in the tourism field, as well as platforms tailored to the changing market, based on user perception, current status, and trend data on tourism platforms.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.47-64
• /
• 2021

The global spread of COVID-19 around the world has not only affected many parts of our daily life but also has a huge impact on many areas, including the economy and society. As the number of confirmed cases and deaths increases, medical staff and the public are said to be experiencing psychological problems such as anxiety, depression, and stress. The collective tragedy that accompanies the epidemic raises fear and anxiety, which is known to cause enormous disruptions to the behavior and psychological well-being of many. Long-term negative emotions can reduce people's immunity and destroy their physical balance, so it is essential to understand the psychological state of COVID-19. This study suggests a method of monitoring medial news reflecting current days which requires striving not only for physical but also for psychological quarantine in the prolonged COVID-19 situation. Moreover, it is presented how an easier method of analyzing social media networks applies to those cases. The aim of this study is to assist health policymakers in fast and complex decision-making processes. News plays a major role in setting the policy agenda. Among various major media, news headlines are considered important in the field of communication science as a summary of the core content that the media wants to convey to the audiences who read it. News data used in this study was easily collected using "Bigkinds" that is created by integrating big data technology. With the collected news data, keywords were classified through text mining, and the relationship between words was visualized through semantic network analysis between keywords. Using the KrKwic program, a Korean semantic network analysis tool, text mining was performed and the frequency of words was calculated to easily identify keywords. The frequency of words appearing in keywords of articles related to COVID-19 emotions was checked and visualized in word cloud 'China', 'anxiety', 'situation', 'mind', 'social', and 'health' appeared high in relation to the emotions of COVID-19. In addition, UCINET, a specialized social network analysis program, was used to analyze connection centrality and cluster analysis, and a method of visualizing a graph using Net Draw was performed. As a result of analyzing the connection centrality between each data, it was found that the most central keywords in the keyword-centric network were 'psychology', 'COVID-19', 'blue', and 'anxiety'. The network of frequency of co-occurrence among the keywords appearing in the headlines of the news was visualized as a graph. The thickness of the line on the graph is proportional to the frequency of co-occurrence, and if the frequency of two words appearing at the same time is high, it is indicated by a thick line. It can be seen that the 'COVID-blue' pair is displayed in the boldest, and the 'COVID-emotion' and 'COVID-anxiety' pairs are displayed with a relatively thick line. 'Blue' related to COVID-19 is a word that means depression, and it was confirmed that COVID-19 and depression are keywords that should be of interest now. The research methodology used in this study has the convenience of being able to quickly measure social phenomena and changes while reducing costs. In this study, by analyzing news headlines, we were able to identify people's feelings and perceptions on issues related to COVID-19 depression, and identify the main agendas to be analyzed by deriving important keywords. By presenting and visualizing the subject and important keywords related to the COVID-19 emotion at a time, medical policy managers will be able to be provided a variety of perspectives when identifying and researching the regarding phenomenon. It is expected that it can help to use it as basic data for support, treatment and service development for psychological quarantine issues related to COVID-19.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.119-134
• /
• 2018

A knowledge map as the taxonomy used in a knowledge repository should be structured to support and supplement knowledge activities of users who sequentially inquire and select knowledge for problem solving. The conventional knowledge map with a hierarchical structure has the advantage of systematically sorting out types and status of the knowledge to be managed, however it is not only irrelevant to knowledge user's process of cognition and utilization, but also incapable of supporting user's activity of querying and extracting knowledge. This study suggests a methodology for constructing a networked knowledge map that can support and reinforce the referential navigation, searching and selecting related and chained knowledge in term of contents, between knowledge. Regarding a keyword as the semantic information between knowledge, this research's networked knowledge map can be constructed by aggregating each set of knowledge links in an automated manner. Since a keyword has the meaning of representing contents of a document, documents with common keywords have a similarity in content, and therefore the keyword-based document networks plays the role of a map expressing interactions between related knowledge. In order to examine the feasibility of the proposed methodology, 50 research papers were randomly selected, and an exemplified networked knowledge map between them with content relevance was implemented using common keywords.

• Journal of Korean Home Economics Education Association
• /
• v.31 no.3
• /
• pp.73-90
• /
• 2019

The purpose of this study was to explore the differences in perceptions of male and female students about population problems and to draw up implications for population education. Using text mining, the report about population problem, which had written by students in population education class, were analysed. After extracting key words, semantic networks were visualized. The results were as follows. First, the high frequency words were the same for each gender. Second, key words based on frequency did not differ depending on gender. And the key words extracted by the correlation analysis and bigram were different. That is, in the semantic network of girls' words, the network of "life"-"marriage"-"birth"-"pregnancy" appeared independently, distinguishing it from male students who showed separate objective links to population problems. Therefore, it drew suggestions that male and female students should be viewed as heterogeneous groups with different cognitive structures on population problems and that the content and methods of population education should be approached differently depending on gender.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.1
• /
• pp.93-114
• /
• 2023

Information extraction can facilitate the intensive analysis of documents by providing semantic triples which consist of named entities and their relations recognized in the texts. However, most of the research so far has been carried out separately for named entity recognition and relation extraction as individual studies, and as a result, the effective performance evaluation of the entire information extraction systems was not performed properly. This paper introduces two models of end-to-end information extraction that can extract various entity names in clinical records and their relationships in the form of semantic triples, namely pipeline and joint models and compares their performances in depth. The pipeline model consists of an entity recognition sub-system based on bidirectional GRU-CRFs and a relation extraction module using multiple encoding scheme, whereas the joint model was implemented with a single bidirectional GRU-CRFs equipped with multi-head labeling method. In the experiments using i2b2/VA 2010, the performance of the pipeline model was 5.5% (F-measure) higher. In addition, through a comparative experiment with existing state-of-the-art systems using large-scale neural language models and manually constructed features, the objective performance level of the end-to-end models implemented in this paper could be identified properly.

• The Journal of the Korea Contents Association
• /
• v.16 no.6
• /
• pp.205-214
• /
• 2016

As a large amount of graph-structured data is widely used in various applications such as social networks, semantic web, and bio-informatics, keyword-based search over graph data has been getting a lot of attention. In this paper, we propose an efficient method for keyword search over graph data to find a set of top-k answers that are relevant as well as non-redundant in structure. We define a non-redundant answer structure for a keyword query and a relevance measure for the answer. We suggest a new indexing scheme on the relevant paths between nodes and keyword terms in the graph, and also propose a query processing algorithm to find top-k non-redundant answers efficiently by exploiting the pre-calculated indexes. We present effectiveness and efficiency of the proposed approach compared to the previous method by conducting an experiment using a real dataset.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3168-3186
• /
• 2020

Automatic topic essay generation (TEG) is a controllable text generation task that aims to generate informative, diverse, and topic-consistent essays based on multiple topics. To make the generated essays of high quality, a reasonable method should consider both diversity and topic-consistency. Another essential issue is the intrinsic link of the topics, which contributes to making the essays closely surround the semantics of provided topics. However, it remains challenging for TEG to fill the semantic gap between source topic words and target output, and a more powerful model is needed to capture the semantics of given topics. To this end, we propose a pretraining-based contextual self-attention (PC-SAN) model that is built upon the seq2seq framework. For the encoder of our model, we employ a dynamic weight sum of layers from BERT to fully utilize the semantics of topics, which is of great help to fill the gap and improve the quality of the generated essays. In the decoding phase, we also transform the target-side contextual history information into the query layers to alleviate the lack of context in typical self-attention networks (SANs). Experimental results on large-scale paragraph-level Chinese corpora verify that our model is capable of generating diverse, topic-consistent text and essentially makes improvements as compare to strong baselines. Furthermore, extensive analysis validates the effectiveness of contextual embeddings from BERT and contextual history information in SANs.