• Journal of Korea Multimedia Society
• /
• v.25 no.3
• /
• pp.493-501
• /
• 2022

This paper is a study on context-sensitive spelling error correction and uses the Korean WordNet (KorLex)[1] that defines the relationship between words as a graph to improve the performance of the correction[2] based on the vector information of the word embedded in the correction technique. The Korean WordNet replaced WordNet[3] developed at Princeton University in the United States and was additionally constructed for Korean. In order to learn a semantic network in graph form or to use it for learned vector information, it is necessary to transform it into a vector form by embedding learning. For transformation, we list the nodes (limited number) in a line format like a sentence in a graph in the form of a network before the training input. One of the learning techniques that use this strategy is Deepwalk[4]. DeepWalk is used to learn graphs between words in the Korean WordNet. The graph embedding information is used in concatenation with the word vector information of the learned language model for correction, and the final correction word is determined by the cosine distance value between the vectors. In this paper, In order to test whether the information of graph embedding affects the improvement of the performance of context- sensitive spelling error correction, a confused word pair was constructed and tested from the perspective of Word Sense Disambiguation(WSD). In the experimental results, the average correction performance of all confused word pairs was improved by 2.24% compared to the baseline correction performance.

• Imaging Science in Dentistry
• /
• v.52 no.4
• /
• pp.383-391
• /
• 2022

Purpose: Periodontitis, the most prevalent chronic inflammatory condition affecting teeth-supporting tissues, is diagnosed and classified through clinical and radiographic examinations. The staging of periodontitis using panoramic radiographs provides information for designing computer-assisted diagnostic systems. Performing image segmentation in periodontitis is required for image processing in diagnostic applications. This study evaluated image segmentation for periodontitis staging based on deep learning approaches. Materials and Methods: Multi-Label U-Net and Mask R-CNN models were compared for image segmentation to detect periodontitis using 100 digital panoramic radiographs. Normal conditions and 4 stages of periodontitis were annotated on these panoramic radiographs. A total of 1100 original and augmented images were then randomly divided into a training (75%) dataset to produce segmentation models and a testing (25%) dataset to determine the evaluation metrics of the segmentation models. Results: The performance of the segmentation models against the radiographic diagnosis of periodontitis conducted by a dentist was described by evaluation metrics(i.e., dice coefficient and intersection-over-union [IoU] score). MultiLabel U-Net achieved a dice coefficient of 0.96 and an IoU score of 0.97. Meanwhile, Mask R-CNN attained a dice coefficient of 0.87 and an IoU score of 0.74. U-Net showed the characteristic of semantic segmentation, and Mask R-CNN performed instance segmentation with accuracy, precision, recall, and F1-score values of 95%, 85.6%, 88.2%, and 86.6%, respectively. Conclusion: Multi-Label U-Net produced superior image segmentation to that of Mask R-CNN. The authors recommend integrating it with other techniques to develop hybrid models for automatic periodontitis detection.

• Journal of Korea Multimedia Society
• /
• v.16 no.11
• /
• pp.1305-1314
• /
• 2013

The existing tag based system deducts a retrieval result with low accuracy through the usage of a single tag matching by using tags tagged in contents. And the system doesn't provide effectively contents related information which the tags have, as the users place tags on contents without considering the priority and associative relation between tags. For a solve of above problems, this paper suggests a tag ranking system which extracts semantic similarity between tags and re-ranks the tags tagged in contents. In order to evaluate the performance of suggested system, this paper experiments and compares the ranking result of this paper's tag ranking system with the result of baseline method using tags tagged in images and frequency method adapting tag co-appearance frequency.

• The Journal of Information Systems
• /
• v.20 no.3
• /
• pp.41-61
• /
• 2011

In order to buy products through the Internet, consumers dissipate much time and efforts in collecting and comparing product information from various online shopping malls. Consumers can save their efforts by using price comparison sites, but there are some shortcomings in comparison shopping. Firstly, comparison sites do not show the lowest price of some products that are selling in shopping malls. Secondly, the product information provided by comparison sites is sometimes wrong. Thirdly, there are too many results. In order to overcome the shortcomings, we suggested a comparison shopping system based on RSS by using ontology matching. We used the current RSS standard for syntactic interoperability instead of suggesting new standards. Moreover, we used ontology matching for semantic interoperability to compare product information with different ontologies. The suggested ontology matching consists of three steps. The first step is finding exact sense from WordNet for a given product category, and the second step is searching for matching product category candidates from the products of RSS feeds. The final step is calculating similarities of the candidates with the target product category. From the experiments, we could get better recall rates that are suitable for e-commerce environments and the results show that our system is effective in product comparison.

• The Journal of Society for e-Business Studies
• /
• v.12 no.1
• /
• pp.135-149
• /
• 2007

There are many kinds of applications or software components to manage files in a local computer, but it is very difficult to organize personal documents in a consistent way and to search expected ones in a precise way. In this paper, we present our development of a document management and retrieval tool, which is named Ontalk. Our system provides a semi-automatic metadata generator and an ontology-based search engine for electronic documents. Ontalk can create and import various ontologies in RDFS or OWL for describing the metadata. Our system that is built upon.NET technology is easily communicated with or flexibly plugged into many different programs.

• Culinary science and hospitality research
• /
• v.23 no.4
• /
• pp.22-32
• /
• 2017

The purpose of this study was to explore awareness of food tourism using big data analysis. For this, this study collected data containing 'food tourism' keywords from google web search, google news, and google scholar during one year from January 1 to December 31, 2016. Data were collected by using SCTM (Smart Crawling & Text Mining), a data collecting and processing program. From those data, degree centrality and eigenvector centrality were analyzed by utilizing packaged NetDraw along with UCINET 6. The result showed that the web visibility of 'core service' and 'social marketing' was high. In addition, the web visibility was also high for destination, such as rural, place, ireland and heritage; 'socioeconomic circumstance' related words, such as economy, region, public, policy, and industry. Convergence of iterated correlations showed 4 clustered named 'core service', 'social marketing', 'destinations' and 'social environment'. It is expected that this diagnosis on food tourism according to changes in international business environment by using these web information will be a foundation of baseline data useful for establishing food tourism marketing strategies.

• Korean Journal of Childcare and Education
• /
• v.16 no.6
• /
• pp.253-272
• /
• 2020

Objective: This study aimed to analyze the counseling contents of daycare center teachers by using text mining and semantic network analysis methods to find the necessary support directions for daycare teachers and to improve the quality of child-care. Methods: Five hundred thirteen cases of counseling recorded on the open bulletin board of online counseling (Naver Bands for Nursery Teacher Counseling) were collected, and frequency analysis, centrality solidarity analysis, and machine learning-based topic analysis were conducted using the NetMiner4.3 program. Results: First, 'teacher-to-child ratio' was highest in the frequency. Second, 'colleagues' were all high in all centrality analysis. Third, machine learning-based topical analysis shows that the topics were categorized as subjects about 'childcare and education', 'working environment that supports professional development' and 'working condition', and among them, 'first-time teacher concerns' accounted for 44% of the total counseling content. Conclusion/Implications: This study implied that it is necessary to provide high-quality child-care and education to infants by lowering the 'teacher-to-child ratio', and a systematic program is needed to help improve effective communication skills in interpersonal relationships such as between parents, fellow teachers, and principals. In addition, self-development and efforts to improve teachers expertise should be prioritized in order to improve infant care quality and quality of teachers.

• Child Health Nursing Research
• /
• v.29 no.3
• /
• pp.182-194
• /
• 2023

Purpose: This study analyzed research trends in infant and toddler rearing behavior among family caregivers over a 10-year period (2010-2021). Methods: Text network analysis and topic modeling were employed on data collected from relevant papers, following the extraction and refinement of semantic morphemes. A semantic-centered network was constructed by extracting words from 2,613 English-language abstracts. Data analysis was performed using NetMiner 4.5.0. Results: Frequency analysis, degree centrality, and eigenvector centrality all revealed the terms ''scale," ''program," and ''education" among the top 10 keywords associated with infant and toddler rearing behaviors among family caregivers. The keywords extracted from the analysis were divided into two clusters through cohesion analysis. Additionally, they were classified into two topic groups using topic modeling: "program and evaluation" (64.37%) and "caregivers' role and competency in child development" (35.63%). Conclusion: The roles and competencies of family caregivers are essential for the development of infants and toddlers. Intervention programs and evaluations are necessary to improve rearing behaviors. Future research should determine the role of nurses in supporting family caregivers. Additionally, it should facilitate the development of nursing strategies and intervention programs to promote positive rearing practices.

• Journal of KIISE:Software and Applications
• /
• v.37 no.7
• /
• pp.548-557
• /
• 2010

In this paper, we propose a semi-automatic modeling approach of ontology to annotate VOD to realize the IPTV's intelligent searching. The ontology is made by combining partial tree that extracts hypernym, hyponym, and synonym of keywords related to a service domain from WordNet. Further, we add to the partial tree new keywords that are undefined in WordNet, such as foreign words and words written in Chinese characters. The ontology consists of two parts: generic hierarchy and specific hierarchy. The former is the semantic model of vocabularies such as keywords and contents of keywords. They are defined as classes including property restrictions in the ontology. The latter is generated using the reasoning technique by inferring contents of keywords based on the generic hierarchy. An annotation generates metadata (i.e., contents and genre) of VOD based on the specific hierarchy. The generic hierarchy can be applied to other domains, and the specific hierarchy helps modeling the ontology to fit the service domain. This approach is proved as good to generate metadata independent of any specific domain. As a result, the proposed method produced around 82% precision with 2,400 VOD annotation test data.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1591-1604
• /
• 2020

This study is a study on classifying land cover by applying high-resolution satellite images to deep learning algorithms and verifying the performance of algorithms for each spatial object. For this, the Fully Convolutional Network-based algorithm was selected, and a dataset was constructed using Kompasat-3 satellite images, land cover maps, and forest maps. By applying the constructed data set to the algorithm, each optimal hyperparameter was calculated. Final classification was performed after hyperparameter optimization, and the overall accuracy of DeeplabV3+ was calculated the highest at 81.7%. However, when looking at the accuracy of each category, SegNet showed the best performance in roads and buildings, and U-Net showed the highest accuracy in hardwood trees and discussion items. In the case of Deeplab V3+, it performed better than the other two models in fields, facility cultivation, and grassland. Through the results, the limitations of applying one algorithm for land cover classification were confirmed, and if an appropriate algorithm for each spatial object is applied in the future, it is expected that high quality land cover classification results can be produced.