• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.1
• /
• pp.117-126
• /
• 2022

Currently, the number of bridge structures in Korea is continuously increasing and enlarged, and the number of old bridges that have been in service for more than 30 years is also steadily increasing. Bridge aging is being treated as a serious social problem not only in Korea but also around the world, and the existing manpower-centered inspection method is revealing its limitations. Recently, various bridge damage detection studies using deep learning-based image processing algorithms have been conducted, but due to the limitations of the bridge damage data set, most of the bridge damage detection studies are mainly limited to one type of crack, which is also based on a close set classification model. As a detection method, when applied to an actual bridge image, a serious misrecognition problem may occur due to input images of an unknown class such as a background or other objects. In this study, five types of bridge damage including crack were defined and a data set was built, trained as a deep learning model, and an open set recognition-based bridge multiple damage recognition model applied with OpenMax algorithm was constructed. And after performing classification and recognition performance evaluation on the open set including untrained images, the results were analyzed.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.5
• /
• pp.308-314
• /
• 2022

This study deals with the technology Convergence Analysis by IPC Code-Based Social Network Analysis of Healthcare Patents filed in Korea. The relationship between core technologies is visualized using Social Network Analysis. At the subclass level of healthcare patents, 1,155 cases (49.4%) of patents with complex IPC codes were investigated, and as a result of Social Network Analysis on them, the IPC codes with the highest Degree Centrality were A61B, G16H, and G06Q, in that order. The IPC codes with the highest Betweenness Centrality are in the order of A61B, G16H, and G06Q. In addition, it was confirmed that healthcare patents consist of two large technology clusters. Cluster-1 corresponds to related business models centered on A61B, G16H and G06Q, and Cluster-2 is consisting of H04L, H04W and H04B. The technology convergence core pairs of the healthcare patent is [G16H-A61B] and [G16H-G06Q] in Cluster-1, and [H04L-H04W] in Cluster-2. The results of this study can contribute to the development of core technologies for healthcare patents.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.2
• /
• pp.363-368
• /
• 2021

Ship engine rooms have improved automation systems owing to the advancement of technology. However, there are many variables at sea, such as wind, waves, vibration, and equipment aging, which cause loosening, cutting, and leakage, which are not measured by automated systems. There are cases in which only one engineer is available for patrolling. This entails many risk factors in the engine room, where rotating equipment is operating at high temperature and high pressure. When the engineer patrols, he uses his five senses, with particular high dependence on vision. We hereby present a preliminary study to implement an engine-room patrol robot that detects and informs the machine room while a robot patrols the engine room. Images of ship engine-room equipment were classified using a convolutional neural network (CNN). After constructing the image dataset of the ship engine room, the network was trained with a pre-trained CNN model. Classification performance of the trained model showed high reproducibility. Images were visualized with a class activation map. Although it cannot be generalized because the amount of data was limited, it is thought that if the data of each ship were learned through transfer learning, a model suitable for the characteristics of each ship could be constructed with little time and cost expenditure.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.1
• /
• pp.1-18
• /
• 2023

Similar software is often developed with the Clone-And-Own (CAO) approach that copies and modifies existing artifacts. The CAO approach is considered as a bad practice because it makes maintenance difficult as the number of cloned products increases. Software product line engineering is a methodology that can solve the issue of the CAO approach by developing a product family through systematic reuse. Migrating product families that have been developed with the CAO approach to the product line engineering begins with finding, integrating, and building them as reusable assets. However, cloning occurs at various levels from directories to code lines, and their structures can be changed. This makes it difficult to build product line code base simply by finding clones. Successful migration thus requires unifying the source code's file path, class name, and method signature. This paper proposes a clustering method that identifies a set of similar codes scattered across product variants and some of their method full paths are different, so path unification is necessary. In order to show the effectiveness of the proposed method, we conducted an experiment using the Apo Games product line, which has evolved with the CAO approach. As a result, the average precision of clustering performed without preprocessing was 0.91 and the number of identified common clusters was 0, whereas our method showed 0.98 and 15 respectively.

• Journal of Internet Computing and Services
• /
• v.23 no.2
• /
• pp.107-114
• /
• 2022

In this paper, availabilities of student-evaluations of team activities in the computer science basic classes were analysed. For the purpose, correlation analysis was conducted to investigate the relationships among peer-evaluation, self-evaluation, and academic achievement, and it was found that there was a statistically significant positive correlation among them. Moreover, the gap between peer-evaluation scores and self-evaluation scores was analyzed. When a one-sample t-test was performed, it was found that the gap was very significant. However, the size of the gap was not different between the two classes. That is, regardless of grade level, the students' self-evaluation scores tended to be on average higher than the evaluation scores received from peers. Finally, when analyzing the relationship between the gap in peer-evaluation and self-evaluation scores and academic achievement, there was no significant correlation between the gap in scores and academic achievement. In other words, there was no difference in the tendency of evaluation for students with high or low academic achievement. The results of the analysis shows the availability of student-evaluations of team activities in the evaluation of team-based instruction. The high correlation between self-evaluation and peer-evaluation indicates the objectivity of student-evaluation. Although it is clear that the self-evaluation score is higher on average than the score received from peers, it is more useful in terms of objectivity because it does not vary according to grade, subject, or academic achievement.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.139-159
• /
• 2022

As interest in health functional foods has increased since COVID-19, the importance of imported food safety inspections is growing. However, in contrast to the annual increase in imports of health functional foods, the budget and manpower required for inspections for import and export are reaching their limit. Hence, the purpose of this study is to propose a machine learning model that efficiently detects unsuitable food suitable for the characteristics of data possessed by government offices on imported food. First, the components of food import/export inspections data that affect the judgment of nonconformity were examined and derived variables were newly created. Second, in order to select features for the machine learning, class imbalance and nonlinearity were considered when performing exploratory analysis on imported food-related data. Third, we try to compare the performance and interpretability of each model by applying various machine learning techniques. In particular, the ensemble model was the best, and it was confirmed that the derived variables and models proposed in this study can be helpful to the system used in import/export inspections.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.347-364
• /
• 2022

Fraudulent companies or sellers strategically manipulate reviews to influence customers' purchase decisions; therefore, the reliability of reviews has become crucial for customer decision-making. Since customers increasingly rely on online reviews to search for more detailed information about products or services before purchasing, many researchers focus on detecting manipulated reviews. However, the main problem in detecting manipulated reviews is the difficulties with obtaining data with manipulated reviews to utilize machine learning techniques with sufficient data. Also, the number of manipulated reviews is insufficient compared with the number of non-manipulated reviews, so the class imbalance problem occurs. The class with fewer examples is under-represented and can hamper a model's accuracy, so machine learning methods suffer from the class imbalance problem and solving the class imbalance problem is important to build an accurate model for detecting manipulated reviews. Thus, we propose an OpenAI-based reviews generation model to solve the manipulated reviews imbalance problem, thereby enhancing the accuracy of manipulated reviews detection. In this research, we applied the novel autoregressive language model - GPT-3 to generate reviews based on manipulated reviews. Moreover, we found that applying GPT-3 model for oversampling manipulated reviews can recover a satisfactory portion of performance losses and shows better performance in classification (logit, decision tree, neural networks) than traditional oversampling models such as random oversampling and SMOTE.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.77-82
• /
• 2023

The Ministry of Agriculture, Food and Rural Affairs established the FarmMap, an digital map of agricultural land. In this study, using deep learning, we suggest the application of farm map reading to farmland such as paddy fields, fields, ginseng, fruit trees, facilities, and uncultivated land. The farm map is used as spatial information for planting status and drone operation by digitizing agricultural land in the real world using aerial and satellite images. A reading manual has been prepared and updated every year by demarcating the boundaries of agricultural land and reading the attributes. Human reading of agricultural land differs depending on reading ability and experience, and reading errors are difficult to verify in reality because of budget limitations. The farmmap has location information and class information of the corresponding object in the image of 5 types of farmland properties, so the suitable AI technique was tested with ResNet50, an instance segmentation model. The results of attribute reading of agricultural land using deep learning and attribute reading by humans were compared. If technology is developed by focusing on attribute reading that shows different results in the future, it is expected that it will play a big role in reducing attribute errors and improving the accuracy of digital map of agricultural land.

• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.665-672
• /
• 2023

Purpose: Underground utility tunnel is facility that is jointly house infrastructure such as electricity, water and gas in city, causing condensation problems due to lack of airflow. This paper aims to prevent electricity leakage fires caused by condensation by detecting whether the control panel door in the underground utility tunnel is open using a deep learning model. Method: YOLO, a deep learning object recognition model, is trained to recognize the opening and closing of the control panel door using video data taken by a robot patrolling the underground utility tunnel. To improve the recognition rate, image augmentation is used. Result: Among the image enhancement techniques, we compared the performance of the YOLO model trained using mosaic with that of the YOLO model without mosaic, and found that the mosaic technique performed better. The mAP for all classes were 0.994, which is high evaluation result. Conclusion: It was able to detect the control panel even when there were lights off or other objects in the underground cavity. This allows you to effectively manage the underground utility tunnel and prevent disasters.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.33 no.1
• /
• pp.25-45
• /
• 2022

This study was to develop KORMARC-bibliographic format reflecting cataloging trends after LRM using literature review, analysis of MARC 21 discussion papers, and comparison of the fields in MARC 21 and KORMARC. The acceptance and consideration of fields and sub-fields that need to be revised in KORMARC are as follows. First, in terms of LRM / RDA, fields 381 or 387 for the representative expression, field 881 and the change and addition of its sub-fields for the manifestation statement, and data provenance code to ▾7 sub-field for date provenance may be considered. Second, in terms of Linked Data, ▾1 sub-field for RWO, and field 758 for related work identifier can be added. Third, for the data exchange of KORMARC and BIBFRAME, it should be developed in consideration of mapping with BIBFRAME classes and attributes in KORMARC. Fourth, additional fields such as 251 version information, 334 mode of issuance, 335 expansion plan, 341 accessibility content, 348 format of notated music, 353 supplementary content characteristics, 532 accessibility note, 370 associated place, 385 audience characteristics, 386 creator/contributor characteristics, 388 time period of creation, 688 subject added entry-type of entity unspecified, 884 description conversion information, 885 matching information could be developed. This study will be used to revise KORMARC-bibliographic format and to build and utilize bibliographic data in domestic libraries.