• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.455-460
• /
• 2023

Text augmentation is a methodology that creates new augmented texts by transforming or generating original texts for the purpose of improving the performance of NLP models. However existing text augmentation techniques have limitations such as lack of expressive diversity semantic distortion and limited number of augmented texts. Recently text augmentation using large language models and few-shot learning can overcome these limitations but there is also a risk of noise generation due to incorrect generation. In this paper, we propose a text augmentation method called TAGS that generates multiple candidate texts and selects the appropriate text as the augmented text. TAGS generates various expressions using few-shot learning while effectively selecting suitable data even with a small amount of original text by using contrastive learning and similarity comparison. We applied this method to task-oriented chatbot data and achieved more than sixty times quantitative improvement. We also analyzed the generated texts to confirm that they produced semantically and expressively diverse texts compared to the original texts. Moreover, we trained and evaluated a classification model using the augmented texts and showed that it improved the performance by more than 0.1915, confirming that it helps to improve the actual model performance.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.29-35
• /
• 2023

CCTV is used for various purposes such as crime prevention, public safety reinforcement, and traffic management. However, as the range and resolution of the camera improve, there is a risk of exposing personal information in the video. Therefore, there is a need for new technologies that can identify individuals while protecting personal information in images. In this paper, we propose histogram-based singular value decomposition for object identification and tracking. The proposed method distinguishes different objects present in the image using color information of the object. For object recognition, YOLO and DeepSORT are used to detect and extract people present in the image. Color values are extracted with a black-and-white histogram using location information of the detected person. Singular value decomposition is used to extract and use only meaningful information among the extracted color values. When using singular value decomposition, the accuracy of object color extraction is increased by using the average of the upper singular value in the result. Color information extracted using singular value decomposition is compared with colors present in other images, and the same person present in different images is detected. Euclidean distance is used for color information comparison, and Top-N is used for accuracy evaluation. As a result of the evaluation, when detecting the same person using a black-and-white histogram and singular value decomposition, it recorded a maximum of 100% to a minimum of 74%.

• Information Systems Review
• /
• v.23 no.3
• /
• pp.97-125
• /
• 2021

Blockchain is a core technology to solve personal information leakage and data management issues, which are limitations of existing Genomic Sequencing services. Due to continuous cost reduction and deregulation, the market size of Genomic Sequencing has been increasing, also the potential of services is expected to increase when Blockchain's security and connectivity are combined. We created our research model by combining the Technology Acceptance Model (TAM) and the Innovation Resistance Theory also analyzed the factors affecting the acceptance intention and innovation resistance of the Blockchain Based Genomic Sequencing Information Platform. A survey was conducted on 150 potential users of Blockchain and Genomic Sequencing services. The analysis was conducted by setting the four Blockchain variables: Security, transparency, availability, and diversity). Also, we set the Perceived Usefulness, Perceived risk, and Perceived Complexity for Technology Acceptance and Innovation Resistance variables and analyzed the effect of the characteristics of the Blockchain on acceptance intention and innovation resistance through these variables. Through this analysis, key variables that need to be considered important to reduce resistance and increase acceptance intention could be identified. This study presents innovation factors that should be considered in companies preparing a new Blockchain Based Genomic Sequencing Information Platform.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.2
• /
• pp.207-216
• /
• 2024

As big data was built due to the 4th Industrial Revolution, personalized services increased rapidly. As a result, the amount of personal information collected from online services has increased, and concerns about users' personal information leakage and privacy infringement have increased. Online service providers provide privacy policies to address concerns about privacy infringement of users, but privacy policies are often misused due to the long and complex problem that it is difficult for users to directly identify risk items. Therefore, there is a need for a method that can automatically check whether the privacy policy is safe. However, the safety verification technique of the conventional blacklist and machine learning-based privacy policy has a problem that is difficult to expand or has low accessibility. In this paper, to solve the problem, we propose a safety verification technique for the privacy policy using the GPT-3.5 API, which is a generative artificial intelligence. Classification work can be performed evenin a new environment, and it shows the possibility that the general public without expertise can easily inspect the privacy policy. In the experiment, how accurately the blacklist-based privacy policy and the GPT-based privacy policy classify safe and unsafe sentences and the time spent on classification was measured. According to the experimental results, the proposed technique showed 10.34% higher accuracy on average than the conventional blacklist-based sentence safety verification technique.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.123-136
• /
• 2024

The U.S. Department of Defense, leading global cybersecurity policies, has two main cybersecurity frameworks: the Cybersecurity Maturity Model Certification (CMMC) for external defense industry certification, and the Risk Management Framework (RMF) for internal organizational security assessments. For Republic of Korea military, starting from 2026, the Korean version of RMF (K-RMF) will be fully implemented. Domestic defense industry companies participating in projects commissioned by the U.S. Department of Defense must obtain CMMC certification by October 2025. In this paper, a new standard compliance meta-model (R3C) development methodology that can simultaneously support CMMC and RMF security audit readiness tasks is introduced, along with the implementation results of a compliance solution based on the R3C meta-model. This research is based on practical experience with the U.S. Department of Defense's cybersecurity regulations gained during the joint project by the South Korean and U.S. defense ministries' joint chiefs of staff since 2022. The developed compliance solution functions are being utilized in joint South Korean-U.S. military exercises. The compliance solution developed through this research is expected to be available for sale in the private sector and is anticipated to be highly valuable for domestic defense industry companies that need immediate CMMC certification.

• Journal of Navigation and Port Research
• /
• v.47 no.6
• /
• pp.437-447
• /
• 2023

By actively adopting technologies from the Fourth Industrial Revolution, the port industry is trending toward new types of ports, such as automated and smart ports. However, behind the development of these ports, there is an increasing risk of cyber security incidents and threats within ports and container terminals, including information leakage through cargo handling equipment and ransomware attacks leading to disruptions in terminal operations. Despite the necessity of research to enhance cyber security within ports, there is a lack of such studies in the domestic context. This study focuses on Busan Port, a representative port in South Korea that actively incorporates technology from the Fourth Industrial Revolution, in order to discover variables for improving cyber security in container terminals. The research results categorized factors for enhancing cyber security in Busan Port's container terminals into network construction and policy support, standardization of education and personnel training, and legal and regulatory factors. Subsequently, multiple regression analysis was conducted based on these factors, leading to the identification of detailed factors for securing and enhancing safety, reliability, performance, and satisfaction in Busan Port's container terminals. The significance of this study lies in providing direction for enhancing cyber security in Busan Port's container terminals and addressing the increasing incidents of cyber security attacks within ports and container terminals.

• Journal of Navigation and Port Research
• /
• v.48 no.3
• /
• pp.192-199
• /
• 2024

Wave overtopping is a significant natural hazard that occurs in coastal areas, primarily driven by high waves, particularly those generated during typhoons, which can cause coastal flooding. The development of residential and commercial areas along the coast, driven by increasing social and economic demands, has led to a concentration of people and assets in these vulnerable areas. This, coupled with long-term sea level rise and an increase in typhoon frequency, has heightened the risk of coastal hazards. Traditionally, the evaluation of wave overtopping volumes has relied on directly measuring the collected volume of water that exceeds the crest height of structures through hydraulic model experiments. These experiments are averaged over a specific measurement period. However, in this study, we propose a new method for estimating individual wave overtopping volumes. We utilize the temporal variation of wave overtopping heights to develop an observation system that can quantitatively assess wave overtopping volumes in actual coastal areas. To test our method, we conducted hydraulic model experiments on rubble mound breakwaters, which are commonly installed along the Korean coast. We introduce wave overtopping discharge coefficients, assuming that the inundation velocity from the structure's crest is the long-wave velocity. We then predict overtopping volumes based on wave overtopping heights and compare and review the results with experimental data. The findings of our study confirm the feasibility of estimating wave overtopping volumes by applying the overtopping discharge coefficients derived in this study to wave overtopping heights.

• Korean Journal of Clinical Laboratory Science
• /
• v.55 no.4
• /
• pp.291-297
• /
• 2023

Gastritis is an inflammation of the gastric mucosa and gastric ulcers are a break in the mucosa of the stomach lining. Past research on gastritis and gastric ulcers has been mainly conducted from the perspective that environmental factors are the primary cause of these gastric diseases. However, recently the importance of genetic factors has been emphasized due to current developments in genetic research. The SLC25A26 gene is believed to be associated with the accumulation of reactive oxygen species. Oxidative stress promotes an inflammatory response, which increases the production of free radicals and causes cellular damage, and these lead to the development of gastric diseases. In this study, the correlation between SLC25A26 and gastric diseases was analyzed. Polymorphisms in SLC25A26 were analyzed in 1,369 domestic gastric disease patients and 7,471 healthy controls. As a result, 11 single nucleotide polymorphisms (SNPs) (in the genotype) and 13 SNPs (in the imputation) showed statistical significance (P<0.05), and high relative risk of gastric diseases. Among them, the rs13874 allele of SLC25A26 showed a highly significant association with gastric diseases. In the genotype-based mRNA expression analysis, the minor allele (C) group showed increased mRNA expression and this could increase oxidative stress. In conclusion, SLC25A26 polymorphisms are associated with gastric diseases. These results may provide a basis for new guidelines for gastric disease management in the Korean population.

• Microbiology and Biotechnology Letters
• /
• v.51 no.4
• /
• pp.517-525
• /
• 2023

The emergence and spread of multidrug-resistant Pseudomonas aeruginosa (MRPA) have become a serious problem worldwide. The involvement of metallo-β-lactamases (MBLs) in inducing carbapenem resistance is particularly acute. However, unlike other members of the Enterobacteriaceae genus, new clones of P. aeruginosa are constantly emerging and rapidly replacing previously prevalent dominant clones. Therefore, this study aimed to perform antimicrobial resistance gene analysis, integron gene cassette analysis using DNA sequencing, and plasmid transfer analysis by conjugation to investigate the antimicrobial resistance dynamics of 18 P. aeruginosa strains isolated from various medical samples at a general hospital in Busan from September 2017 to September 2019. All 18 strains showed extensively drug-resistant (XDR) phenotype and were resistant to most antibiotics, except colistin (100%) but were susceptible to aztreonam (22.2%) and ceftazidime (16.6%). Approximately 66.7% of the strains had Class 1 integrons showing various antimicrobial resistances. Notably, IMP-6 ST235 (66.7%), VIM-2 ST357 (16.7%), and IMP-1 ST446(16.7%) were identified. The identification of IMP-1-producing ST446, previously unreported in Korea, is noteworthy considering the emergence and prevalence of another MRPA high-risk clone.

• Journal of Pharmacopuncture
• /
• v.27 no.1
• /
• pp.14-20
• /
• 2024

Objectives: Frozen shoulder (FS) is one of the most challenging shoulder disorders for patients and clinicians. Its symptoms mainly include any combination of stiffness, nocturnal pain, and limitation of active and passive glenohumeral joint movement. Conventional treatment options for FS are physical therapy, nonsteroidal anti-inflammatory drugs, injection therapy, and arthroscopic capsular release, but adverse and limited effects continue to present problems. As a result, pharmacoacupuncture (PA) is getting attention as an alternative therapy for patients with FS. PA is a new form of acupuncture treatment in traditional Korean medicine (TKM) that is mainly used for musculoskeletal diseases. It has similarity and specificity compared to corticosteroid injection and hydrodilatation, making it a potential alternative injection therapy for FS. However, no systematic reviews investigating the utilization of PA for FS have been published. Therefore, this review aims to standardize the clinical use of PA for FS and validate its therapeutic effect. Methods: The protocol was registered in Prospero (CRD42023445708) on 18 July 2023. Until Aug. 31, 2023, seven electronic databases will be searched for randomized controlled trials of PA for FS. Authors will be contacted, and manual searches will also be performed. Two reviewers will independently screen and collect data from retrieved articles according to predefined criteria. The primary outcome will be pain intensity, and secondary outcomes will be effective rate, Constant-Murley Score, Shoulder Pain and Disability Index, range of motion, quality of life, and adverse events. Bias and quality of the included trials will be assessed using the Cochrane handbook's risk-of-bias tool for randomized trials. Meta analyses will be conducted using Review Manager V.5.3 software. GRADE will be used to evaluate the level of evidence for each outcome. Results: This systematic review and meta-analysis will be conducted following PRISMA statement. The results will be published in a peer-reviewed journal. Conclusion: This review will provide scientific evidence to support health insurance policy as well as the standardization of PA in clinical practice.