• Journal of Wetlands Research
• /
• v.25 no.4
• /
• pp.284-290
• /
• 2023

Domestic water supply and sewage facilities are rapidly aging and maintenance difficulties such as aging of operation and management personnel are overlapping, so Digital Twin technology is attracting attention as an intelligent means of process management. Digital twin projects for domestic water treatment processes include the smart sewage treatment project promoted by the Ministry of Environment, projects independently promoted by some local governments, and digital twin purification plant projects promoted by K-water. However, the content of digital twin promotion is different for each institution. Therefore, in the water treatment process, technological standardization and step-by-step implementation methods for digital twins must be preceded to reduce trial and error in future business promotion. This study aims to provide an efficient promotion plan by prescribing the digital twin element technology and composition method in the water treatment process and reviewing the contents currently being promoted by the Ministry of Environment, local governments, and K-Water individually.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.99-105
• /
• 2023

In the 4th industrial revolution, the field of criminal justice is paying attention to Legaltech using artificial intelligence to provide efficient legal services. This paper attempted to create a crime prediction model that can apply Recurrent Neural Network(RNN) to increase the potential for using legal technology in the domestic criminal justice field. To this end, the crime process was divided into pre, during, and post stages based on the criminal facts described in the judgment, utilizing crime script analysis techniques. In addition, at each time point, the method and evidence of crime were classified into objects, actions, and environments based on the sentence composition elements and the 8 principles of investigation. The case summary analysis framework derived from this study can contribute to establishing situational crime prevention strategies because it is easy to identify typical patterns of specific crime methods. Furthermore, the results of this study can be used as a useful reference for research on generating crime situation prediction data based on RNN models in future follow-up studies.

• Industry Promotion Research
• /
• v.8 no.4
• /
• pp.131-137
• /
• 2023

This study collected and analyzed articles related to military sex crimes covered in the news from February 2019 to May 28, 2022 in order to identify problems arising from sexual crimes in the military. In order to understand the current status of military sexual violence reported in the media, articles were collected using BIGKinds, a news big data analysis system, and using the Textom program, the study was conducted using frequency analysis by period, word cloud, and semantic network analysis techniques for keywords. The study was conducted using the technique. As a result of data analysis, first, it was confirmed that the public's attention was focused on the victims in reports related to sex crimes within the military. Second, the problem of the lukewarm system of the relevant authorities in responding to sex crimes was revealed. Third, there was a lack of support for victims of sex crimes.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.1-7
• /
• 2023

The advent of deep learning technologies has led to the development of various medical applications, making healthcare services more convenient and effective. Among these applications, heart rate estimation is considered a vital method for assessing an individual's health. Traditional methods, such as photoplethysmography through smart watches, have been widely used but are invasive and require additional hardware. Recent advancements allow for contactless heart rate estimation through facial image analysis, providing a more hygienic and convenient approach. In this paper, we propose a lightweight methodology capable of accurately estimating heart rate in mobile environments, using a specialized 2-channel network structure based on 2D convolution. Our method considers both subtle facial movements and color changes resulting from blood flow and muscle contractions. The approach comprises two major components: an Encoder for analyzing image features and a regression layer for evaluating Blood Volume Pulse. By incorporating both features simultaneously our methodology delivers more accurate results even in computing environments with limited resources. The proposed approach is expected to offer a more efficient way to monitor heart rate without invasive technology, particularly well-suited for mobile devices.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.875-883
• /
• 2023

In Korea, the number of preservation and management entities to connect the traditional cultural heritage to next generations is rapidly decreasing. Building an infrastructure to pass on traditional cultural heritage to the next generation and to pay attention to the preservation and management of the next generation is important including the 'Seowon', a World Cultural Heritage listed by UNESCO. This study is based on the laws that regulates the preservation and support of traditional cultural assets and 'Seowon, through Big Data analysis techniques. The main keywords in each law were extracted, schematized, and a mutual Word Network was constructed and policy advice was derived. As policy advice, it is necessary to establish and implement policies to nurture and support businesses specialized in the region for the preservation·utilization, preservation·management and preservation·support of Seowons.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• Convergence Security Journal
• /
• v.24 no.1
• /
• pp.11-20
• /
• 2024

Recently, smart buildings that can efficiently manage energy using ICT technology and operate and control through the building automation system by collecting data from a large number of IoT sensors in real time are attracting attention. However, as data management is carried out through an open environment, the safety of smart buildings is threatened by the security vulnerability of the existing building automation protocol. Therefore, in this paper, we analyze the major data link technology of BACnet, which is used universally, and propose OWE-based efficient BACnet/SC that can ensure the reliability of data in a wireless environment. The proposed protocol enables safe communication even in an open network by applying OWE and provides the same level of security as BACnet/SC in a TLS environment. As a result, it reduces the connection process twice and reduces the average time required by 40%, enabling more efficient communication than before.

• Anatomy and Cell Biology
• /
• v.56 no.2
• /
• pp.200-204
• /
• 2023

Although in counterpart, the sphenopalatine artery (SPA), has been well described in the medical literature, the sphenopalatine vein (SPV) has received scant attention. Therefore, the present anatomical study was performed. Additionally, we discuss the variations, embryology, and clinical significance of the SPV. Adult cadaveric specimens underwent dissection of the SPV. In addition, some specimens were submitted for histological analysis of this structure. The SPV was found to drain from the sphenoidal sinus and nasal septum. Small tributaries traveled through the nasal septum with the posterior septal branches of the SPA and nasopalatine nerve. The SPA and SPV were found to travel through the sphenopalatine foramen and another tributary was found to perforate the medial plate of the pterygoid process and to connect to the pterygoid venous plexus which traveled lateral to the medial plate of the pterygoid process. The vein traveled through the posterior part of the lateral wall of the nasal cavity with the posterior lateral nasal branches of the SPA and the lateral superior posterior nasal branches of the maxillary nerve. To our knowledge, this is the first anatomical study on the SPV in humans. Data on the SPV provides an improved anatomical understanding of the vascular network of the nasal cavity. Developing a more complete picture of the nasal cavity and its venous supply might help surgeons and clinicians better manage clinical entities such as posterior epistaxis, cavernous sinus infections, and perform endoscopic surgery with fewer complications.

• IMMUNE NETWORK
• /
• v.21 no.6
• /
• pp.44.1-44.15
• /
• 2021

Tumor peptides associated with MHC class I molecules or their synthetic variants have attracted great attention for their potential use as vaccines to induce tumor-specific CTLs. However, the outcome of clinical trials of peptide-based tumor vaccines has been disappointing. There are various reasons for this lack of success, such as difficulties in delivering the peptides specifically to professional Ag-presenting cells, short peptide half-life in vivo, and limited peptide immunogenicity. We report here a novel peptide vaccination strategy that efficiently induces peptide-specific CTLs. Nanoparticles (NPs) were fabricated from a biodegradable polymer, poly(D,L-lactic-co-glycolic acid), attached to H-2K^b molecules, and then the natural peptide epitopes associated with the H-2K^b molecules were exchanged with a model tumor peptide, SIINFEKL (OVA_257-268). These NPs were efficiently phagocytosed by immature dendritic cells (DCs), inducing DC maturation and activation. In addition, the DCs that phagocytosed SIINFEKL-pulsed NPs potently activated SIINFEKL-H2K^b complex-specific CD8⁺ T cells via cross-presentation of SIINFEKL. In vivo studies showed that intravenous administration of SIINFEKL-pulsed NPs effectively generated SIINFEKL-specific CD8⁺ T cells in both normal and tumor-bearing mice. Furthermore, intravenous administration of SIINFEKL-pulsed NPs into EG7.OVA tumor-bearing mice almost completely inhibited the tumor growth. These results demonstrate that vaccination with polymeric NPs coated with tumor peptide-MHC-I complexes is a novel strategy for efficient induction of tumor-specific CTLs.

• Animal Bioscience
• /
• v.37 no.7
• /
• pp.1289-1302
• /
• 2024

Objective: There is a strong relationship between the content of beneficial fatty acids in milk and milk fat metabolic activity in the mammary gland. To improve milk quality, it is therefore necessary to study fatty acid metabolism in bovine mammary gland tissue. In adipose tissue, peroxisome proliferator-activated receptor gamma (PPARG), the core transcription factor, regulates the fatty acid metabolism gene network and determines fatty acid deposition. However, its regulatory effects on mammary gland fatty acid metabolism during lactation have rarely been reported. Methods: Transcriptome sequencing was performed during the prelactation period and the peak lactation period to examine mRNA expression. The significant upregulation of PPARG drew our attention and led us to conduct further research. Results: According to bioinformatics prediction, dual-luciferase reporter system detection, real-time quantitative reverse transcription polymerase chain reaction and Western blotting, miR-130a and miR-130b could directly target PPARG and inhibit its expression. Furthermore, triglyceride and oil red O staining proved that miR-130a and miR-130b inhibited milk fat metabolism in bovine mammary epithelial cells (BMECs), while PPARG promoted this metabolism. In addition, we also found that the coexpression of miR-130a and miR-130b significantly enhanced their ability to regulate milk fat metabolism. Conclusion: In conclusion, our findings indicated that miR-130a and miR-130b could target and repress PPARG and that they also have a functional superposition effect. miR-130a and miR-130b seem to synergistically regulate lipid catabolism via the control of PPARG in BMECs. In the long-term, these findings might be helpful in developing practical means to improve high-quality milk.