연구성과로 돌아가기
2023 연구성과 (242 / 285)
※ 컨트롤 + 클릭으로 열별 다중 정렬 가능합니다.
Excel 다운로드
| WoS | SCOPUS | Document Type | Document Title | Abstract | Authors | Affiliation | ResearcherID (WoS) | AuthorsID (SCOPUS) | Author Email(s) | Journal Name | JCR Abbreviation | ISSN | eISSN | Volume | Issue | WoS Edition | WoS Category | JCR Year | IF | JCR (%) | FWCI | FWCI Update Date | WoS Citation | SCOPUS Citation | Keywords (WoS) | KeywordsPlus (WoS) | Keywords (SCOPUS) | KeywordsPlus (SCOPUS) | Language | Publication Stage | Publication Year | Publication Date | DOI | JCR Link | DOI Link | WOS Link | SCOPUS Link |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ○ | ○ | Article | A pilot lab trial for enhanced oxidative transformation of procymidone fungicide and its aniline metabolite using heterogeneous MnO2 catalysts | In this study, the feasibility of two heterogeneous catalysis (non-Fenton heterogeneous catalysis and catalytic ozonation) was evaluated for the oxidative transformation of the fungicide procymidone and its major metabolite (3,5-dichloroaniline; 3,5-DCA) under a pilot lab experiment. Among the studied treatments, only H2O2 or O-3 significantly oxidized procymidone and 3,5-DCA. However, heterogeneous catalysis used with various types of MnO2 catalysts was found to be an effective rapid strategy for transformation of procymidone and its aniline metabolite. Among the studied catalysts, delta-MnO2 performed well in the enhanced oxidative transformation of procymidone and 3,5-DCA in MnO2-mediator system assay. The optimal reaction parameters, such as reaction pH, and initial catalyst concentration were comparatively evaluated. However, heterogeneous catalysis and catalytic ozonation were revealed as the rapid strategy for oxidative transformation of investigated procymidone and 3,5-DCA as compared to single oxidation by peroxide/ozone. Finally, as a novel insight of this investigation, a postulated reaction mechanism underlying the accelerated transformation of aniline metabolites via heterogeneous catalysis was explored. The findings of this study will open new avenues for evaluating heterogeneous catalysis during oxidative transformation of non-phenolic pollutants in both lab trial and field applications. This study can be expanded for use in actual field settings, using environmental samples from contaminated areas exposed to non-phenolic pesticides and their metabolites. | Sarker, Aniruddha; Islam, Tofazzal; Kim, Jang-Eok | Kyungpook Natl Univ, Sch Appl Biosci, Daegu 41566, South Korea; Bangabandhu Sheikh Mujibur Rahman Agr Univ, Inst Biotechnol & Genet Engn, Gazipur 1706, Bangladesh | Islam, Tofazzal/F-2563-2010; Sarker, Aniruddha/GYQ-6800-2022; Islam, Tofazzal/C-9184-2013 | 57211874397; 58402647300; 7601387161 | jekim@knu.ac.kr; | ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH | ENVIRON SCI POLLUT R | 0944-1344 | 1614-7499 | 30 | 2 | SCIE | ENVIRONMENTAL SCIENCES | 2023 | N/A | 0.39 | 2025-06-25 | 4 | 4 | Oxidative transformation; Heterogeneous catalysis; MnO2 catalyst; Procymidone; 3,5-Dichloroaniline; Catalytic ozonation | DEGRADATION; OZONATION; WATER | 3,5-Dichloroaniline; Catalytic ozonation; Heterogeneous catalysis; MnO<sub>2</sub> catalyst; Oxidative transformation; Procymidone | Aniline Compounds; Catalysis; Fungicides, Industrial; Hydrogen Peroxide; Manganese Compounds; Oxidative Stress; Oxides; Ozone; Water Pollutants, Chemical; aniline; aniline derivative; fungicide; hydrogen peroxide; manganese derivative; oxide; ozone; procymidone; catalysis; catalyst; chemical compound; fungicide; manganese oxide; oxidation; ozonation; secondary metabolite; transformation; catalysis; oxidative stress; water pollutant | English | 2023 | 2023-01 | 10.1007/s11356-022-22520-z | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||
| ○ | ○ | Proceedings Paper | A Resource Provisioning Manager for Edge Devices | This paper presents a virtualization-based computing and storage resource provisioning manager, termed RPM, for edge devices. Given a request from an edge device, RPM can perform dynamic volume provisioning and accelerated computation on augmented computing resources. Also, RPM can migrate application execution conducted by edge devices online. We show that RPM is a promising approach through our experiments. | Jang, Youngwoo; Na, Gap-Joo; Choi, Illyoung; Chun, In-Geol; Nam, Dukyun; Suh, Young-Kyoon | Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu, South Korea; Elect & Telecommun Res Inst, Daejeon, South Korea; Univ Arizona, CyVerse, Tucson, AZ USA | Nam, Dukyun/AFX-2852-2022 | 58704648200; 13103777300; 57202980306; 15844758900; 35805721000; 55443739900 | jangscon6568@knu.ac.kr;funkygap@etri.re.kr;iychoi@arizona.edu;igchun@etri.re.kr;dynam@knu.ac.kr;yksuh@knu.ac.kr; | 2023 20TH ANNUAL IEEE INTERNATIONAL CONFERENCE ON SENSING, COMMUNICATION, AND NETWORKING, SECON | 2473-0440 | 0.54 | 2025-06-25 | 0 | 1 | Edge devices; Dynamic volume provisioning; Resource augmentation; Kubernetes; EdgeCPS | Dynamic volume provisioning; Edge devices; EdgeCPS; Kubernetes; Resource augmentation | Application execution; Computing resource; Dynamic volume provisioning; Edge device; EdgeCPS; Kubernetes; Resource augmentation; Storage resources; Virtualizations | English | 2023 | 2023 | 10.1109/secon58729.2023.10287437 | 바로가기 | 바로가기 | 바로가기 | ||||||||||||
| ○ | Article | A Scene-Specific Object Detection System Utilizing the Advantages of Fixed-Location Cameras | This paper introduces an edge AI-based scene-specific object detection system for long-term traffic management, focusing on analyzing congestion and movement via cameras. It aims to balance fast processing and accuracy in traffic flow data analysis using edge computing. We adapt the YOLOv5 model, with four heads, to a scene-specific model that utilizes the fixed camera’s scene-specific properties. This model selectively detects objects based on scale by blocking nodes, ensuring only objects of certain sizes are identified. A decision module then selects the most suitable object detector for each scene, enhancing inference speed without significant accuracy loss, as demonstrated in our experiments. © 2023 The Korea Institute of Information and Communication Engineering. All Rights Reserved. | Lee, Jin Ho; Kim, In Su; Acosta, Hector; Kim, Hyeong Bok; Lee, Seung Won; Jung, Soon Ki | School of Computer Science and Engineering, Kyungpook National University, Daegu, 41566, South Korea; School of Computer Science and Engineering, Kyungpook National University, Daegu, 41566, South Korea; School of Computer Science and Engineering, Kyungpook National University, Daegu, 41566, South Korea; Testworks Inc., Seoul, 01000, South Korea; Testworks Inc., Seoul, 01000, South Korea; School of Computer Science and Engineering, Kyungpook National University, Daegu, 41566, South Korea | 57022795200; 57204720189; 58881264800; 57754599500; 58075930400; 57226791905 | skjung@knu.ac.kr; | Journal of Information and Communication Convergence Engineering | 2234-8255 | 21 | 4 | 0.11 | 2025-06-25 | 1 | Edge AI; Embedded System; Scene-specific System; You Only Look Once Version 5 (YOLOv5) | English | Final | 2023 | 10.56977/jicce.2023.21.4.329 | 바로가기 | 바로가기 | ||||||||||||||||
| ○ | ○ | Proceedings Paper | A Smith-Waterman Hardware Accelerator Design using Sliding Window for Genomic Sequence Alignment | This paper presents a hardware accelerator based on the Smith-Waterman algorithm, a well-known sequence alignment technique in bioinformatics. The proposed accelerator enhances its hardware efficiency significantly by employing a sliding window technique under a linear systolic array structure. The multiple processing element (PE) in the array allows parallel computations of the alignment, improving hardware resource utilization. When implemented in a 32-nm CMOS technology, the proposed Smith-Waterman hardware design enhances the area, delay, power, and energy by 80.6%, 52.9%, 67.4%, and 84.6%, respectively, versus the traditional counterpart without the sliding window scheme. | Baik, Junhyuk; Lee, Donghui; Kim, Yongtae | Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu, South Korea | 57995712600; 57266466900; 55699627900 | yongtae@knu.ac.kr; | 2023 20TH INTERNATIONAL SOC DESIGN CONFERENCE, ISOCC | 2163-9612 | 0.68 | 2025-06-25 | 0 | 1 | Smith-Waterman aigorithm; hardware accelerator; sequence alignment; sliding window; systolic array; processing element | hardware accelerator; processing element; sequence alignment; sliding window; Smith-Waterman algorithm; systolic array | Alignment; Bioinformatics; Genes; VLSI circuits; Accelerator design; Genomic sequence; Hardware accelerators; Hardware efficiency; Processing elements; Sequence alignment techniques; Sequence alignments; Sliding Window; Smith-Waterman; Smith-waterman algorithms; Systolic arrays | English | 2023 | 2023 | 10.1109/isocc59558.2023.10396043 | 바로가기 | 바로가기 | 바로가기 | |||||||||||||
| ○ | Article | A Structural Equation Model on Health Status in Delivery Workers: Based on the Theory of Salutogenesis | Purpose: This study aimed to develop and test a structural equation model on health status of delivery workers. The conceptual model was based on the theory of salutogenesis. Methods: Data were collected from 262 delivery workers working in D and K cities from August 2 to August 27, 2021. The structural equation model was used to assess the relationships among the variables. The model comprised three exogenous variables (working environment, social support, health promotion activities) and two endogenous variables (sense of coherence, health status). The data were analyzed using SPSS 23.0 and AMOS 22.0. Results: The hypothetical model showed a good fit to the data: χ2/df=2.38, TLI=.91, CFI=.93, SRMR=.08, RMSEA=.07. Out of 10 research hy-potheses, 10 were supported, and explained 62.3% of the variance in the health status of delivery workers. The model confirmed that sense of coherence was the most important factor. Health status is directly affected by working environment, social support, and health promotion ac-tivities. Health status is indirectly affected by working environment, social support, and health promotion activities through mediation of sense of coherence. Conclusion: The theory of salutogenesis is adequate to use for developing health promotion programs for delivery workers. There is a need to develop a customized program to increase health status of delivery workers by enhancing sense of coherence. © 2023 Korean Academy of Community Health Nursing. | Kim, Min Ji; Choi, Eun Suk | Department of Nursing, Kyungil University, Gyeongsan, South Korea; Department of Nursing, Research Institute of Nursing Science, Kyungpook National University, Daegu, South Korea | 58628305300; 56542373200 | eschoi2007@knu.ac.kr; | Research in Community and Public Health Nursing | 2983-0648 | 34 | 3 | 0 | 2025-06-25 | 0 | Health status; Sense of coherence; Transportation; Worker; Workplace | Korean | Final | 2023 | 10.12799/rcphn.2023.00171 | 바로가기 | 바로가기 | ||||||||||||||||
| ○ | Article | A Study on Public Building Location Evaluation Using GIS and Entropy-TOPSIS | As modern cities become larger and more overcrowded, the demand for service quality of public building increases, and the role of public buildings has expanded from simple administration to cultural and welfare services. The Public buildings play an important role in the development of cities and residents' convenience, making their location an important issue. The location of public buildings predominantly hinges on subjective assessment, revealing a scarcity of clearly defined objective criteria for location. Recently, there has been a surge in research concerning site selection through Geographic Information Systems (GIS) utilization and substantial datasets. However, when it comes to public edifices, GIS application is constrained due to the intricate nature of quantifying site-specific factors. Therefore, this research aims to facilitate the placement of public buildings by harnessing quantitative data and employing Multi-Criteria Decision Making (MCDM) methods. We propose a site selection method using MCDM, entropy weighting Method, and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). For this purpose, we first selected location factors through previous studies then quantified the data using GIS and public data. We selected Bisan-dong in Seo-gu district of Daegu Metropolitan City as our study's target site with Administrative Welfare Center as our target building for experiments and analyses. Location evaluation was made possible by considering each administrative building's factor weight in Bisan-dong targeting our building. As per the weighting analysis results accessibility emerged as most important category with site area being most important sub-factor. Comparative analysis was enabled by comparing evaluation values across each location factor. This study presents a useful method for performing location evaluations using quantitative data which can serve as foundation for future research that can be extended to various other types of public buildings. © 2023 Architectural Institute of Korea. | Yu, Jinhyeon; Kim, Taehoon; Hong, Soonmin; Choo, Seungyeon | Dept. of Architecture, Kyungpook National University, South Korea; Dept. of Architecture, Kyungpook National University, South Korea; Dept. of Architecture, Kyungpook National University, South Korea; Dept. of Architecture, Kyungpook National University, South Korea | 57914616400; 58260945000; 57734398300; 36835366900 | choo@knu.ac.kr; | Journal of the Architectural Institute of Korea | 2733-6239 | 39 | 12 | 0 | 2025-06-25 | 0 | Decision making support; Entropy Weight Method; GIS(Geographic Information System); Location evaluation; MCDM(Multi-Criteria Decision Making); Public Buildings; TOPSIS Method | Korean | Final | 2023 | 10.5659/jaik.2023.39.12.23 | 바로가기 | 바로가기 | ||||||||||||||||
| ○ | Conference paper | A Study on the Location Selection Model for a Remote Image Dispenser Using Machine Learning | One of the phenomena of regional medical disparity is the time gap during late night hours, holidays, and weekends when pharmacies are not operated, and the concentration of pharmacies or stores selling over-the-counter medicines in the metropolitan area. As a way to solve this problem, an image dispenser appeared. There is a restriction that the image dispenser should be installed only in front of a pharmacy. However, if the restrictions are followed, the temporal gap will be resolved, but the phenomenon of concentration in the metropolitan area still exists. Based on these points, this paper proposes and compares the location selection model for the image dispenser in the case where it is installed only in front of the pharmacy and the case where it is installed without being limited to the pharmacy to the policy proponent. Through thesis analysis, the elderly who use primary medical facilities and pharmacies the most were set as the target. As a result of comparing the two models using the number of the elderly population with access to medicines, it was found that the number of cases where the area where the image dispenser was installed was not restricted to a pharmacy was 573% more than the case where the country was restricted to the previous country. This shows that the case where the installation area is not limited to the pharmacy can solve the preceding problem more efficiently. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. | Ryu, Teachang; Choi, Changhoon; Kim, Ga-young | Department of Fire and Disaster Protection Engineering, Woosong University, Daejeon, South Korea; Department of Software, College of Science & Technology, Kyungpook National University, Sangju, South Korea; Faculty of General Education, Kangnam University, Yongin-si, South Korea | 58450842400; 55495946200; 57190116527 | dolga2000@kangnam.ac.kr; | Lecture Notes in Electrical Engineering | 1876-1100 | 1028 LNEE | 0 | 2025-06-25 | 0 | Elbow method; K-means; Location selection analysis; Machine learning; Video dispenser | K-means clustering; Location; Elbow method; K-means; Location selection; Location selection analyse; Location selection models; Machine-learning; Metropolitan area; Over the counters; Time gap; Video dispenser; Machine learning | English | Final | 2023 | 10.1007/978-981-99-1252-0_44 | 바로가기 | 바로가기 | ||||||||||||||||
| ○ | Article | A Study on the Vertical Articulation of Physics in the 2015 Revised National Curriculum: Focused on the Middle School Science and the High School Integrated Science; [2015 개정 교육과정 물리 영역의 연계성에 관한 연구: 중학교 과학과 고등학교 통합과학을 중심으로] | This study analyzed the vertical articulation of the physics domain between middle school science (MSS) and high school integrated science (HSIS) based on the 2015 revised national curriculum. Physics domains in five HSIS textbooks and four MSS textbooks for each grade were comparatively analyzed to check if the intent of HSIS is well embodied and to propose supplementary measures. For the articulation analysis, we utilized the taxonomy (overlap, development, and gap) according to the extent of articulation developed by Song et al. The results based on physics terms in HSIS showed that overlap, development, and gap accounted for 33.3%, 52.8%, and 13.9%, respectively. Moreover, the ratio of overlap, development, and gap varied for each HSIS chapter, and the number of related physics terms also showed a difference. Considering the object of HSIS, we recommend reducing overlaps, minimizing gaps, and increasing development. We also suggest modifying and supplementing the curriculum, developing a curriculum commentary that expresses the hierarchy of concepts, and supplementing the linkage criterion model. © 2023 The Korean Physical Society. All rights reserved. | Park, Donghee; Kwon, Munho; Ha, Sangwoo; Choi, Ho-Meoyng | Yakmok High School, Chilgok, 39827, South Korea; Kyungpook National University High School, Daegu, 41950, South Korea; Department of Physics Education, Kyungpook National University, Daegu, 41566, South Korea; Department of Physics Education, Kyungpook National University, Daegu, 41566, South Korea | 58537707600; 57208348111; 55215468100; 7404339783 | New Physics: Sae Mulli | 0374-4914 | 73 | 6 | 0.12 | 2025-06-25 | 1 | 2015 revised curriculum; Analysis of articulation; High school integrated science; Middle school science; Vertical articulation | Korean | Final | 2023 | 10.3938/npsm.73.515 | 바로가기 | 바로가기 | |||||||||||||||||
| ○ | ○ | Proceedings Paper | A STUDY ON THRESHOLDING METHODS OF DAMAGED AREA DETECTION BY WILDFIRES FOR NEWLY LAUNCHING MICROSATELLITES | The increasing deployment of microsatellites in recent years has emerged as a cost-effective and efficient alternative to traditional high-weight satellites. These smaller satellites offer the advantage of frequent revisits, allowing for the monitoring and analysis of dynamic events and changes over time. This study specifically focuses on harnessing the potential of microsatellite imagery in disaster response scenarios, with a particular emphasis on the detection and assessment of wildfires. The research explores the development of methods for the rapid and effective detection of wildfires using microsatellite data, employing the Morphological Active Contours without Edge algorithm for analysis. Additionally, the study introduces the NEONSAT satellite constellation system, a significant initiative aimed at providing efficient analysis results for disaster response efforts. Simulated datasets were utilized to test the thresholding methods, and the evaluation of results was conducted using the Normalized Burned Ratio metric. Future research will focus on validating with actual microsatellite data and comprehensively assessing the performance of different algorithms for disaster response applications. | Kim, Yeji; Song, Ahram; Lee, Hongtak; Kim, Hyun Ok; Lee, Sun Gu | Korea Aerosp Res Inst, Natl Satellite Operat & Applicat Ctr, Daejeon, South Korea; Kyungpook Natl Univ, Dept Locat Based Informat Syst, Sangju Si, South Korea | 56672284100; 56496312900; 57215433417; 39863093200; 54398799900 | IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM | 2153-6996 | 0 | 2025-06-25 | 0 | 0 | Thresholding methods; wildfires; disaster | disaster; Thresholding methods; wildfires | English | 2023 | 2023 | 10.1109/igarss52108.2023.10283272 | 바로가기 | 바로가기 | 바로가기 | |||||||||||||||
| ○ | ○ | Proceedings Paper | A Style-Based Caricature Generator | A facial caricature is a creation of new artistic and exaggerated faces which translates into a real image to convey sarcasm or humor while keeping the identity of the subject. In this work, we proposed a new way to create caricatures by exaggerating facial features like the eyes and mouth while keeping the facial contour intact and a realistic style. Our method can be categorized into two steps. First, the facial exaggeration process transformed faces into caricature face images while maintaining facial contours. Second, the appearance style generator is trained in unpaired using the generated caricature faces to produce a facial caricature that can change to any realistic style of our preference. Experimental results show our model produces more realistic and disentangled caricature images as compared to some of the previous methods. Our method can also generate caricature images from real images. | Laishram, Lamyanba; Shaheryar, Muhammad; Lee, Jong Taek; Jung, Soon Ki | Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu, South Korea | ; Shaheryar, Muhammad/NBW-9729-2025; Jung, Soon Ki/P-7687-2018 | 57219930647; 56132068000; 24341317500; 57226791905 | yanbalaishram@knu.ac.kr;shaheryar@knu.ac.kr;jongtaeklee@knu.ac.kr;skjung@knu.ac.kr; | FRONTIERS OF COMPUTER VISION, IW-FCV 2023 | 1865-0929 | 1865-0937 | 1857 | 1.96 | 2025-06-25 | 0 | 3 | Caricature; Style Generator; Generative Adversarial Network | FACES | Caricature; Generative Adversarial Network; Style Generator | Caricature; Face images; Facial caricature; Facial feature; Real images; Style generator; Generative adversarial networks | English | 2023 | 2023 | 10.1007/978-981-99-4914-4_6 | 바로가기 | 바로가기 | 바로가기 | |||||||||
| ○ | Article | A Survey on the Perception and Behavior Regarding Tinea Pedis among Korean Adults | Dermatophyte infection is one of the most common skin diseases affecting the skin, hair, and nails. Despite widespread recognition of the disease, missing details and misperceptions are commonplace in the general population. Objective: This study aimed to investigate the public perception and behavior regarding dermatophytosis of the hands and feet. Methods: This results from an online survey conducted between July 2022 and August 2022. The survey included 1,000 Korean participants aged 20 to 69 years, of whom 60% experienced symptoms of tinea pedis or onychomycosis. The questionnaire focused on the awareness and personal experience of tinea pedis and perception of the treatment of dermatophytosis. Results: Of the 1,000 participants, nearly 80% regarded tinea pedis as a common skin condition by which anyone can be affected. Furthermore, 88.4% had heard that the treatment of tinea pedis could be harmful, causing skin rash (60.4%) and worsening liver function (48.5%). Among 896 participants who noticed suspicious symptoms, 81.2% did not visit the clinic because it was not severe (50.1%) and seemed easily manageable (25.7%). Of the respondents, 84.4% preferred to meet dermatologists rather than non-dermatologist doctors regarding skin diseases, mainly because of trust in experts and belief in a faster cure. Conclusion: Providing accurate and detailed information via online media, educational campaigns, and medical papers can rectify misconceptions and improve patient appliance, contributing to public skin health. © 2023 Korean Dermatological Association. All rights reserved. | Cho, Minkyung; Lee, Yang Won; Lee, Dong Hun; Jeong, Ki-Heon; Kwon, Soon Hyo; Kim, Jung Eun; Kim, Hyojin; Na, Chan Ho; Seo, Hyun-Min; Shin, Min Kyung; Ahn, Jiyoung; Woo, Yu Ri; Lee, Ga-Young; Jang, Yong Hyun; Jung, Hye Jung; Choi, Yu Sung; Han, Tae Young; Lee, Ha-Eun; Bang, Chan Yl; Lee, Mi Woo; Kim, Dong Hyun | Department of Dermatology, CHA Bundang Medical Center, CHA University College of Medicine, Seongnam, South Korea; Department of Dermatology, Konkuk University School of Medicine, South Korea; Department of Dermatology, Seoul National University College of Medicine, South Korea; Department of Dermatology, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, South Korea; Department of Dermatology, Kyung Hee University Hospital at Gangdong, Kyung Hee University College of Medicine, Seoul, South Korea; Department of Dermatology, Soonchunhyang University Cheonan Hospital, Soonchunhyang University College of Medicine, Cheonan, South Korea; Department of Dermatology, Busan Paik Hospital, Inje University College of Medicine, Busan, South Korea; Department of Dermatology, Chosun University School of Medicine, Gwangju, South Korea; Department of Dermatology, Hanyang University Guri Hospital, Hanyang University College of Medicine, Guri, South Korea; Department of Dermatology, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, South Korea; Department of Dermatology, National Medical Center, Seoul, South Korea; Department of Dermatology, Incheon St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea; Department of Dermatology, Kangbuk Samsung Hospital, Sungkyunkwan University College of Medicine, Seoul, South Korea; Department of Dermatology, School of Medicine, Kyungpook National University, Daegu, South Korea; Department of Dermatology, National Medical Center, Seoul, South Korea; Department of Dermatology, Soonchunhyang University Seoul Hospital, Soonchunhyang University College of Medicine, South Korea; Department of Dermatology, Nowon Eulji Medical Center, Eulji University College of Medicine, South Korea; Foret Dermatology Clinic, Asan Medical Center, University of Ulsan, College of Medicine, Seoul, South Korea; Human Dermatology Clinic, Asan Medical Center, University of Ulsan, College of Medicine, Seoul, South Korea; Department of Dermatology, Asan Medical Center, University of Ulsan, College of Medicine, Seoul, South Korea; Department of Dermatology, CHA Bundang Medical Center, CHA University College of Medicine, Seongnam, South Korea | 57903140100; 15033490400; 55649570908; 22957662500; 50861268500; 56508490400; 57202104039; 24475283700; 55642437700; 57201780499; 56532916200; 57190872027; 55664272600; 57016046400; 56382664000; 57219874632; 17434022300; 59152566300; 38861053100; 58742270800; 55574224600 | Korean Journal of Dermatology | 0494-4739 | 61 | 7 | 0 | 2025-06-25 | 0 | Behavior; Dermatologists; Perception; Tinea pedis | Korean | Final | 2023 | 바로가기 | |||||||||||||||||||
| ○ | ○ | Proceedings Paper | A Transfer Learning-Based New User Recognition for Minimizing Retraining Time in Edge Deep Learning | Manually adding new users to user recognition systems can ensure high accuracy, but it is a cumbersome process. Recent research is focused on methods for automatically detecting and adding new users. Researchers consider high-performance servers essential because they utilize massive deep learning models to ensure accuracy. Moreover, obtaining a substantial amount of new user data requires both the edge node and the server to consume a significant amount of time during data exchange. To address this, researchers have explored various methods, such as conducting online learning on the edge node. However, there are many constraints due to the resource limitations of the edge node. Thus, this paper suggests a system where learning takes place on the server, and all other functions are carried out on the edge node. The proposed system suggests the use of the transfer learning method to minimize the time required for adding new users with a high similarity foot pressure dataset. Through this method, the required amount of new user data for retraining was reduced by 25 %. Additionally, a system was developed to dynamically update the deep learning model received from the server in real-time on the edge node. As a result, using a model trained on the existing 10 users as a basis, retraining 10 new users with 140 training data each achieved a recognition performance of 86 % for 20 users. Additionally, it was shown that by reducing the training data, it is possible to add a new user within 7.7 minutes, which is an 80 % decrease in time. | Heo, Dong Hyuk; Kang, Soon Ju | Kyungpook Natl Univ, Sch Elect & Eletr Engn, Daegu, South Korea | 58313533000; 55666313900 | dhheo92@knu.ac.kr;sjkang@knu.ac.kr; | 2023 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND COMPUTATIONAL INTELLIGENCE, CSCI 2023 | 2769-5670 | 0 | 2025-06-25 | 0 | 0 | Real-time Embedded System; Edge AI; Transfer Learning; Fast User Addition System | ANOMALY DETECTION | Edge AI; Fast User Addition System; Real-time Embedded System; Transfer Learning | Data reduction; Deep learning; Embedded systems; Learning systems; Edge AI; Edge nodes; Fast user addition system; Learning models; Performance; Real-time embedded systems; Recognition systems; Training data; Transfer learning; User data; Electronic data interchange | English | 2023 | 2023 | 10.1109/csci62032.2023.00031 | 바로가기 | 바로가기 | 바로가기 | ||||||||||||
| ○ | Article | A Vision-Based Ranging Algorithm Combining Monocular Camera and Laser for Indoor Positioning | The core issue for indoor positioning is reducing the ranging error. The traditional Time-of-Flight (ToF) method has errors caused by time error calculation, and the Received Signal Strength Indicator (RSSI) method requires huge calculation and data collection. Moreover, the vision-based binocular ranging method has poor performance in dark environments. Therefore, considering the above weaknesses, we designed a hybrid device based on a Monocular Camera and four Lasers (MC4L), which uses four lasers to mark the target object and record the irradiation spot with a high-definition monocular camera. Due to the angle between the laser emitter and the base, the center point and laser irradiation area will change with distance. We can obtain the corresponding relationship between the irradiated area and real distance by a logarithmic regression algorithm. In addition, we propose a new indoor positioning algorithm based on the MC4L device to control the error within 2.4 cm. © 2023, Korean Institute of Communications and Information Sciences. All rights reserved. | Yin, Nan; Sun, Yuxiang; Zou, Zhengyang; Kim, Jae-Soo | Kyungpook National University, Computer Science and Engineering, South Korea; Kyungpook National University, Software Technology Research Center, South Korea; Kyungpook National University, Department of French Language and Literature, South Korea; Kyungpook National University, Computer Science and Engineering, South Korea | 59143277000; 57202927837; 59144096500; 57191684854 | kjs@knu.ac.kr; | Journal of Korean Institute of Communications and Information Sciences | 1226-4717 | 48 | 11 | 0.27 | 2025-06-25 | 2 | Binocular ranging; Logarithmic regression; Monocular ranging; Time-of-Flight | English | Final | 2023 | 10.7840/kics.2023.48.11.1378 | 바로가기 | 바로가기 | ||||||||||||||||
| ○ | Proceedings Paper | A W-Band Low-Noise Amplifier in 50-nm InP HEMT Technology | This paper presents a W-band low noise amplifier (LNA) in 50-nm InP high-electron-mobility-transistor (HEMT) technology. The LNA employs a threestage design in common-source (CS) configuration using 2x20 mu m transistors, coplanar waveguides (CPW), metal-insulator-metal capacitors (MIM), and NiCr-based thin film resistors (TFR). The first two stages employ inductive source feedback for concurrent noise and gain matching and in-band stability. The 3rd stage utilizes resistive parallel feedback. This design shows a simulated noise figure of 1.4 dB with a measured associated gain of 14 dB at 94 GHz while consuming a DC power of 75 mW. | Mehraban, Haniye; Park, Wan-Soo; Jo, Hyeon-Bin; Choi, Su-Min; Kim, Dae-Hyun; Kim, Sang-Kuk; Yun, Jacob; Kim, Ted; Choi, Wooyeol | Oklahoma State Univ, Stillwater, OK 74078 USA; Kyungpook Natl Univ, Daegu, South Korea; QSI Inc, Cheonan, South Korea | Kim, Ted/JDW-4515-2023; Kim, Junghwan/AAQ-9204-2021; Choi, Wooyeol/AFH-7149-2022 | wchoi@okstate.edu; | 2023 IEEE TEXAS SYMPOSIUM ON WIRELESS AND MICROWAVE CIRCUITS AND SYSTEMS, WMCS | 2638-3845 | 1 | Coplanar waveguide (CPW); high-electron-mobility transistor (HEMT); indium phosphide (InP); low noise amplifier (LNA); W-band | English | 2023 | 2023 | 10.1109/wmcs58822.2023.10194275 | 바로가기 | 바로가기 | ||||||||||||||||||||
| ○ | ○ | Proceedings Paper | Abdominal CT Segmentation for Body Composition Assessment Using Network Consistency Learning | Estimating skeletal muscle (SM) and adipose tissues is an invaluable prognostic indicator in cancer treatment, major surgeries, and general health screening. Body composition is usually measured with abdominal computed tomography (CT) scans acquired in clinical settings. The whole-body SM volume is correlated with the estimated SM based on the measurement of a single two-dimensional vertebral slice. It is necessary to label a CT image at the pixel level to estimate SM, known as semantic segmentation. In this work, we trained a segmentation model using the labeled abdominal CT slices and the additional unlabeled slices. In particular, we trained two identical segmentation networks with differently initialized weights. Network Consistency Learning (NCL) allowed learning from unlabeled images by forcing the predictions from both networks to be the same. We segmented abdominal CT images from a newly created in-house dataset. The proposed approach gained 10% better performance in terms of Dice similarity score (DSC) than that obtained by a standard supervised network demonstrating the effectiveness of NCL in exploiting unlabeled images. | Ali, Shahzad; Lee, Yu Rim; Park, Soo Young; Tak, Won Young; Jung, Soon Ki | Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu, South Korea; Kyungpook Natl Univ Hosp, Kyungpook Natl Univ, Dept Internal Med, Coll Med, Daegu, South Korea | Ali, Shahzad/GPG-6925-2022; Lee, YuRim/GRF-4873-2022; Jung, Soon Ki/P-7687-2018 | 57709386500; 57194094753; 57191674344; 7004074582; 57226791905 | shahzadali@knu.ac.kr;skjung@knu.ac.kr; | 2023 45TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY, EMBC | 1557-170X | 1558-4615 | 0 | 2025-06-25 | 0 | 0 | MUSCLE | Abdomen; Adipose Tissue; Body Composition; Muscle, Skeletal; Tomography, X-Ray Computed; Biochemistry; Computerized tomography; Semantic Segmentation; Semantics; Abdominal computed tomographies; Adipose tissue; Body composition; Computed tomography images; Computed tomography scan; Health screenings; Muscle tissues; Network consistencies; Prognostic indicators; Skeletal muscle; abdomen; adipose tissue; body composition; diagnostic imaging; skeletal muscle; x-ray computed tomography; Cost effectiveness | English | 2023 | 2023 | 10.1109/embc40787.2023.10340476 | 바로가기 | 바로가기 | 바로가기 |
페이지 이동: