연구성과로 돌아가기
2025 연구성과 (98 / 151)
※ 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 | Valacyclovir for the prevention of cytomegalovirus infection after kidney transplantation | BackgroundCytomegalovirus (CMV) infection is a frequent complication after kidney transplantation (KT) and has various effects on recipient and graft survival. Although guidelines recommend anti-viral prophylaxis with ganciclovir or valganciclovir, there is a demand for alternative regimen for CMV prevention. We investigated the effects of a 3-month valacyclovir-based prophylaxis on CMV infection and clinical outcomes in KT recipients using a nationwide cohort.MethodsOverall, 2,584 KT recipients from 20 transplant centers registered with the Korean Organ Transplantation Registry between May 2014 and December 2019 were analyzed in this study. The recipients were divided into valacyclovir prophylaxis and non-prophylaxis groups, a 1:3 propensity score matching was performed, and 1,036 recipients (291 and 745 in the prophylaxis and non-prophylaxis groups, respectively) were analyzed. The impact of valacyclovir-based prophylaxis on CMV after KT, other clinical outcomes, and the risk factors for CMV infection development were investigated.ResultsThe prophylaxis group showed a lower incidence of CMV infection and rejection compared to the non-prophylaxis group (3.64 vs. 10.25 events/100 person-years and 1.85 vs. 7.27 events/100 person-years, respectively). Valacyclovir prophylaxis, donor age, deceased donor, length of hospitalization after KT, anti-thymocyte globulin use, and CMV serological mismatch between the donor and recipient were independent risk factors for CMV infection after KT.ConclusionsValacyclovir prophylaxis after KT significantly reduced CMV infection and rejection. We suggest that valacyclovir could be considered as an alternative strategy for CMV prophylaxis after KT. However, our study has limitations, including its retrospective design, variability in valacyclovir dosing and CMV monitoring, and unassessed confounding factors. Further prospective studies with standardized protocols and larger cohorts are needed to validate our findings. | Kim, Jin Sug; Lee, Na Rae; Park, Kyun-Ik; Hwang, Hyeon Seok; Lee, Sang Ho; Chung, Byung Ha; Jung, Cheol Woong; Cho, Jang-Hee; Park, Woo Yeong; Kim, Hyo Jin; Jeong, Jong Cheol; Yang, Jaeseok; Lee, Yu Ho; Park, Jae Berm; Jeon, Jin Seok; Lee, Juhan; Kim, Yeong Hoon; Choi, Soo Jin Na; Oh, Jieun; Yoon, Hye Eun; Kim, Deok Gie; Shin, Ho Sik; Ban, Tae Hyun; Kim, Myoung Soo; Ko, Min Jung; Jeong, Kyung Hwan | Kyung Hee Univ, Med Ctr, Coll Med, Div Nephrol,Dept Internal Med, 26 Kyungheedae Ro, Seoul 02447, South Korea; Natl Evidence Based Healthcare Collaborating Agcy, Div Healthcare Technol Assessment Res, 400 Neungdong Ro, Seoul 04933, South Korea; Kyung Hee Univ, Coll Med, Kyung Hee Univ Hosp Gangdong, Div Nephrol,Coll Med, 892 Dongnam Ro, Seoul 05278, South Korea; Seoul St Marys Hosp, Dept Internal Med, Div Nephrol, Seoul, South Korea; Korea Univ, Anam Hosp, Dept Surg, Seoul, South Korea; Kyungpook Natl Univ, Chilgok Hosp, Sch Med, Daegu, South Korea; Keimyung Univ, Dongsan Hosp, Dept Internal Med, Div Nephrol,Sch Med, Daegu 42601, South Korea; Pusan Natl Univ, Pusan Natl Univ Hosp, Div Nephrol, Div Nephrol,Sch Med, Busan, South Korea; Seoul Natl Univ, Bundang Hosp, Dept Neurosurg, Seongnam, South Korea; Yonsei Univ, Severance Hosp, Dept Internal Med, Div Nephrol,Coll Med, 50 Yonsei Ro, Seoul, South Korea; CHA Univ, CHA Bundang Med Ctr, Dept Internal Med, Div Nephrol, Seongnam, South Korea; Sungkyunkwan Univ, Sch Med, Samsung Med Ctr, Dept Surg, Seoul, South Korea; Soonchunhyang Univ, Seoul Hosp, Dept Internal Med, Seoul, South Korea; Yonsei Univ, Coll Med, Dept Surg, Seoul, South Korea; Inje Univ, Busan Paik Hosp, Dept Internal Med, Busan, South Korea; Chonnam Natl Univ, Med Sch, Dept Surg, Gwangju, South Korea; Hallym Univ, Coll Med, Kangdong Sacred Heart Hosp, Dept Internal Med, Seoul, South Korea; Catholic Univ Korea, Incheon St Marys Hosp, Coll Med, Div Nephrol,Dept Internal Med, Incheon 21431, South Korea; Yonsei Univ, Wonju Severance Christian Hosp, Dept Surg, Wonju Coll Med, Wonju, South Korea; Kosin Univ, Coll Med, Dept Internal Med, Renal Div,Coll Med, Busan 602703, South Korea; Kosin Univ, Coll Med, Dept Pathol, Busan 602702, South Korea; Catholic Univ Korea, Eunpyeong St Marys Hosp, Coll Med, Div Nephrol,Dept Internal Med, Seoul, South Korea | ; Park, Woo Yeong/AGK-9140-2022; Kim, Jin Sug/AAY-6890-2021; Cho, Jang-hee/ABD-3534-2020 | 56313589100; 55775673200; 57277120600; 13805711400; 55890136000; 57201863822; 7402016375; 7403536291; 36344980100; 58366794000; 37761626800; 59636583700; 56344334200; 13605451500; 36120293400; 56875061400; 7410196419; 35784016900; 8409118400; 57737628900; 57198637675; 57216238599; 56119751700; 57991986800; 56727527900; 8443579300 | minjung.ko@neca.re.kr; khjeong@khu.ac.kr; | BMC INFECTIOUS DISEASES | BMC INFECT DIS | 1471-2334 | 25 | 1 | SCIE | INFECTIOUS DISEASES | 2024 | 3 | 34.7 | 0 | 2025-05-07 | 0 | 0 | Cytomegalovirus; Kidney transplantation; Valacyclovir | CONSENSUS GUIDELINES; ORAL GANCICLOVIR; VIRAL-INFECTION; PROPHYLAXIS; DISEASE; MANAGEMENT; RECIPIENTS; THERAPY; VALGANCICLOVIR; SEROPREVALENCE | Cytomegalovirus; Kidney transplantation; Valacyclovir | Adult; Antiviral Agents; Cytomegalovirus; Cytomegalovirus Infections; Female; Humans; Incidence; Kidney Transplantation; Male; Middle Aged; Republic of Korea; Retrospective Studies; Risk Factors; Valacyclovir; albumin; creatinine; ganciclovir; globulin; hemoglobin; rituximab; steroid; tacrolimus; valaciclovir; valganciclovir; antivirus agent; valaciclovir; adult; all cause mortality; antiviral therapy; Article; biopsy; cardiovascular disease; clinical outcome; cohort analysis; cystitis; cytomegalovirus infection; diabetes mellitus; encephalitis; end stage renal disease; estimated glomerular filtration rate; female; gastrointestinal disease; glomerulonephritis; graft recipient; graft survival; hepatitis; hospitalization; human; hypertension; kidney transplantation; major clinical study; male; middle aged; multicenter study; myocarditis; nephritis; outcome assessment; pancreatitis; plasmapheresis; pneumonia; propensity score; prophylaxis; prospective study; real time polymerase chain reaction; retinitis; risk factor; statistical analysis; adverse event; Cytomegalovirus; cytomegalovirus infection; drug effect; epidemiology; incidence; prevention and control; retrospective study; South Korea | English | 2025 | 2025-03-05 | 10.1186/s12879-025-10671-6 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||
| ○ | ○ | Article | A Self-Decoupled MIMO Patch Antenna System for V2X Communications | This article presents a new method for self-decoupling in multiple-input-multiple-output (MIMO) circular patch antenna (CPA) system. In the presented method, three shorting vias are strategically placed in the E-plane of the probe-fed CPA resonating in TM11 mode to create a weak-current density region on the ground plane where the adjacent antenna element can be placed. Initially, a two-element MIMO antenna system is designed, developed, and tested for vehicle-to-everything (V2X) communication in the IEEE 802.11p band. High inter-port isolation of 78 dB across the entire 5.82 to 5.98 GHz operating band is obtained. Both antenna pairs exhibit identical radiation properties, with a peak gain of 7.4 dBi. Furthermore, a 10-element MIMO antenna system is developed, showing promising results for V2X MIMO communications. | Kumar, Amit; Rana, Sandeep; Mohan, Akhilesh; Srivastava, Gunjan; Kumar, Sachin; Kim, Kang Wook | Indian Inst Technol Roorkee, Dept Elect & Commun Engn, Roorkee 247667, India; GB Pant Inst Engn & Technol, Dept Elect & Commun Engn, Pauri Garhwal 246194, India; Graph Era, Dept Elect & Commun Engn, Dehra Dun 248002, India; Galgotias Coll Engn & Technol, Dept Elect & Commun Engn, Greater Noida 201310, India; Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea | ; Kumar, Sachin/W-2211-2019 | 59912707600; 58985455400; 9239858400; 56427565100; 56907994000; 59813507900 | am@ece.iitr.ac.in; kang_kim@ee.knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 13 | SCIE | ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS | 2024 | 3.6 | 34.8 | 0 | 2025-05-07 | 0 | 0 | Antennas; Current density; Vehicle-to-everything; Current distribution; MIMO; Gain; Pins; Resonant frequency; Patch antennas; Couplings; Circular patch antenna (CPA); isolation; multiple-input-multiple-output (MIMO) antenna system; self-decoupling; V2X communication | INVERTED-F ANTENNAS; CHARACTERISTIC MODE; ARRAY; REDUCTION | Circular patch antenna (CPA); isolation; multiple-input-multiple-output (MIMO) antenna system; self-decoupling; V2X communication | Aircraft communication; Antenna feeders; Antenna grounds; Decoding; Feedback control; Magnetic levitation vehicles; Microwave antennas; Antenna system; Circular patch antenna; Circular-patch antennas; Decouplings; Isolation; Multiple inputs; Multiple outputs; Multiple-input-multiple-output antenna systems; Self-decoupling; V2X communication; Slot antennas | English | 2025 | 2025 | 10.1109/access.2025.3554151 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | Asymmetric and Harmonic Current Suppression of Dual Three-Phase PMSM Based on Double-Integral Sliding Mode Control | Asymmetric and harmonic current components, primarily the fundamental, 5(th)-, and 7(th) -order harmonics, are inherent in asymmetric dual three-phase permanent magnet synchronous motors (DTP-PMSMs). These components reduce power efficiency and may cause system instability. To cope with these issues, in this study, a novel control scheme based on double-integral sliding mode control (DISMC) is proposed to suppress the asymmetric and harmonic current components. The proposed control scheme operates by managing the currents in the x-y subspace of vector space decomposition (VSD) stationary reference frame to zero. Therefore, the proposed control scheme significantly reduces the number of required controllers and eliminates the need for coordinate transformation. In addition, owing to its extra integral term, which offers superior performance in suppressing steady-state error, the proposed method delivers enhanced performance across the entire operating range compared to the widely used quasi-proportional-integral-resonance (Q-PIR) control. Furthermore, unlike resonant controllers that require variable gains, this method employs a fixed gain, resulting in reduced current oscillations during transient conditions. Detailed simulation and experimental results have confirmed the validity and effectiveness of the proposed method. | Hyun, Jae-Ho; Maaz, Syed Mohammad; Lee, Dong-Choon; Kim, Dong-Hun | SAMSUNG Elect Co Ltd, Suwon 16677, South Korea; Yeungnam Univ, Dept Elect Engn, Gyongsan 38541, Gyeongsangbuk D, South Korea; Kyungpook Natl Univ, Dept Elect Engn, Daegu 41566, South Korea | Lee, Dong-Choon/L-6825-2019 | 58572333700; 59656531900; 8510130400; 57198637128 | dclee@yu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 13 | SCIE | ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS | 2024 | 3.6 | 34.8 | 0 | 2025-05-07 | 0 | 0 | Harmonic analysis; Transforms; Windings; Steady-state; Sliding mode control; Inverters; Current control; Couplings; Vectors; PI control; double-integral sliding mode control (DISMC); dual three-phase PMSM (DTP-PMSM); vector space decomposition (VSD) | CURRENT CONTROL SCHEME; MOTOR; COMPENSATION; MACHINE; DESIGN | Current control; double-integral sliding mode control (DISMC); dual three-phase PMSM (DTP-PMSM); vector space decomposition (VSD) | Permanent magnets; Proportional control systems; Speed regulators; Three term control systems; Two term control systems; Vector control (Electric machinery); X-Y model; 'current; Asymmetric currents; Double-integral sliding mode; Double-integral sliding mode control; Dual three-phase; Dual three-phase PMSM; Harmonic currents; Integral sliding mode control; Space decomposition; Vector space decomposition; Vector spaces | English | 2025 | 2025 | 10.1109/access.2025.3542459 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | BH Curve Tracing Method Based on Magnetic Contact Force | This paper proposes a novel method for tracing the BH curve of electrical steel based on magnetic contact force. Generally, the BH curve of electrical steel is measured using methods such as the Epstein frame or the vibrating sample magnetometer (VSM). However, these conventional methods have inherent limitations. The Epstein frame struggles with accurate measurements at high magnetic fields, while the VSM is costly and difficult to miniaturize. The proposed method addresses these challenges by precisely measuring the magnetic contact force between a sensor and a core to trace the magnetic flux density and field strength within the sample. By employing a DC magnetic field, this approach eliminates errors caused by harmonics. Additionally, the system utilizes a simple closed-loop magnetic circuit without air gaps, significantly enhancing measurement accuracy. This design enables the generation of high magnetic fields with minimal energy, allowing for a cost-effective and compact implementation that differentiates it from existing methods. To validate the proposed method, a simple electromagnet model was developed, and its performance was assessed by comparing numerical calculations with experimental measurements. The results demonstrate the effectiveness and feasibility of this innovative approach for BH curve measurement. | Seok, Chang-Hoon; Seo, Jangho; Kim, Yang-Hyun; Kim, Gui-Hwan; Choi, Hong-Soon | Daegu Mechatron & Mat Inst, Daegu 42715, South Korea; Kyungpook Natl Univ, Sch Automot Engn, Sangju 37224, South Korea; Kyungpook Natl Univ, Dept Elect Engn, Daegu 41566, South Korea | 57581239400; 12791073600; 59552360400; 57193239440; 7404338767 | j.seo@knu.ac.kr; tochs@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 13 | SCIE | ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS | 2024 | 3.6 | 34.8 | 0 | 2025-05-07 | 0 | 0 | BH curve; electromagnetic; magnetic contact force; magnetic devices; magnetic flux density; BH curve; electromagnetic; magnetic contact force; magnetic devices; magnetic flux density | BH curve; electromagnetic; magnetic contact force; magnetic devices; magnetic flux density | Electromagnets; Galvanomagnetic effects; Magnetic field measurement; Magnetic flux; Magnetic logic devices; BH curve; Electrical steels; Electromagnetics; Epstein frames; Flux densities; High magnetic fields; Magnetic contact forces; Simple++; Tracing method; Vibrating sample magnetometer; Magnetic circuits | English | 2025 | 2025 | 10.1109/access.2025.3539373 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||||
| ○ | ○ | Article | Compact 16-Port MIMO Antenna for Sub-6 GHz Communications | A 16-port multiple-input-multiple-output (MIMO) antenna for sub-6 GHz communication systems is presented in this paper. It is designed by arranging the eight dual polarized antenna elements in 2 x 4 array pattern. Each dual polarized antenna element is incorporated inside a shielded quarter-mode substrate integrated waveguide (S-QMSIW) cavity, which is orthogonally fed by a pair of 50 Omega coaxial lines. Two U-shaped slots are etched on the top-surface of S-QMSIW resonator to obtain two radiating patches in each of the dual-polarized unit element. The designed antenna radiates over the frequency band of 5.32-6.35 GHz (FBW = 17.54 %), which covers n46, n47, n96 and n102 bands of sub-6 GHz communications. Due to the strategic placement of dual polarized antenna elements, high inter-port isolation (>45 dB) over the entire operating bandwidth is attained. The overall dimensions of the proposed MIMO antenna are 88 mm x 44 mm x 0.508 mm. The designed antenna also exhibits high gain and excellent MIMO performance. | Srivastava, Gunjan; Mohan, Akhilesh; Kumar, Sachin; Choi, Hyun Chul; Kim, Kang Wook | Graph Era Deemed Univ, Dept Elect & Commun Engn, Dehra Dun 248002, India; Indian Inst Technol Roorkee, Dept Elect & Commun Engn, Roorkee 247667, India; Galgotias Coll Engn & Technol, Dept Elect & Commun Engn, Greater Noida 201310, India; Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea | Kumar, Sachin/W-2211-2019 | 56427565100; 9239858400; 56907994000; 57193342681; 57204432422 | gunjansrivastava.ece@geu.ac.in; kang_kim@ee.knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 13 | SCIE | ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS | 2024 | 3.6 | 34.8 | 0 | 2025-05-07 | 0 | 1 | Antennas; Scattering parameters; Antenna arrays; Resonant frequency; Bandwidth; MIMO; Substrates; Radio spectrum management; 5G mobile communication; Mirrors; Antenna; isolation; multiple-input-multiple-output (MIMO); quarter-mode substrate integrated waveguide (QMSIW); sub-6 GHz | INTEGRATED WAVE-GUIDE; DESIGN; SYSTEM | Antenna; isolation; multiple-input-multiple-output (MIMO); quarter-mode substrate integrated waveguide (QMSIW); sub-6 GHz | Antenna arrays; Antenna feeders; Bandwidth; Directional patterns (antenna); Masers; Microstrip antennas; MIM devices; Monolithic microwave integrated circuits; Quadrature amplitude modulation; Slot antennas; Substrate integrated waveguides; Dual polarized antennas; Isolation; Multiple input multiple output antennas; Multiple inputs; Multiple outputs; Multiple-input-multiple-output; Polarized antenna elements; Quarter-mode substrate integrated waveguide; Sub-6 GHz; Substrate-integrated waveguides; Microwave antennas | English | 2025 | 2025 | 10.1109/access.2025.3541738 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | Conditional Generation of Building Bubble Diagrams Based on Stochastic Differential Equations | This study introduces a novel conditional generative model based on stochastic differential equations (SDEs) for synthesizing architectural bubble diagrams that meet specific customer requirements. The forward SDE progressively injects noise into the data, transforming it into a tractable prior distribution, while the reverse SDE removes the noise to reconstruct the original data distribution. Since the reverse SDE relies on the gradient of the data distribution (i.e., the score function), we employ a neural network to approximate these gradients. The trained score-based model enables conditional sampling from pure noise to generate new diagrams. To evaluate the quality of the generated outputs, we propose an effective metric tailored to conditionally generated graphs. Experimental results demonstrate that the proposed framework produces high-quality diagrams that adhere to specified structural constraints. | Wei, Zhiwen; Lee, Joonki; Gu, Hyeongmo; Choo, Seungyeon; Kim, Jaeil | Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea; Kyungpook Natl Univ, Sch Architecture, Daegu 41566, South Korea | wei, zhiwen/MIP-4835-2025 | 57939755200; 59905250400; 59905864500; 36835366900; 57211615348 | jaeilkim@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 13 | SCIE | ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS | 2024 | 3.6 | 34.8 | 0 | 2025-06-11 | 0 | 0 | Noise; Noise reduction; Mathematical models; Training; Data models; Stochastic processes; Buildings; Semantics; Noise measurement; Diffusion models; Graph generation; conditional generation; graph neural network | GRAPH GENERATION | conditional generation; Graph generation; graph neural network | Graph neural networks; Graphic methods; Network theory (graphs); Stochastic models; Conditional generation; Customer requirements; Data distribution; Generative model; Graph generation; Graph neural networks; Model-based OPC; Prior distribution; Score function; Stochastic differential equations; Differential equations | English | 2025 | 2025 | 10.1109/access.2025.3571825 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | Deep Learning for Video Fluoroscopic Swallowing Study Analysis: A Survey on Classification, Detection, and Segmentation Techniques | Deep learning has significantly advanced the analysis of Video Fluoroscopic Swallowing Study data, an essential diagnostic tool for dysphagia assessment. This review explores recent applications of deep learning across key VFSS analysis tasks, including classification, detection, and segmentation. Classification methods utilizing convolutional neural networks achieve high accuracy, ranging from 91.7% to 95.98%, and Area Under the ROC Curve scores between 0.71 and 0.97, thus enhancing the consistency and reliability of swallowing phase identification. Detection approaches employing advanced deep learning architectures effectively localize anatomical landmarks and temporal swallowing events, reaching Mean Average Precision values of up to 0.89 and tracking errors as low as 2.38 pixels. Segmentation techniques based on variants of U-Net and related architectures accurately delineate critical anatomical regions, with Dice Similarity Coefficients ranging from 0.67 to 0.90. Collectively, these advances substantially improve VFSS interpretation by increasing accuracy, reducing subjective variability, and streamlining clinical workflows. This survey summarizes recent methodologies and discusses strategies for dataset collection and preprocessing, including both proprietary and limited publicly available datasets, discusses ongoing challenges such as computational demands and dataset diversity, and highlights future directions in leveraging deep learning to enhance dysphagia diagnosis and treatment. | Fakhry, Ahmed; Antony, Sarah Mary; Park, Eunhee; Lee, Jong Taek | Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea; Kyungpook Natl Univ, Sch Med, Dept Rehabil Med, Daegu 41944, South Korea; Kyungpook Natl Univ, Dept Rehabil Med, Chilgok Hosp, Daegu 41404, South Korea | Emad El-Din, Ahmed/KSL-9541-2024 | 59026744800; 59923815400; 56107216400; 24341317500 | ehmdpark@knu.ac.kr; jongtaeklee@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 13 | SCIE | ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS | 2024 | 3.6 | 34.8 | 0 | 2025-06-11 | 0 | 0 | Deep learning; Image segmentation; Three-dimensional displays; Computational modeling; Accuracy; Surveys; Image classification; Data models; Video sequences; Training; Classification; deep learning; detection; segmentation; video fluoroscopic swallowing study | TRACKING | Classification; deep learning; detection; segmentation; video fluoroscopic swallowing study | Convolutional neural networks; Classification methods; Classification technique; Convolutional neural network; Deep learning; Detection; Diagnostics tools; High-accuracy; Segmentation; Segmentation techniques; Video fluoroscopic swallowing study; Image segmentation | English | 2025 | 2025 | 10.1109/access.2025.3573282 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | DRANet: Deep Learning-Based Automatic White Balancing Approach to CVCC | As a core component of the image processing pipeline, an image signal processor plays a critical role in automatic white balancing (AWB) for computer vision color constancy (CVCC). With the recent advent of deep convolutional neural network (DCNN), image signal processors have experienced enormous progress in CVCC. A myriad of deep learning-based CVCC models have emerged and outperformed their statistics-based, shallow counterparts. In this context, this article presents a novel deep learning-based AWB approach: the Dual Residual Aggregated Network (DRANet). Homogeneous Dual Residual Blocks (DRBs) are a key component of the proposed DRANet, intended to design the architecture with high cardinality. The homogeneous DRBs perform transformations simultaneously and their outputs are processed in a concatenating manner. This characterizes the proposed DRANet as a simple and wide but still deep structure which contributes to advancing illumination estimation accuracy to an innovative level and addressing the overfitting and long-term dependency issues that conventional approaches have long been struggling with. The proposed DRANet offers another advantage that comes with high cardinality, that is, a reduction in the number of parameters necessary to run the architecture. The experimental results provide compelling evidence that the proposed AWB approach has achieved an innovative progress in illumination estimation accuracy, as well as validating the invariance of both illumination and image device. | Choi, Ho-Hyoung | Kyungpook Natl Univ, Adv Dent Device Dev Inst, Sch Dent, Daegu 41940, South Korea | 37048369000 | chhman2000@msn.com; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 13 | SCIE | ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS | 2024 | 3.6 | 34.8 | 0 | 2025-05-07 | 1 | 1 | Image color analysis; Computer architecture; Accuracy; Transforms; Lighting; Estimation; Supervised learning; Computational modeling; Convolutional neural networks; Overfitting; Deep learning-based CVCC; DRANet; illuminant estimation; automatic white balancing; dual residual block | COLOR CONSTANCY; ILLUMINATION ESTIMATION; IMAGE-CONTRAST; ALGORITHM; OPTIMIZATION; FRAMEWORK; MODEL | automatic white balancing; Deep learning-based CVCC; DRANet; dual residual block; illuminant estimation | Color image processing; Deep neural networks; Gluing; Aggregated networks; Automatic white balancing; Colour constancy; Deep learning-based computer vision color constancy; Dual residual aggregated network; Dual residual block; Illuminant estimation; Image signal; Signal processor; White balancing; Pipeline processing systems | English | 2025 | 2025 | 10.1109/access.2025.3545633 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | Drone Video Anomaly Detection by Future Segmentation Prediction and Spatio- Temporal Relational Modeling | In traffic surveillance, accurate video anomaly detection is vital for public safety, yet environmental changes, occlusions, and visual obstructions pose significant challenges. In this research, we introduce DAD-FSM, an innovative drone-based video anomaly detection system that leverages a spatio-temporal relational cross-transformer to enhance the encoding of visual and temporal features for future segmentation. Additionally, we propose the motion-aware frame prediction loss function (MAFL) to improve the model's representation and the background and foreground separation of moving objects. Our method achieves state-of-the-art (SOTA) AUC scores of 68.13% on the UIT-ADrone dataset and 73.5% mAUC on the Drone-Anomaly dataset, surpassing previous methods by 2.68% and 5.71% respectively. The approach is further validated on the CUHK Avenue dataset, underscoring its global applicability and effectiveness in diverse traffic scenarios. These results demonstrate the potential of our model for broad use in traffic surveillance applications. | Fakhry, Ahmed; Lee, Janghoon; Lee, Jong Taek | Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea | Emad El-Din, Ahmed/KSL-9541-2024 | 59026744800; 59544298800; 59484914800 | jongtaeklee@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 13 | SCIE | ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS | 2024 | 3.6 | 34.8 | 0 | 2025-05-07 | 0 | 2 | Anomaly detection; Drones; Predictive models; Feature extraction; Visualization; Transformers; Decoding; Video sequences; Traffic control; Surveillance; Deep learning; drone anomaly detection; future segmentation prediction; traffic surveillance | Deep learning; drone anomaly detection; future segmentation prediction; traffic surveillance | Aircraft detection; Prediction models; Anomaly detection; Anomaly detection systems; Deep learning; Drone anomaly detection; Environmental change; Future segmentation prediction; Public safety; Relational modeling; Spatio-temporal; Traffic surveillance; Drones | English | 2025 | 2025 | 10.1109/access.2025.3536623 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | Edge-Preserving Probabilistic Downsampling for Reliable Medical Segmentation in Resource-Constrained Environments | Downsampling, often necessitated due to resource constraints such as limited memory, development timelines, or the need to accelerate learning from large volumes of unlabeled medical data, results in the loss of fine-grained details, including small objects and thin class boundaries. When applied to ground truth (GT) labels without proper care, downsampling can significantly impair the segmentation network's ability to accurately interpret and predict detailed features. This, in turn, leads to a degraded performance compared to networks trained on higher-resolution labels. This situation exemplifies the trade-off between computational efficiency and segmentation accuracy, with higher downsampling factors further impairing performance. Preserving critical information during label downsampling is particularly crucial for medical image segmentation. This study introduces a novel approach, Edge-Preserving Probabilistic Downsampling (EPD), designed to retain critical details and bridge the performance gap between networks trained on original and downsampled resolutions. It leverages class uncertainty within a local window to produce soft labels, with the window size determining the downsampling factor. This approach enables segmentation networks to maintain high-quality predictions at lower resolutions. Beyond preserving edge details more effectively than conventional nearest-neighbor downsampling, the proposed algorithm, when adapted for images, exhibits notable performance improvements over conventional bilinear interpolation. Experimental results indicate EPD improves Intersection over Union (IoU) for a multi-class abdominal CT dataset by 2.54%, 10.66%, and 16.31% when downsampling to 1/2, 1/4, and 1/8, respectively, compared to conventional interpolation methods. | Ali, Shahzad; Lee, Yu Rim; Park, Soo Young; Tak, Won Young; Jung, Soon Ki | Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea; Kyungpook Natl Univ, Kyungpook Natl Univ Hosp, Coll Med, Dept Internal Med, Daegu 41944, South Korea | ; Jung, Soon Ki/P-7687-2018; Ali, Shahzad/GPG-6925-2022 | 57709386500; 57194094753; 57191674344; 7004074582; 57226791905 | skjung@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 13 | SCIE | ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS | 2024 | 3.6 | 34.8 | 0 | 2025-05-07 | 0 | 0 | Interpolation; Biomedical imaging; Image edge detection; Probabilistic logic; Libraries; Uncertainty; Image coding; Training; Reliability; Principal component analysis; Downsampling ground truth; resizing segmentation labels; soft labels; nearest neighbor interpolation; bilinear interpolation; semantic segmentation; multi-class segmentation | bilinear interpolation; Downsampling ground truth; multi-class segmentation; nearest neighbor interpolation; resizing segmentation labels; semantic segmentation; soft labels | Computerized tomography; Image enhancement; Medical image processing; Deep learning in medical imaging; Down sampling; Edge preserving; Edge-preserving downsampling; Labelings; Medical image segmentation; Multi-class segmentations; Probabilistic labeling; Probabilistics; Semantic segmentation; Soft labels; Semantic Segmentation | English | 2025 | 2025 | 10.1109/access.2025.3536286 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | Enhanced Multi-Pill Detection and Recognition Using VFI Augmentation and Auto-Labeling for Limited Single-Pill Data | This study presents a method for object detection and recognition to identify the positions and types of pills in images containing multiple pills using a small-scale dataset of single-pill images for training. The proposed approach aims to detect multiple pills at the final stage despite the initial training data, which includes only single pills. The method consists of three primary steps. First, a data augmentation technique is introduced to prevent overfitting and improve learning efficiency. This augmentation uses a video frame interpolation (VFI) technique based on the latent diffusion model (LDM). A capturing system is developed for this purpose, and differences between images are used as additional information in weight maps to train the LDM. Second, an automatic labeling system is proposed to generate label data for the paired dataset efficiently. Accurate labeling requires the position and type of pills as training data, but manually labeling the augmented dataset of 61,440 images would be costly. Therefore, an automatic labeling system using an attention map and a deep U-Net is proposed to generate the label data efficiently. Third, a method is presented to detect the position and type of multiple pills based on a training dataset containing only single-pill images. Reliable detection and recognition of multiple pills usually require datasets containing various pill combinations. However, as the number of classes increases, the possible combinations grow exponentially. To address this, we propose a system that learns from single-pill images to detect multiple pills accurately. This study uses a dataset containing 40 types of pills for experimentation, and the results demonstrate superior precision, recall, individual pill accuracy, and image accuracy compared to other methods. | Lee, Seung-Hwan; Son, Dong-Min; Lee, Sung-Hak | Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea | Son, Dong-Min/LZH-4025-2025 | 58149054300; 57216612214; 7601395661 | shak2@ee.knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 13 | SCIE | ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS | 2024 | 3.6 | 34.8 | 0 | 2025-05-07 | 0 | 0 | Object detection and recognition; data augmentation; video frame interpolation; automatic labeling system; Object detection and recognition; data augmentation; video frame interpolation; automatic labeling system | OBJECT DETECTION | automatic labeling system; data augmentation; Object detection and recognition; video frame interpolation | Data accuracy; Labeled data; Network security; Automatic labeling system; Automatic labelling; Data augmentation; Frame interpolation; Labelings; Labelling systems; Object detection and recognition; Training data; Video frame; Video frame interpolation; Interpolation | English | 2025 | 2025 | 10.1109/access.2025.3557569 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | Enhancing User Experience in Free and Open-Source Software: An Integrated Maturity Model Framework | Free and open-source software has rapidly grown and garnered considerable attention in recent years. However, the design complexities and guidelines inherent to Free and Open Source Software (FOSS) pose a challenging task in enhancing the User Experience (UX) of FOSS. Several pre-existing models have significantly contributed to the existing body of knowledge, yet they often overlook FOSS-specific attributes that establish a direct correlation with the efficiency of the UX in FOSS. To address this gap, the study proposes a FOSS UX enhancement model (FUEM) designed to align with current FOSS practices and guidelines, aiming to improve user experience in free and open-source software. The proposed model consists of six levels, with each level encompassing UX maturity influencing factors (UMXIF) identified in prior research. These factors are re-evaluated through a Likert scale questionnaire to gather feedback from developers, project managers, and UI/UX designers, as the previous study solely included the perspectives of UX experts. Our findings reveal that these factors positively impact FOSS projects, and integrating them into FUEM will enable the FOSS community to ascertain their level of UX maturity and identify which missing UMXIF they must adopt to progress to the next stage of UX maturity in FUEM. Furthermore, the tailored model developed for FOSS is validated through feedback analysis of expert reviews and quantitative analysis employing a one-way ANOVA test. The ANOVA test indicates that the p-value exceeds the significant threshold of. 05, suggesting that the FOSS UX model can considerably enhance UX in FOSS projects by providing a structured pathway for improving UX maturity, serving as a valuable resource for the FOSS community, guiding the development of more user-centric open-source software, and fostering a deeper understanding of UX maturity practices explicitly tailored for FOSS environments. | Zamir, Elif; Rehman, Abdul; Zamir, Sara; Al-Yarimi, Fuad A. M.; Abbas, Assad | COMSATS Univ Islamabad, Dept Comp Sci, Islamabad 45550, Pakistan; Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea; King Khalid Univ, Dept Comp Sci, Abha 61421, Saudi Arabia | Al Yarimi, Fuad/CAA-2602-2022; Rehman, Abdul/D-5630-2019 | 59534018400; 57200894071; 59534368400; 57203456925; 56349574400 | a.rehman.knu@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 13 | SCIE | ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS | 2024 | 3.6 | 34.8 | 0 | 2025-05-07 | 0 | 0 | User experience; Usability; Open source software; Guidelines; Biological system modeling; Standards organizations; Companies; Computer science; Computational modeling; User centered design; Exploratory factor analysis; free and open-source software; FOSS UX enhancement model; Kaiser Meyer Olkin; principles axis factoring; user experience; user experience maturity influencing factor | USABILITY; QUALITY | Exploratory factor analysis; FOSS UX enhancement model; free and open-source software; Kaiser Meyer Olkin; principles axis factoring; user experience; user experience maturity influencing factor | Open source software; Software testing; Exploratory factor analyze; Factors analysis; Free and open source software UX enhancement model; Free and open source softwares; Kaiser mey olkin; Principle axes; Principle axis factoring; User experience maturity influencing factor; Users' experiences | English | 2025 | 2025 | 10.1109/access.2025.3543304 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | Extended State Observer-Based Estimation for Nonlinear Markov Jump Systems With Dynamic Event-Triggered Communication | This paper primarily investigates the extended state observer design issue for nonlinear Markov jump systems under limited communication bandwidth. In order to achieve reasonable network resource configurations while estimating the system states and total disturbances, a continuous-time dynamic event-triggered strategy is incorporated into the observer design. Accordingly, the transmission of the measured output occurs only when the predefined conditions are satisfied. In contrast to the conventional static triggering strategy, the dynamic event-triggered mechanism enables adaptive threshold adjustment by introducing an internal dynamic variable. In addition, a carefully constructed intermediate variable is considered to indirectly obtain the estimate of the extended state. Then, combining Lyapunov method with stochastic analysis technique, it is proved that the estimation error is exponentially ultimately bounded in mean square under the proposal. At last, a case study of the mass-spring system with four operating modes is presented to illustrate the feasibility of the proposed design approach. | Zhang, Pengcheng; Jiao, Shiyu; Chen, Jun; Lee, Sangmoon | Nanjing Univ Sci & Technol, Sch Automat, Nanjing 210094, Peoples R China; Huaiyin Inst Technol, Fac Automat, Huaian 223003, Peoples R China; Jiangsu Normal Univ, Sch Elect Engn & Automat, Xuzhou 221116, Peoples R China; Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea | Jiao, Shiyu/HNB-8103-2023; Zhang, Pengcheng/LKN-4427-2024; Lee, Sangmoon/C-4502-2018 | 58043447700; 57200945980; 57206951849; 59510733500 | moony@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 13 | SCIE | ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS | 2024 | 3.6 | 34.8 | 0 | 2025-05-07 | 0 | 0 | Uncertainty; Observers; Event detection; Vehicle dynamics; Protocols; Topology; Nonlinear dynamical systems; Automation; Analytical models; Tuning; Markov jump system; extended state observer; intermediate variable; dynamic event triggering | TIME; STABILITY | dynamic event triggering; extended state observer; intermediate variable; Markov jump system | Markov processes; Nonlinear analysis; Stochastic systems; Dynamic event triggering; Dynamic events; Event-triggered; Events triggering; Extended state observer; Intermediate variable; Markov jump system; Nonlinear markov jump systems; Observer-based; Observers designs; Continuous time systems | English | 2025 | 2025 | 10.1109/access.2025.3539586 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | From Data to Decisions: The Power of Machine Learning in Business Recommendations | This research aims to explore the impact of machine learning (ML) on the evolution and efficacy of recommendation systems (RS), particularly in the context of their growing significance in commercial business environments. Methodologically, the study delves into the role of ML in crafting and refining these systems, focusing on aspects such as data sourcing, feature engineering, and the importance of evaluation metrics, thereby highlighting the iterative nature of enhancing recommendation algorithms. The deployment of recommendation engines (RE), driven by advanced algorithms and data analytics, is explored across various domains, showcasing their significant impact on user experience and decision-making processes. These REs not only streamline information discovery and enhance collaboration, but also accelerate knowledge acquisition, which is vital in navigating the digital landscape for businesses. They contribute significantly to sales, revenue, and the competitive edge of enterprises by offering improved recommendations that align with the individual needs of the customer. The research identifies the growing expectations of users for a seamless and intuitive online experience, where content is personalized and dynamically adapted to changing preferences. Future research includes exploring advances in deep learning models, ethical considerations in the deployment of RS, and addressing scalability challenges. This study emphasizes the indispensability of comprehending and using ML in RS for researchers and practitioners to tap into the full potential of personalized recommendation in commercial business prospects. | Gangadharan, Kapilya; Purandaran, Anoop; Malathi, K.; Subramanian, Barathi; Jeyaraj, Rathinaraja; Jung, Soon Ki | Saveetha Inst Med & Tech Sci, Saveetha Sch Engn, Chennai 600077, India; Lowes Co Inc, Charlotte, NC 28262 USA; Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea; Univ Houston Victoria, Dept Comp & Informat Sci, Victoria, TX 77901 USA | ; Jung, Soon Ki/P-7687-2018; Subramanian, Barathi/HLP-9548-2023; Jeyaraj, Rathinaraja/ABB-7781-2021; Gangadharan, Kapilya/JSK-8922-2023 | 58902739800; 58902885400; 56294527300; 57221053219; 57203111601; 57226791905 | skjung@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 13 | SCIE | ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS | 2024 | 3.6 | 34.8 | 3.67 | 2025-05-07 | 1 | 1 | Business; Motion pictures; User experience; Accuracy; Electronic commerce; Companies; Optimization; Engines; Data models; Analytical models; Business recommendation; data governance and management; machine learning; personalized recommendations; recommendation systems | USER INTEREST; SYSTEM; OPTIMIZATION; FACTORIZATION; INFORMATION; RESOURCES; TOOLS | Business recommendation; data governance and management; machine learning; personalized recommendations; recommendation systems | Business environments; Business recommendation; Commercial business; Data governance and management; Data governances; Data sourcing; Feature engineerings; Machine-learning; Personalized recommendation; Power; Adversarial machine learning | English | 2025 | 2025 | 10.1109/access.2025.3532697 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | Identifying AC Control Patterns From a Massive Longitudinal Log Dataset Using Deep Clustering | An air conditioner is a household appliance and one of the most innovative inventions, primarily used to cool indoor temperatures and lower humidity to provide a comfortable environment. The sale of air conditioners increased continuously, reaching approximately 135 million units annually, with nearly 1.6 billion devices currently in operation. While it is important to devise and develop technologies for improving their energy efficiency, it is even more important to analytically investigate the performance of its main objective, user experience, or comfortableness. Here, we collected a massive set of logs collected in a longitudinal manner during the summer season of the year 2021 from approximately 1.47 million AC devices manufactured by LG Electronics and located in South Korea. Among the many features in the log, the current temperature, target temperature, humidity, energy consumption, and wind strength features were used to identify clusters embedding meaningful time-course feature patterns. We particularly focused on identifying patterns and user groups who either actively or inactively controlled the target temperature since such behavior likely indicates a discomforting air state. As a result, a total of 10 distinctive patterns and 14 representative user groups were searched. Among the 10 patterns, five showed active target temperature control and the other five inactive control. Regardless of control activity, all patterns are highly correlated with the progressing weather conditions during the summer. The feature patterns of the actively controlled group significantly differed from those of the inactively controlled group. Further investigation of the semantic difference between the groups would provide valuable research directions for improving the user experience of AC usage. It may also be used to devise an AI-driven automatic AC controller to minimize user intervention while providing an optimal air state. | Bae, Seunghwan; Kim, Donghee; Seong, Seokhwan; Jang, Jaeyeon; Suh, Young-Kyoon; Kim, Honghyun; Han, Dongwoo; Jung, Inuk | Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea; Seoul Natl Univ Hosp Biomed Res Inst, Seoul 03082, South Korea; LG Elect Home Appliance & Air Solut Co, Air Solut Res & Dev Lab, Changwon Si 51554, Gyeongsangnam D, South Korea | 59713431600; 59712796700; 59713431700; 57392305900; 55443739900; 59713003200; 59714055000; 56067575500 | inukjung@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 13 | SCIE | ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS | 2024 | 3.6 | 34.8 | 0 | 2025-05-07 | 0 | 0 | Humidity; Temperature measurement; Indexes; User experience; Temperature distribution; Object recognition; Market research; Home appliances; Heating systems; Focusing; Air conditioner; big data; time series; clustering; deep learning | THERMAL COMFORT; TEMPERATURE | Air conditioner; big data; clustering; deep learning; time series | Air conditioner; Air state; Clusterings; Deep learning; Feature pattern; Target temperature; Temperature/ humidities; Times series; User groups; Users' experiences; Domestic appliances | English | 2025 | 2025 | 10.1109/access.2025.3554749 | 바로가기 | 바로가기 | 바로가기 | 바로가기 |
페이지 이동: