연구성과로 돌아가기

2023 연구성과 (255 / 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 Diagnostic imaging findings of subcutaneous mast cell tumor in a dog A 5-year-old Labrador Retriever presented with a subcutaneous mass on the right scapular region with localized calor. On magnetic resonance imaging (MRI), a heterogeneously hypointense mass was seen on T1-weighted images (WI) and hyperintense on T2WI and fat-suppressed T2WI with marginal contrast enhancement on postcontrast T1WI and invasion into the surrounding tissue. Histopathological examination of the mass confirmed subcutaneous mast cell tumor (MCT) infiltrating to the adjacent subcutaneous fat. This is the first report to describe the MRI findings of subcutaneous MCT in veterinary medicine. This study suggests that MRI may help evaluate the extent of invasion of subcutaneous MCT. © 2023 The Korean Society of Veterinary Science. Kwon, Sojeong; Jang, Min; Lee, Sang-Kwon; Lee, Kija College of Veterinary Medicine, Kyungpook National University, Daegu, 41566, South Korea; College of Veterinary Medicine, Kyungpook National University, Daegu, 41566, South Korea; College of Veterinary Medicine, Kyungpook National University, Daegu, 41566, South Korea; College of Veterinary Medicine, Kyungpook National University, Daegu, 41566, South Korea 58493352200; 55341507600; 56494541400; 35311016000 leekj@knu.ac.kr; Korean Journal of Veterinary Research 2466-1384 63 2 0 2025-06-25 0 diagnostic imaging; dogs; magnetic resonance imaging; mast cell tumor; subcutaneous English Final 2023 10.14405/kjvr.20230010 바로가기 바로가기
Proceedings Paper Differential Image-based Fast and Compatible Convolutional Layers for Multi-core Processors Convolutional neural networks with powerful visual image analysis for artificial intelligence are gaining popularity in many research fields, leading to the development of various high-performance algorithms for convolution operators present in these networks. One of these approaches is implemented with general matrix multiplication (GEMM) using the well-known im2col transform for fast convolution operations. In this paper, we propose a multi-core processor-based convolution technique for high-speed convolutional neural networks (CNNs) using differential images. The proposed method improves the convolutional layer's response speed by reducing the computational complexity and using multi-thread technology. In addition, the proposed algorithm has the advantage of being compatible with all types of CNNs. We use the darknet network to evaluate the convolutional layer's performance and show the best performance of the proposed algorithm when using 4-thread parallel processing. Hong, Sunghoon; Park, Daejin Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu, South Korea 55726350900; 55463943600 hopsison@knu.ac.kr;boltanut@knu.ac.kr; 2023 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE IN INFORMATION AND COMMUNICATION, ICAIIC 2831-6991 0.97 2025-06-25 2 2 Convolutional neural networks; Convolution techniques; Deep learning; Fast convolution; Multicore processors Convolution techniques; Convolutional neural networks; Deep learning; Fast convolution; Multicore processors Convolution; Deep learning; Image processing; Multilayer neural networks; Convolution techniques; Convolutional neural network; Deep learning; Differential image; Fast convolution; Image-analysis; Image-based; Multi-core processor; Performance; Visual image; Convolutional neural networks English 2023 2023 10.1109/icaiic57133.2023.10066972 바로가기 바로가기 바로가기
Conference paper Digital Transformation of Simulation Process to Support Decision-Making on Green Remodeling In this study, we propose a model that supports green remodeling decision-making through the digital transformation of the simulation process. Energy performance improvement measures are defined through a rule-based filter, which saves computation time and resources in the automation process. The derived combinations of improvement plans are written into a simulation file through an automated process to gain improvement plan options as an outcome, which fit the goal and budget for saving energy. In this study, model tests were performed at the sites where the green remodeling project was implemented. Computing time required for each case study building was approximately 40 min, and various efficient improvement methods were derived compared to the existing ones through experts. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. Yun, Woo-Seung; Ryu, Wontaek; Jo, Ye-Bon; Seo, Hyuncheol Kyungpook National University, Daegu, South Korea; Kyungpook National University, Daegu, South Korea; Kyungpook National University, Daegu, South Korea; Kyungpook National University, Daegu, South Korea 57221104908; 58203608600; 58451551100; 56083741500 charles@knu.ac.kr; Lecture Notes in Electrical Engineering 1876-1100 1028 LNEE 0 2025-06-25 0 Building energy simulation; Digital transformation; Green remodeling Automation; Budget control; Building energy simulations; Computation resources; Decisions makings; Digital transformation; Energy performance; Green remodeling; Improvement measure; Improvement plans; Rule-based filters; Simulation process; Decision making English Final 2023 10.1007/978-981-99-1252-0_68 바로가기 바로가기
Proceedings Paper Direct Demonstration-Based Imitation Learning and Control for Writing Task of Robot Manipulator In this paper, we propose an imitation learning method based on a direct demonstration of robot manipulators. To track the desired position and force, we designed an impedance controller. As a result of imitation learning, the robot can be acted as intended even if the initial position is different, and be able to perform a writing task well even if a different contact force is applied to the changing environment. We propose Long Short-Term Memory (LSTM)-based imitation learning method through the demonstration data. Finally, the proposed method was verified by applying the writing task with the actual industrial robot manipulator that acts as the expert's intention for the direct demonstration. Park, Sejun; Park, Ju Hyun; Lee, Sangmoon Kyungpook Natl Univ, Dept Elect & Elect Engn, Daegu, South Korea; Yeungnam Univ, Dept Elect Engn, Kyongsan, South Korea Lee, Sangmoon/C-4502-2018; Park, Ju H./J-8796-2012; Park, Sejun/KUD-3460-2024 58097901300; 15036553900; 59510733500 sjpark0710@knu.ac.kr;jessie@ynu.ac.kr;moony@knu.ac.kr; 2023 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS, ICCE 3.56 2025-06-25 3 4 Robot Manipulator; Impedance Controller; Direct Demonstration; Imitation Learning; LSTM; Writing Task Direct Demonstration; Imitation Learning; Impedance Controller; LSTM; Robot Manipulator; Writing Task Demonstrations; Flexible manipulators; Industrial robots; Learning systems; Modular robots; Robot applications; Changing environment; Contact forces; Desired position; Direct demonstration; Imitation learning; Impedance controllers; Learning methods; Robots manipulators; Writing task; Long short-term memory English 2023 2023 10.1109/icce56470.2023.10043386 바로가기 바로가기 바로가기
Review Disease Resistance-Based Management of Alternaria Black Spot in Cruciferous Crops; [십자화과 작물의 Alternaria 흑점의 질병 저항성 기반 관리] Alternaria black spots or blights in cruciferous crops have been devastating diseases worldwide and led to economic losses in broccoli, Chinese cabbage, kale, radish, rapeseed, etc. These diseases are caused by different Alternaria spp., including A. brassicae, A. brassicicola and A. raphani transmitted from infected seeds or insect vectors. Efforts to excavate disease resistance traits of cruciferous crops against Alternaria black spots or blights have been demonstrated. Genetic resource of disease resistance was investigated in the wild relatives of cruciferous crops, and different cultivars were screened under different inoculation conditions. Development of the disease-resistant lines against Alternaria black spots or blights was also tried via genetic transformation of the cruciferous crops using diverse plant defence-associated genes. Plant immunity activated by pre-treatment with chemicals, i. e. β-amino-n-butyric acid and melatonin, was suggested for reducing Alternaria black spots or blights in cruciferous crops. The disease resistance traits have also been evaluated in model plant Arabidopsis originating from different habitats. Various plant immunity-related mutants showing different disease responses from wild-type Arabidopsis provided valuable information for managing Alternaria black spots or blights in cruciferous crops. In particular, redox regulation and antioxidant responses altered in the Alternaria-infected mutants were discussed in this review. © 2023 Korean Society of Plant Pathology. All rights reserved. Lee, Young Hee; Kim, Su Min; Lee, Seoung Bin; Kim, Sang Hee; Yun, Byung-Wook; Hong, Jeum Kyu Division ofHorticultural Science, College ofAgriculture and Life Sciences, Gyeongsang National University, Jinju, 52725, South Korea, Agri-Food Bio Convergence Institute, Gyeongsang National University, Jinju, 52725, South Korea; Division ofHorticultural Science, College ofAgriculture and Life Sciences, Gyeongsang National University, Jinju, 52725, South Korea; Division ofHorticultural Science, College ofAgriculture and Life Sciences, Gyeongsang National University, Jinju, 52725, South Korea; Division ofApplied Life Science (BK21 Four Program), Plant Molecular Biology and Biotechnology Research Center, Gyeongsang National University, Jinju, 52828, South Korea; Department ofApplied Biosciences, College ofAgriculture and Life Sciences, Kyungpook National University, Daegu, 41566, South Korea; Division ofHorticultural Science, College ofAgriculture and Life Sciences, Gyeongsang National University, Jinju, 52725, South Korea, Agri-Food Bio Convergence Institute, Gyeongsang National University, Jinju, 52725, South Korea 57218134067; 59288070000; 58785950400; 57196226259; 8245123600; 7404118554 jkhong@gnu.ac.kr; Research in Plant Disease 1598-2262 29 4 0.06 2025-06-25 1 Alternaria black spot; Cruciferous plants; Disease management; Plant immunity Korean Final 2023 10.5423/rpd.2023.29.4.363 바로가기 바로가기
Book chapter Displacement field measurement of stacked geotextile tubes by digital image correlation Displacements often need to be measured to evaluate the stability of earth dams. Various instruments for measuring the displacement exist, but most contacting position sensors can measure the displacement only at a certain position. Digital image correlation is a promising technique for measuring a displacement field through a camera without any contact with the measurement points. In this study, variations in the displacement fields of stacked geotextile tubes with the water level are evaluated using digital image correlation. Experimental results show that the vertical and horizontal displacements of the bottom layers are larger than the top layers with an increased water level. The top layer mainly moves backward and then moves upward and forward. In contrast, the bottom layer consistently moves upward and forward after an initial downward and backward movement. Thus, the digital image correlation method suggested in this study may be effectively used to evaluate the behavior of a temporary dam structured with geotextile tubes. © 2023 selection and editorial matter, Askar Zhussupbekov, Assel Sarsembayeva & Victor N. Kaliakin; individual chapters, the contributors. Kim, Dong-Ju; Lee, Jong-Sub; Bae, Jun Hyung; Son, Dong Geon; Byun, Yong-Hoon; Heo, Yoon Geom Korea University, Seoul, South Korea; Korea University, Seoul, South Korea; Korea University, Seoul, South Korea; Kyungpook National University, Daegu, South Korea; Kyungpook National University, Daegu, South Korea; Kyungpook National University, Daegu, South Korea 7409760881; 55690048400; 58574596600; 58490365100; 42761048000; 58574724200 Smart Geotechnics for Smart Societies 1.77 2025-06-25 2 English Final 2023 10.1201/9781003299127-111 바로가기 바로가기
Article Dissemination and characteristics of high-level erythromycin-resistant Enterococcus faecalis from bulk tank milk of dairy companies in Korea Enterococci are environmental pathogens that can cause bovine mastitis, which is treated with macrolides, one of which is erythromycin (ERY). The aim of this study was to compare the characteristics of high-level erythromycin-resistant (HLER) Enterococcus faecalis (E. faecalis) isolates from bulk tank milk of 4 dairy companies, identified as A to D, in order to assess the threat to public health. Although isolates from company D showed the highest prevalence of E. faecalis, the prevalence of HLER E. faecalis in isolates from company A showed a significant difference. A total of 149 of the 301 HLER E. faecalis isolates showed the highest rate of resistance to tetracycline. In the distribution of antimicrobial resistance genes, 147 isolates carried the ermB gene alone and 2 isolates carried both ermA and ermB genes. Also, 72 and 60 isolates carried both tetM and tetL genes and the tetM gene alone, respectively, and 38 isolates carried the optrA gene. The prevalence of both aac(6ʹ)Ie-aph(20)-la and ant(6ʹ)-Ia genes was the highest and 104 isolates harbored the Int-Tn gene carrying the Tn916/1545-like transposon. Although the distribution of the ermB gene showed no significant difference among dairy companies, the prevalence of other resistance genes and transposons showed significant differences among dairy companies. Virulence genes were highly conserved in the HLER E. faecalis isolates. Our results indicated that there were significant differences in phenotypic and genotypic characteristics of HLER E. faecalis isolates in milk from 4 different dairy companies. A structured management protocol by companies and constant monitoring are therefore necessary to minimize public health hazards. © 2023, Canadian Veterinary Medical Association. All rights reserved. Lee, Yu Jin; Kim, Koeun; Lee, Young Ju College of Veterinary Medicine and Zoonoses Research Institute, Kyungpook National University, Daegu, 41566, South Korea; College of Veterinary Medicine and Zoonoses Research Institute, Kyungpook National University, Daegu, 41566, South Korea; College of Veterinary Medicine and Zoonoses Research Institute, Kyungpook National University, Daegu, 41566, South Korea 57352999000; 57220805028; 56612134500 youngju@knu.ac.kr; Canadian Journal of Veterinary Research 0830-9000 87 1 1.1 2025-06-25 3 Animals; Anti-Bacterial Agents; Cattle; Drug Resistance, Bacterial; Enterococcus faecalis; Erythromycin; Female; Microbial Sensitivity Tests; Milk; Republic of Korea; ampicillin; beta lactamase AmpC; chloramphenicol; ciprofloxacin; cytolysin; doxycycline; erythromycin; extended spectrum beta lactamase; gentamicin; macrolide; penicillin derivative; rifampicin; tetracycline; vancomycin; antiinfective agent; erythromycin; antibiotic resistance; antibiotic sensitivity; Article; bacterial gene; bacterium isolate; bacterium isolation; bovine; broth dilution; dairy industry; disk diffusion; DNA extraction; Enterococcus faecalis; genotype; Korea; mastitis; milk; minimum inhibitory concentration; multidrug resistance; nonhuman; phenotype; polymerase chain reaction; prevalence; public health; transposon; animal; antibiotic resistance; epidemiology; female; genetics; microbial sensitivity test; milk; South Korea; veterinary medicine English Final 2023 바로가기
Book chapter Diversity, distribution and status of phytoplasmas diseases in Myanmar Phytoplasma diseases are not considered as destructive diseases in Myanmar as compared with fungi, bacteria, viruses, and nematodes. Five “Ca. Phytoplasma” species have been identified associated with 21 plant species in Myanmar. Ca. P. aurantifolia was the most widespread strain in Myanmar followed by, “Ca. P. asteris,” “Ca. P. oryzae,” “Ca. P. cynodontis,” and “Ca. P. balanitae.” “Ca. P. balanitae” was proposed as a new Candidatus species in Myanmar. Phytoplasma diseases associated with sesame phyllody, legumes, cucurbits, tomato, sugarcane, and ornamentals are the most important economical diseases in Myanmar which are causing regular losses to the crops every year. Not much work has been done on natural reservoirs and transmission studies of phytoplasma strain reported on different crops in Myanmar. In this chapter, an updated account of phytoplasma diseases in different crops, their identification, diversity, symptoms, and distribution has been discussed. © 2023 Elsevier Inc. All rights reserved. Kyu Win, Nang Kyu; Hee-Young, Jung Department of Plant Pathology, Yezin Agricultural University, NayPyiTaw, Myanmar; Lab of Plant Pathology, College of Agriculture and Life Sciences, Kyungpook National University, Daegu, South Korea 55900503400; 7403029383 Diversity, Distribution, and Current Status 0 2025-06-25 0 Classification; Identification; Myanmar; “Candidatus Phytoplasma” species English Final 2023 10.1016/b978-0-323-91896-1.00015-5 바로가기 바로가기
Article Divide Cleaning Area Method for Multi-cleaning Robots Using Manufacturing Execution Systems Based on Contamination-level Estimation The Agricultural Products processing Center (APC) in Korea performs various tasks such as pre-cooling, sorting, packaging, and storage during the production of agricultural goods. To address the issue of dust occurring during the production processes at the APC, cleaning robots are employed. These robots are equipped to recognize the APC environment and perform cleaning tasks according to a specified pattern. However, variations in dust levels may lead to differences in cleaning effectiveness. Manufacturing Execution Systems (MES) can record the flow of agricultural products during production processes; this information can be utilized to predict dust areas and levels. The present study proposes a method based on MES to efficiently address the issue of dust at the APC. By setting the locations of the equipment within the APC and their respective discharge capacities for contaminants, and by considering the discrepancy between the input and output quantities of raw materials, the dust levels at various locations can be predicted. Based on the prediction, specific cleaning areas can be assigned to multiple cleaning robots. The utilization of MES can thus significantly increase the efficiency of multiple cleaning robots, ranging from 3% to as high as 22%. © ICROS 2023. Kwak, Jeonghoon; Shin, Heeseok; Yoon, Hyewon; Oh, Jangseok; Seo, Kap-Ho; Lee, Kyungsook Innovation Lab-Seoul, Korea Institute of Robotics and Technology Convergence (KIRO), South Korea; Innovation Lab-Seoul, Korea Institute of Robotics and Technology Convergence (KIRO), South Korea; Innovation Lab-Seoul, Korea Institute of Robotics and Technology Convergence (KIRO), South Korea; Innovation Lab-Seoul, Korea Institute of Robotics and Technology Convergence (KIRO), South Korea; Innovation Lab-Seoul, Korea Institute of Robotics and Technology Convergence (KIRO), South Korea, Department of Robot and Smart System Engineering, Kyungpook National University (KNU), South Korea; Future Security Strategy Agile Research Team, Korea Institute of Science and Technology Information (KISTI), South Korea 56963328600; 57210450396; 58701482900; 24479996400; 7201838999; 57201079674 kslee@kisti.re.kr; Journal of Institute of Control, Robotics and Systems 1976-5622 29 10 0.28 2025-06-25 2 agricultural products processing center; cleaning robot; divide cleaning area; manufacturing execution systems Agricultural robots; Cleaning; Dust; Agricultural product processing center; Area method; Cleaning robot; Contamination levels; Divide cleaning area; Dust levels; Manufacturing Execution System; Processing center; Product processing; Production process; Agricultural products Korean Final 2023 10.5302/j.icros.2023.23.0117 바로가기 바로가기
Book chapter Donor-Recipient Size Mismatch in Pediatric Renal Transplantation Donor-recipient size mismatch, which is common in pediatric kidney transplantation, can lead to various medical problems, such as hemodynamic imbalance, graft hypoperfusion, increased cardiac burden, challenges in the surgical approach, and poorer graft outcome. In this chapter, we will talk about clinical situations and outcomes originating from donor-recipient size mismatch and how to manage these problems. © Springer Nature Singapore Pte Ltd. 2023. Cho, Min Hyun Department of Pediatrics, Kyungpook National University, School of Medicine, Daegu, South Korea 7401727726 chomh@knu.ac.kr; Pediatric Solid Organ Transplantation: A Practical Handbook 0 2025-06-25 0 Donor; Kidney transplantation; Pediatric; Recipient; Size mismatch English Final 2023 10.1007/978-981-19-6909-6_4 바로가기 바로가기
Article Double Hatchet Flap for the Reconstruction of a Posterior Neck Soft Tissue Defect due to Surgical Site Infection After Posterior Cervical Spine Surgery Study Design: A case report. Objectives: To report a case of reconstruction surgery with a double hatchet flap for a posterior neck soft tissue defect due to a surgical site infection (SSI) after posterior cervical spine surgery in a 72-year-old man. Summary of Literature Review: SSI after spinal surgery may cause devastating complications and is difficult to manage. Posterior cervical surgery is associated with a higher incidence of SSI than the posterior lumbar and anterior cervical approaches. It often requires multiple surgical debridements and long-term antibiotic use. Multiple debridements could lead to irreparable large soft tissue defects requiring reconstruction surgery with local flaps. Materials and Methods: A 72-year-old male patient was referred to our center with tetraplegia (motor 2/5) after slipping down. The patient was diagnosed with a spinal cord injury with degenerative changes, ossification of the posterior longitudinal ligament, and multi-level cervical stenosis. The patient underwent laminectomy and posterolateral fusion via a posterior cervical approach, but starting on the third day after surgery, SSI progressed. Proper antibiotics were used and removal of the infected tissue was performed several times. This resulted in a large soft tissue defect in the posterior neck, and reconstruction surgery using a double hatchet flap was performed. Results: The wound healed well, without any complications. Conclusions: A double hatchet flap can be a simple option available for defects in the posterior cervical region. © 2023 Korean Society of Spine Surgery. Yoon, Sung-Hyuk; Park, Eugene J.; Min, Woo-Kie Department of Orthopaedic Surgery, Kyungpook National University Hospital, Kyungpook National University School of Medicine, Daegu, South Korea; Department of Orthopaedic Surgery, Kyungpook National University Hospital, Kyungpook National University School of Medicine, Daegu, South Korea; Department of Orthopaedic Surgery, Kyungpook National University Hospital, Kyungpook National University School of Medicine, Daegu, South Korea 56323207000; 55371642100; 8548041000 oswkmin@gmail.com; Journal of Korean Society of Spine Surgery 2093-4378 30 3 0 2025-06-25 0 Double hatchet flap; Posterior cervical spine surgery; Reconstruction; Surgical site infection English Final 2023 10.4184/jkss.2023.30.3.103 바로가기 바로가기
Article Draft Genome Sequence of Bacillus thuringiensis serovar aizawai AS23, Isolated from the Rhizosphere of Korean Melon (Cucumis melo L.) We report the draft genome sequence of Bacillus thuringiensis serovar aizawai AS23, an insecticidal strain targeting lepidopteran pests, which was isolated from the rhizosphere of Korean melon (Cucumis melo L.). The genome of strain AS23 comprising 6,846,584 bp with a G + C content of 34.83% was assembled to 11 contigs obtained using hybrid assembly. Additionally, we mined the genome for pesticidal genes, identifying several insecticidal genes, including Cry1Aa3, Cry1Ca9, Cry1Da2, Cry1Ia44, Cry2Ab41, Cry9Ea9, Spp1Aa1, and Vip3Aa86. © 2023 Korean Society for Microbiology and Biotechnology. All rights reserved. Jung, Da-Ryung; Lee, GyuDae; Lim, Kyeongmo; Lee, Yeonkyeong; Nam, Ga-Yeon; Won, Do-Yeun; Park, Na-Yun; Seo, Young-Jin; Shin, Jae-Ho Department of Applied Biosciences, Kyungpook National University, Daegu, 41566, South Korea; Department of Applied Biosciences, Kyungpook National University, Daegu, 41566, South Korea; Department of Applied Biosciences, Kyungpook National University, Daegu, 41566, South Korea; Department of Integrative Biology, Kyungpook National University, Daegu, 41566, South Korea; Department of Applied Biosciences, Kyungpook National University, Daegu, 41566, South Korea; Seongju Korean Melon Fruit and Vegetable Research Institute, Seongju, 40054, South Korea; Seongju Korean Melon Fruit and Vegetable Research Institute, Seongju, 40054, South Korea; Seongju Korean Melon Fruit and Vegetable Research Institute, Seongju, 40054, South Korea; Department of Applied Biosciences, Kyungpook National University, Daegu, 41566, South Korea, Department of Integrative Biology, Kyungpook National University, Daegu, 41566, South Korea, NGS Core Facility, Kyungpook National University, Daegu, 41566, South Korea 57221116102; 57222101785; 57805008000; 58790988900; 58791574500; 58790875400; 58791683900; 57222255148; 57224125922 jhshin@knu.ac.kr; Microbiology and Biotechnology Letters 1598-642X 51 4 0 2025-06-25 0 Bacillus thuringiensis serovar aizawai; biopesticide; draft genome; Korean melon contig; genomic DNA; ribosome RNA; single stranded DNA; transfer RNA; untranslated RNA; Article; Bacillus thuringiensis; bacterial genome; bacterium isolate; DNA base composition; gene sequence; high throughput sequencing; insecticidal activity; Korea; Lepidoptera; muskmelon; nonhuman; rhizosphere bacterium; serotype English Final 2023 10.48022/mbl.2310.10001 바로가기 바로가기
Conference paper Dual Encoding++ : Optimization of Text-Video Retrieval via Fine-tuning and Pruning Video-text retrieval involves searching for related videos based on text queries and vice versa. While video-text retrieval models effectively retrieve information, they can be slow to train and computationally expensive. Our study applies optimization and compression techniques to an existing Dual Encoding model to address these issues. In the fine-tuning phase, various learning strategies are applied to enhance the model performance. Moreover, Architecture adjustments and network pruning are used to reduce complexity. The results of the experiments show improved performance with fewer parameters. The contributions of this study include a lightweight model with enhanced performance achieved through optimization and compression techniques. These findings suggest directions for future research on model enhancements in video-text retrieval. Re-implemented code can be found at https://github.com/dongYoun2/dual-encoding-system. © 2023 IEEE. Lee, Dongyoun; Lee, Dong-Hun; Gali, Vani Priyanka; Park, Sang-Hyo Kyungpook National University, School of Computer Science and Engineering, South Korea; Kyungpook National University, School of Computer Science and Engineering, South Korea; Kyungpook National University, School of Computer Science and Engineering, South Korea; Kyungpook National University, School of Computer Science and Engineering, South Korea 58766501100; 57220892471; 58766501200; 55362514700 ehddbs6425@knu.ac.kr; 2023 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2023 0 2025-06-25 0 compression; Dual Encoding; fine-tuning; learning strategies; model size reduction; optimization; pruning.; video-text retrieval Encoding (symbols); Information retrieval; Signal encoding; Video signal processing; Compression; Dual encoding; Encodings; Fine tuning; Learning strategy; Model size reductions; Optimisations; Pruning.; Text retrieval; Video-text retrieval; Learning systems English Final 2023 10.1109/icce-asia59966.2023.10326384 바로가기 바로가기
Book chapter Dye [No abstract available] Choi, Jae Hong Department of Textile System Engineering, Kyungpook National University, Daegu, South Korea 56175157400 Encyclopedia of Color Science and Technology 0 2025-06-25 0 Dyes English Final 2023 10.1007/978-3-030-89862-5_182 바로가기 바로가기
Book chapter Dye, Functional [No abstract available] Kim, Sung-Hoon; Lee, Eun-Mi Department of Textile System Engineering, Kyungpook National University, Daegu, South Korea; Department of Textile System Engineering, Kyungpook National University, Daegu, South Korea 59902482100; 59902869700 Encyclopedia of Color Science and Technology 0 2025-06-25 0 Functionals; Dyes English Final 2023 10.1007/978-3-030-89862-5_155 바로가기 바로가기
페이지 이동:

논문 데이터 용어 설명

용어 설명
WoS Web of Science. Clarivate Analytics에서 제공하는 학술 데이터베이스입니다. 해당 논문이 WoS에 수록되어 있는지 여부를 표시합니다 (○: 수록됨).
SCOPUS Elsevier에서 제공하는 세계 최대 규모의 초록 및 인용 데이터베이스입니다. 해당 논문이 SCOPUS에 수록되어 있는지 여부를 표시합니다 (○: 수록됨).
Document Type 문헌의 유형을 나타냅니다. Article(원저), Review(리뷰), Proceeding Paper(학회논문), Editorial Material(편집자료), Letter(레터) 등으로 분류됩니다.
Title 논문의 제목입니다.
Abstract 논문의 초록(요약)입니다. 연구의 목적, 방법, 결과, 결론을 간략히 요약한 내용입니다.
Authors 논문의 저자 목록입니다. 공동 저자가 여러 명인 경우 세미콜론(;)으로 구분됩니다.
Affiliation 저자들의 소속 기관 정보입니다. 대학, 연구소, 기업 등 저자가 소속된 기관명이 표시됩니다.
ResearcherID (WoS) Web of Science의 고유 연구자 식별번호입니다. 동명이인을 구분하고 연구자의 업적을 정확하게 추적할 수 있습니다.
AuthorsID (SCOPUS) SCOPUS의 고유 저자 식별번호입니다. 연구자의 모든 출판물을 추적하고 관리하는 데 사용됩니다.
Journal 논문이 게재된 학술지의 정식 명칭입니다.
JCR Abbreviation Journal Citation Reports에서 사용하는 저널의 공식 약어입니다. 저널을 간략하게 표기할 때 사용됩니다.
ISSN International Standard Serial Number. 국제표준연속간행물번호로, 인쇄본 저널에 부여되는 고유 식별번호입니다.
eISSN Electronic ISSN. 전자 버전 저널에 부여되는 고유 식별번호입니다.
Volume 저널의 권(Volume) 번호입니다. 보통 연도별로 하나의 권이 부여됩니다.
Issue 저널의 호(Issue) 번호입니다. 한 권 내에서 여러 호로 나누어 출판되는 경우가 많습니다.
WoS Edition Web of Science의 에디션입니다. SCIE(Science Citation Index Expanded), SSCI(Social Sciences Citation Index), AHCI(Arts & Humanities Citation Index) 등으로 구분됩니다.
WoS Category Web of Science의 주제 분류 카테고리입니다. 저널과 논문이 속한 학문 분야를 나타냅니다.
JCR Year 해당 저널의 JCR(Journal Citation Reports) 지표가 산출된 연도입니다.
IF (Impact Factor) 저널 영향력 지수. 최근 2년간 발표된 논문이 해당 연도에 평균적으로 인용된 횟수를 나타냅니다. 저널의 학술적 영향력을 나타내는 대표적인 지표입니다.
JCR (%) 해당 카테고리에서 저널이 위치하는 상위 백분율입니다. 값이 낮을수록 우수한 저널임을 의미합니다 (예: 5%는 상위 5%를 의미).
FWCI Field-Weighted Citation Impact. 분야별 가중 인용 영향력 지수입니다. 논문이 받은 인용을 동일 분야, 동일 연도, 동일 문헌 유형의 평균과 비교한 값입니다. 1.0이 평균이며, 1.0보다 높으면 평균 이상의 인용을 받았음을 의미합니다.
FWCI UpdateDate FWCI 값이 마지막으로 업데이트된 날짜입니다. FWCI는 인용이 누적됨에 따라 주기적으로 업데이트됩니다.
WOS Citation Web of Science에서 집계된 해당 논문의 총 인용 횟수입니다.
SCOPUS Citation SCOPUS에서 집계된 해당 논문의 총 인용 횟수입니다.
Keywords (WoS) 저자가 논문에서 직접 지정한 키워드입니다. Web of Science에 등록된 저자 키워드 목록입니다.
KeywordsPlus (WoS) Web of Science에서 자동으로 추출한 추가 키워드입니다. 논문의 참고문헌 제목에서 자주 등장하는 단어들로 생성됩니다.
Keywords (SCOPUS) 저자가 논문에서 직접 지정한 키워드입니다. SCOPUS에 등록된 저자 키워드 목록입니다.
KeywordsPlus (SCOPUS) SCOPUS에서 자동으로 추출하거나 추가한 색인 키워드입니다.
Language 논문이 작성된 언어입니다. 대부분 English이며, 그 외 다양한 언어로 작성된 논문이 포함될 수 있습니다.
Publication Year 논문이 출판된 연도입니다.
Publication Date 논문의 정확한 출판 날짜입니다 (년-월-일 형식).
DOI Digital Object Identifier. 디지털 객체 식별자로, 논문을 고유하게 식별하는 영구적인 식별번호입니다. 이를 통해 논문의 온라인 위치를 찾을 수 있습니다.