연구성과로 돌아가기

2023 연구성과 (275 / 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 Quality and physicochemical characteristics of germinated brown-rice-based weaning foods; [발아현미 이유식의 품질 및 이화학적 특성] This study investigated the quality and physicochemical characteristics of weaning foods containing germinated brown-rice flour. Ten weaning foods were prepared using untreated and roasted grain flours (germinated brown rice, oat, waxy rice, millet, and white rice). The moisture content of the weaning foods ranged from 5.02 to 13.66%. Grain roasting decreased the particle size, pasting viscosity, and solubility of the weaning foods, whereas it increased the sugar content and water-holding capacity. The pH values were not significantly different among the tested weaning foods. The total polyphenol content of the weaning foods containing roasted grain flour was higher than that of the foods containing unroasted grain flour. Weaning foods containing 100% roasted germinated brown-rice flour showed the highest antioxidant activity among the tested weaning foods. © The Korean Society of Food Science and Technology. Jeong, Duyun; Chung, Hyun-Jung Department of Food and Service Industry, Kyungpook National University, South Korea; Division of Food and Nutrition, Chonnam National University, South Korea 57203059723; 7404006790 hchung@jnu.ac.kr; Korean Journal of Food Science and Technology 0367-6293 55 3 0.16 2025-06-25 1 germinated brown rice; physicochemical properties; quality characteristics; roasting; weaning food Korean Final 2023 10.9721/kjfst.2023.55.3.244 바로가기 바로가기
Article Quality characteristics of different parts of garlic sprouts produced by smart farms during growth; [스마트팜 생산 새싹마늘의 부위별 및 생육 기간에 따른 품질 특성] Garlic sprouts can provide data on functional and food processing materials. This study compared the leaves, bulbs, and roots of garlic sprouts grown on smart farms during two growth periods (20 and 25 days). In addition, data for garlic bulbs grown in open fields were presented as reference materials. All garlic sprouts’ total free sugar content decreased as the growth period increased. All plant parts’ total organic acid content decreased as the growth period progressed, except for the root section. Potassium, phosphorus, and sulfur content increased during growth in all parts of the garlic sprouts. Alliin content decreased in all parts of the plant over time, whereas thiosulfinate content increased in the roots but decreased in the leaves and bulbs. Total polyphenol content increased in all parts of the plant during the growth period, except for the bulb, whereas the flavonoid content did not change significantly over time. The 2,2-diphenyl-1-picrylhydrazy (DPPH) and 2,2′-azinobis (3-ethylben-zothiazoline 6-sulfonate) (ABTS) free radical scavenging activities, as well as the superoxide dismutase (SOD)-like activity of garlic sprouts were 37.45-65.47%, 59.12-89.81%, and 89.52-98.59%, respectively. These activities tend to decrease during the growth period. Here, we showed that garlic sprouts have higher levels of functional substances and physiological activities than general garlic sprouts. It was also determined that a growth period of 20 days was suitable for garlic sprouts. Data for research on functional and food-processing materials can be obtained by analyzing garlic sprouts produced by smart farms. Copyright © 2023 The Korean Society of Food Preservation. Choi, Yu-Ri; Kim, Su-Hwan; Lee, Chae-Mi; Lee, Dong-Hun; Lee, Chae-Yun; Jo, Hyeong-Woo; Jeong, Jae-Hee; Oh, Imkyung; Ha, Ho-Kyung; Kim, Jungsil; Huh, Chang-Ki Department of Food Science and Technology, Sunchon National University, Suncheon, 57922, South Korea; Research Institute of Food Industry, Sunchon National University, Suncheon, 57922, South Korea; Jeonnam Institute of Natural Resources Research, Jangheung, 59338, South Korea; Department of Food Science and Technology, Sunchon National University, Suncheon, 57922, South Korea; Department of Food Science and Technology, Sunchon National University, Suncheon, 57922, South Korea; Department of Food Science and Technology, Sunchon National University, Suncheon, 57922, South Korea; Department of Food Science and Technology, Sunchon National University, Suncheon, 57922, South Korea; Department of Food Science and Technology, Sunchon National University, Suncheon, 57922, South Korea; Department of Animal Science and Technology, Sunchon National University, Suncheon, 57922, South Korea; Department of Bio-Industrial Machinery Engineering, Kyungpook National University, Daegu, 41566, South Korea; Department of Food Science and Technology, Sunchon National University, Suncheon, 57922, South Korea, Research Institute of Food Industry, Sunchon National University, Suncheon, 57922, South Korea 57826578300; 57200314827; 57278116500; 57826065800; 57825567300; 58482371900; 57208102458; 7101831013; 57203253755; 56523661500; 56487159600 hck1008@scnu.ac.kr; Korean Journal of Food Preservation 1738-7248 30 2 0 2025-06-25 0 alliin; garlic bulb; garlic sprout; quality characteristics; total thiosulfinate English Final 2023 10.11002/kjfp.2022.30.2.272 바로가기 바로가기
Article Quality Characteristics of Gijeongtteok Made with Kimchi Broth and Extract Mulberry (Cudrania tricuspidate) Fruit; [김치 발효액과 꾸지뽕 추출액이 첨가된 기정떡의 품질특성 분석] This study investigated the quality characteristics of the traditional rice cake of Gijeongtteok added with an extract from Cudrania tricuspidate fruit and different amounts of kimchi broth. The pH measurement showed a significant decrease with the increase of the kimchi broth from pH 5.48 (control) to 4.86 (KG180). Hunter color L-values were decreased while redness and yellowness were increased as the amount of kimchi broth increased. Texture profile analysis showed that hardness and adhesiveness significantly increased and decreased as the amount of kimchi broth increased. Gijeongtteok with kimchi broth (KG180) had the lowest specific volume with increased gummy layers in the crumb structure. Sensory evaluation of color, flavor, taste, appearance, and overall acceptance for various levels of kimchi broth showed that the KG140 sample had the highest acceptability. Therefore, this study suggests that Gijeogtteok made with the KG140 mixing ratio has excellent quality and sensory characteristics. © 2023 Korean Society for Food Engineering. All rights reserved. Jeong, Duyun; Sim, Duyun; Chung, Hyun-Jung Department of Food and Food Service Industry, Kyungpook National University, South Korea; Hwasun Farming Association Corporation, South Korea; Division of Food and Nutrition, Chonnam National University, South Korea 57203059723; 58195832500; 7404006790 hchung@jnu.ac.kr; Food Engineering Progress 1226-4768 27 1 0.14 2025-06-25 1 Cudrania tricuspidate; Gijeongtteok; kimchi broth; quality characteristics; sensory evaluation Korean Final 2023 10.13050/foodengprog.2023.27.1.11 바로가기 바로가기
Article Quality Characteristics of Squeezed Yuzu (Citrus junos) Juice Subjected to Commercial Sterilization Technologies The objective of this study was to find the optimal commercial sterilization technology for squeezed yuzu (Citrus junos) juice by analyzing microbes, antioxidant activity, and physicochemical properties after commercial sterilization [LTLT (low temperature long time) at 60°C for 30 min, HTST (high temperature short time) at 75°C for 1 min, and HPP (high pressure processing) at 500 MPa for 3 min]. Juices were stored for 84 days at 4°C after sterilization, during which no microbes were detected. Juice pH was not a significant difference regardless of treatments, but significant differences were observed in °Brix and color values between HTST and LTLT treatments and HPP treatment due to the conversion of pectin into reducing sugars and carotenoid pigment changes during thermal treatments. HPP treatment resulted in 90% and 10% higher DPPH radical scavenging activity and total phenol contents, respectively, compared to HTST treatment, which was attributed to the destruction of phenol and vitamin C during thermal treatment. This study shows that HPP was the most effective sterilization technology because it effectively maintained antioxidant activity and physicochemical properties and extended the shelf life of squeezed yuzu juice. Furthermore, our results suggest HPP should be considered the sterilization technology of choice in the juice industry. © 2023 The Korean Society of Food Science and Nutrition. Lee, Changheon; Moon, Seungmin; Cha, Eunsong; Sim, Jin Ha; Kim, Jin Hyeon; Jeong, Duyun; Yu, Daeung Interdisciplinary Program in Senior Human-Ecology, Major in Food and Nutrition, Changwon National University, South Korea; Interdisciplinary Program in Senior Human-Ecology, Major in Food and Nutrition, Changwon National University, South Korea; Interdisciplinary Program in Senior Human-Ecology, Major in Food and Nutrition, Changwon National University, South Korea; Interdisciplinary Program in Senior Human-Ecology, Major in Food and Nutrition, Changwon National University, South Korea; Interdisciplinary Program in Senior Human-Ecology, Major in Food and Nutrition, Changwon National University, South Korea; Department of Food and Food Service Industry, Kyungpook National University, South Korea; Interdisciplinary Program in Senior Human-Ecology, Major in Food and Nutrition, Changwon National University, South Korea, Department of Food and Nutrition, Changwon National University, South Korea 57209368463; 58202774000; 58202774100; 57428959700; 57206197613; 57203059723; 55696816300 duyu@changwon.ac.kr; Journal of the Korean Society of Food Science and Nutrition 1226-3311 52 2 0 2025-06-25 0 antioxidant; microbe; squeezed yuzu; sterilization Korean Final 2023 10.3746/jkfn.2023.52.2.216 바로가기 바로가기
Article Quantitative Analysis of SO2 and NO2 Adsorption and Desorption on Quartz Crystal Microbalance Coated with Cobalt Gallate Metal-Organic Framework Metal-organic frameworks (MOFs) of cobalt gallate were synthesized and deposited on gold electrodes using self-assembly monolayers (SAMs) and hydrothermal processing. These MOF films exhibit strong adsorption capabilities for gaseous particulates, and the use of SAMs allows the synthesis and deposition processes to be completed in a single step. When cobalt gallate is mixed with SAMs, a coordination bond is formed between the cobalt ion and the carboxylate or hydroxyl groups of the SAMs, particularly under hydrothermal conditions. Additionally, the quartz crystal microbalance (QCM) gas sensor accurately measures the number of particulates adsorbed on the MOF films in real-time. Thus, the QCM gas sensor is a valuable tool for quantitatively measuring gases, such as SO2, NO2, and CO2. Furthermore, the QCM MOF film gas sensor was more effective for gas adsorption than the MOF particles alone and allowed the accurate modeling of gas adsorption. Moreover, the QCM MOF films accurately detect the adsorption-desorption mechanisms of SO2 and NO2, which exist as gaseous particulate matter, at specific gas concentrations. © 2023, Korean Sensors Society. All rights reserved. Ahn, Junhyuck; Kim, Taewook; Park, Sunghwan; Lee, Young-Sei; Yim, Changyong Department of Advanced Science and Technology Convergence, Kyungpook National University (KNU), 2559 Gyeongsang-daero Gyeongsangbuk-do, Sangju-si, 37224, South Korea; Department of Advanced Science and Technology Convergence, Kyungpook National University (KNU), 2559 Gyeongsang-daero Gyeongsangbuk-do, Sangju-si, 37224, South Korea, Department of Energy Chemical Engineering, Kyungpook National University (KNU), 2559 Gyeongsang-daero Gyeongsangbuk-do, Sangju-si, 37224, South Korea; Department of Advanced Science and Technology Convergence, Kyungpook National University (KNU), 2559 Gyeongsang-daero Gyeongsangbuk-do, Sangju-si, 37224, South Korea, Department of Energy Chemical Engineering, Kyungpook National University (KNU), 2559 Gyeongsang-daero Gyeongsangbuk-do, Sangju-si, 37224, South Korea; Department of Advanced Science and Technology Convergence, Kyungpook National University (KNU), 2559 Gyeongsang-daero Gyeongsangbuk-do, Sangju-si, 37224, South Korea, Department of Energy Chemical Engineering, Kyungpook National University (KNU), 2559 Gyeongsang-daero Gyeongsangbuk-do, Sangju-si, 37224, South Korea; Department of Advanced Science and Technology Convergence, Kyungpook National University (KNU), 2559 Gyeongsang-daero Gyeongsangbuk-do, Sangju-si, 37224, South Korea, Department of Energy Chemical Engineering, Kyungpook National University (KNU), 2559 Gyeongsang-daero Gyeongsangbuk-do, Sangju-si, 37224, South Korea 57925320400; 57030752600; 56402062100; 36013623600; 36877182000 cy.yim@knu.ac.kr;ysl@knu.ac.kr; Journal of Sensor Science and Technology 1225-5475 32 3 0.15 2025-06-25 1 Gas adsorption kinetics; Gaseous particulate matter; Metal-organic framework; Quartz crystal microbalance; Self-assembly monolayer English Final 2023 10.46670/jsst.2023.32.3.147 바로가기 바로가기
Proceedings Paper Query Latency Optimization by Resource-Aware Task Placement in Fog The advancement of IoT (Internet of Things) technology has led to the proliferation of IoT-enabled applications. These IoT applications demand low query latency for fast data analytics. Fog computing has aided in reducing the query response time, but challenges still exist regarding query latency reduction in network-compute heterogeneous fog environment. In this paper, we propose a query latency reduction approach that formulates the query execution plan in a network-compute aware manner by considering the resource capacity of fog nodes and current network conditions. We introduce a query task placement algorithm that performs task placement by jointly considering both compute and network resources. The proposed algorithm selects set of nodes for query task placement based on minimum-latency criteria. Moreover, the proposed algorithm mitigates the computational bottleneck by offloading the tasks of computationally overloaded nodes. The proposed approach reduces latency by 71% and 24%, and decreases network usage by 52% and 35% compared to other approaches. Abdullah, Fatima; Peng, Limei; Tak, Byungchul Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu, South Korea 57225376681; 7201574271; 6506911621 fatima@knu.ac.kr;auroraplm@knu.ac.kr;bctak@knu.ac.kr; 2023 IEEE/ACM 23RD INTERNATIONAL SYMPOSIUM ON CLUSTER, CLOUD AND INTERNET COMPUTING WORKSHOPS, CCGRIDW 0 2025-06-25 0 0 IoT; fog computing; query execution EDGE fog computing; IoT; query execution Cloud analytics; Computation offloading; Data Analytics; Fog; Internet of things; Data analytics; In networks; Internet of things technologies; Latency optimizations; Latency reduction; Query execution; Query latency; Query response time; Query tasks; Resource aware; Fog computing English 2023 2023 10.1109/ccgridw59191.2023.00062 바로가기 바로가기 바로가기
Proceedings Paper Radar Fault Detection via Camera-Radar Branches Learning Network Radars are widely used in autonomous driving technology. Self-driving usually relies on radar signals to recognize pedestrians and vehicles, identify the surrounding environments reliably, avoid car crashes and navigation, and provide a reliable route to avoid collisions. The radar plays an important role in vehicle systems, and maintaining its proper functioning is necessary for the safety of self-driving systems to be considered. However, sensor faults are unavoidable. When the radar sensor is faulty, the radar signal will not receive the correct feedback information. Currently, it is hard to detect fault errors in radars, and the algorithm is complicated to work with. To analyze the radar cross section (RCS) signal and distance relationship, we used the RCS signal feature and combined the real-time features of the vehicle camera with the convolutional neural network (CNN) model to identify the fault information as expected. The paper uses a new data generator feature and deep learning model, recognizes the input signal as normal and abnormal, and the accuracy improves to 95.54%. Ning, Dian; Han, Dong Seog Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu, South Korea; Kyungpook Natl Univ Daegu, Sch Elect Engn, Daegu, South Korea Ning, Daoguan/IRZ-7360-2023 58175410800; 7403219442 ningdian@knu.ac.kr;dshan@knu.ac.kr; 2023 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE IN INFORMATION AND COMMUNICATION, ICAIIC 2831-6991 1.45 2025-06-25 2 3 Anomaly Detection; Radar Cross Section(RCS); Convolutional Neural Network(CNN) Anomaly Detection; Convolutional Neural Network(CNN); Radar Cross Section(RCS) Accidents; Anomaly detection; Cameras; Convolution; Deep learning; Fault detection; Learning systems; Radar cross section; Tracking radar; Anomaly detection; Autonomous driving; Car navigation; Convolutional neural network; Faults detection; Learning network; Radar cross-sections; Radar signals; Self drivings; Surrounding environment; Convolutional neural networks English 2023 2023 10.1109/icaiic57133.2023.10067071 바로가기 바로가기 바로가기
Proceedings Paper Radar Signal Abnormal Point Classification based on Camera-Radar Sensor Fusion For safe driving, it is essential to accept reliable information from recognition sensors. In this paper, we present a deep learning model that classifies whether radar signals coming in are normal or abnormal. The abnormal signal is defined as noise from the radar and all signals received when the radar fails or is in trouble. It is difficult to determine whether reflected signals are normal or not based only on radar data. Therefore, the camera and radar sensors are used together, considering the radar cross section (RCS) distribution varies by the angle and distance of the object. The proposed model uses data received from camera and radar sensors to determine the normality of object signals. The model shows an accuracy of 96.24%. Through the results of this study, the reliability of radar signals can be determined in the actual driving environment, thereby ensuring the safety of vehicles and pedestrians. Seo, Hyojeong; Han, Dong Seog Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu, South Korea; Kyungpook Natl Univ, Sch Elect Engn, Daegu, South Korea 58175210900; 7403219442 jk05135@knu.ac.kr;dshan@knu.ac.kr; 2023 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE IN INFORMATION AND COMMUNICATION, ICAIIC 2831-6991 0.48 2025-06-25 1 1 Radar; RCS; deep learning; classification; sensor fusion classification; deep learning; Radar; RCS; sensor fusion Automobile drivers; Deep learning; Pedestrian safety; Radar cross section; Radar equipment; Abnormal point; Camera sensor; Deep learning; Learning models; Radar cross-sections; Radar sensors; Radar signals; Reflected signal; Safe driving; Sensor fusion; Cameras English 2023 2023 10.1109/icaiic57133.2023.10067112 바로가기 바로가기 바로가기
Proceedings Paper Raspberry Pi-based Low-cost Portable Optical Coherence Tomography to Deliver Health Care Services Research for miniaturization and portability of optical coherence tomography, which has received considerable attention as one of the pre-diagnosis methods, has been conducted for several years to further expand the utility of optical coherence tomography. In this study, we introduce a method that can dramatically reduce the size of a system and resources using a Raspberry Pi miniature computer and the proposed small spectrometer. The optical systems of the sample stage and the reference stage were configured as half- inch optical components to reduce the size of the system. The size of the sample stage was minimized by using a MEMS scanning mirror. We designed a board that converts the unipolar drive signal into a bipolar signal to drive the MEMS scanning mirror with Raspberry Pi. The MEMS mirror was controlled by a commercial AD/DA conversion board and a developed board that can be controlled via the generalpurpose input-output (GPIO) pin of Raspberry Pi. Furthermore, we also designed the spectrometer to fit the 1-inch optical system. The camera was selected as a product that can supply power and transmit data through the USB terminal to operate all other components, including the camera, through a portable charger. Due to camera performance limitations, A- scan 5 kHz was the maximum speed, but the resolution was axial 8.5 mu m (Air) and lateral 17.54 mu m, showing similar performance to a commercial system. Although the operating speed is slow, it is expected to be used in various fields due to its portability advantage. Cho, Hoseong; Kim, Pilun; Kim, Hyeree; Wijesinghe, Ruchire Eranga; Jeon, Mansik; Kim, Jeehyun Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea; LG Elect, Prod Engn Res Inst, 222 LG Ro Jinwi Myeon, Pyeongtaek Si, Gyeonggi Do, South Korea; Univ Sri Jayewardenepura, Fac Technol, Dept Mat & Mech Technol, Homagama 10200, Sri Lanka Kim, Jinhyun/AAK-3695-2020; Wijesinghe, Ruchire/K-3797-2016 57209416599; 56967482800; 57209102795; 56018152300; 24171094000; 7601373350 ghtjd419@knu.ac.kr;msjeon@knu.ac.kr;jeehk@knu.ac.kr; OPTICS AND BIOPHOTONICS IN LOW-RESOURCE SETTINGS IX 0277-786X 1996-756X 12369 0 2025-06-25 0 0 Ultra-compact Optical Coherence Tomography; Raspberry Pi; OCT (RB-OCT); Portable Biomedical Imaging System Cameras; Costs; Digital storage; Mirrors; Optical systems; Spectrometers; Bipolar signal; Diagnosis methods; Drive signal; Healthcare services; Low-costs; MEMS scanning mirror; Miniaturisation; Optical components; Sample stages; Unipolar drives; Optical tomography English 2023 2023 10.1117/12.2651248 바로가기 바로가기 바로가기
Article RDA-Genebank and Digital Phenotyping for Next-Generation Research on Plant Genetic Resources The National Agrobiodiversity Center under the Rural Development Administration (RDA) in Jeonju, Republic of Korea stands as the foremost national genebank in the country. Over the years, the National Agrobiodiversity Center has remained committed to enriching its collection with foreign genetic resources, elevating its status to a world-class plant genetic resources (PGR)- holding genebank. Currently, several steps are being undertaken to improve the accessibility of the collection to national as well as international researchers, improve the data available on the resources, and amend the passport information for the accessions. With the implementation of the Nagoya Protocol, the origin of genetic resources is being highlighted as an important input in the passport information. The RDA-Genebank actively responds to the Nagoya Protocol by supplementing passport data for resources lacking information on their origin. In addition, a large number of conserved resources are continuously multiplied, and agronomic traits are investigated concurrently. With the traditional methods of characterization of the germplasm requiring a significant amount of time and effort, we have initiated high-throughput phenotyping using digital techniques to improve our germplasm data. Primarily, we have started adding seed phenotype information followed by measuring root phenotypes which are stored under agronomic traits. This may be the initial step toward using largescale high-throughput techniques for a germplasm. In this study, we aim to provide an introduction to the RDA-Genebank, to adopted international standards, and to the establishment of high-throughput phenotyping techniques for the improvement of passport information. Kim, Seong-Hoon; Subramanian, Parthiban; Na, Young-Wang; Hahn, Bum-Soo; Kim, Yoonha RDA, Natl Inst Agr Sci, Natl Agrobiodivers Ctr, Jeonju 5487, South Korea; Kyungpook Natl Univ, Dept Appl Biosci, Lab Crop Prod, Daegu 41566, South Korea Subramanian, Parthiban/CAJ-0756-2022; Kim, Seong-Hoon/AHE-2059-2022 57208236056; 57191611989; 56462169700; 7201799276; 57224866763 shkim0819@korea.kr;ywna@korea.kr;bshahn@korea.kr;kyh1229@knu.ac.kr; PLANTS-BASEL 2223-7747 12 15 0.59 2025-06-25 2 3 genebank; digital phenotyping; Nagoya Protocol; agronomic traits NAGOYA PROTOCOL agronomic traits; digital phenotyping; genebank; Nagoya Protocol English 2023 2023-08 10.3390/plants12152825 바로가기 바로가기 바로가기
Conference paper Real-time incoherent hologram recording with high-speed geometric phase switching device A real-time incoherent hologram acquisition method is proposed, utilizing liquid crystal based geometric phase switching device. The principle involves recording three geometric phase-shifted interferograms at high speed to create a single complex-valued hologram. © 2023 The Author (s). Choi, Kihong; Lee, Jae-Won; Shin, JungYeop; Hong, Keehoon; Park, Joongki; Kim, Hak-Rin Digital Holography Research Section, Electronics and Telecommunications Research Institute, Daejeon, 34129, South Korea; School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, 41566, South Korea; School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, 41566, South Korea; Digital Holography Research Section, Electronics and Telecommunications Research Institute, Daejeon, 34129, South Korea; Digital Holography Research Section, Electronics and Telecommunications Research Institute, Daejeon, 34129, South Korea; School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, 41566, South Korea, School of Electronics Engineering, Kyungpook National University, Daegu, 41566, South Korea 56706731400; 58377059800; 57956975700; 26326352800; 34868474500; 7410124944 kihong08@etri.re.kr; 3D Image Acquisition and Display: Technology, Perception and Applications in Proceedings Optica Imaging Congress, 3D, COSI, DH, FLatOptics, IS, pcAOP 2023 0 2025-06-25 0 Geometry; Liquid crystals; Complex-valued; Geometric phase; High Speed; Hologram recording; Interferograms; Liquid-crystals; Phase shifted; Phase switching devices; Real- time; Holograms English Final 2023 10.1364/3d.2023.jw2a.19 바로가기 바로가기
Conference paper Real-time Rotational Obstacle Detection based Intelligent Safety Management for Construction Machines The number of industrial accidents has been recorded by construction cranes for a high proportion compared to other machines on construction sites. For this reason the technology for preventing collision between salvages and obstacles is strongly demanded. In this study, we propose an intelligent safety management method based on a rotational obstacle detection that detects obstacles around a crane by learning a private dataset acquired in an environment similar to an actual construction site. The rotational obstacle detection model of the proposed method is designed to more accurately predict obstacles around a crane using RGB video sequences images from the multi-domain dataset. It is composed of the real-time models for object detection, one of the typical onestage detectors, and the self attention distillation (SAD) method. In the experimental results, its performance of accuracy over than 70% mAP. This study can be applied not only to cranes but also to other machines for safety monitoring systems on various domain fields. © 2023 SPIE. Woo, Minwoo; Yun, Jong-Pil; Won, Hong-In; Jeong, Seung Hyun; Kim, Byeong Hak Korea Institute of Industrial Technology (KITECH), 15 Jisiksanneop-ro, Gyeongsan, South Korea, Kyungpook National University (KNU), 80 Daehakro, Daegu, South Korea; Korea Institute of Industrial Technology (KITECH), 15 Jisiksanneop-ro, Gyeongsan, South Korea; Korea Institute of Industrial Technology (KITECH), 15 Jisiksanneop-ro, Gyeongsan, South Korea; Korea Institute of Industrial Technology (KITECH), 15 Jisiksanneop-ro, Gyeongsan, South Korea; Korea Institute of Industrial Technology (KITECH), 15 Jisiksanneop-ro, Gyeongsan, South Korea 57297761400; 16644164300; 57548175800; 57219224526; 56406686400 bhkim81@kitech.re.kr; Proceedings of SPIE - The International Society for Optical Engineering 0277-786X 12571 0 2025-06-25 0 crane; deep learning; machine learning; multi-domain; obstacle detection; rotation object detection; Self attention distillation Accident prevention; Accidents; Deep learning; Distillation; Industrial hygiene; Learning systems; Object detection; Object recognition; Obstacle detectors; Occupational diseases; Construction sites; Deep learning; Machine-learning; Multi-domains; Objects detection; Obstacles detection; Real- time; Rotation object detection; Safety management; Self attention distillation; Cranes English Final 2023 10.1117/12.2665505 바로가기 바로가기
Proceedings Paper Realtime Disaster Detection Through GNN Models Using Disaster Knowledge Graphs In the context of the increasing scale and complexity of disasters caused by rapid climate change, a comprehensive understanding of disaster big data is essential for effective detection and response. The disaster knowledge graph proposed in this paper fills this gap by capturing the connections between various disaster-related data sources and their potential for growth across heterogeneous datasets. We generate time-series disaster graphs every minute using SNS data (e.g., Twitter) and public data, specifically focusing on disasters. Then, we create disaster knowledge graphs to represent the relationships between various data sources and try to predict their potential developments. We label and annotate knowledge graphs and then detect sudden changes in time-series disaster knowledge graphs for disaster detection. To that end, we assess the effectiveness of three state-of-the-art GNN models for graph-based event classification using Graph Convolutional Network (GCN), Graph Attention Network (GAT), and SageConv. In addition, we evaluate a simple clustering model, K-means, for comparison. Our experiments show promising results with approximately 87% precision in detecting disaster events using structural data and connectivity patterns within disaster graphs. Finally, we measure the result of disaster detection time with an unseen dataset, showing positive results that about 70% detect a disaster in less than 3 minutes. To comprehensively analyze real-time social media data and understand the patterns of disaster to enhance disaster management and response strategies, our approach combines the strength of GNNs with a designed disaster knowledge graph. Kim, Seonhyeong; Khan, Irshad; Kwon, Young-Woo Kyungpook Natl Univ, Comp Sci & Engn, Daegu, South Korea ; Kwon, Young-Woo/HGE-6607-2022; Khan, Irshad/AAN-8522-2020 57256850100; 36166674500; 57208480210 kimsh951027@knu.ac.kr;irshad.cs@knu.ac.kr;ywkwon@knu.ac.kr; PROCEEDINGS OF THE 2023 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING, ASONAM 2023 2473-9928 2473-991X 1.14 2025-06-25 1 2 knowledge graphs; graph neural networks; disaster detection SOCIAL NETWORKS disaster detection; graph neural networks; knowledge graphs Climate change; Emergency services; Graph neural networks; Graphic methods; K-means clustering; Social networking (online); Time series; Data-source; Disaster detection; Graph neural networks; Heterogeneous datasets; Knowledge graphs; Public data; Rapid climate change; Real- time; Sudden change; Times series; Knowledge graph English 2023 2023 10.1145/3625007.3627514 바로가기 바로가기 바로가기
Proceedings Paper Recognizing Social Touch Gestures using Optimized Class-weighted CNN-LSTM Networks Socially aware robotic applications such as companion and therapeutic robots usually require human emotions or intent to be conveyed. As the scope of these applications increases, the need for recognizing affective touch gestures which are often used to convey these emotions or intent becomes eminent. However, existing touch gesture recognition modalities either have low recognition accuracy or depend heavily on carefully hand-crafted features, therefore limiting their deployment in real-life applications. Motivated by the need for learning models with superior accuracy which do not rely on manually selected hand-crafted features, this paper proposes an optimized class-weighted CNN-LSTM for social touch gesture recognition evaluated on the CoST and HAART datasets. Specifically, contrary to vanilla training schemes where equal importance is given to each class in the dataset, different class weights are introduced to give priority to classes that are difficult for the network to distinguish during training. Furthermore, the weights associated with each of the classes are obtained through optimization using Genetic Algorithm. The proposed model demonstrates superior performance compared with other existing models in the literature. Darlan, Daison; Ajani, Oladayo S.; Parque, Victor; Mallipeddi, Rammohan Kyungpook Natl Univ, Sch Convergence, Dept Artificial Intelligence, Daegu, South Korea; Waseda Univ, Grad Sch Creat Sci & Engn, Fac Sci & Engn, Tokyo, Japan ; Darlan, Daison/KQA-9542-2024; Parque, Victor/K-7732-2018; Mallipeddi, Rammohan/AAL-5306-2020; AJANI, Oladayo/HIR-9607-2022 58164208500; 57465126000; 35305647500; 25639919900 daisondarlan33@gmail.com;oladayosolomon@gmail.com;Parque@aoni.waseda.jp;mallipeddi.ram@gmail.com; 2023 32ND IEEE INTERNATIONAL CONFERENCE ON ROBOT AND HUMAN INTERACTIVE COMMUNICATION, RO-MAN 1944-9445 0.53 2025-06-25 1 2 Social touch recognition; HAART; CoST; class weights; CNN-LSTM NEURAL-NETWORKS class weights; CNN-LSTM; CoST; HAART; Social touch recognition Emotion Recognition; Genetic algorithms; Long short-term memory; Palmprint recognition; Class weight; CNN-LSTM; Companion robot; CoST; Gestures recognition; HAART; Human emotion; Robotics applications; Social touch recognition; Therapeutic robots; Gesture recognition English 2023 2023 10.1109/ro-man57019.2023.10309595 바로가기 바로가기 바로가기
Conference paper Recurrence Plot based Person Identification with ECG using CNN model With the COVID-19 pandemic and an aging population, there has been a rise in demand for homecare for patients with chronic diseases that require continuous monitoring outside of the hospital. One important bio-signal for such monitoring is an electrocardiogram (ECG), which measures the electrical activity of the heart and can detect dangerous conditions such as arrhythmias and myocardial infarctions. The application of deep learning classification algorithms to arrhythmia and myocardial infarction diagnosis has gained interest. However, to be effectively utilized in everyday life, a method to determine who performed the measurement is necessary. In this study, we evaluated the use of recurrence plot pre-processing and convolutional neural network (CNN) models to identify individuals based on their ECG signals. Our proposed method demonstrated high accuracy results across various CNN models and was capable of identifying individuals. © 2023 IEEE. Jeon, Yeong Jun; Lee, Cheolhwan; Kang, Soon Ju Kyungpook National University, School of Electronic and Electrical Engineering, Daegu, South Korea; Kyungpook National University, School of Electronic and Electrical Engineering, Daegu, South Korea; Kyungpook National University, School of Electronic and Electrical Engineering, Daegu, South Korea 57208863636; 57216824872; 55666313900 thg333@naver.com;sjkang@ee.knu.ac.kr; International Conference on Ubiquitous and Future Networks, ICUFN 2165-8528 2023-July 0.5 2025-06-25 1 Classification; Convolutional neural network; Deep Learning; Electrocardiogram; Person identification; Recurrence plot Biomedical signal processing; Classification (of information); Computer aided diagnosis; Convolution; Convolutional neural networks; Deep learning; Diseases; Aging population; Chronic disease; Continuous monitoring; Convolutional neural network; Deep learning; Homecare; Myocardial Infarction; Neural network model; Person identification; Recurrence plot; Electrocardiograms English Final 2023 10.1109/icufn57995.2023.10199670 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.