연구성과로 돌아가기

2021 연구성과 (233 / 281)

※ 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
Conference paper A Prototype Implementation of NNEF Execution Framework with CUDA Acceleration Recently, we have many research works on the neural networks and their related issues. For exchangeability of neural network frameworks, the Neural Network Exchange Format (NNEF) specification is now widely used. Due to very large size of these neural networks, their accelerations are actively explored, and can be achieved through parallel processing techniques. In this paper, we present a prototype implementation of NNEF execution system with parallel-processing accelerations based on CUDA (compute unified device architecture). We will tune the prototype acceleration to achieve more remark-able speed ups. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. Baek, Nakhoon School of Computer Science and Engineering, Kyungpook National University, Daegu, 41566, South Korea 7007017954 nbaek@knu.ac.kr; Lecture Notes in Electrical Engineering 1876-1100 739 LNEE 0 2025-07-30 0 Acceleration; CUDA; Neural network; NNEF; Parallel processing Electrical engineering; Mathematical techniques; CUDA (compute unified device architecture); Exchange format; Execution framework; Execution systems; Network frameworks; Parallel processing; Prototype implementations; Neural networks English Final 2021 10.1007/978-981-33-6385-4_12 바로가기 바로가기
Proceedings Paper A Prototype Implementation of the NNEF Interpreter Baek, Nakhoon Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu, South Korea; Louisiana State Univ, Sch Elect Engn & Comp Sci, Baton Rouge, LA 70803 USA nbaek@knu.ac.kr; ADVANCES IN ARTIFICIAL INTELLIGENCE AND APPLIED COGNITIVE COMPUTING 2569-7072 2569-7080 0 English 2021 2021 10.1007/978-3-030-70296-0_51 바로가기 바로가기
Article A Q-Methodological Study of Suicidal Attitudes in Male Baby Boomers Purpose: The purpose of this study was to identify attitudes of male baby boomers towards suicide. Methods: Q-Methodology which provides a method of analyzing the subjectivity of each item was used. Thirty-five q-statements were selected from total 110 statements. The recruited P-sample consisted of thirty-three male baby boomers in 1 town and 4 cities. Q-statements were classified into a shape of normal distribution of a 9-point scale. Collected data were analyzed using PQMethod Program 2.11. Results: Three types of attitudes towards suicide were identified. The first type was self-overcoming type that oppose suicide. The second type was burden recognition type with ambivalence toward suicide. The third type was social support-seeking types that oppose suicide. Conclusion: The results of this study suggest that it is necessary to apply a suicide prevention program differentiated according to the three types for suicide prevention among male baby boomers in Korea. © 2021 The Korean Academy of Psychiatric and Mental Health Nursing. Shin, Eun Jeong; Kim, Hee Sook Department of Nursing, Kyungbuk College, Yeongju, South Korea; College of Nursing, The Research Institute of Nursing Science, Kyungpook National University, Daegu, South Korea 57189046623; 58668801200 hskim8879@knu.ac.kr; Journal of Korean Academy of Psychiatric and Mental Health Nursing 1225-8482 30 3 0 2025-07-30 0 Attitude; Baby boom; Male; Suicide Korean Final 2021 10.12934/jkpmhn.2021.30.3.257 바로가기 바로가기
Book chapter A re-evaluation of backward design in goal setting, assessment and instruction planning in international baccalaureate Much research in the field of International Baccalaureate (IB) education has focused on the strengths and weaknesses of this innovative system of education. In contrast, this chapter aims to return the discus¬sion to the more fundamental aspects of IB by considering more deeply the issue of "backward design" and its relevance to the IB in the Korean and Asian contexts. The backward design consists of a) setting goals for learning, b) designing evaluation criteria to assess mastery of the course materials, and c) planning of the instruction in order to attain the learning goals. © 2021, IGI Global. Kang, Hyeon-Suk; Na, Kang-Ye Department of Education, Kyungpook National University, South Korea; Department of Education, Kyungpook National University, South Korea 56393476400; 57572865300 Educational Reform and International Baccalaureate in the Asia-Pacific 0 2025-07-30 0 English Final 2021 10.4018/978-1-7998-5107-3.ch002 바로가기 바로가기
Conference paper A Region Descriptive Pre-training Approach with Self-attention Towards Visual Question Answering Concatenation of text (question-answer) and image has been the bedrock of most visual language systems. Existing models concatenate the text (question-answer) and image inputs in a forced manner. In this paper, we introduce a region descriptive pre-training approach with self-attention towards VQA. The model is a new learning method that uses the image region descriptions combined with object labels to create a proper alignment between the text(question-answer) and the image inputs. We study the text associated with each image and discover that extracting the region descriptions from the image and using it during training greatly improves the model’s performance. In this research work, we use the region description extracted from the images as a bridge to map the text and image inputs. The addition of region description makes our model perform better against some recent state-of-the-art models. Experiments demonstrated in this paper show that our model significantly outperforms most of these models. © 2021, Springer Nature Switzerland AG. Kolawole, Bisi Bode; Lee, Minho School of Electrical and Electronics Engineering, Kyungpook National University, 80, Daehak-ro, Buk-go, Daegu, South Korea; Graduate School of Artificial Intelligence, Kyungpook National University, 80, Daehak-ro, Buk-go, Daegu, South Korea 59929924900; 57191730119 legionpath@gmail.com; Communications in Computer and Information Science 1865-0929 1517 CCIS 0 2025-07-30 0 Object label; Pre-training; Region descriptions; Visual question answering Computer vision; Image enhancement; Learning systems; Image inputs; Image regions; Learning methods; Object label; Performance; Pre-training; Question Answering; Region description; Text input; Visual question answering; Visual languages English Final 2021 10.1007/978-3-030-92310-5_9 바로가기 바로가기
Article A Relationship between the Second Largest Eigenvalue and Local Valency of an Edge-regular Graph For a distance-regular graph with valency k, second largest eigenvalue r and diameter D, it is known that r >= min{lambda+root lambda(2)+4k/2, a(3)} if D = 3 and r >= lambda+root lambda(2)+4k/2 if D >= 4, where lambda = a(1). This result can be generalized to the class of edge-regular graphs. For an edge-regular graph with parameters (v, k, lambda) and diameter D >= 4, we compare lambda+root lambda(2)+4k/2 with the local valency lambda to find a relationship between the second largest eigen-value and the local valency. For an edge-regular graph with diameter 3, we look at the number lambda-(mu) over bar+root(lambda-(mu) over bar)(2)+4(k-(mu) over bar)/2, where (mu) over bar = k(k-1-lambda)/v-k-1, and compare this number with the local valency lambda to give a relationship between the second largest eigenvalue and the local valency. Also, we apply these relationships to distance-regular graphs. Park, Jongyook Kyungpook Natl Univ, Dept Math, Daegu 41566, South Korea 36091826300 jongyook@knu.ac.kr; KYUNGPOOK MATHEMATICAL JOURNAL KYUNGPOOK MATH J 1225-6951 0454-8124 61 3 ESCI MATHEMATICS 2021 N/A 0.34 2025-07-30 2 2 edge-regular graphs; distance-regular graphs; second largest eigen-values; local valency distance-regular graphs; edge-regular graphs; local valency; second largest eigen-values English 2021 2021-09 10.5666/kmj.2021.61.3.671 바로가기 바로가기 바로가기 바로가기
Review A review of the stratigraphy of the Lower Paleozoic Joseon Supergroup Lower Paleozoic strata exposed in the northeastern part of the Taebaeksan Basin, Korea, are composed of ten lithostratigraphic units that include the Jangsan/Myeonsan, Myobong, Daegi, Sesong, Hwajeol, Dongjeom, Dumugol, Makgol, Jigunsan and Duwibong formations in ascending order. These descriptive lithostratigraphic units used for regional correlation, but are limited to delineate basin history due to lack of information on the temporal variations in sedimentation occurring across the basin. Previously published stratigraphic, sedimentologic and paleontologic data from the formations are being reviewed and analyzed to make a more sophisticated understanding on stratigraphic response to tectonic evolution of the basin. As an interim result, six distinct unconformity-bounded sequences are recognized in the basin (I to VI). Sequences I to IV are well correlated across the basin and represent a mixed siliciclastic-carbonate succession that was deposited on the slowly subsiding stable carbonate platform with eustatic sea-level changes from the Series II in Cambrian to the early Middle Ordovician. The overlying sequence V is a mixed siliciclastic-carbonate succession deposited on the carbonate platform during the late Middle Ordovician, but it shows rapid temporal facies variation that results in hindering a basinwide stratigraphic correlation. Locally, the sequence V typifies a wedge-shaped breccia (e.g., Yemi Breccia) which might be due to rapid sedimentation along the rifted platform margin. Tectonic inversion occurred during Late Ordovician so that Late Ordovician recorded as a hiatus in the basin. The overlying unit VI may represent a mixed siliciclastic-carbonate succession that was deposited along the locally isolated remnant basins after tectonic inversion. The stratigraphic and tectonic model, which is newly proposed as a result of this study, provides very useful information to make a coherent regional stratigraphic correlation of the Lower Paleozoic strata and to help a more comprehensive understanding on stratigraphic response to tectonic evolution of the Taebaeksan Basin. Together with the spatial and temporal correlation of the Lower Paleozoic basins in adjacent areas, this model will give much better insight to unravel tectonic history of East Asia during the Lower Paleozoic. Jang, Hwimin; Ryu, In-Chang Korea Inst Ocean Sci & Technol, Global Ocean Res Ctr, Busan 49111, South Korea; Kyungpook Natl Univ, Coll Nat Sci, Dept Geol, Daegu 41566, South Korea 57218160119; 7006705952 inchangryu@knu.ac.kr; JOURNAL OF THE GEOLOGICAL SOCIETY OF KOREA J GEOL SOC KOREA 0435-4036 2288-7377 57 4 ESCI GEOSCIENCES, MULTIDISCIPLINARY 2021 N/A 0.1 2025-07-30 2 1 Lower Paleozoic; Joseon Supergroup; carbonate platform; mixed siliciclastic-carbonate; sequence stratigraphy TRILOBITE FAUNAL SUCCESSIONS; GROUP CAMBRIAN-ORDOVICIAN; TAEBAEKSAN BASIN; SEQUENCE STRATIGRAPHY; MIDDLE ORDOVICIAN; DAEGI FORMATION; DEPOSITIONAL PROCESSES; SEOKGAEJAE SECTION; DUMUGOL FORMATION; SESONG FORMATION Carbonate platform; Joseon supergroup; Lower paleozoic; Mixed siliciclastic-carbonate; Sequence stratigraphy Korean 2021 2021-08 10.14770/jgsk.2021.57.4.495 바로가기 바로가기 바로가기 바로가기
Proceedings Paper A Sensor Fusion System with Thermal Infrared Camera and LiDAR for Autonomous Vehicles: Its Calibration and. Application Vision, Radar, and LiDAR sensors are widely used for autonomous vehicle perception technology. Especially object detection and classification are primarily dependent on vision sensors. However, under poor lighting conditions, risiziling sunlight, or bad weathers an object might be difficult to be identified with general vision sensors. In this paper, we propose a sensor fission system with a thermal infrared camera and LiDAR sensor that can reliably detect and identify objects even in environments where visibility is poor, such as in severe glare and fog or smoke. The proposed method obtains intrinsic parameters by calibrating the thermal infrared camera and LiDAR sensor. Extrinsic calibration algorithm between two sensors is made to obtain the extrinsic parameters (rotation and translation matrix) using 3D calibration targets. This system and proposed algorithm show that it can reliably detect and identify objects even in hard visibility environments, such as in severe glare due to direct sunlight or headlights or in low visibility environments, such as in severe fog or smoke. Choi, Ji Dong; Kim, Min Young Kyungpook Natl Univ, Dept Future Automot & IT Convergence, Daegu, South Korea; Kyungpook Natl Univ, Sch Elect Engn, Daegu, South Korea 57216614368; 56739349100 jidong1119@naver.com;minykim@knu.ac.kr; 12TH INTERNATIONAL CONFERENCE ON UBIQUITOUS AND FUTURE NETWORKS (ICUFN 2021) 2165-8528 2165-8536 2.62 2025-07-30 11 16 Calibration; Autonomous Vehicles; Sensor fusion; LiDAR; Thermal Infrared Camera Autonomous Vehicles; Calibration; LiDAR; Sensor fusion; Thermal Infrared Camera Autonomous vehicles; Calibration; Glare; Object detection; Optical radar; Smoke; Visibility; Autonomous Vehicles; Calibration algorithm; Extrinsic calibration; Extrinsic parameter; Intrinsic parameters; LiDAR; Lighting conditions; Sensor fusion; Sensor fusion systems; Vision sensors; Infrared devices English 2021 2021 10.1109/icufn49451.2021.9528609 바로가기 바로가기 바로가기
Conference paper A Study of Anisotropic Yield Function Based on J2 and J3 Invariants In this paper a new anisotropic yield function that describes the elastoplastic behavior of sheet metals depends not only on the second stress invariant J2 for the yield, but also on the third stress invariant J3, both may affect the shape of the yield surface. The new anisotropic yield function is general and applicable to three-dimensional stress states. The proposed model is identified by calibration parameters from experimental data of material including uniaxial and biaxial tests. In this study, the predictive capabilities of the new anisotropic yield function are demonstrated by comparison between the predictions and experimental data for yield locus, normalized yield stress, and r-value. The result indicates that the new anisotropic model is reasonable to predict not only the symmetric shape but also the asymmetric shape of yield surface of the sheet metals. © 2021, The Minerals, Metals & Materials Society. Kim, YoungSuk; Nguyen, PhuVan; Kim, JinJae School of Mechanical Engineering, Kyungpook National University, 80 Daehakro, Daegu, 41566, South Korea; Graduate School, Kyungpook National University, 80 Daehakro, Daegu, 41566, South Korea; Graduate School, Kyungpook National University, 80 Daehakro, Daegu, 41566, South Korea 36065820800; 57214384991; 57209555877 caekim@knu.ac.kr; Minerals, Metals and Materials Series 2367-1181 0 2025-07-30 0 Anisotropic yield function and asymmetric yield function; Invariant J<sub>2</sub> ; Invariant J<sub>3</sub> ; Isotropic yield function; Stress deviator Anisotropy; Plasticity; Sheet metal; Anisotropic models; Anisotropic yield functions; Biaxial tests; Calibration parameters; Elastoplastic behavior; Predictive capabilities; Stress invariants; Three dimensional stress state; Yield stress English Final 2021 10.1007/978-3-030-75381-8_165 바로가기 바로가기
Article A Study of Gotrabhū in Pāli Literature - Focused on the concept and its development This thesis examines the concept of ‘gotrabhū’ and its development in Pāli literature from Nikāya to Abhidhamma. In Pāli literature, we can find a technical term ‘gotrabhū’, a combination of ‘gotra’ and ‘bhū’; ‘gotra’ is Sanskrit form of Pāli gotta meaning ‘lineage’. When ‘gotrabhū’ refers to a person, in Majjhimanikāya ‘gotrabhū’ is described as a person who acts inappropriately and is far from a saint. But in Aṅguttaranikāya, Puggalapaññatti and Kathāvatthu, it means a person who is in the state just before entering Sotāpattimagga, the first stage of saints. And it seems that the meaning of ‘gotrabhū’, which meant a person who has a state or condition to become a saint, has gradually developed to refer to the state of mind or awareness that such person possesses. In Paṭisambhidāmagga, ‘gotrabhū’ means the first state of leaping into nibbāna and the state in which the elements that must be overcome in order to attain jhānas or the paths of the saints are removed, and this presents a new interpretation. In Paṭṭhāna, it develops into a concept that clearly represents a state of awareness, meaning a state of mind that is experienced only once just before the Sotāpattimagga. This leads to the theory of javana in Visuddhimagga, in which ‘gotrabhū’ means one of the mind of javana just before samādhis and the path of the saints, at the time of attaining jhānas and entering lokuttara respectively. Also, according to the explanations of commentaries and subcommentaries, the meaning of ‘gotrabhū’ can be interpreted as three ways: first, overcoming (abhibhavana) negative factors such as puthujjana or nīvaraṇa and positive factors like previous magga or phala; second, producing (bhāvanā) the lineage of saints; and third, maintaining (dhāraṇa) of just the name of samaṇa. © 2021, Korean Association of Buddhist Studies. All rights reserved. Han, Sang-Hee Department of Philosophy, Kyungpook National University, South Korea 59752642200 kate1213@hanmail.net; Korean Journal of Buddhist Studies 1598-0642 69 0 2025-07-30 0 ariya; gotrabhū; nibbāna; Nikāya; Paṭisambhidāmagga; Visuddhimagga Korean Final 2021 10.21482/jbs.69..202112.23 바로가기 바로가기
Article A Study on a New Method for Flexoelectric Coefficient Estimation of the Flexoelectric Unimorph Sensing Element In a flexoelectric sensing element using bending mode, estimation of the flexoelectric coefficient was investigated using 3-D stress/strain analysis and experiments. The proposed method uses the results (deformation and strain) from the finite element analysis (FEA). The estimated flexoelectric coefficients were compared with those obtained via the conventional method (Euler's beam theory) under the assumption of the quasi 1-D stress field. The results show that the RMS value and standard deviation of the estimated flexoelectric coefficient for the 3-D stress field case of the sensing element are 31.51 mu C/m and 0.24%, respectively. In addition, we found that the flexoelectric coefficient obtained from the results of the 3-D stress analysis is 1.8% smaller than that of the quasi-1-D stress analysis. Therefore, in order to obtain a more reliable flexoelectric coefficient in the sensing element, the results of the 3-D numerical stress analysis should be used for accurate estimation of the flexoelectric coefficient. Kwon, Seol Ryung; Roh, Yongrae Korea Inst Robot Ind Advancement, Daegu 41496, South Korea; Kyungpook Natl Univ, Sch Mech Engn, Daegu 41566, South Korea 55542309100; 7102361870 seolkwon@kiria.org;yryong@knu.ac.kr; APPLIED MECHANICS 2673-3161 2 4 0 2025-07-30 0 0 bending mode; strain gradient; stress analysis; flexoelectric coefficient; flexoelectricity; unimorph sensing element bending mode; flexoelectric coefficient; flexoelectricity; strain gradient; stress analysis; unimorph sensing element English 2021 2021-12 10.3390/applmech2040048 바로가기 바로가기 바로가기
Article A Study on the Application Design of Soil Moisture Diffusion and Crop Roots According to Subsurface Irrigation Method Purpose: Global climate change has increased drought frequency and caused significant damage to agricultural industries worldwide; for example, soybean yield has decreased by 30% on small-scale farms. Therefore, the development of subsurface irrigation methods, which conserve both water and labor, is urgently needed for open-field cropping systems. Although water and nutrient supply through subsurface irrigation shows clear advantages, the specific design of these irrigation systems relies on empirical data rather than systematic research and practical optimization. Because of irregularities and uncertainties in field soil conditions, the theoretical approach for water diffusion in soil frequently could give a wrong range of data to an irrigation system. In this study, the water diffusion by means of a commercial subsurface irrigation system has been experimentally tested in several soil types to get practical application and understand the water diffusion performance. Methods: In the present study, to better understand the shape of the subsurface diffusion plume in an open-field soybean crop during irrigation, we supplied 4 L of water through 3 mm vertical tubes using three types of dripper, at transfer rates of 2, 4, and 8 L/h. A map of the wetted soil near the dripper showed that the optimal water supply depends on the growth stage of the soybeans. Results: Subsurface irrigation testing was conducted on well-graded sand containing clay (SWC: sand well + sand clay) and poorly graded sand (SP: sand plastic). As both SWC and SP showed that the wetted area rises well upward to the ground surface from the dripping point with 2 L/h supply, it is considered that 2 L/h case is effective for water absorption by the roots of the crops. Besides, the size of the grown root of 30 days showed 450 mm of width and 300 mm of depth, so it was estimated that 150 mm wide and 100 mm deep after 10 days, and 300 mm wide and 200 mm deep after 20 days. Judging from the results of the root growth and water diffusion rate, it is desirable that over 8 L and 5–6 L supply after 10 days and 20 days of the bean sowing, respectively. Also, since the roots after 30 days grow 300 mm deep and reach to water supply drip line, it is appropriate to supply about 4 L. Conclusions: We obtained empirical vertical and horizontal diffusion data to characterize soil water transport during subsurface irrigation. In summary, in terms of water supply rate, 2 L/h was the most effective for subsurface irrigation. Additionally, depending on the growth stages of the soybeans, early, 20 days, and 30 days, 8 L, 5–6 L, and 4 L are recommended for the supplied water amount, respectively. © 2021, The Korean Society for Agricultural Machinery. Kim, Jin Hyun; Kim, Tae Wook; Kim, Seol Ha; Lee, Hwang Gyu; Eum, Duk Ho; Lee, Sang Hun Department of Precision Mechanical Engineering, Kyungpook National University, Sangju, 37224, South Korea; Department of Precision Mechanical Engineering, Kyungpook National University, Sangju, 37224, South Korea; Department of Precision Mechanical Engineering, Kyungpook National University, Sangju, 37224, South Korea, Young Engineering Education Program for Multidisciplinary Smart Disaster Management, Kyungpook National University, Sangju, 37224, South Korea; Department of Precision Mechanical Engineering, Kyungpook National University, Sangju, 37224, South Korea; Nam Kyung Co., Ltd., 497-48 Chorok-Ro Yanggam-Myeon, Gyeonggido, 445-932, Hwaseong, 18626, South Korea; Department of Southern Area Crop Science, National Institute of Crop Science, Rural Development Administration, Miryang, 50424, South Korea 57189383494; 57030752600; 57195257413; 57224504819; 57224525620; 56181002600 sangusa@korea.kr; Journal of Biosystems Engineering 1738-1266 46 3 0.21 2025-07-30 3 Drip line; Flow rates; Root zone; Soil moisture diffusion; Subsurface irrigation Agricultural robots; Chlorine containing polymers; Climate change; Crops; Diffusion in liquids; Sand; Soil moisture; Subirrigation; Water supply; Well testing; Wetting; Agricultural industries; Application design; Global climate changes; Horizontal diffusions; Irrigation systems; Moisture diffusion; Systematic research; Theoretical approach; Water absorption English Final 2021 10.1007/s42853-021-00099-6 바로가기 바로가기
Article A Study on the Correlation between Persistence of Rainfall and Frequency of Landslide Occurrence Increasing incidences of landslides in Korea are endangering life and damaging property. To ascertain the cause of the rapid increase in landslides in 2020, this study analyzed the correlation between frequency of their occurrence and persistence of rainfall. The study area comprised seven areas in Gangwon-do, Gyeonggi-do, Gyeongsangnam-do, Gyeongsangbuk-do, Jeollanam-do, Jeollabuk-do, and Chungcheongnam-do. The used rainfall factors were monthly rainfall in June, July, and August, rainfall during the summer (June-August), rainfall during the monsoon season, and number of precipitation days during the summer and during the monsoon season. The effect of these factors on landslides was identified by comparing them with the occurrence of landslides in the year of increased landslide occurrence in each area. The results confirmed that not only rainfall but also the number of precipitation days during the monsoon season affect the occurrence of landslides. The rapid increase in landslide occurrence in 2020 was attributed to increases in both the number of precipitation days during the monsoon season and rainfall during the monsoon season in 2020. These results are expected to be used as basic data for future landslide warning standards that consider the effect of the persistence of rainfall. © 2021 The Korean Society of Engineering Geology. Jeong, Youjin; Choi, Junghae Department of Earth Science Education, Kyungpook National University, South Korea; Department of Earth Science Education, Kyungpook National University, South Korea 57614147700; 55839820300 choi.jh@knu.ac.kr; Journal of Engineering Geology 1226-5268 31 4 0 2025-07-30 0 landslide; monsoon season; precipitation days; rainfall Korean Final 2021 10.9720/kseg.2021.4.631 바로가기 바로가기
Article A study on the effectiveness of response to commercial gentrification through district unit plan-focusing on the appropriateness of the time of policy intervention The purpose of this study was to analyze the possibility and limitations of responding to commercial gentrification through district unit planning by comparing and analyzing the permission trends in food service businesses and the time of establishment and application of district unit plans. It took 1year and 8months to 3years and 2months from the establishment of the district unit plan to the public notice, and compared with the permission trends in food service businesses, It is relatively fast, but it can be predicted that, due to the delay in time until the public notice, at the point when the district unit plan was finally announced, gentrification has already progressed considerably. In addition, most regional changes during the district unit planning period are made through 'change of use' activities, so it is necessary to implement measures to control those actions in conjunction with gentrification response policies. © 2021 Architectural Institute of Korea. Kim, Su-Young Department of Architectural Engineering, Kyungpook National University, South Korea 57222484391 suyoung@knu.ac.kr; Journal of the Architectural Institute of Korea 2733-6239 37 2 0 2025-07-30 1 Commercial Gentrification; District Unit Plan; Effectiveness; Food Service Business Korean Final 2021 10.5659/jaik.2021.37.2.143 바로가기 바로가기
Proceedings Paper A Study on the Effectiveness of the Comparative Neural Network Model for Abnormal Beat Detection in Electrocardiogram Signals Abnormal beat detection is an important research field in electrocardiogram (ECG) signal analysis. However, because the shapes and characteristics of beats vary according to the individual, it is difficult to classify normal and abnormal beats. To imitate cardiologists' analysis scheme, deep learning based analysis is becoming active. In particular, cardiologists' abnormal beat detection techniques resemble comparative learning in that they use normal beats as a reference. In this paper, we examined a comparative learning method by acquiring a normal reference beat using a template cluster to imitate a cardiologists' scheme. To analyze a suitable model for the comparative learning of ECG signals, we tested our method using ResNet, GoogLeNet, and DarkNet, which are widely used models provided by MATLAB deepNetworkDesigner. Our experimental results indicate that GoogLeNet minimized non-detection, DarkNet minimized over-detection, and ResNet showed intermediate results. In ECG signals, it is important to minimize the non-detection of abnormal beats. Thus, we confirmed that GoogLeNet is effective for comparative learning. Bae, Jinkyung; Kwak, Minsoo; Noh, Kyeungkap; Lee, Dongkyu; Lee, Seungmin; Park, Daejin Daegu Sci High Sch, Daegu, South Korea; Kyungpook Natl Univ, Daegu, South Korea 57433498800; 57433065200; 57432919500; 55698915100; 57200005388; 55463943600 boltanut@knu.ac.kr; 2021 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS-ASIA (ICCE-ASIA) 0 2025-07-30 0 0 electrocardiogram signal; deep learning; comparative learning; abnormal beat detection; premature ventricular contraction Abnormal beat detection; Comparative learning; Deep learning; Electrocardiogram signal; Premature ventricular contraction Biomedical signal processing; Deep learning; Abnormal beat detection; Beat detection; Comparative learning; Darknets; Deep learning; Electrocardiogram signal; Neural network model; Non-detection; Premature ventricular contraction; Research fields; Electrocardiography English 2021 2021 10.1109/icce-asia53811.2021.9641960 바로가기 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.