연구성과로 돌아가기
2023 연구성과 (153 / 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 | Comparison of Characteristics of a ZnO Gas Sensor Using a Low-Dimensional Carbon Allotrope | Owing to the increasing construction of new buildings, the increase in the emission of formaldehyde and volatile organic compounds, which are emitted as indoor air pollutants, is causing adverse effects on the human body, including life-threatening diseases such as cancer. A gas sensor was fabricated and used to measure and monitor this phenomenon. An alumina substrate with Au, Pt, and Zn layers formed on the electrode was used for the gas sensor fabrication, which was then classified into two types, A and B, representing the graphene spin coating before and after the heat treatment, respectively. Ultrasonication was performed in a 0.01 M aqueous solution, and the variation in the sensing accuracy of the target gas with the operating temperature and conditions was investigated. As a result, compared to the ZnO sensor showing excellent sensing characteristics at 350 degrees C, it exhibited excellent sensing characteristics even at a low temperature of 150 degrees C, 200 degrees C, and 250 degrees C. | Lee, Jihoon; Park, Jaebum; Huh, Jeung-Soo | Kyungpook Natl Univ, Inst Global Climate Change & Energy, Dept Convergence & Fus Syst Engn, Daegu 41566, South Korea; Kyungpook Natl Univ, Dept Energy Convergence & Climate Change, Daegu 41566, South Korea | jshuh@knu.ac.kr; | SENSORS | SENSORS-BASEL | 1424-8220 | 23 | 1 | SCIE | CHEMISTRY, ANALYTICAL;ENGINEERING, ELECTRICAL & ELECTRONIC;INSTRUMENTS & INSTRUMENTATION | 2023 | 3.4 | 30.9 | 1 | gas sensor; ZnO; graphene; carbonnanotube; formaldehyde | GRAPHENE | English | 2023 | 2023-01 | 10.3390/s23010052 | 바로가기 | 바로가기 | 바로가기 | |||||||||||
| ○ | ○ | Article | Construction of Asbestos Slate Deep-Learning Training-Data Model Based on Drone Images | The detection of asbestos roof slate by drone is necessary to avoid the safety risks and costs associated with visual inspection. Moreover, the use of deep-learning models increases the speed as well as reduces the cost of analyzing the images provided by the drone. In this study, we developed a comprehensive learning model using supervised and unsupervised classification techniques for the accurate classification of roof slate. We ensured the accuracy of our model using a low altitude of 100 m, which led to a ground sampling distance of 3 cm/pixel. Furthermore, we ensured that the model was comprehensive by including images captured under a variety of light and meteorological conditions and from a variety of angles. After applying the two classification methods to develop the learning dataset and employing the as-developed model for classification, 12 images were misclassified out of 475. Visual inspection and an adjustment of the classification system were performed, and the model was updated to precisely classify all 475 images. These results show that supervised and unsupervised classification can be used together to improve the accuracy of a deep-learning model for the detection of asbestos roof slate. | Baek, Seung-Chan; Lee, Kwang-Hyun; Kim, In-Ho; Seo, Dong-Min; Park, Kiyong | Kyungil Univ, Dept Architecture, Gyongsan 38428, South Korea; Kunsan Natl Univ, Dept Civil Engn, Kunsan 54150, South Korea; Kyungpook Natl Univ, Sch Architecture Civil Environm & Energy Engn, Daegu 41566, South Korea; Chungbuk Natl Univ, Dept Big Data, Cheongju 28644, South Korea | 56909374400; 57205582553; 58576577100; 57222555933; 57189763255 | seungchan1318@gmail.com;kh.lee@kiu.kr;inho.kim@kunsan.ac.kr;dmseo@knu.ac.kr;pky3489@chungbuk.ac.kr; | SENSORS | SENSORS-BASEL | 1424-8220 | 23 | 19 | SCIE | CHEMISTRY, ANALYTICAL;ENGINEERING, ELECTRICAL & ELECTRONIC;INSTRUMENTS & INSTRUMENTATION | 2023 | 3.4 | 30.9 | 0.26 | 2025-06-25 | 2 | 2 | deep learning; drone survey; asbestos slate; image classification | CHRYSOTILE ASBESTOS; CLASSIFICATION; EXPOSURE | asbestos slate; deep learning; drone survey; image classification | English | 2023 | 2023-10 | 10.3390/s23198021 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Review | Convolutional Neural Networks or Vision Transformers: Who Will Win the Race for Action Recognitions in Visual Data? | Understanding actions in videos remains a significant challenge in computer vision, which has been the subject of several pieces of research in the last decades. Convolutional neural networks (CNN) are a significant component of this topic and play a crucial role in the renown of Deep Learning. Inspired by the human vision system, CNN has been applied to visual data exploitation and has solved various challenges in various computer vision tasks and video/image analysis, including action recognition (AR). However, not long ago, along with the achievement of the transformer in natural language processing (NLP), it began to set new trends in vision tasks, which has created a discussion around whether the Vision Transformer models (ViT) will replace CNN in action recognition in video clips. This paper conducts this trending topic in detail, the study of CNN and Transformer for Action Recognition separately and a comparative study of the accuracy-complexity trade-off. Finally, based on the performance analysis's outcome, the question of whether CNN or Vision Transformers will win the race will be discussed. | Moutik, Oumaima; Sekkat, Hiba; Tigani, Smail; Chehri, Abdellah; Saadane, Rachid; Tchakoucht, Taha Ait; Paul, Anand | Euro Mediterranean Univ, Euromed Res Ctr, Engn Unit, Fes 30030, Morocco; Royal Mil Coll Canada, Dept Math & Comp Sci, Kingston, ON K7K 7B4, Canada; Hassania Sch Publ Works, SIRC LaGeS, Casablanca 8108, Morocco; Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea | ; Sekkat, Hiba/KIB-0438-2024; Paul, Anand/V-6724-2017; Tigani, Smail/MTB-3485-2025; Saadane, Rachid/J-4558-2019; Chehri, Abdellah/X-9516-2019 | 57292723700; 57240657800; 56464301300; 55666436200; 56074327000; 57190496695; 56650522400 | chehri@rmc.ca; | SENSORS | SENSORS-BASEL | 1424-8220 | 23 | 2 | SCIE | CHEMISTRY, ANALYTICAL;ENGINEERING, ELECTRICAL & ELECTRONIC;INSTRUMENTS & INSTRUMENTATION | 2023 | 3.4 | 30.9 | 3.8 | 2025-06-25 | 63 | 75 | convolutional neural networks; vision transformers; recurrent neural networks; conversational systems; action recognition; natural language understanding; action recognitions | COMPUTER VISION; REPRESENTATION; ATTENTION | action recognition; action recognitions; conversational systems; convolutional neural networks; natural language understanding; recurrent neural networks; vision transformers | Computers; Humans; Image Processing, Computer-Assisted; Neural Networks, Computer; Recognition, Psychology; Vision, Ocular; Computer vision; Convolution; Convolutional neural networks; Economic and social effects; Natural language processing systems; Action recognition; Conversational systems; Convolutional neural network; Human vision systems; Natural language understanding; Natural languages; Video image analysis; Vision transformer; Visual data; computer; human; image processing; procedures; vision; Recurrent neural networks | English | 2023 | 2023-01 | 10.3390/s23020734 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||
| ○ | ○ | Article | CVCC Model: Learning-Based Computer Vision Color Constancy with RiR-DSN Architecture | To achieve computer vision color constancy (CVCC), it is vital but challenging to estimate scene illumination from a digital image, which distorts the true color of an object. Estimating illumination as accurately as possible is fundamental to improving the quality of the image processing pipeline. CVCC has a long history of research and has significantly advanced, but it has yet to overcome some limitations such as algorithm failure or accuracy decreasing under unusual circumstances. To cope with some of the bottlenecks, this article presents a novel CVCC approach that introduces a residual-in-residual dense selective kernel network (RiR-DSN). As its name implies, it has a residual network in a residual network (RiR) and the RiR houses a dense selective kernel network (DSN). A DSN is composed of selective kernel convolutional blocks (SKCBs). The SKCBs, or neurons herein, are interconnected in a feed-forward fashion. Every neuron receives input from all its preceding neurons and feeds the feature maps into all its subsequent neurons, which is how information flows in the proposed architecture. In addition, the architecture has incorporated a dynamic selection mechanism into each neuron to ensure that the neuron can modulate filter kernel sizes depending on varying intensities of stimuli. In a nutshell, the proposed RiR-DSN architecture features neurons called SKCBs and a residual block in a residual block, which brings several benefits such as alleviation of the vanishing gradients, enhancement of feature propagation, promotion of the reuse of features, modulation of receptive filter sizes depending on varying intensities of stimuli, and a dramatic drop in the number of parameters. Experimental results highlight that the RiR-DSN architecture performs well above its state-of-the-art counterparts, as well as proving to be camera- and illuminant-invariant. | Choi, Ho-Hyoung | Kyungpook Natl Univ, Sch Dent, Adv Dent Device Dev Inst, Daegu 41940, South Korea | 37048369000 | chhman2000@msn.com; | SENSORS | SENSORS-BASEL | 1424-8220 | 23 | 11 | SCIE | CHEMISTRY, ANALYTICAL;ENGINEERING, ELECTRICAL & ELECTRONIC;INSTRUMENTS & INSTRUMENTATION | 2023 | 3.4 | 30.9 | 0.39 | 2025-06-25 | 5 | 3 | computer vision color constancy; scene illuminant color; illumination estimation; RiR-DSN architecture | computer vision color constancy; illumination estimation; RiR-DSN architecture; scene illuminant color | Algorithms; Color; Color Perception; Color Vision; Computers; Delayed Emergence from Anesthesia; Humans; Color; Computer vision; Image enhancement; Neural networks; Neurons; Color constancy models; Colour constancy; Computer vision color constancy; Digital image; Illuminant color; Illumination estimation; Model learning; Residual-in-residual dense selective kernel network architecture; Scene illuminant color; True colors; algorithm; color; color vision; delayed emergence from anesthesia; human; physiology; Network architecture | English | 2023 | 2023-06-05 | 10.3390/s23115341 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | Degradation Feature Extraction Method for Prognostics of an Extruder Screw Using Multi-Source Monitoring Data | Laboratory-scale data on a component level are frequently used for prognostics because acquiring them is time and cost efficient. However, they do not reflect actual field conditions. As prognostics is for an in-service system, the developed prognostic methods must be validated using real operational data obtained from an actual system. Because obtaining real operational data is much more expensive than obtaining test-level data, studies employing field data are scarce. In this study, a prognostic method for screws was presented by employing multi-source real operational data obtained from a micro-extrusion system. The analysis of real operational data is more challenging than that of test-level data because the mutual effect of each component in the system is chaotically reflected in the former. This paper presents a degradation feature extraction method for interpreting complex signals for a real extrusion system based on the physical and mechanical properties of the system as well as operational data. The data were analyzed based on general physical properties and the inferred interpretation was verified using the data. The extracted feature exhibits valid degradation behavior and is used to predict the remaining useful life of the screw in a real extrusion system. | Park, Jun-Kyu; Lee, Howon; Kim, Woojin; Kim, Gyu-Man; An, Dawn | Korea Elect Power Res Inst, Renewable Energy Solut Grp, Naju 58277, South Korea; Korea Inst Ind Technol, Adv Mechatron R&D Grp, Daegu 42994, South Korea; Kyungpook Natl Univ, Sch Mech Engn, Daegu 41566, South Korea | 57193059569; 57957951600; 57210398468; 55664733000; 35168410500 | dawnan@kitech.re.kr; | SENSORS | SENSORS-BASEL | 1424-8220 | 23 | 2 | SCIE | CHEMISTRY, ANALYTICAL;ENGINEERING, ELECTRICAL & ELECTRONIC;INSTRUMENTS & INSTRUMENTATION | 2023 | 3.4 | 30.9 | 0.26 | 2025-06-25 | 2 | 2 | degradation feature; data processing; prognostics; screw; extrusion system; real operational data; multi-source data; structural health monitoring | POLYMER EXTRUSION; QUALITY; DESIGN | data processing; degradation feature; extrusion system; multi-source data; prognostics; real operational data; screw; structural health monitoring | Bone Screws; Prognosis; Data handling; Data mining; Extraction; Extrusion; Feature extraction; Structural health monitoring; Component levels; Degradation feature; Extrusion system; Feature extraction methods; Multi-Sources; Multisource data; Operational data; Prognostic; Real operational data; Test levels; bone screw; prognosis; Screws | English | 2023 | 2023-01 | 10.3390/s23020637 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | Design and Fabrication of a High-Sensitivity and Wideband Cymbal Hydrophone | So far, cymbal transducers have been developed primarily for transmitting purposes, and even when used for receiving, the focus has been mostly on improving the receiving sensitivity. In this study, we developed a cymbal hydrophone with a higher sensitivity and a wider bandwidth than other existing hydrophones. First, the initial structure of the cymbal hydrophone was established, and then the effects of structural variables on the hydrophone's performance were analyzed using the finite element method. Based on the analysis results, the structure having the highest sensitivity and widest bandwidth, with a receiving voltage sensitivity level above a certain threshold, was derived using optimal design techniques. A prototype of the cymbal hydrophone with the designed structure was fabricated, and its performance was measured, validating the effectiveness of the design by comparing the measurement results with the design values. The developed cymbal hydrophone is expected to be utilized in various underwater precision measurements, as it possesses a significantly broader reception frequency bandwidth when compared with other hydrophones used for the same purpose. | Kim, Donghyun; Roh, Yongrae | Kyungpook Natl Univ, Sch Mech Engn, Daegu 41566, South Korea | 58950709000; 7102361870 | roy4435@naver.com;yryong@knu.ac.kr; | SENSORS | SENSORS-BASEL | 1424-8220 | 23 | 22 | SCIE | CHEMISTRY, ANALYTICAL;ENGINEERING, ELECTRICAL & ELECTRONIC;INSTRUMENTS & INSTRUMENTATION | 2023 | 3.4 | 30.9 | 0.39 | 2025-06-25 | 2 | 3 | cymbal hydrophone; high sensitivity; broadband characteristics; receiving voltage sensitivity (RVS); optimal design | TRANSDUCER | broadband characteristics; cymbal hydrophone; high sensitivity; optimal design; receiving voltage sensitivity (RVS) | Bandwidth; Design; Fabrication; Optimal systems; Broadband characteristics; Cymbal hydrophone; Cymbal transducer; High sensitivity; Optimal design; Performance; Receiving voltage sensitivity; Voltage sensitivity; Wide bandwidth; Wide-band; adult; article; bandwidth; controlled study; electric potential; finite element analysis; human; Hydrophones | English | 2023 | 2023-11 | 10.3390/s23229086 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | Designing a Geodesic Faceted Acoustical Volumetric Array Using a Novel Analytical Method | We present a novel analytical method as an efficient approach to design a geodesic-faceted array (GFA) for achieving a beam performance equivalent to that of a typical spherical array (SA). GFA is a triangle-based quasi-spherical configuration, which is conventionally created using the icosahedron method imitated from the geodesic dome roof construction process. In this conventional approach, the geodesic triangles have nonuniform geometries due to some distortions that occur during the random icosahedron division process. In this study, we took a paradigm shift from this approach and adopt a new technique to design a GFA that is based on uniform triangles. The characteristic equations that relate the geodesic triangle with a spherical platform were first developed as functions of the operating frequency and geometric parameters of the array. Then, the directional factor was derived to calculate the beam pattern associated with the array. A sample design of GFA for a given underwater sonar imaging system was synthesized through an optimization process. The GFA design was compared with that of a typical SA, and a reduction of 16.5% in the number of array elements was recorded in the GFA at a nearly equivalent performance. Both arrays were modeled, simulated, and analyzed using the finite element method (FEM) to validate the theoretical designs. Comparison of the results showed a high degree of compliance between the FEM and the theoretical method for both arrays. The proposed novel approach is faster and requires fewer computer resources than the FEM. Moreover, this approach is more flexible than the traditional icosahedron method in adjusting geometrical parameters in response to desired performance outputs. | Yusuf, Taofeek Ayotunde; Roh, Yongrae | Kyungpook Natl Univ, Sch Mech Engn, Daegu 41566, South Korea | Yusuf, Taofeek/G-7512-2017 | 57192692590; 7102361870 | yryong@knu.ac.kr; | SENSORS | SENSORS-BASEL | 1424-8220 | 23 | 6 | SCIE | CHEMISTRY, ANALYTICAL;ENGINEERING, ELECTRICAL & ELECTRONIC;INSTRUMENTS & INSTRUMENTATION | 2023 | 3.4 | 30.9 | 0.13 | 2025-06-25 | 0 | 1 | geodesic-faceted array; spherical array; acoustic transducers; beam patterns; finite element method | ANTENNA-ARRAY; NUMBER; LOCALIZATION; OPTIMIZATION; TRANSDUCER | acoustic transducers; beam patterns; finite element method; geodesic-faceted array; spherical array | Acoustic transducers; Design; Roofs; Spheres; Underwater acoustics; Analytical method; Beam pattern; Beam performance; Geodesic domes; Geodesic triangle; Geodesic-faceted array; Performance; Spherical array; Spherical configurations; Volumetric arrays; Finite element method | English | 2023 | 2023-03 | 10.3390/s23063173 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||
| ○ | ○ | Article | Development of Multilayer Transducer and Omnidirectional Reflection Model for Active Reflection Control | Underwater detection is accomplished using an underwater ultrasonic sensor, sound navigation and ranging (SONAR). Stealth to avoid detection by SONAR plays a major role in modern underwater warfare. In this study, we propose a smart skin that avoids detection by SONAR via controlling the signal reflected from an unmanned underwater vehicle (UUV). The smart skin is a multilayer transducer composed of an acoustic window, a double-layer receiver, and a single-layer transmitter. It separates the incident signal from the reflected signal from outside through the time-delay separation method and cancels the reflected wave from the phase-shifted transmission sound. The characteristics of the receiving and transmitting sensors were analyzed using a finite element analysis. Three types of devices were compared in the design of the sensors. Polyvinylidene fluoride (PVDF), which had little effect on the transmitted sound, was selected as the receiving sensor. A stacked piezoelectric transducer with high sensitivity compared to a cymbal transducer was used as the transmitter. The active reflection control system was modeled and verified using 2D 360 degrees reflection experiments. The stealth effect that could be achieved by applying a smart skin to a UUV was presented through an active reflection-control omnidirectional reflection model. | Park, Beom Hoon; Choi, Han Bin; Seo, Hee-Seon; Je, Yub; Yi, Hak; Park, Kwan Kyu | Hanyang Univ, Dept Convergence Mech Engn, Seoul 04763, South Korea; Agcy Def Dev, Maritime Technol Res Inst, Chang Won 51682, South Korea; Kyungpook Natl Univ, Dept Mech Engn, Daegu 41566, South Korea | Park, Kwan/AAC-1269-2021; Park, Kwan Kyu/L-1074-2016 | 57222087803; 58055166500; 24765212200; 35086291000; 56567311000; 55827729700 | kwankyu@hanyang.ac.kr; | SENSORS | SENSORS-BASEL | 1424-8220 | 23 | 1 | SCIE | CHEMISTRY, ANALYTICAL;ENGINEERING, ELECTRICAL & ELECTRONIC;INSTRUMENTS & INSTRUMENTATION | 2023 | 3.4 | 30.9 | 0 | 2025-06-25 | 1 | 0 | cymbal transducer; stacked piezoelectric transducer; active reflection control; SONAR; piezo material; unmanned underwater vehicle (UUV) | SOUND-ABSORPTION; DESIGN; AIR | active reflection control; cymbal transducer; piezo material; SONAR; stacked piezoelectric transducer; unmanned underwater vehicle (UUV) | Fluorine compounds; Multilayers; Piezoelectric transducers; Transmitters; Ultrasonic applications; Underwater acoustics; Unmanned underwater vehicles; Active reflection control; Cymbal transducer; Multilayer transducers; Omni-directional reflections; Piezomaterials; Reflection Models; Smart skin; Sound navigation and ranging; Stacked piezoelectric transducer; Unmanned underwater vehicle; Piezoelectricity | English | 2023 | 2023-01 | 10.3390/s23010521 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||
| ○ | ○ | Article | Development of Water Level Prediction Improvement Method Using Multivariate Time Series Data by GRU Model | The methods for improving the accuracy of water level prediction were proposed in this study by selecting the Gated Recurrent Unit (GRU) model, which is effective for multivariate learning at the Paldang Bridge station in Han River, South Korea, where the water level fluctuates seasonally. The hydrological data (i.e., water level and flow rate) for Paldang Bridge station were entered into the GRU model; the data were provided by the Water Resources Management Information System (WAMIS), and the meteorological data for Seoul Meteorological Observatory and Yangpyeong Meteorological Observatory were provided through the Korea Meteorological Administration. Correlation analysis was used to select the training data for hydrological and meteorological data. Important input data affecting the daily water level (DWL) were daily flow rate (DFR), daily vapor pressure (DVP), daily dew point temperature (DDPT), and 1 h max precipitation (1HP), and were used as the multivariate learning data for water level prediction. However, the DWL prediction accuracy did not improve even if the meteorological data from a single meteorological observatory far from the DWL prediction point were used as the multivariate learning data. Therefore, in this study, methods for improving the predictive accuracy of DWL through multivariate learning that effectively utilize meteorological data from each meteorological observatory were presented. First, it was a method of arithmetically averaging meteorological data for two meteorological observatories and using it as the multivariate learning data for the GRU model. Second, a method was proposed to use the meteorological data of the two meteorological observatories as multivariate learning data by weighted averaging the distances from each meteorological observatory to the water level prediction point. Therefore, in this study, improved water level prediction results were obtained even if data with some correlation between meteorological data provided by two meteorological observatories located far from the water level prediction point were used. | Park, Kidoo; Seong, Yeongjeong; Jung, Younghun; Youn, Ilro; Choi, Cheon Kyu | Kyungpook Natl Univ, Emergency Management Inst, Fac Engn, Sangju 37224, Gyeongbuk, South Korea; Kyungpook Natl Univ, Fac Engn, Dept Adv Sci & Technol Convergence, Sangju 37224, Gyeongbuk, South Korea; Kyungpook Natl Univ, Fac Engn, Dept Construct & Disaster Prevent Engn, Sangju 37224, Gyeongbuk, South Korea; Korea Inst Civil Engn & Bldg Technol, Dept Hydro Sci & Engn Res, Goyang 10223, Gyeonggi, South Korea | 57204532542; 57202956507; 55195880200; 57202961719; 56591215100 | bnmjkl31@knu.ac.kr; | WATER | WATER-SUI | 2073-4441 | 15 | 3 | SCIE | ENVIRONMENTAL SCIENCES;WATER RESOURCES | 2023 | 3 | 30.9 | 1 | 2025-06-25 | 4 | 6 | water level; GRU; meteorological data; multivariate learning; correlation; meteorological observatory | FUZZY INFERENCE SYSTEM; FLOOD | correlation; GRU; meteorological data; meteorological observatory; multivariate learning; water level | Han River [Far East]; Seoul [South Korea]; South Korea; Information management; Learning systems; Meteorology; Observatories; Water resources; Weather forecasting; Correlation; Gated recurrent unit; Hydrological data; Improvement methods; Learning data; Meteorological data; Meteorological observatories; Multivariate learning; Multivariate time series; Water level prediction; correlation; dew point; hydrological modeling; meteorology; multivariate analysis; observatory; prediction; time series analysis; water level; Water levels | English | 2023 | 2023-02 | 10.3390/w15030587 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | Dynamic Repositioning of Aerial Base Stations for Enhanced User Experience in 5G and Beyond | The ultra-dense deployment (UDD) of small cells in 5G and beyond to enhance capacity and data rate is promising, but since user densities continually change, the static deployment of small cells can lead to wastes of capital, the underutilization of resources, and user dissatisfaction. This work proposes the use of Aerial Base Stations (ABSs) wherein small cells are mounted on Unmanned Aerial Vehicles (UAVs), which can be deployed to a set of candidate locations. Furthermore, based on the current user densities, this work studies the optimal placement of the ABSs, at a subset of potential candidate positions, to maximize the total received power and signal-to-interference ratio. The problems of the optimal placement for increasing received power and signal-to-interference ratio are formulated, and optimal placement solutions are designed. The proposed solutions compute the optimal candidate locations for the ABSs based on the current user densities. When the user densities change significantly, the proposed solutions can be re-executed to re-compute the optimal candidate locations for the ABSs, and hence the ABSs can be moved to their new candidate locations. Simulation results show that a 22% or more increase in the total received power can be achieved through the optimal placement of the Aerial BSs and that more than 60% users have more than 80% chance to have their individual received power increased. | Rahman, Shams Ur; Khan, Ajmal; Usman, Muhammad; Bilal, Muhammad; Cho, You-Ze; El-Sayed, Hesham | UET Mardan, Dept Comp Sci, Charsadda Rd, Mardan 23200, Pakistan; Woosong Univ, Dept Artificial Intelligence & Big Data, 171 Dongdaejeon Ro, Daejeon 34606, South Korea; Hankuk Univ Foreign Studies, Dept Comp Engn, Yongin 17035, South Korea; Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea; United Arab Emirates Univ, Coll Informat Technol, Comp & Network Engn Dept, Al Ain 16427, U Arab Emirates | ; Usman, Muhammad/P-5066-2015; Bilal, Muhammad/F-5225-2019; khan, Ajmal/P-8860-2019; Muhammad, Usman/W-6993-2019 | 57270540500; 7404909217; 58618444000; 56562681700; 7404469829; 10739584700 | shams@uetmardan.edu.pk;engajmal@wsu.ac.kr;usman@uetmardan.edu.pk;m.bilal@ieee.org;yzcho@ee.knu.ac.kr;helsayed@uaeu.ac.ae; | SENSORS | SENSORS-BASEL | 1424-8220 | 23 | 16 | SCIE | CHEMISTRY, ANALYTICAL;ENGINEERING, ELECTRICAL & ELECTRONIC;INSTRUMENTS & INSTRUMENTATION | 2023 | 3.4 | 30.9 | 0.26 | 2025-06-25 | 2 | 2 | 5G; dynamic repositioning; ultra-dense deployment; UAV network; throughput maximization; optimal positioning | UAV; PLACEMENT; COVERAGE | 5G; dynamic repositioning; optimal positioning; throughput maximization; UAV network; ultra-dense deployment | 5G mobile communication systems; Base stations; Location; Unmanned aerial vehicles (UAV); 5g; Aerial vehicle; Candidate locations; Dynamic repositioning; Optimal positioning; Throughput maximization; Ultra-dense deployment; Unmanned aerial vehicle network; User density; Vehicle network; article; human; simulation; unmanned aerial vehicle; Antennas | English | 2023 | 2023-08 | 10.3390/s23167098 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||
| ○ | ○ | Article | Efficient Object Detection Using Semantic Region of Interest Generation with Light-Weighted LiDAR Clustering in Embedded Processors | Many fields are currently investigating the use of convolutional neural networks to detect specific objects in three-dimensional data. While algorithms based on three-dimensional data are more stable and insensitive to lighting conditions than algorithms based on two-dimensional image data, they require more computation than two-dimensional data, making it difficult to drive CNN algorithms using three-dimensional data in lightweight embedded systems. In this paper, we propose a method to process three-dimensional data through a simple algorithm instead of complex operations such as convolution in CNN, and utilize its physical characteristics to generate ROIs to perform a CNN object detection algorithm based on two-dimensional image data. After preprocessing the LiDAR point cloud data, it is separated into individual objects through clustering, and semantic detection is performed through a classifier trained based on machine learning by extracting physical characteristics that can be utilized for semantic detection. The final object recognition is performed through a 2D-based object detection algorithm that bypasses the process of tracking bounding boxes by generating individual 2D image regions from the location and size of objects initially detected by semantic detection. This allows us to utilize the physical characteristics of 3D data to improve the accuracy of 2D image-based object detection algorithms, even in environments where it is difficult to collect data from camera sensors, resulting in a lighter system than 3D data-based object detection algorithms. The proposed model achieved an accuracy of 81.84% on the YOLO v5 algorithm on an embedded board, which is 1.92% higher than the typical model. The proposed model achieves 47.41% accuracy in an environment with 40% higher brightness and 54.12% accuracy in an environment with 40% lower brightness, which is 8.97% and 13.58% higher than the general model, respectively, and can achieve high accuracy even in non-optimal brightness environments. The proposed technique also has the advantage of reducing the execution time depending on the operating environment of the detection model. | Jung, Dongkyu; Chong, Taewon; Park, Daejin | Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea; Carnavicom Co Ltd, Incheon 21984, South Korea; Hanyang Univ, Dept Phys, Seoul 04763, South Korea | 57223051842; 57302218000; 55463943600 | wjdxyz@knu.ac.kr;twchong@carnavi.com;boltanut@knu.ac.kr; | SENSORS | SENSORS-BASEL | 1424-8220 | 23 | 21 | SCIE | CHEMISTRY, ANALYTICAL;ENGINEERING, ELECTRICAL & ELECTRONIC;INSTRUMENTS & INSTRUMENTATION | 2023 | 3.4 | 30.9 | 0 | 2025-06-25 | 0 | 0 | convolution neural network (CNN); object detection; LiDAR sensor; point cloud; semantic detection | convolution neural network (CNN); LiDAR sensor; object detection; point cloud; semantic detection | algorithm; article; brightness; camera; classifier; controlled study; convolutional neural network; detection algorithm; diagnosis; diagnostic test accuracy study; human; human experiment; illumination; light; machine learning; sensor | English | 2023 | 2023-11 | 10.3390/s23218981 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | Global Context Attention for Robust Visual Tracking | Although there have been recent advances in Siamese-network-based visual tracking methods where they show high performance metrics on numerous large-scale visual tracking benchmarks, persistent challenges regarding the distractor objects with similar appearances to the target object still remain. To address these aforementioned issues, we propose a novel global context attention module for visual tracking, where the proposed module can extract and summarize the holistic global scene information to modulate the target embedding for improved discriminability and robustness. Our global context attention module receives a global feature correlation map to elicit the contextual information from a given scene and generates the channel and spatial attention weights to modulate the target embedding to focus on the relevant feature channels and spatial parts of the target object. Our proposed tracking algorithm is tested on large-scale visual tracking datasets, where we show improved performance compared to the baseline tracking algorithm while achieving competitive performance with real-time speed. Additional ablation experiments also validate the effectiveness of the proposed module, where our tracking algorithm shows improvements in various challenging attributes of visual tracking. | Choi, Janghoon | Kyungpook Natl Univ, Grad Sch Data Sci, Daegu 41566, South Korea | 57202773325 | jhchoi09@knu.ac.kr; | SENSORS | SENSORS-BASEL | 1424-8220 | 23 | 5 | SCIE | CHEMISTRY, ANALYTICAL;ENGINEERING, ELECTRICAL & ELECTRONIC;INSTRUMENTS & INSTRUMENTATION | 2023 | 3.4 | 30.9 | 0.39 | 2025-06-25 | 3 | 3 | visual tracking; object tracking; attention models; model-free tracking | attention models; model-free tracking; object tracking; visual tracking | Algorithms; Benchmarking; Benchmarking; Large dataset; Target tracking; Attention model; Embeddings; Global context; Large-scales; Model free; Model-free tracking; Object Tracking; Target object; Tracking algorithm; Visual Tracking; algorithm; benchmarking; Embeddings | English | 2023 | 2023-03 | 10.3390/s23052695 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | High-Quality 3D Visualization System for Light-Field Microscopy with Fine-Scale Shape Measurement through Accurate 3D Surface Data | We propose a light-field microscopy display system that provides improved image quality and realistic three-dimensional (3D) measurement information. Our approach acquires both high-resolution two-dimensional (2D) and light-field images of the specimen sequentially. We put forward a matting Laplacian-based depth estimation algorithm to obtain nearly realistic 3D surface data, allowing the calculation of depth data, which is relatively close to the actual surface, and measurement information from the light-field images of specimens. High-reliability area data of the focus measure map and spatial affinity information of the matting Laplacian are used to estimate nearly realistic depths. This process represents a reference value for the light-field microscopy depth range that was not previously available. A 3D model is regenerated by combining the depth data and the high-resolution 2D image. The element image array is rendered through a simplified direction-reversal calculation method, which depends on user interaction from the 3D model and is displayed on the 3D display device. We confirm that the proposed system increases the accuracy of depth estimation and measurement and improves the quality of visualization and 3D display images. | Kwon, Ki Hoon; Erdenebat, Munkh-Uchral; Kim, Nam; Khuderchuluun, Anar; Imtiaz, Shariar Md; Kim, Min Young; Kwon, Ki-Chul | Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea; Chungbuk Natl Univ, Sch Informat & Commun Engn, Cheongju 28644, South Korea | ; Imtiaz, Shariar Md/ACG-8972-2022 | 57190749004; 36166588400; 35494120000; 57203638261; 57213601979; 56739349100; 7201503212 | minykim@knu.ac.kr;kckwon@chungbuk.ac.kr; | SENSORS | SENSORS-BASEL | 1424-8220 | 23 | 4 | SCIE | CHEMISTRY, ANALYTICAL;ENGINEERING, ELECTRICAL & ELECTRONIC;INSTRUMENTS & INSTRUMENTATION | 2023 | 3.4 | 30.9 | 0.52 | 2025-06-25 | 4 | 4 | light field; light-field microscopy; depth estimation; fine-scale shape measurement; 3D visualization; integral imaging | INTEGRAL IMAGING MICROSCOPE; DEPTH-OF-FIELD | 3D visualization; depth estimation; fine-scale shape measurement; integral imaging; light field; light-field microscopy | 3D modeling; Data visualization; Field emission displays; Image enhancement; Laplace transforms; Three dimensional computer graphics; Three dimensional displays; 3D Visualization; Depth Estimation; Field microscopy; Fine-scale; Fine-scale shape measurement; Integral imaging; Light fields; Light-field microscopy; Shape measurements; algorithm; article; calculation; microscopy; reference value; reliability; three-dimensional imaging; Visualization | English | 2023 | 2023-02 | 10.3390/s23042173 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||
| ○ | Review | Hydrotropism: Understanding the Impact of Water on Plant Movement and Adaptation | Hydrotropism is the movement or growth of a plant towards water. It is a type of tropism, or directional growth response, that is triggered by water. Plants are able to detect water through various stimuli, including changes in moisture levels and changes in water potential. The purpose of this study is to provide an overview of how root movement towards water and plant water uptake are stabilized. The impact of hydrotropism on plants can be significant. It can help plants to survive in environments where water is scarce, and it can also help them to grow more efficiently by directing their roots towards the most nutrient-rich soil. To make sure that plant growth and water uptake are stabilized, plants must sense water. Flowing down the roots, being absorbed by roots, and evaporating from the leaves are all processes that are governed by plant physiology and soil science. Soil texture and moisture affect water uptake. Hydraulic resistances can impede plants’ water absorption, while loss of water and water movement can change plants’ water potential gradients. Growth causes water potential gradients. Plants respond to gradient changes. Stomata and aquaporins govern water flow and loss. When water is scarce, stomatal closure and hydraulic conductance adjustments prevent water loss. Plants adapt to water stream changes by expanding their roots towards water and refining the architecture of their roots. Our study indicates that water availability, or gradients, are impacted by systemic and local changes in water availability. The amount of water available is reflected in plant turgor. There is still a lot of work to be done regarding the study of how the loss and availability of water affect plant cells, as well as how biophysical signals are transformed in a certain way during their transmission into chemical signals so that pathways such as abscisic acid response or organ development can be fed with information. © 2023 by the authors. | Gul, Malik Urfa; Paul, Anand; Manimurugan, S.; Chehri, Abdellah | Department of Computer Science & Engineering, Kyungpook National University Daegu, Daegu, 41566, South Korea; Department of Computer Science & Engineering, Kyungpook National University Daegu, Daegu, 41566, South Korea, Department of Computer Science & Engineering, Karpagam Academy of Higher Education, Coimbatore, 641021, India; Department of Computer Engineering, University of Tabuk, Tabuk P.O. Box 741, Saudi Arabia; Department of Mathematics and Computer Science, Royal Military College of Canada, Kingston, K7K 7B4, ON, Canada | 58087464900; 56650522400; 38661419700; 55666436200 | paul.editor@gmail.com; | Water (Switzerland) | WATER-SUI | N/A | 2073-4441 | 15 | 3 | SCIE | ENVIRONMENTAL SCIENCES;WATER RESOURCES | 2023 | 3 | 30.9 | 1.25 | 2025-06-25 | 19 | computational modelling; Darcy’s law; hydrotropism; Ohm’s law; plant–water relations; water potential gradient; water sense in plants; water stress in plants | Flow of water; Moisture; Plant shutdowns; Textures; Water absorption; Computational modelling; Darcy’s law; Hydrotropism; Ohm’s law; Plant water relations; Potential gradients; Water potential; Water potential gradient; Water sense in plant; Water stress; Water stress in plant; Darcy law; growth response; hydrological modeling; movement; plant water relations; water availability; water flow; water stress; water uptake; Plants (botany) | English | Final | 2023 | 10.3390/w15030567 | 바로가기 | 바로가기 | 바로가기 | |||||||
| ○ | ○ | Article | Incremental Learning for Online Data Using QR Factorization on Convolutional Neural Networks | Catastrophic forgetting, which means a rapid forgetting of learned representations while learning new data/samples, is one of the main problems of deep neural networks. In this paper, we propose a novel incremental learning framework that can address the forgetting problem by learning new incoming data in an online manner. We develop a new incremental learning framework that can learn extra data or new classes with less catastrophic forgetting. We adopt the hippocampal memory process to the deep neural networks by defining the effective maximum of neural activation and its boundary to represent a feature distribution. In addition, we incorporate incremental QR factorization into the deep neural networks to learn new data with both existing labels and new labels with less forgetting. The QR factorization can provide the accurate subspace prior, and incremental QR factorization can reasonably express the collaboration between new data with both existing classes and new class with less forgetting. In our framework, a set of appropriate features (i.e., nodes) provides improved representation for each class. We apply our method to the convolutional neural network (CNN) for learning Cifar-100 and Cifar-10 datasets. The experimental results show that the proposed method efficiently alleviates the stability and plasticity dilemma in the deep neural networks by providing the performance stability of a trained network while effectively learning unseen data and additional new classes. | Kim, Jonghong; Lee, Wonhee; Baek, Sungdae; Hong, Jeong-Ho; Lee, Minho | Keimyung Univ, Dongsan Hosp, Sch Med, Dept Obstet & Gynecol, Daegu 42601, South Korea; Keimyung Univ, Dept Med Informat, Sch Med, Daegu 42601, South Korea; Kyungpook Natl Univ, Grad Sch Artificial Intelligence, Daegu 41566, South Korea; Biolink Inc, Daegu 42601, South Korea | Lee, Min-Ho/ABE-5735-2021; Hong, Jeong-Ho/T-8099-2018; Hong, Jeong-Ho/AAE-1002-2022 | 57022250500; 58643852600; 58064927200; 55931654800; 57191730119 | jonghong89@gmail.com;harukuma1049@gmail.com;scar9cube@gmail.com;neurohong79@gmail.com;mholee@gmail.com; | SENSORS | SENSORS-BASEL | 1424-8220 | 23 | 19 | SCIE | CHEMISTRY, ANALYTICAL;ENGINEERING, ELECTRICAL & ELECTRONIC;INSTRUMENTS & INSTRUMENTATION | 2023 | 3.4 | 30.9 | 0 | 2025-06-25 | 0 | 0 | image processing; incremental learning; convolutional neural network; deep learning; artificial intelligence; compressed sensing | RECOGNITION; STABILITY | artificial intelligence; compressed sensing; convolutional neural network; deep learning; image processing; incremental learning | Convolution; Convolutional neural networks; E-learning; Factorization; Image processing; Catastrophic forgetting; Compressed-Sensing; Convolutional neural network; Deep learning; Images processing; Incremental learning; Learn+; Learning frameworks; Online data; QR factorizations; article; artificial intelligence; convolutional neural network; deep learning; deep neural network; hippocampus; image processing; learning; memory; Deep neural networks | English | 2023 | 2023-10 | 10.3390/s23198117 | 바로가기 | 바로가기 | 바로가기 | 바로가기 |
페이지 이동: