연구성과로 돌아가기
2022 연구성과 (143 / 280)
※ 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 | Deep Learning-Based Facial Landmarks Localization Using Compound Scaling | Facial landmarks are crucial information needed in numerous facial analysis applications which can help to resolve difficult computer vision-related problems. The localization of landmarks, which involves facial keypoints such as eye centers, eyebrows, nose center, etc, offers necessary information for face analysis like expressions, emotions, health conditions, etc. The applications with requirement constraints such as the model size and computational load are often scaled up with better accuracy and efficiency. In this paper, we propose a deep learning-based approach for facial landmarks localization with compound dimension scaling. We modify the baseline network called EfficientNet with multi-scale fully connected layers to predict the facial landmarks on human faces which are mapped on the detected face in real-time. The proposed model with the compound scaling method gives a scalable model by uniformly scaling the width, depth and resolution dimensions. The model is evaluated with an adaptive wing loss function for both larger and smaller models. We also assessed the robustness of the model with various head poses and occlusion conditions. The proposed model which is trained with a large dataset can achieve 90% of accuracy for a larger model with a model size of 24.6 MB and approximately 88%similar to 89% of accuracy for smaller models. Hence, the smaller models can still achieve acceptable accuracy compared to the larger model with fewer parameters. | Colaco, Savina Jassica; Han, Dong Seog | Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea | Han, Dong Seog/N-8949-2018 | 57211180064; 7403219442 | dshan@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 10 | SCIE | COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS | 2022 | 3.9 | 36.2 | 1.03 | 2025-06-25 | 9 | 12 | Adaptive wing loss; compound scaling; facial landmarks | FACE ALIGNMENT; NETWORK | Adaptive wing loss; Compound scaling; Facial landmarks | Deep learning; Job analysis; Large dataset; Neural networks; Adaptation models; Adaptive wing; Adaptive wing loss; Compound scaling; Computational modelling; Convolutional neural network; Face; Facial landmark; Location awareness; Scalings; Task analysis; Face recognition | English | 2022 | 2022 | 10.1109/access.2022.3141791 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | Deep Learning-Based Speech Emotion Recognition Using Multi-Level Fusion of Concurrent Features | The detection and classification of emotional states in speech involves the analysis of audio signals and text transcriptions. There are complex relationships between the extracted features at different time intervals which ought to be analyzed to infer the emotions in speech. These relationships can be represented as spatial, temporal and semantic tendency features. In addition to emotional features that exist in each modality, the text modality consists of semantic and grammatical tendencies in the uttered sentences. Spatial and temporal features have been extracted sequentially in deep learning-based models using convolutional neural networks (CNN) followed by recurrent neural networks (RNN) which may not only be weak at the detection of the separate spatial-temporal feature representations but also the semantic tendencies in speech. In this paper, we propose a deep learning-based model named concurrent spatial-temporal and grammatical (CoSTGA) model that concurrently learns spatial, temporal and semantic representations in the local feature learning block (LFLB) which are fused as a latent vector to form an input to the global feature learning block (GFLB). We also investigate the performance of multi-level feature fusion compared to single-level fusion using the multi-level transformer encoder model (MLTED) that we also propose in this paper. The proposed CoSTGA model uses multi-level fusion first at the LFLB level where similar features (spatial or temporal) are separately extracted from a modality and secondly at the GFLB level where the spatial-temporal features are fused with the semantic tendency features. The proposed CoSTGA model uses a combination of dilated causal convolutions (DCC), bidirectional long short-term memory (BiLSTM), transformer encoders (TE), multi-head and self-attention mechanisms. Acoustic and lexical features were extracted from the interactive emotional dyadic motion capture (IEMOCAP) dataset. The proposed model achieves 75.50% and 75.82% of weighted and unweighted accuracy, 75.32% and 75.57% of recall and F1 score respectively. These results imply that concurrently learned spatial-temporal features with semantic tendencies learned in a multi-level approach improve the model's effectiveness and robustness. | Kakuba, Samuel; Poulose, Alwin; Han, Dong Seog | Kyungpook Natl Univ, Grad Sch Elect & Elect Engn, Daegu 41566, South Korea; Kabale Univ, Fac Engn Technol Appl Design & Fine Art, Kabale, Uganda; Univ Michigan, Dept Elect & Comp Engn, Dearborn, MI 48128 USA; Kyungpook Natl Univ, Sch Elect Engn, Daegu 41566, South Korea | , ALWIN POULOSE/S-4914-2018; POULOSE, ALWIN/S-4914-2018; Kakuba, Samuel/HLX-4856-2023; Han, Dong Seog/N-8949-2018 | 57988218000; 57205504085; 7403219442 | dshan@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 10 | SCIE | COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS | 2022 | 3.9 | 36.2 | 3.35 | 2025-06-25 | 25 | 38 | Emotion recognition; Acoustics; Convolutional neural networks; Brain modeling; Speech recognition; spatial features; temporal features; semantic tendency features; multi-head attention | Emotion recognition; multi-head attention; semantic tendency features; spatial features; temporal features | Character recognition; Convolution; Emotion Recognition; Feature extraction; Recurrent neural networks; Signal analysis; Signal encoding; Speech recognition; Emotion recognition; Feature learning; Grammatical models; Multi-head attention; Multilevels; Semantic tendency feature; Spatial features; Spatial temporal model; Spatial-temporal features; Temporal features; Semantics | English | 2022 | 2022 | 10.1109/access.2022.3225684 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | Design of Generalized Sinusoidal Frequency Modulated Pulse Train Waveform to Improve Tracking Performance of High Duty Cycle Sonar Systems | High duty cycle sonar (HDCS) systems have a high potential for improving tracking performance compared to conventional pulsed active sonar systems, but their implementation has been challenging to achieve. This is because conventional waveform design studies for HDCS systems had focused primarily on solving direct blast interference problems caused by continuous transmission and reception of pulse train waveforms. So far, there are no studies for waveform design to improve HDCS tracking performance. In this paper, we proposed a generalized sinusoidal frequency modulated (GSFM) pulse train waveform design scheme to improve HDCS tracking performance. The proposed design scheme utilizes the trade-off relationship between detection performance in a reverberation environment and measurement uncertainty according to the parameter rho of the GSFM waveform. To accomplish the goal, we developed a framework for pulse train waveform design considering HDCS tracking performance. In the framework, the detection probability and measurement noise covariance matrix of the Kalman filter are calculated based on the designed GSFM pulse train waveform. Therefore, the pulse train waveform design and HDCS tracking performance can be associated. The simulation using the HDCS tracking framework demonstrated that optimal tracking performance was obtained when the parameter rho was 1.07. | Kim, Geunhwan; Lee, Seokjin; Yoon, Kyungsik; Ryu, Changsoo; Park, Minseuk; Choo, Youngmin | Sejong Univ, Dept Ocean Syst Engn, Seoul 05006, South Korea; Kyungpook Natl Univ, Coll IT Engn, Sch Elect & Elect Engn, Daegu 41566, South Korea; Gimcheon Univ, Dept IT Convergence Engn, Gamcheon 39528, South Korea; Yeungnam Univ Coll, Div ICT Semicond Elect, Daegu 42415, South Korea; Sejong Univ, Dept Def Syst Engn, Seoul 05006, South Korea | 57214800540; 36174416200; 57214791009; 57918306000; 57386230400; 54894104100 | ychoo@sejong.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 10 | SCIE | COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS | 2022 | 3.9 | 36.2 | 0.18 | 2025-06-25 | 0 | 2 | Generalized sinusoidal frequency modulated waveform; high-duty cycle sonar system; high duty cycle sonar tracking; pulse train waveform design | CONTINUOUS ACTIVE SONAR | Generalized sinusoidal frequency modulated waveform; high duty cycle sonar tracking; high-duty cycle sonar system; pulse train waveform design | Clutter (information theory); Covariance matrix; Economic and social effects; Reverberation; Sonar; Target tracking; Uncertainty analysis; Duty-cycle; Frequency modulated; Generalized sinusoidal frequency modulated waveform; High duty cycle sonar tracking; High-duty cycle sonar system; Interference; Measurement uncertainty; Modulated waveforms; Pulse measurements; Pulse train waveform design; Pulse train waveforms; Sinusoidal frequency; Sonar system; Sonar tracking; Targets tracking; Waveform designs; Frequency modulation | English | 2022 | 2022 | 10.1109/access.2022.3210986 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | Design of Secure Handover Authentication Scheme for Urban Air Mobility Environments | Urban air mobility (UAM) is a future air transportation system to solve the air pollution and movement efficiency problems of the traditional mobility system. In UAM environments, unmanned aerial vehicles (UAV) are used to transport passengers and goods providing various convenient services such as package delivery, air bus, and air taxi. However, UAVs communicate with ground infrastructures through open channels that can be exposed to various security attacks. Therefore, a secure mutual authentication scheme is necessary for UAM environments. Moreover, a handover authentication is also necessary to ensure seamless communication when the service location is changed. In this paper, we design a secure and efficient handover authentication scheme for UAM environments considering various security vulnerabilities and efficiency using elliptic curve cryptography (ECC). We utilize informal security analysis, Real-or-Random (RoR), Burrows-Abadi-Needham (BAN) logic, and Automated Validation of Internet Security Protocols and Applications (AVISPA) to prove the security of the proposed scheme. Furthermore, we compare the computation and communication cost comparisons of the proposed scheme with the other related schemes. The results show that the proposed scheme is secure and efficient for UAM environments. | Kwon, Deokkyu; Son, Seunghwan; Park, Yohan; Kim, Hyungpyo; Park, Youngho; Lee, Sangwoo; Jeon, Yongsung | Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea; Keimyung Univ, Sch Comp Engn, Daegu 42601, South Korea; Kyungpook Natl Univ, Dept Elect Engn, Daegu 41566, South Korea; Kyungpook Natl Univ, Sch Elect Engn, Daegu 41566, South Korea; Elect & Telecommun Res Inst, Daejeon 34129, South Korea | 57221739597; 57221744477; 55660095600; 57190069232; 56962990300; 57201864359; 59627026200 | parkyh@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 10 | SCIE | COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS | 2022 | 3.9 | 36.2 | 3.09 | 2025-06-25 | 30 | 35 | Authentication; Handover; Security; Transportation; Elliptic curve cryptography; Autonomous aerial vehicles; Computational modeling; Urban air mobility; handover; authentication; BAN logic; RoR model; AVISPA | PROTOCOL; INTERNET; PRIVACY | Authentication; AVISPA; BAN logic; Handover; RoR model; Urban air mobility | Antennas; Authentication; Computation theory; Efficiency; Geometry; Network security; Public key cryptography; Taxicabs; Unmanned aerial vehicles (UAV); Urban transportation; Automated validation of internet security protocol and application; BAN logic; Computational modelling; Hand over; Internet security; Random Model; Real-or-random model; Security; Security application; Security protocols; Urban air; Urban air mobility; Air mobility | English | 2022 | 2022 | 10.1109/access.2022.3168843 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | Design of Secure Mutual Authentication Scheme for Metaverse Environments Using Blockchain | During the COVID-19 pandemic, engagement in various remote activities such as online education and meetings has increased. However, since the conventional online environments typically provide simple streaming services using cameras and microphones, there have limitations in terms of physical expression and experiencing real-world activities such as cultural and economic activities. Recently, metaverse environments, three-dimensional virtual reality that use avatars, have attracted increasing attention as a means to solve these problems. Thus, many metaverse platforms such as Roblox, Minecraft, and Fortnite have been emerging to provide various services to users. However, such metaverse environments are potentially vulnerable to various security threats because the users and platform servers communicate through public channels. In addition, sensitive user data such as identity, password, and biometric information are managed by each platform server. In this paper, we design a system model that can guarantee secure communication and transparently manage user identification data in metaverse environments using blockchain technology. We also propose a mutual authentication scheme using biometric information and Elliptic Curve Cryptography (ECC) to provide secure communication between users and platform servers and secure avatar interactions between avatars and avatars. To demonstrate the security of the proposed mutual authentication scheme, we perform informal security analysis, Burrows-Abadi-Needham (BAN) logic, Real-or-Random (ROR) model, and Automated Validation of Internet Security Protocols and Applications (AVISPA). In addition, we compare the computation costs, communication costs, and security features of the proposed scheme with existing schemes in similar environments. The results demonstrate that the proposed scheme has lower computation and communication costs and can provide a wider range of security features than existing schemes. Thus, our proposed scheme can be used to provide secure metaverse environments. | Ryu, Jongseok; Son, Seunghwan; Lee, Joonyoung; Park, Yohan; Park, Youngho | Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea; Keimyung Univ, Sch Comp Engn, Daegu 42601, South Korea; Kyungpook Natl Univ, Sch Elect Engn, Daegu 41566, South Korea | 57431417300; 57221744477; 57203970123; 55660095600; 56962990300 | yhpark@kmu.ac.kr;parkyh@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 10 | SCIE | COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS | 2022 | 3.9 | 36.2 | 10.5 | 2025-06-25 | 80 | 122 | Metaverse; Avatars; Blockchains; Security; Authentication; Servers; Solid modeling; Cryptography; Metaverse; avatar; authentication; BAN logic; ROR model; AVISPA; blockchain; elliptic curve cryptography; biohashing | KEY AGREEMENT PROTOCOL | authentication; avatar; AVISPA; BAN logic; biohashing; blockchain; elliptic curve cryptography; Metaverse; ROR model | Biometrics; Blockchain; Computation theory; Computer circuits; Geometry; Information management; Network security; Public key cryptography; Security systems; Virtual reality; Automated validation of internet security protocol and application; Avatar; BioHashing; Block-chain; Burrow-abadi-needham logic; Curve cryptography; Elliptic curve; Elliptic curve cryptography; Internet security; Metaverses; Random Model; Real-or-random model; Security application; Security protocols; Authentication | English | 2022 | 2022 | 10.1109/access.2022.3206457 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | Designing Gamified Application: An Effective Integration of Augmented Reality to Support Learning | Early childhood learning is an important concern for the concept building of children. Students have been taught with traditional methods from the beginning. However, these methods lack kids' attention. Application of Augmented Reality (AR) in a traditional way of teaching can help students in better engagement and better learning. In this research, an ABCD-AR mobile based application is designed to overcome the flaws in the traditional education system. While designing AR mobile applications, certain guidelines need to be considered that cause problems for kids in their learning. These may include but are not limited to small screen size and irregularity. Considering these problems, this study proposes 23 usability principles for AR based learning applications for kids. These identified usability principles are validated by human experts. Furthermore, experiments are carried out to evaluate the application in terms of efficiency, effectiveness, learn-ability, user satisfaction & engagement. The results implies that the developed game-based application is highly effective and efficient because the mean of marks obtained by students before using ABCD-AR application is lower (M = 4.97, SD = 1.650) than the marks obtained after using ABCD-AR application (M = 7.97, SD = 1.608). Similarly, results indicate that mean of time taken to perform tests without using ABCD-AR application (M = 7.97, SD = 1.650) is higher as compared to with using it (M = 4.37, SD = 1.608). Majority of the students were entertained by playing the game while learning, and felt motivated to continue based on the game's scenario due to the variety of activities included. Teachers and parents involved in these experiments have shown satisfaction towards the use of ABCD-AR application in learning process of preschool kids. | Farooq, Sehar Shahzad; Rahman, Hameedur; Raza, Syed Ali Naqi; Raees, Muhammad; Jung, Soon Ki | Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea; Air Univ, Fac Comp & AI, Dept Comp Games Dev, Islamabad 44000, Pakistan; HITEC Univ, Dept Comp Sci, Taxila 47080, Pakistan; Dept Higher Educ, Peshawar 25120, Khyber Pakhtunk, Pakistan | ; Rahman, Hameedur/AAK-6179-2021; Raees, Muhammmad/J-3526-2019; Jung, Soon Ki/P-7687-2018 | 57217701362; 57006213600; 56784481100; 56730766100; 57226791905 | skjung@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 10 | SCIE | COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS | 2022 | 3.9 | 36.2 | 1.32 | 2025-06-25 | 9 | 15 | Augmented reality; usability principles; mobile application; kid's learning | SKILLS | Augmented reality; kid's learning; mobile application; usability principles | Computer aided instruction; E-learning; Learning systems; Mobile computing; Students; Augmented reality applications; Game; Game-based Learning; Kid’s learning; Mobile applications; Programming profession; Technology to support learning; Usability; Usability principle; Augmented reality | English | 2022 | 2022 | 10.1109/access.2022.3221473 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | Digital Twin Model: A Real-Time Emotion Recognition System for Personalized Healthcare | Emotion recognition (ER) in healthcare has drawn substantial attention owing to recent advancements in machine-learning (ML) and deep-learning (DL) techniques. The ER system, along with a digital twin of a person in real time, will facilitate the monitoring, understanding, and improvement of the physical entity's capabilities, as well as provide constant input to improve quality of life and well-being for personalized healthcare. However, building such ER systems in real time involves technical challenges, such as limited datasets, occlusion and lighting issues, identifying important features, false classification of emotions, and high implementation costs. To resolve this issue, we built a simple, efficient, and adaptable ER system by acquiring and processing images in real time using a web camera. In addition, we propose an end-to-end framework that combines an ER system with a digital twin setup, in which the predicted result can be analyzed and tested prior to providing the best possible personal healthcare treatment before it leads to any life-threatening disease. Our proposed ER system achieved promising results in less training time without compromising the accuracy. Thus, in real time, it will be helpful in healthcare centers to monitor a patient's health condition, early diagnosis of life-threatening diseases, and to obtain the best and most effective treatment for patients during emergencies. | Subramanian, Barathi; Kim, Jeonghong; Maray, Mohammed; Paul, Anand | Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea; King Khalid Univ, Coll Comp Sci & Informat Syst, Abha 61421, Saudi Arabia | Subramanian, Barathi/HLP-9548-2023; Paul, Anand/V-6724-2017 | 57221053219; 55138548100; 57214776817; 56650522400 | jhk@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 10 | SCIE | COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS | 2022 | 3.9 | 36.2 | 3.88 | 2025-06-25 | 27 | 44 | Medical services; Emotion recognition; Face recognition; Feature extraction; Real-time systems; Diseases; Digital twins; Deep learning; emotion recognition; intelligence system; MediaPipe; smart healthcare system | Deep learning; emotion recognition; intelligence system; MediaPipe; smart healthcare system | Classification (of information); Deep learning; Diagnosis; Diseases; E-learning; Face recognition; Interactive computer systems; Patient treatment; Real time systems; Speech recognition; Deep learning; Emotion recognition; Features extraction; Intelligence systems; Mediapipe; Medical services; Real - Time system; Recognition systems; Smart healthcare systems; Emotion Recognition | English | 2022 | 2022 | 10.1109/access.2022.3193941 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | Efficient Sensor Processing Technique Using Kalman Filter-Based Velocity Prediction in Large-Scale Vehicle IoT Application | Sensor nodes that operate as edge devices in Internet-of-Things (IoT) networks have various limitations, such as insufficient power supply and small memory size. Therefore, the sensor node must be able to use resources efficiently to achieve the specified software behavior of the target application. The application in this study involves an IoT network in which the sensor node requests the position from a moving vehicle and estimates the velocity by using a Kalman filter. Using the same sensing cycle for all vehicles improves accuracy regardless of the predicted velocity of the sensor node but increases unnecessary computations. The proposed technique defines distance weight W-D which controls weight policy of the vehicle's speed change. The distance weight W-D determines a communication cycle between the sensor node and vehicle, therefore this approach enables the sensor node to adaptively determine the data request period based on the state of the vehicle. When a slow-moving vehicle intermittently communicates with a sensor node, the time required for the computation performed by the sensor node can be significantly reduced. To evaluate the proposed technique, we experimented with a traffic simulator that was implemented in MATLAB. Compared with the increment in the root mean square error of the reference velocity that sensed the position at every time step, the decrement in the processing time of the sensor node was considerable. Experiments with four manually determined distance weights and a number of spawned vehicles showed that the sensor node processing time was reduced by up to 72.91%. | Kwon, Jisu; Park, Daejin | Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea; Kyungpook Natl Univ, Sch Elect Engn, Daegu 41566, South Korea | 57215531728; 55463943600 | boltanut@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 10 | SCIE | COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS | 2022 | 3.9 | 36.2 | 0.17 | 2025-06-25 | 2 | 2 | Embedded system; Kalman filter; sensor node; traffic simulation; vehicle tracking | ENERGY-EFFICIENCY; NETWORKS; INTERNET; STATE; EDGE | Embedded system; Kalman filter; sensor node; traffic simulation; vehicle tracking | Application programs; Bandpass filters; Embedded systems; Internet of things; MATLAB; Mean square error; Sensor nodes; Vehicle to vehicle communications; Vehicles; Velocity; Embedded-system; Filter-based; Moving vehicles; Processing technique; Processing time; Road traffic; Sensor processing; Traffic simulations; Vehicles detection; Kalman filters | English | 2022 | 2022 | 10.1109/access.2022.3215166 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | Energy-Efficient Speed Planner for Connected and Automated Electric Vehicles on Sloped Roads | This paper proposes an energy-efficient speed planning strategy for a connected and automated vehicle (CAV) considering the upcoming traffic and road gradient information, which can be provided by the vehicle-to-everything communication systems. Unlike human drivers, CAV that receives long and short sighted traffic and road geometry information can optimize their speed profile to increase energy efficiency, depending on the powertrain types. In particular, the developed speed planner reducing the battery output power through the energy-efficiency improvement systems in electrified vehicles. Consequently, the CAV that is aware of the existence of the upcoming road gradient increases the speed on the uphill, and decreases the speed on the downhill to minimize the battery output power, which is different from the natural behaviors of human-driven vehicles on sloped roads. To consider the constraints, the model predictive control-based speed planner is developed, and its effectiveness is verified under various driving conditions. Simulation results show that our approach significantly outperforms the alternative speed profiles in terms of battery energy-saving, achieving about 27.21% of the energy efficiency improvement. | Wang, Xiangfei; Park, Suyong; Han, Kyoungseok | Kyungpook Natl Univ, Sch Mech Engn, Daegu 41566, South Korea | 57310750400; 57560254700; 56465294700 | kyoungsh@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 10 | SCIE | COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS | 2022 | 3.9 | 36.2 | 0.62 | 2025-06-25 | 6 | 7 | Roads; Batteries; Automobiles; Trajectory; Power generation; Vehicles; State of charge; Connected and automated vehicle; model predictive control; electric vehicle; energy-efficiency improvement; energy-efficient driving | CONSUMPTION; GRADIENT | Connected and automated vehicle; electric vehicle; energy-efficiency improvement; energy-efficient driving; model predictive control | Automation; Battery management systems; Behavioral research; Charging (batteries); Electric vehicles; Model predictive control; Roads and streets; Secondary batteries; Speed; Vehicle to vehicle communications; Automated vehicles; Connected and automated vehicle; Energy efficiency improvements; Energy efficient; Energy-efficient driving; Model-predictive control; Power- generations; Road gradients; Speed profile; States of charges; Energy efficiency | English | 2022 | 2022 | 10.1109/access.2022.3162871 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | Enhancement of Shielding Effectiveness of Double-Layer Shielding Structures With Narrow Slots Due to Parallel Wires | This study investigated the enhancement characteristics of the shielding effectiveness (SE) of a double-layer shielding structure with narrow slots when a plane wave is incident on the slot. Integral equations for aperture magnetic currents in narrow slots were derived and solved by applying Galerkin's method of moments. The numerical results demonstrate that SE depends on the layer wall spacing for a given frequency. The SE fluctuates with the spacing of the layers, and the fluctuation period is approximately 0.5 lambda at the resonant frequency. These periodic SE patterns gradually increase in magnitude with increasing layer wall spacing. To enhance the SE against electromagnetic interference at the resonant frequency, two parallel wires were used to minimize the transmission (maximize SE) through the narrow slots. The analysis results show that the SE can be enhanced by connecting the parallel wires to the slots at the resonant frequency. Experimental results are presented to validate the theory. | Kim, Ki-Chai; Min, Gyeong-Jun; Park, Gyeong-Sik; Cho, Young-Ki | Yeungnam Univ, Dept Elect Engn, Gyongsan 38541, South Korea; Daegu Gyeongbuk Med Innovat Fdn K MEDI Hub, Med Device Dev Ctr, Daegu 41061, South Korea; SL Corp, Gyongsan 38470, South Korea; Kyungpook Natl Univ, Sch Elect Engn, Daegu 41566, South Korea | 7409319315; 56537879100; 57346145100; 7404469777 | kckim@ynu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 10 | SCIE | COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS | 2022 | 3.9 | 36.2 | 0 | 2025-06-25 | 0 | 0 | Double-layer shielding structure; minimum transmission; narrow slot; shielding effectiveness; two parallel wires | ELECTROMAGNETIC PENETRATION; APERTURES; ENCLOSURES; PLATES | Double-layer shielding structure; minimum transmission; narrow slot; shielding effectiveness; two parallel wires | Electric fields; Electromagnetic pulse; Electromagnetic shielding; Integral equations; Magnetic resonance; Magnetic shielding; Method of moments; Wire; A-plane; Aperture; Double-layer shielding; Double-layer shielding structure; Minimum transmission; Narrow slot; Parallel wires; Shielding effectiveness; Two parallel wire; Wall spacing; Natural frequencies | English | 2022 | 2022 | 10.1109/access.2022.3219212 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | Extending Contrastive Learning to Unsupervised Coreset Selection | Self-supervised contrastive learning offers a means of learning informative features from a pool of unlabeled data. In this paper, we investigate another useful approach. We propose an entirely unlabeled coreset selection method. In this regard, contrastive learning, one of several self-supervised methods, was recently proposed and has consistently delivered the highest performance. This prompted us to choose two leading methods for contrastive learning: the simple framework for contrastive learning of visual representations (SimCLR) and the momentum contrastive (MoCo) learning framework. We calculated the cosine similarities for each example of an epoch for the entire duration of the contrastive learning process and subsequently accumulated the cosine similarity values to obtain the coreset score. Our assumption was that a sample with low similarity would likely behave as a coreset. Compared with existing coreset selection methods with labels, our approach reduced the cost associated with human annotation. In this study, the unsupervised method implemented for coreset selection achieved improvements of 1.25% (for CIFAR10), 0.82% (for SVHN), and 0.19% (for QMNIST) over a randomly selected subset with a size of 30%. Furthermore, our results are comparable to those of the existing supervised coreset selection methods. The differences between the proposed and the above mentioned supervised coreset selection method (forgetting events) were 0.81% on the CIFAR10 dataset, -2.08% on the SVHN dataset (the proposed method outperformed the existing method), and 0.01% on the QMNIST dataset at a subset size of 30%. In addition, our proposed approach exhibited robustness even if the coreset selection model and target model were not identical (e.g., using ResNet18 as a selection model and ResNet101 as the target model). Lastly, we obtained more concrete proof that our coreset examples are highly informative by showing the performance gap between the coreset and non-coreset samples in the coreset cross test experiment. We observed a pair of performance ((testing: non-coreset, training: coreset), (testing: coreset, training: non-coreset)), i.e. (94.27%, 67.39 %) for CIFAR10, (98.24%, 83.30%) for SVHN, and (99.89%, 93.07%) for QMNIST with a subset size of 30%. | Ju, Jeongwoo; Jung, Heechul; Oh, Yoonju; Kim, Junmo | Korea Adv Inst Sci & Technol, Div Future Vehicle, Daejeon 34141, South Korea; Kyungpook Natl Univ, Dept Artificial Intelligence, Daegu 41566, South Korea; Korea Adv Inst Sci & Technol, Sch Elect Engn, Daejeon 34141, South Korea | Jung, Heechul/HTL-7199-2023 | 55651859700; 55652175200; 57222422146; 36015494900 | junmo.kim@kaist.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 10 | SCIE | COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS | 2022 | 3.9 | 36.2 | 0.88 | 2025-06-25 | 9 | 10 | Task analysis; Training; Measurement; Annotations; Licenses; Feature extraction; Deep learning; Coreset selection; image classification; self-supervised learning; contrastive learning | Annotations; Deep learning; Feature extraction; Licenses; Measurement; Task analysis; Training | Deep learning; Image annotation; Job analysis; Statistical tests; Supervised learning; Annotation; Contrastive learning; Core set; Coreset selection; Deep learning; Features extraction; Images classification; License; Self-supervised learning; Task analysis; Feature extraction | English | 2022 | 2022 | 10.1109/access.2022.3142758 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | Fibrous and granular activated carbon mixed media for effective gas removal as a cabin air filter | There is a need for the purification of indoor air owing to a high rate of pollution in today's world. For this, cabin air filters (CAFs) are widely used, which requires the addition of certain adsorbents to increase the volatile organic compound (VOC) removal efficiency. However, this addition causes high-pressure resistance, which may hamper commercial applications by requiring more energy and negatively affecting fresh air delivery rate. Hence, in this study, a high-performance combined CAF (CCAF) with excellent dust and chemical filtration performance and low differential pressure was prepared using granular activated carbon (GAC)/activated carbon fiber (ACF) mixed medium. The GAC/ACF mixed medium had higher air permeability than the ACF medium of the same weight, and it exhibited similar ultrafine dust filtration performance to the ACF medium without an increase in differential pressure. In addition, the GAC/ACF mixed medium showed excellent gas removal performance without increasing differential pressure by combining the VOC removal characteristics of the GAC and ACF filter media. The improved VOC removal performance of the GAC/ACF mixed medium was due to the hybrid effect of the hierarchical pore structures of the GAC and the nearly uniform pore structures of the ACF, which resulted in a slow and increased gas adsorption by the GAC and rapid gas adsorption of the ACF. | Wee, Jae-Hyung; Bae, Younghwan; Ahn, Hyunchul; Choi, Yeong Og; Jeong, Euigyung; Yeo, Sang Young | Korea Inst Ind Technol, Adv Text R&D Dept, 143 Hanggaulro, Ansan 15588, Gyeonggi Do, South Korea; Kyungpook Natl Univ, Dept Text Syst Engn, 80 Daehakro, Daegu 41566, South Korea | ; yeo, sangyeoung/AAT-3273-2021 | 57188639537; 56311100100; 49962911700; 55644172100; 35885596300; 7101872189 | wolfpack@knu.ac.kr;miracle@kitech.re.kr; | CARBON LETTERS | CARBON LETT | 1976-4251 | 2233-4998 | 32 | 4 | SCIE | CHEMISTRY, MULTIDISCIPLINARY;MATERIALS SCIENCE, MULTIDISCIPLINARY | 2022 | 4.5 | 36.2 | 0.95 | 2025-06-25 | 11 | 12 | Activated carbon; Activated carbon fiber; Differential pressure; VOC removal; Cabin air filter | ADSORPTION; PERFORMANCE; FIBERS; VOCS | Activated carbon; Activated carbon fiber; Cabin air filter; Differential pressure; VOC removal | Air filters; Carbon fibers; Cleaning; Dust; Gas adsorption; Granular materials; Indoor air pollution; Pore structure; Volatile organic compounds; Activated carbon fibres; Cabin air filter; Cabin airs; Differential pressures; Fiber medium; Filtration performance; Gas removal; Granular activated carbons; Mixed medias; Volatile organic compound removals; Activated carbon | English | 2022 | 2022-06 | 10.1007/s42823-022-00345-7 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |
| ○ | ○ | Article | Forward and Backward Propagation of Stereo Matching Cost for Incremental Refinement of Multiview Disparity Maps | This study proposes a multiview stereo (MVS) method that is based on the forward and backward propagation of matching costs for the incremental refinement of multiview disparity maps. The volume-based MVS method requires numerous three-dimensional (3D) memory volumes to compute, store, and process the stereo matching costs. However, owing to memory limitations, conventional MVS methods allocate the memory of the 3D cost volumes only to the reference and its neighbor views. Thus, each reference view can only use the matching costs from a limited number of neighbor views. This study addresses this inherent MVS problem and proposes a new method by employing a forward and backward cost propagation (FBCP). First, a subpart of the input views is used to obtain disparity maps with a dense MVS method. Once all matching costs of the subpart views are sufficiently refined, the FBCP is performed for a new neighbor view. Immediately after the cost volume of the new view is computed, all matching costs of the subpart are forward propagated and fused with the initial cost of the new view. Furthermore, the new fused cost is backward propagated into the subpart to refine the previous costs again using the new fused cost. All cost volumes can be incrementally computed and refined without any limitation on the number of views using the proposed FBCP scheme. In the final step, all disparity maps are obtained from the refined cost volumes and fused into single point clouds. Moreover, we propose the use of surface consensus to obtain accurate fused point clouds for the fusion of the disparity maps. The performance of the proposed method is evaluated using the fused point clouds. The proposed method achieves less than 0.5 mm in mean distance error and about 82 percentage F-score within 2 mm distance threshold value. | Lee, Min-Jae; Park, Soon-Yong | Kyungpook Natl Univ, Sch Electron & Elect Engn, Daegu 41566, South Korea | Park, Soon-Yong/HGV-2374-2022 | 57201267778; 7501834063 | sypark@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 10 | SCIE | COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS | 2022 | 3.9 | 36.2 | 0 | 2025-06-25 | 0 | 0 | Multiview stereo; 3D reconstruction; matching cost volume; cost propagation; disparity map refinement | 3D reconstruction; cost propagation; disparity map refinement; matching cost volume; Multiview stereo | Costs; Stereo image processing; Three dimensional displays; 3D reconstruction; Cost propagation; Disparity map refinements; Images reconstruction; Matching cost volume; Matchings; Memory-management; Multi-view stereo; Point cloud compression; Point-clouds; Three-dimensional display; Image reconstruction | English | 2022 | 2022 | 10.1109/access.2022.3230949 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | ||||
| ○ | ○ | Article | FPGA Realization of the Observer-Based Sliding Discrete Fourier Transform | Discrete Fourier transform (DFT) is a widely used method of signal analysis in digital signal processing. The DFT converts a signal from time domain to frequency domain for further processing. For fixed-size sliding window applications of the DFT, the observer-based sliding DFT (oSDFT) algorithm has been shown to be stable, accurate, and theoretically faster, than the well-known block-oriented fast Fourier transforms (FFT). However, no hardware implementation of the oSDFT has been proposed yet. In this paper, a hardware optimized implementation of two variants of the algorithm for FPGA is presented. Such implementation is compared with the Xilinx FFT Intellectual Property in terms of processing speed and hardware requirements. The structure is implemented in Verilog HDL using Vivado IDE, with the aim of maximizing the processing speed and minimizing the required hardware resources. The analysis of the FPGA-based oSDFT and FFT circuits in a sample-by-sample processing scenario, reveals that the latency and energy usage of the oSDFT are smaller relative to the FFT. The latency and energy usage per sample processed of the implemented structures are up to 9 and 10 times lower than those of FFT respectively. The required resources for these methods are also presented and analyzed. | Plesznik, Peter; Kollar, Zsolt; Park, Daejin | Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea; Budapest Univ Technol & Econ, Dept Measurement & Informat Syst, H-1111 Budapest, Hungary | Kollar, Zsolt/E-4171-2013 | 57216431056; 36682655600; 55463943600 | boltanut@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 10 | SCIE | COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS | 2022 | 3.9 | 36.2 | 0.44 | 2025-06-25 | 2 | 5 | Discrete Fourier transforms; Hardware; Field programmable gate arrays; Signal processing algorithms; Observers; Resonant frequency; Mathematical models; Sliding DFT; oSDFT; FFT; FPGA; low latency | RECURSIVE DFT; ARCHITECTURE; COMPLEXITY; ALGORITHM | FFT; FPGA; low latency; oSDFT; Sliding DFT | Digital signal processing; Discrete Fourier transforms; Field programmable gate arrays (FPGA); Frequency domain analysis; Signal analysis; Time domain analysis; Energy usage; Hardware; Low latency; Observer; Observer-based; Observer-based sliding DFT; Processing speed; Signal processing algorithms; Sliding discrete fourier transform; Time domain; Natural frequencies | English | 2022 | 2022 | 10.1109/access.2022.3153050 | 바로가기 | 바로가기 | 바로가기 | 바로가기 | |||
| ○ | ○ | Article | Full Operational Envelope Control of a Wind Turbine Using Model Predictive Control | This study presents a full operational envelope controller for a full nonlinear 5 MW Supergen exemplar wind turbine based on multivariable model predictive control (MPC). Below the rated wind speed, the primary objective of the controller is to maximize the energy capture. Above the rated wind speed, the controller maintains the rated power. The controller switches between control modes according to the prevailing wind speed to maintain control over the full envelope of operating regions. A linearized model is derived from a model of an exemplar 5 MW Supergen wind turbine in state-space form. The linearized model is then used to realize a feedback MPC (FB-MPC) and feedforward MPC (FF-MPC) to consider the lack and incorporation, respectively, of wind speed information. The switching strategy is tracked on the torque-speed plane. Simulations are performed at multiple wind speeds to evaluate the robustness and switching performances of the designed controllers by applying them to a full nonlinear 5 MW Matlab/SIMULINK model of the same exemplar Supergen wind turbine. Improved tracking is achieved over the full envelope with FF-MPC rather than FB-MPC. Simulation results are presented in the time and frequency domain in addition to the torque-speed plane demonstrating that the control performance is improved without an increase in the control activity (i.e., pitch action) of the turbine; that is, the controller's gain crossover frequency remains within the acceptable range, around 1 rad/s. Note that most work presented in the literature focus on specific wind speeds only; that is, either only below rated wind speed or above rated wind speed. In contrast, the controllers reported here cover the full envelope of operation regions, making this work more practical and novel. | Routray, Abhinandan; Hur, Sung-Ho | Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea; Kyungpook Natl Univ, Sch Elect Engn, Daegu 41566, South Korea | ROUTRAY, ABHINANDAN/IVU-9009-2023 | 57200499011; 36455858700 | shur@knu.ac.kr; | IEEE ACCESS | IEEE ACCESS | 2169-3536 | 10 | SCIE | COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS | 2022 | 3.9 | 36.2 | 0.53 | 2025-06-25 | 6 | 6 | Wind turbine; modeling; predictive control; feedforward control | POWER EXTRACTION; SYSTEMS; DESIGN | feedforward control; modeling; predictive control; Wind turbine | Controllers; Frequency domain analysis; Linearization; MATLAB; Model predictive control; Predictive control systems; State space methods; Turbomachine blades; Wind speed; Blade; Energy capture; Linearized models; Model-predictive control; Modeling; Multivariable modeling; Predictive control; Primary objective; Rated wind speed; Wind speed; Wind turbines | English | 2022 | 2022 | 10.1109/access.2022.3223087 | 바로가기 | 바로가기 | 바로가기 | 바로가기 |
페이지 이동: