연구성과로 돌아가기

2023 연구성과 (162 / 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 Deep Learning Approaches for Bimodal Speech Emotion Recognition: Advancements, Challenges, and a Multi-Learning Model Though acoustic speech emotion recognition has been studied for a while, bimodal speech emotion recognition using both acoustic and text has gained momentum since speech emotion recognition doesn't only involve the acoustic modality. However, there is less review work on the available bimodal speech emotion recognition (SER) research. The review works available mostly concentrate on the use of convolution neural networks (CNNs) and recurrent neural networks (RNNs). However, recent deep learning techniques like attention mechanisms and fusion strategies have shaped the bimodal SER research without explicit analysis of their significance when used singly or in combination with the traditional deep learning techniques. We therefore, review the recently published literature that involves these deep learning techniques in this paper to ascertain the current trends and challenges of bimodal SER research that have hampered it to be fully deployed in the natural environment for off-the-shelf SER applications. In addition, we carried out experiments to ascertain the optimal combination of acoustic features and the significance of the attention mechanisms and their combination with the traditional deep learning techniques. We propose a multi-technique model called the deep learning-based multi-learning model for emotion recognition (DBMER) that operates with multi-learning capabilities of CNNs, RNNs, and multi-head attention mechanisms. We noted that attention mechanisms play a pivotal role in the performance of bimodal dyadic SER systems. However, few publicly available datasets, the difficulty in acquisition of bimodal SER data, cross-corpus and multilingual studies remain open problems in bimodal SER research. Our experiments on the proposed DBMER model showed that though each of the deep learning techniques benefits the task, the results are more accurate and robust when they are used in careful combination with multi-level fusion approaches. 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; Indian Inst Sci Educ & Res Thiruvananthapuram IISE, Sch Data Sci, Thiruvananthapuram 695551, Kerala, India; Kyungpook Natl Univ, Sch Elect Engn, Daegu 41566, South Korea Kakuba, Samuel/HLX-4856-2023; Han, Dong Seog/N-8949-2018; , ALWIN POULOSE/S-4914-2018; POULOSE, ALWIN/S-4914-2018 57988218000; 57205504085; 7403219442 dshan@knu.ac.kr; IEEE ACCESS IEEE ACCESS 2169-3536 11 SCIE COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS 2023 3.4 34.4 3.37 2025-06-25 17 27 Emotion recognition; acoustic and lexical data; deep learning; attention mechanisms ATTENTION MECHANISMS; FUSION; EXTRACTION acoustic and lexical data; attention mechanisms; deep learning; Emotion recognition Character recognition; Emotion Recognition; Feature extraction; Learning algorithms; Recurrent neural networks; Acoustic and lexical data; Attention mechanisms; Computational modelling; Deep learning; Emotion recognition; Features extraction; Learning techniques; Speech emotion recognition; Speech recognition English 2023 2023 10.1109/access.2023.3325037 바로가기 바로가기 바로가기 바로가기
Article Design and Implementation of Optimal Control Scheme for DFIG Based Wind Plant to Mitigate Sub-Synchronous Resonance Issues This article presents an investigation of sub-synchronous resonance (SSR) issues in doubly-fed induction generator (DFIG) based wind plant and proposes an optimal control scheme for its mitigation. The article firstly reviews the causes of SSR, namely compensation level and wind speed in DFIG-based wind plant. The proportional resonance controller with harmonic compensators (PR+HC) is designed to mitigate SSR without compromising total harmonic distortions (THD) in the power signal. The series compensated IEEE first benchmarked model energized with a 100MW DFIG-based wind plant is used as a platform in MATLAB/Simulink for the implementation of the proposed scheme. The comparative analysis of the designed PR+HC controller is carried out with the conventional Proportional Integral (PI) controller to validate the optimal response of PR+HC controller. In addition, high performance of PR+HC in coordination with a flexible AC transmission (FACT) device in terms of damped oscillations and low THD is achieved. The overall simulation results are analyzed in both time domain and frequency domain to authenticate the damped, low harmonic, and smooth response of proposed scheme under varying compensation level and wind speeds. Ul Islam, Saif; Kim, Soobae Kyungpook Natl Univ, Sch Elect & Elect Engn, Dept Elect Engn, Daegu 41566, South Korea ; Uddin, Waqar/X-3686-2019 59083068700; 55377374400 soobae.kim@knu.ac.kr; IEEE ACCESS IEEE ACCESS 2169-3536 11 SCIE COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS 2023 3.4 34.4 1.42 2025-06-25 9 11 Renewable energy resources; DFIG-based wind plant; flexible AC transmission devices; harmonic compensators; optimization; proportional resonant controller; sub-synchronous resonance DAMPING CONTROLLER; MODAL-ANALYSIS; SSR; FARMS DFIG-based wind plant; flexible AC transmission devices; harmonic compensators; optimization; proportional resonant controller; Renewable energy resources; sub-synchronous resonance Asynchronous generators; Controllers; Electric fault currents; Electric machine control; Electric power transmission; Frequency domain analysis; Harmonic analysis; MATLAB; Two term control systems; Wind; AC transmission devices; Doubly fed induction generators; Doubly-feed induction generator-based wind plant; Flexible AC transmission; Flexible AC transmission device; Harmonic compensator; Optimisations; Power capacitor; Power transmission lines; Proportional resonant controllers; Shaft; Sub-synchronoi resonance; Sub-synchronous; Wind plant; Wind speed; Wind turbines English 2023 2023 10.1109/access.2023.3341884 바로가기 바로가기 바로가기 바로가기
Article Design of Secure and Lightweight Authentication Scheme for UAV-Enabled Intelligent Transportation Systems Using Blockchain and PUF Unmanned-aerial-vehicle (UAV)-enabled intelligent transportation system (ITS) is an advanced technology that can provide various services including autonomous driving, real-time creation of high-definition maps, and car sharing. In particular, a UAV-enabled ITS can be realized through the combination of traditional vehicular ad hoc networks (VANETs) and UAVs that can act as flying roadside units (RSUs) at the outskirts and monitor road conditions from predefined locations to spot car accidents and any law violations. Notably, to realize these services, real-time communication between UAVs and RSUs must be guaranteed. However, UAVs have limited computing powers, and if extensive computation is required during communication, the provision of real-time ITS services may be hindered. Furthermore, UAVs and RSUs communicate via public channels that are prone to various attacks, such as replay, impersonation, trace, and session key disclosure attacks. Thus, in this article, a secure and lightweight authentication scheme is proposed for UAVs and RSUs using the blockchain technology. The proposed scheme is analyzed using informal and formal methods including Burrows-Abadi-Nikoogadam (BAN) logic, automated validation of internet security protocols and applications (AVISPA) simulation tool, and real-or-random (RoR) model, and its performance is compared with that of related schemes. The results reveal that the proposed scheme is more efficient and secure as compared to the other competing schemes. Son, Seunghwan; Kwon, Deokkyu; Lee, Sangwoo; Jeon, Yongsung; Das, Ashok Kumar; Park, Youngho Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea; Elect & Telecommun Res Inst, Daejeon 34129, South Korea; Int Inst Informat Technol, Ctr Secur Theory & Algorithm Res, Hyderabad 500032, India ; Das, Ashok Kumar/U-2790-2019 57221744477; 57221739597; 57201864359; 59627026200; 55450732800; 56962990300 parkyh@knu.ac.kr; IEEE ACCESS IEEE ACCESS 2169-3536 11 SCIE COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS 2023 3.4 34.4 3.5 2025-06-25 19 27 Blockchain; wireless communication; unmanned aerial vehicle; lightweight authentication; physically unclonable function; security KEY-EXCHANGE Blockchain; lightweight authentication; physically unclonable function; security; unmanned aerial vehicle; wireless communication Accidents; Antennas; Blockchain; Computation theory; Drones; Formal methods; Intelligent systems; Intelligent vehicle highway systems; Network security; Real time systems; Vehicle to vehicle communications; Vehicular ad hoc networks; Aerial vehicle; Block-chain; Curve cryptography; Elliptic curve; Elliptic curve cryptography; Lightweight authentication; Physically unclonable functions; Security; Unmanned aerial vehicle; Wireless communications; Authentication English 2023 2023 10.1109/access.2023.3286016 바로가기 바로가기 바로가기 바로가기
Article Development of Seismic Intensity Maps Using Low-Cost Micro-Electro-Mechanical Systems Seismic Network The low-cost IoT seismometer (LCIS), which embeds a micro-electro-mechanical systems accelerometer and LTE communication sensor, has been developed and deployed in South Korea. Currently, approximately 7,000 stations (with an average density of 0.07/km2) with LCIS devices are operating in real-time, which is about 25 times higher density than the national seismic network with high performance seismometers. This study shows a method for processing LCIS data and plotting an intensity map considering its installation characteristics and density. The majority of LCISs are installed inside buildings, so an adjustment converting to the free-surface equivalent vibration is applied. Seismic intensity maps are derived using only high-density LCIS network data, which showed very similar distributions to the maps from the high-performance seismometer network. This validates the usefulness of the LCIS, a low-cost but new technology on seismic network devices, for the generation of high-resolution seismic intensity map and earthquake early warning systems. Ahn, Jae-Kwang; Lee, Jangsoo; Kwon, Young-Woo; Kim, Jung-Kyu; Kwak, Dong Youp Korea Meteorol Adm, Earthquake & Volcano Technol Team, Seoul 07062, South Korea; Kyungpook Natl Univ, Dept IT Engn Comp Sci, Daegu 41566, South Korea; Infra BM, SK Telecom, Seoul 04539, South Korea; Hanyang Univ, Dept Civil & Environm Engn, ER Campus, Ansan 15588, South Korea Kwon, Young-Woo/HGE-6607-2022; Ahn, Jae-Kwang/IQV-7073-2023 57214806947; 57208408850; 57208480210; 58196256900; 55648053100 dkwak@hanyang.ac.kr; IEEE ACCESS IEEE ACCESS 2169-3536 11 SCIE COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS 2023 3.4 34.4 0.52 2025-06-25 4 4 Micromechanical devices; Earthquakes; Buildings; Accelerometers; Sensitivity; Observatories; Noise level; Seismic measurements; MEMS; modified mercalli intensity (MMI) map; high density seismic network; South Korea seismic network; ground motion model EARTHQUAKE; MEMS; ACCELEROMETERS; PROGRAM ground motion model; high density seismic network; MEMS; modified mercalli intensity (MMI) map; South Korea seismic network Accelerometers; Earthquakes; Seismographs; Ground motion modeling; High density seismic network; Intensity maps; Micromechanical device; Modified mercalli intensities; Modified mercallus intensity map; Noise levels; Seismic networks; Sensitivity; South Korea; South korea seismic network; MEMS English 2023 2023 10.1109/access.2023.3268520 바로가기 바로가기 바로가기 바로가기
Article Dielectric chiral metasurfaces for enhanced circular dichroism spectroscopy at near infrared regime Numerous applications of chiro-optical effects can be found in nanophotonics, including imaging and spin-selective absorption, particularly in sensing for separating and detecting chiral enantiomers. Flat single-layer metasurfaces composed of chiral or achiral sub-wavelength structures offer unique properties to manipulate the light due to their extraordinary light-matter interaction. However, at optical wavelengths, the generation of strong chirality is found to be challenging via conventional chiral metasurface approaches. This work intends to design and optimize a dielectric chiral meta-nano-surface based on a diatomic design strategy to comprehend giant chiro-optical effects in the near-infrared (NIR) regime for potential application in circular dichroism (CD) spectroscopy. Instead of using a single chiral structure that limits the CD value at optical wavelengths, the proposed metasurface used a diatomic (two meta-atoms with distinct geometric parameters) chiral structure as a building block to significantly enhance the chiro-optical effect. Combining both meta-atoms in a single periodicity of the building block introduces constructive and destructive interferences to attain the maximum circular dichroism value exceeding 75%. Moreover, using multipolar resonance theory, the physics behind the generation of giant chiro-optical effects have also been investigated. The proposed dielectric chiral meta-platform based on the extra degree of freedom can find application in compact integrated optical setups for CD spectroscopy, enantiomer separation and detection, spin-dependent color filters, and beam splitters. Ali, Asif; Khaliq, Hafiz Saad; Asad, Aqsa; Akbar, Jehan; Zubair, Muhammad; Mehmood, Muhammad Qasim; Massoud, Yehia Informat Technol Univ ITU Punjab, MicroNano Lab, Deaprtment Elect Engn, Ferozepur Rd, Lahore 54600, Pakistan; Univ Elect Sci & Technol China, Glasgow Coll, Chengdu, Peoples R China; King Abdullah Univ Sci & Technol KASUT, Innovat Technol Labs ITL, Thuwal, Saudi Arabia; Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea ; Mehmood, Muhammad Qasim/U-4675-2019; Khaliq, Hafiz Saad/ITW-2129-2023 57850761400; 56725698200; 58072931900; 37071868800; 56581448000; 56276474100; 14018366500 muhammad.zubair3@kaust.edu.sa;qasim.mehmood@itu.edu.pk;yehia.massoud@kaust.edu.sa; RSC ADVANCES RSC ADV 2046-2069 13 30 SCIE CHEMISTRY, MULTIDISCIPLINARY 2023 3.9 34.4 1.55 2025-06-25 8 15 Circular dichroism spectroscopy; Degrees of freedom (mechanics); Enantiomers; Infrared devices; Building blockes; Chiral structures; Diatomics; Metasurface; Near Infrared; Near-infrared; Optical effects; Optical wavelength; Selective absorption; Single layer; Dichroism English 2023 2023-07-07 10.1039/d3ra02331a 바로가기 바로가기 바로가기 바로가기
Article Effect of Driver Mass Loading on Bone Conduction Transfer in an Implantable Bone Conduction Transducer This paper focuses on transducers, which are the most important components of bone conduction implants. To improve vibration magnitude, we develop a coil vibration transducer in which the driver mass loading is reduced by about 3.25-fold compared to magnet vibration transducers. We use finite element analysis to derive and implement the maximum Lorentz force and frequency characteristics. We compare the effect of driver mass loading on the vibration magnitude to that of an older transducer. The new transducer vibrates about 4.4-fold more strongly. To compare force magnitude between the two transducers, output force is measured using an artificial mastoid. The force imparted by the new transducer is higher than that of the older transducer only below 1.4 kHz, and tends to be lower at high frequencies. Nevertheless, the improved force in the low-frequency region will improve conductive hearing loss. Shin, Dong Ho; Seong, Ki Woong; Lee, Kyu-Yup Kyungpook Natl Univ, Inst Biomed Engn Res, Daegu 41944, South Korea; Kyungpook Natl Univ Hosp, Dept Biomed Engn, Daegu 41944, South Korea; Kyungpook Natl Univ, Sch Med, Dept Otorhinolaryngol Head & Neck Surg, Daegu, South Korea ; Lee, Doh Young/GLR-9586-2022 56693502600; 23968197900; 22135779500 drlky@hanmail.net; IEEE ACCESS IEEE ACCESS 2169-3536 11 SCIE COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS 2023 3.4 34.4 0.26 2025-06-25 2 2 Transducers; Vibrations; Auditory system; Magnetic resonance; Permanent magnets; Lorentz covariance; Implants; Bones; Finite element methods; Artificial mastoid; bone conduction implants; finite element analysis; output force level; transducer HEARING-AIDS; HISTORY; DEVICE; SYSTEM; ADULTS Artificial mastoid; bone conduction implants; finite element analysis; output force level; transducer Audition; Bone; Magnetic resonance; Transducers; Artificial mastoid; Auditory systems; Bone conduction implants; Ear; Finite element analyse; Force level; Lorentz covariances; Output force; Output force level; Vibration; Finite element method English 2023 2023 10.1109/access.2023.3247738 바로가기 바로가기 바로가기 바로가기
Article Effect of Number of Lanes on Traffic Characteristics of Reinforcement Learning Based Autonomous Driving Traffic characteristics such as signalized intersections and high vehicle density combined with low vehicle speeds account for 12-55% increase in commute time. Increasing the number of lanes in the highway infrastructure can help increase the highway capacity and consequently reduce the associated commute delay. However, due to human-related features such as driver behavior and vehicle interaction as well as induced demand, it is recommended to limit the number of highway lanes to four. Recently, in view of the rising discussion regarding the deployment of Autonomous Vehicles (AVs), it is important to study the effect of the number of highway lanes on traffic characteristics with respect to AVs. This will provide insights into the full potential of AVs in terms of reducing commute time as well as provide crucial insights into the design of future road networks. Therefore, in this study, RL-based AV frameworks are developed to investigate the effect of the number of highway lanes on traffic characteristics. Specifically, we study the effect of the number of lanes on traffic characteristics in terms of travel speed, collision, and driving on the right-most lane. Results with two well-known RL-based AV frameworks simulated on highways with lanes ranging from 2 to 8 and increasing vehicle count respectively show improved traffic characteristics as the number of lanes increases. However, improvement depends on the RL algorithm employed. Aboyeji, Esther; Ajani, Oladayo S.; Mallipeddi, Rammohan Kyungpook Natl Univ, Dept Artificial Intelligence, Daegu 37224, South Korea ; AJANI, Oladayo/HIR-9607-2022; Aboyeji, Esther/IZP-8228-2023; Mallipeddi, Rammohan/AAL-5306-2020 58406711200; 57465126000; 25639919900 mallipeddi.ram@gmail.com; IEEE ACCESS IEEE ACCESS 2169-3536 11 SCIE COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS 2023 3.4 34.4 0.39 2025-06-25 2 3 ~Number of highway lanes; autonomous vehicles; reinforcement learning; traffic characteristics SPEED autonomous vehicles; Number of highway lanes; reinforcement learning; traffic characteristics Behavioral research; Highway planning; Job analysis; Motor transportation; Traffic signals; Vehicles; Autonomous Vehicles; Behavioral science; Highway lanes; Number of highway lane; Optimisations; Q-learning; Reinforcement learnings; Road; Road transportation; Task analysis; Traffic characteristics; Reinforcement learning English 2023 2023 10.1109/access.2023.3299860 바로가기 바로가기 바로가기 바로가기
Article Electronic origin of ferroelectricity in multiferroic Lu0.5Sc0.5FeO3 We conducted a comprehensive study on the electronic structure of a multiferroic Lu0.5Sc0.5FeO3 single crystal using a range of techniques, including x-ray absorption spectroscopy, cluster model calculations, and ab initio analyses. Our x-ray linear dichroism measurements revealed strong hybridization of A-site d orbitals with neighboring O p orbitals. The hybridization strength of Lu 5d turns out to be not only much stronger but also more anisotropic than that of Sc 3d, leading to a huge ligand-field splitting between the out-of-plane a1g orbital state and in-plane e pi g one. Based on our findings, we confirmed that Lu has a significantly larger ferroelectric energy gain compared to Sc. By combining our results with a simple phononic potential energy, we were able to quantify the ferroelectric energy landscape, which agrees well with the ab initio calculation result. Through a comparative analysis of Lu 5d and Sc 3d cases, we revalidate the rehybridization mechanism as the origin of ferroelectricity appearing in the h-A(Mn,Fe)O3 family. Kim, Jeong Kyu; Kim, Bongjae; Kim, Dong-Hwan; Kim, Kyoo; Tanaka, Arata; Kim, Younghak; Cheong, Sang-Wook; Ko, Kyung-Tae; Park, Jae-Hoon Max Planck Korea POSTECH, Ctr Complex Phase Mat, Pohang 37673, South Korea; Pohang Univ Sci & Technol, Dept Phys, Pohang 37673, South Korea; POSTECH, Pohang Accelerator Lab, Pohang 37673, South Korea; Kunsan Natl Univ, Dept Phys, Gunsan 54150, South Korea; Kyungpook Natl Univ, Dept Phys, Daegu 41566, South Korea; Samsung Elect Co Ltd, 1 Samsungjeonja Ro, Hwasung Si 445701, Gyeonggi Do, South Korea; Korea Atom Energy Res Inst, Daejeon 34057, South Korea; ADSM Hiroshima Univ, Dept Quantum Matter, Higashihiroshima 7398530, Japan; Rutgers State Univ, Rutgers Ctr Emergent Mat, Piscataway, NJ 08854 USA; Rutgers State Univ, Dept Phys & Astron, Piscataway, NJ 08854 USA; POSTECH, Lab Pohang Emergent Mat, Pohang 37673, South Korea; Korea Basic Sci Inst, Daejeon 305806, South Korea Kim, Dong/ABI-4104-2020; Park, Jae/A-1275-2018; Tanaka, Arata/S-4466-2018; Ko, Kyung-Tae/AAA-5417-2022 57219918202; 55650566000; 59110602000; 57214859153; 7404667119; 57193423066; 57205982477; 26026021900; 15036184900 kkt0706@kbsi.re.kr;jhp@postech.ac.kr; PHYSICAL REVIEW B PHYS REV B 2469-9950 2469-9969 108 15 SCIE MATERIALS SCIENCE, MULTIDISCIPLINARY;PHYSICS, APPLIED;PHYSICS, CONDENSED MATTER 2023 3.2 34.4 0 2025-06-25 0 0 TRANSITION-METAL OXIDES; POLARIZATION; SPECTRA Circular dichroism spectroscopy; Crystal structure; Dichroism; Electronic structure; Ferroelectricity; Iron compounds; Lutetium compounds; Single crystals; X ray absorption spectroscopy; Ab initio analysis; Cluster model calculation; D orbitals; Electronic origin; Electronic.structure; Hybridisation; Multiferroics; Orbitals; X-ray absorption spectroscopy; X-ray linear dichroisms; Potential energy English 2023 2023-10-31 10.1103/physrevb.108.155152 바로가기 바로가기 바로가기 바로가기
Article Enhancing Recommendation Capabilities Using Multi-Head Attention-Based Federated Knowledge Distillation As the internet and mobile computing have advanced, recommendation algorithms are used to manage large amounts of data. However, traditional recommendation systems usually require collecting user data on a central server, which may expose user privacy. Furthermore, data and models from different organizations may be proprietary and cannot be shared directly, leading to data isolation. To address these challenges, we propose a method that combines federated learning (FL) with the recommendation system using a federated knowledge distillation algorithm based on a multi-head attention mechanism. In the proposed approach, knowledge distillation is introduced on the basis of FL to induce the training of the local network and facilitate knowledge transfer. Further, to address the non-independent identical distribution of training samples in FL, Wasserstein distance and regularization terms are incorporated into the objective function of federated knowledge distillation to reduce the distribution difference between server and client networks. A multi-head attention mechanism is used to enhance user encoding information. A combined adaptive learning rate is adopted to further improve the convergence. Compared to the benchmark model, this approach demonstrates significant improvements, with accuracy enhanced up to 10%, model training time shortened by approximately 45%, and average error and NDCG values decreased by 10%. Wu, Aming; Kwon, Young-Woo Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea ; Kwon, Young-Woo/HGE-6607-2022 58262125900; 57208480210 ywkwon@knu.ac.kr; IEEE ACCESS IEEE ACCESS 2169-3536 11 SCIE COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS 2023 3.4 34.4 0.39 2025-06-25 2 3 Data models; Adaptive learning; Data privacy; Servers; Privacy; Computational modeling; Solid modeling; Federated learning; multi-head attention; Wasserstein distance; adaptive learning rate CHALLENGES adaptive learning rate; Federated learning; multi-head attention; Wasserstein distance Data privacy; Distillation; Knowledge management; Learning algorithms; Learning systems; Adaptive learning; Adaptive learning rates; Attention mechanisms; Computational modelling; Federated learning; Multi-head attention; Privacy; Solid modelling; Wasserstein distance; Recommender systems English 2023 2023 10.1109/access.2023.3271678 바로가기 바로가기 바로가기 바로가기
Article Event Message Clustering Algorithm for Selection of Majority Message in VANETs The trustworthiness of nodes in Vehicular Ad-Hoc Networks (VANETs) is essential for disseminating truthful event messages. False messages may cause vehicles to behave in unintended ways, creating an unreliable transportation system. The efficiency and reliability of the transportation system can be obtained through trustworthy vehicular nodes providing correct event messages. In a VANET, the consensus issue can be resolved by employing blockchain. Even if we employ blockchain in a VANET, the trustworthiness of each message recorded needs to be verified separately since the blockchain itself does not guarantee the trust level of each event message. For instance, when there are multiple conflicting messages associated with a single accident on the road, a vote based on majority opinion can be considered one option for making a decision regarding the accident. In this work, we design the VANET event message clustering algorithm (VEMCA) to resolve the conflicting message problem. Furthermore, we develop a simulator for the VANET environment that demonstrates how the clustering algorithm can be used for event message validation. Experimental results show that our algorithm outperforms state-of-the-art clustering algorithms in terms of accuracy, precision, recall, f1-score, and computational time. Khatri, Narayan; Lee, Sihyung; Mateen, Abdul; Nam, Seung Yeob Yeungnam Univ, Dept Informat & Commun Engn, Gyongsan 38541, South Korea; Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea; Fed Urdu Univ Arts Sci & Technol, Dept Comp Sci, Islamabad 45570, Pakistan ; Mateen, Abdul/AAC-7013-2022; Nam, Seung/Q-7486-2019; Khatri, Narayan/AAT-9029-2020 57222726965; 15623380100; 58024251000; 7402276352 synam@ynu.ac.kr; IEEE ACCESS IEEE ACCESS 2169-3536 11 SCIE COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS 2023 3.4 34.4 1.55 2025-06-25 8 12 Vehicular ad hoc networks; Peer-to-peer computing; Clustering algorithms; Blockchains; Trust management; Safety; Road traffic; VANET; clustering algorithm; trustworthiness; blockchain; simulator TRUST MANAGEMENT; K-MEANS; BLOCKCHAIN; NETWORK blockchain; clustering algorithm; simulator; trustworthiness; VANET Accidents; Clustering algorithms; Vehicular ad hoc networks; Block-chain; Computational time; Efficiency and reliability; F1 scores; Network environments; State of the art; Transportation system; Trust level; Trustworthiness; Vehicular Adhoc Networks (VANETs); Blockchain English 2023 2023 10.1109/access.2023.3244327 바로가기 바로가기 바로가기 바로가기
Article Extensive Knowledge Distillation Model: An End-to-End Effective Anomaly Detection Model for Real-Time Industrial Applications Detecting anomalies is an essential task in many industries. Current state-of-the-art methods rely on a large number of parameters for high accuracy, which may not be suitable for implementing cost-effective real-time applications. Additionally, developing robust detection models is difficult due to limited anomaly samples. To address these issues, we propose an end-to-end anomaly detection method that utilizes effective data generation and comprehensive knowledge distillation. In particular, the proposed approach first employs a highly effective generative model to generate realistic anomaly images. It then transfers the pre-trained master network's essential intermediate layers and final layer knowledge to a novice network by using the knowledge distillation technique. In the conducted experiments with 4 real-life datasets, the proposed model outperforms its counterparts, including state-of-the-art models, by 0.6% on MNIST and CIFAR-10 datasets, 0.2% on the custom dataset, and stays competitive on the MVTec AD dataset. Additionally, the proposed model outperforms all of its peers in trainable parameter numbers by having only 0.17 M parameters. This is at least twice as few parameters as the baseline model. Overall, the proposed approach offers an efficient solution to anomaly detection that achieves high accuracy despite limited anomaly samples and fewer parameters. Rakhmonov, Akhrorjon Akhmadjon Ugli; Subramanian, Barathi; Olimov, Bekhzod; Kim, Jeonghong Kyungpook Natl Univ, Dept Comp Sci & Engn, Daegu 41566, South Korea; Vitasoft, IT Convergence Res & Dev Ctr, AI Dept, Seoul 04522, South Korea ; Olimov, Bekhzod/AAA-9362-2021; Subramanian, Barathi/HLP-9548-2023 58482208000; 57221053219; 57220579660; 55138548100 jhk@knu.ac.kr; IEEE ACCESS IEEE ACCESS 2169-3536 11 SCIE COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS 2023 3.4 34.4 1.42 2025-06-25 11 11 Anomaly detection; deep convolutional neural networks; image generation; knowledge distillation Anomaly detection; deep convolutional neural networks; image generation; knowledge distillation Cost effectiveness; Deep neural networks; Distillation; Job analysis; Anomaly detection; Computational modelling; Convolutional neural network; Deep convolutional neural network; End to end; Features extraction; Image generations; Knowledge distillation; Task analysis; Feature extraction English 2023 2023 10.1109/access.2023.3293108 바로가기 바로가기 바로가기 바로가기
Article Gradient-Descent-Based Learning Gain for Backstepping Controller and Disturbance Observer of Nonlinear Systems This paper proposes a gradient-descent-based learning (GL) gain for backstepping controller and disturbance observer (DOB) of nonlinear system. The proposed method consists of the GL gain update law, controller, and DOB. The GL gain update law is proposed to adapt the control gain and DOB gain according to the direction that minimizes the cost function. The mathematical analysis reveals that the GL gain always has a positive sign and upper bound. The controller is designed via a backstepping procedure to track the desired output with GL control gain. The DOB is designed to estimate the unknown external disturbance with the GL DOB gain. Because the control and DOB gains are simultaneously tuned to achieve improved performance, the time consumption for tuning can be reduced. In addition, the peaking phenomenon can be avoided initially by a small initial value of GL gains. The stability of the closed-loop system is guaranteed using the input-to-state stability property. The performance of the proposed method was validated via simulations and experiments using a DC motor. You, Sesun; Son, Young Seop; Gui, Yonghao; Kim, Wonhee Chung Ang Univ, Dept Energy Syst Engn, Seoul 06974, South Korea; Kyungpook Natl Univ, Dept Robot & Smart Syst Engn, Daegu 41566, South Korea; Oak Ridge Natl Lab, Electrificat & Energy Infrastruct Div, Knoxville, TN 37932 USA; Chung Ang Univ, Sch Energy Syst Engn, Seoul, South Korea Gui, Yonghao/M-4377-2019; Kim, Wonhee/AAJ-9848-2020; You, Sesun/AAF-8123-2021 57208402018; 35203958300; 55268646100; 34770809600 ys.son@knu.ac.kr;whkim79@cau.ac.kr; IEEE ACCESS IEEE ACCESS 2169-3536 11 SCIE COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS 2023 3.4 34.4 0.39 2025-06-25 3 3 Cost function; Upper bound; Tuning; Backstepping; Stability criteria; Disturbance observers; Perturbation methods; Gradient methods; Learning systems; Stability analysis; Nonlinear systems; Learning control; disturbance observer (DOB); gradient-descent; input-to-state stability (ISS) FEEDBACK-CONTROL; ROBUST TRACKING; CONTROL DESIGN; PERFORMANCE disturbance observer (DOB); gradient-descent; input-To-state stability (ISS); Learning control Closed loop systems; Controllers; Cost functions; DC motors; Gradient methods; Perturbation techniques; Stability criteria; Cost-function; Disturbance observer; Gradient's methods; Gradient-descent; Input-to-state stability; Learning control; Perturbation method; Stability analyze; Stability criterions; Tuning; Upper Bound; Backstepping English 2023 2023 10.1109/access.2023.3234439 바로가기 바로가기 바로가기 바로가기
Article Handling Big Microarray Data: A Novel Approach to Design Accurate Fuzzy-Based Medical Expert System The genes data produced by microarray experiments is complex in terms of dimensions and samples. It consumes a lot of computation power and time when it is processed for a disease analysis while working with an expert system. At the same time, data can help doctors identify a patient's health condition if it is presented in a meaningful way and processed on time. Several methods have been proposed to reduce the dimensions of medical microarray data and optimize its search space with minimal accuracy loss. However, the discretization of continuous gene-values in the process of dimension reduction is failed to preserve the inherent meaning of genes. Also, ensuring high accuracy and interpretability in the reduction process may result in extra processing time, which is unfavorable for time-critical applications. To overcome these issues, in this paper, we propose a dimension reduction method in conjunction with a fuzzy expert system (FES) optimization approach, while keeping an accuracy-interpretability-speedy tradeoff in mind. To accomplish this, we use a fuzzy rough set on f-information to identify meaningful genes without changing their original values. We propose a conditionally guided particle swarm optimization for faster knowledge acquisition, where the velocity is adjusted based on a predefined update probability, resulting in a faster search. A big data processing architecture is designed using the Hadoop ecosystem along with a MapReduce-equivalent algorithm of the proposed method for speedy processing, enabling parallel processing on microarray data to reduce dimensions and perform classification through knowledge extraction. The proposed method is thoroughly tested on eleven microarray datasets by considering accuracy-interpretability-speed tradeoff. The results show that the proposed method is effective in identifying disease-causing genes while also understanding the patient's genetic profile with only a few operations and a small amount of CPU time. Statistical tests are also run to validate the proposed method's efficacy in comparison to other methods. Pugalendhi, Ganeshkumar; Rathore, M. Mazhar; Shukla, Dhirendra; Paul, Anand Anna Univ Reg Campus, Dept Informat Technol, Coimbatore 641046, India; Univ New Brunswick, Dr J Herbert Smith Ctr, Fredericton, NB E3B 5A3, Canada; Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea Paul, Anand/V-6724-2017; Pugalendhi, Ganeshkumar/D-5585-2019 57203113010; 56650727000; 57202226465; 56650522400 paul.editor@gmail.com; IEEE ACCESS IEEE ACCESS 2169-3536 11 SCIE COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS 2023 3.4 34.4 0.52 2025-06-25 3 4 f-information; fuzzy expert system; microarray data; particle swarm optimization MUTUAL INFORMATION; FEATURE-SELECTION; GENE SELECTION; CANCER; PATTERNS; CLASSIFICATION f-information; fuzzy expert system; microarray data; particle swarm optimization Computer architecture; Data mining; Genes; Iron; MapReduce; Medical information systems; Particle swarm optimization (PSO); Rough set theory; <italic xmlns:ali="; Dimensionality reduction; Fuzzy-expert systems; Medical services; Microarrays data; Particle swarm; Particle swarm optimization; Rough set; Swarm optimization; Xmlns:mml="; Xmlns:xlink="; Xmlns:xsi="; Expert systems English 2023 2023 10.1109/access.2023.3257875 바로가기 바로가기 바로가기 바로가기
Article High-Quality Face Caricature via Style Translation Caricature is an exaggerated form of artistic portraiture that accentuates unique yet subtle characteristics of human faces. Recently, advancements in deep end-to-end techniques have yielded encouraging outcomes in capturing both style and elevated exaggerations in creating face caricatures. Most of these approaches tend to produce cartoon-like results that could be more practical for real-world applications. In this study, we proposed a high-quality, unpaired face caricature method that is appropriate for use in the real world and uses computer vision techniques and GAN models. We attain the exaggeration of facial features and the stylization of appearance through a two-step process: Face caricature generation and face caricature projection. The face caricature generation step creates new caricature face datasets from real images and trains a generative model using the real and newly created caricature datasets. The Face caricature projection employs an encoder trained with real and caricature faces with the pre-trained generator to project real and caricature faces. Using the encoder and generator's latent space, we perform an incremental facial exaggeration from the real image to the caricature faces. Our projection preserves the facial identity, attributes, and expressions from the input image. Also, it accounts for facial occlusions, such as reading glasses or sunglasses, to enhance the robustness of our model. Furthermore, we comprehensively compared our approach with various state-of-the-art face caricature methods, highlighting our process's distinctiveness and exceptional realism. Laishram, Lamyanba; Shaheryar, Muhammad; Lee, Jong Taek; Jung, Soon Ki Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea Jung, Soon Ki/P-7687-2018; Shaheryar, Muhammad/NBW-9729-2025 57219930647; 56132068000; 24341317500; 57226791905 skjung@knu.ac.kr; IEEE ACCESS IEEE ACCESS 2169-3536 11 SCIE COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS 2023 3.4 34.4 0.65 2025-06-25 4 5 Face caricature; facial exaggeration; image translation; GAN NETWORKS Face caricature; facial exaggeration; GAN; image translation Computer vision; Iterative methods; Signal encoding; Face; Face caricature; Facial exaggeration; Facial feature; GAN; Generator; High quality; Image translation; Real-world; Shape; Generative adversarial networks English 2023 2023 10.1109/access.2023.3340788 바로가기 바로가기 바로가기 바로가기
Article Human-Object Relations and Security Control in Inference System for the User Intention The Internet of Things (IoT) networks are getting bigger and bigger. In most cases, all IT assets are connected to the network and various resources and services are provisioned proactively as needed. To achieve this, many smart objects are being developed in the field of intelligent devices. However, most of these objects can only enable their smart functionalities only after the user starts interacting with the object, which leads to an absence of intelligence between things. Bridging the gap between these entities to improve network productivity and improve network security is a challenge. Because the logs generated by IoT devices are vast and diverse, it is difficult to detect and defend against cyber-attacks with existing network security technologies. Existing cyber-attack detection systems cannot detect new attacks because they defend by defining known attack patterns as rules. This paper presents relations and security control in inference system to infer with which object a person wishes to interact by observing his behavior. Security control for services in this paper is important, and specialized. To achieve this goal, this inference problem is resolved into a problem of distinguishing, for each object, whether the IoT device has the intention to interact with it. It analyzes human behavior and detects whether there is a cyber-attack intention. Subsequently, for every object, a set of human-device relations, including Relative Distance, Relative Angle, Movement Speed, Approach Efficiency and Movement Efficiency, is extracted from the person's behavior. These relationships are used to determine whether a person wants to interact with a particular object using a Support Vector Machine (SVM) classifier. And new mechanisms are needed to shrink massive raw logs and detect new attack patterns. Thus, this paper suggests a method for securing a huge network supporting IoT services. The proposed inference systems detect unusual network patterns by calculating correlations between events based on graphs and network measurements. We model ensemble of events based on log graphs interconnected between network devices and IoT gateways. We implement and evaluate an algorithm that detects new attack patterns by estimating the attack probability by clustering the event ensemble in real time. Finally, for the effectiveness of the proposed relations, the experimental application of a real dataset is evaluated, with encouraging results. Using the proposed human-object relations, it is possible to sense users' interaction intentions in advance and thus to proactively provide user-adaptive services based on safety. Park, Boseok; Tang, Jiamei; Kim, Sangwook Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea; Shenzhen Polytech Xili, Dept Artificial Intelligence, Shenzhen 518055, Peoples R China 57209976784; 58561777500; 57169169400 boseok4u@knu.ac.kr; IEEE ACCESS IEEE ACCESS 2169-3536 11 SCIE COMPUTER SCIENCE, INFORMATION SYSTEMS;ENGINEERING, ELECTRICAL & ELECTRONIC;TELECOMMUNICATIONS 2023 3.4 34.4 0.26 2025-06-25 1 2 Internet of Things; Security; Behavioral sciences; Botnet; Authentication; Servers; Control systems; Event detection; Intrusion detection; Support vector machines; Event correlation; intrusion detection; network security; support vector machine Event correlation; intrusion detection; network security; support vector machine Behavioral research; Botnet; Computer crime; Crime; Cybersecurity; Efficiency; Internet of things; Intrusion detection; Support vector machines; Behavioral science; Botnets; Cyber-attacks; Event correlation; Inference systems; Intrusion-Detection; Networks security; Security; Security controls; Support vectors machine; Network security English 2023 2023 10.1109/access.2023.3310217 바로가기 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.