2025 연구성과 (88 / 151)

※ 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 ⓘ Optimizing sum rates in IoT networks: A novel IRS-NOMA cooperative system ⓘ Intelligent Reflecting Surfaces (IRS) offer a promising solution for enhancing sum rates in wireless networks by dynamically adjusting signal reflections to optimize propagation paths. When combined with Non-Orthogonal Multiple Access (NOMA), which enables multiple users to share the same frequency band, significant improvements in spectral efficiency can be achieved. However, as the number of users increases in IRS-NOMA systems, ensuring consistently high data rates for all users becomes challenging due to coverage limitations and inefficient power allocation in static network configurations, leading to performance degradation in multiuser scenarios. To address these limitations, we propose a novel IRS-NOMA cooperative system designed to optimize sum rates through an intelligent power allocation algorithm, nearby users, and IRS to assist the base station in delivering signals and expanding network coverage. The proposed system operates in two phases: during the first phase, the base station transmits signals directly to users and indirectly through the IRS. In the second phase, nearby users assist in relaying signals to enhance coverage and reliability. The proposed system adopts a cascaded channel model to accurately capture the interactions between the base station, IRS, and users. By leveraging our optimization algorithm, the proposed system ensures efficient resource allocation, achieving superior spectral efficiency and fairness among users compared to traditional models. Numerical results validate the effectiveness of the proposed system, demonstrating its potential for next-generation IoT networks. ⓘ Kumar, Mukkara Prasanna; Summaq, Ammar; Chinnadurai, Sunil; Selvaprabhu, Poongundran; Kumaravelu, Vinoth Babu; Sarker, Md. Abdul Latif; Han, Dong Seog ⓘ SRM Univ AP, Sch Engn & Sci, Dept Elect & Commun Engn, Guntur 522502, India; Vellore Inst Technol, Sch Elect Engn, Dept Commun Engn, Vellore 632014, Tamil Nadu, India; Kyungpook Natl Univ, Ctr ICT & Automot Convergence, Daegu 41566, South Korea; Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea ⓘ Chiinnadurai, Sunil/IUM-1982-2023; Kumaravelu, Vinoth/N-5144-2019; Selvaprabhu, Poongundran/T-7131-2019 ⓘ 59481303600; 59481187900; 57485185900; 56518192300; 54982753600; 42262729500; 59307662300 ⓘ mukkaraprasanna_kumar@srmap.edu.in; ammar_summaq@srmap.edu.in; sunil.c@srmap.edu.in; poongundran.selvaprabhu@vit.ac.in; vinothbab@gmail.com; latifsarker@knu.ac.kr; dshan@knu.ac.kr; ⓘ ICT EXPRESS ⓘ ICT EXPRESS ⓘ 2405-9595 11 3 SCIE TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS ⓘ 2024 4.2 28.1 N/A ⓘ 0 0 Intelligent Reflecting Surface; Orthogonal multiple access; Non-orthogonal multiple access; IoT ⓘ MULTIPLE-ACCESS ⓘ Intelligent Reflecting Surface; IoT; Non-orthogonal multiple access; Orthogonal multiple access ⓘ ⓘ English 2025 2025-06 10.1016/j.icte.2025.04.003 ⓘ 바로가기 바로가기 바로가기 바로가기
○ ○ Article ⓘ Transition toward Healthcare 5.0: Impact of COVID-19 in the healthcare industry ⓘ The COVID-19 pandemic has prompted healthcare advancements, enhanced security and efficiency, and reduced disease transmission. The industry rapidly addresses technological gaps and growing service demands. The pandemic has driven a pivotal shift from Healthcare 4.0 to Healthcare 5.0. Healthcare 4.0 emphasizes technology-centered care, whereas Healthcare 5.0 prioritizes patient-centric, personalized, and participatory approaches. This review assesses COVID-19's impact on this transition, comparing pre-pandemic and pandemic literature. It examines how digital tools enable healthcare providers to deliver patient-centered and personalized care, fostering a shift from Healthcare 4.0 to Healthcare 5.0. ⓘ Raisa, Jasiya Fairiz; Rahman, Md. Sazzadur; Mahmud, Imtiaz; Kaiser, M. Shamim; Han, Dong Seog ⓘ Bangladesh Univ Profess, Mirpur Cantonment, Dhaka 1216, Bangladesh; Jahangirnagar Univ, Inst Informat Technol, Savar 1342, Dhaka, Bangladesh; Lawrence Berkeley Natl Lab, Berkeley, CA 94720, USA; Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea ⓘ Mahmud, Imtiaz/R-1089-2019 ⓘ 57221115739; 59860333500; 56203487900; 56446362000; 59307662300 ⓘ jasiyafairiz@gmail.com; sazzad@juniv.edu; imtiaztee@gmail.com; mskaiser@juniv.edu; dshan@knu.ac.kr; ⓘ ICT EXPRESS ⓘ ICT EXPRESS ⓘ 2405-9595 11 3 SCIE TELECOMMUNICATIONS;COMPUTER SCIENCE, INFORMATION SYSTEMS ⓘ 2024 4.2 28.1 0 2025-05-07 ⓘ 0 0 Healthcare 4.0; Healthcare 5.0; Healthcare systems; COVID-19 ⓘ PERSONAL DIGITAL ASSISTANT; AUGMENTED REALITY; SMARTPHONE APPS; SYSTEM; INTELLIGENT; MANAGEMENT; MEDICINE; MOBILE; IOT; ERA ⓘ COVID-19; Healthcare 4.0; Healthcare 5.0; Healthcare systems ⓘ ⓘ English 2025 2025-06 10.1016/j.icte.2025.04.002 ⓘ 바로가기 바로가기 바로가기 바로가기
○ ○ Article ⓘ 6-DoF Pose Estimation from Single RGB Image and CAD Model Retrieval Using Feature Similarity Measurement ⓘ This study presents six degrees of freedom (6-DoF) pose estimation of an object from a single RGB image and retrieval of the matching CAD model by measuring the similarity between RGB and CAD rendering images. The 6-DoF pose estimation of an RGB object is one of the important techniques in 3D computer vision. However, in addition to 6-DoF pose estimation, retrieval and alignment of the matching CAD model with the RGB object should be performed for various industrial applications such as eXtended Reality (XR), Augmented Reality (AR), robot's pick and place, and so on. This paper addresses 6-DoF pose estimation and CAD model retrieval problems simultaneously and quantitatively analyzes how much the 6-DoF pose estimation affects the CAD model retrieval performance. This study consists of two main steps. The first step is 6-DoF pose estimation based on the PoseContrast network. We enhance the structure of PoseConstrast by adding variance uncertainty weight and feature attention modules. The second step is the retrieval of the matching CAD model by an image similarity measurement between the CAD rendering and the RGB object. In our experiments, we used 2000 RGB images collected from Google and Bing search engines and 100 CAD models from ShapeNetCore. The Pascal3D+ dataset is used to train the pose estimation network and DELF features are used for the similarity measurement. Comprehensive ablation studies about the proposed network show the quantitative performance analysis with respect to the baseline model. Experimental results show that the pose estimation performance has a positive correlation with the CAD retrieval performance. ⓘ Park, Sieun; Jeong, Won-Je; Manawadu, Mayura; Park, Soon-Yong ⓘ Kyungpook Natl Univ, Sch Elect & Elect Engn, 80 Daehak Ro, Daegu 41566, South Korea ⓘ Park, Soon-Yong/HGV-2374-2022 ⓘ 59685274700; 58074469700; 58875158200; 7501834063 ⓘ swanyh@naver.com; autowmacma@gmail.com; mmayurapavan@gmail.com; sypark@knu.ac.kr; ⓘ APPLIED SCIENCES-BASEL ⓘ APPL SCI-BASEL ⓘ 2076-3417 15 3 SCIE CHEMISTRY, MULTIDISCIPLINARY;ENGINEERING, MULTIDISCIPLINARY;MATERIALS SCIENCE, MULTIDISCIPLINARY;PHYSICS, APPLIED ⓘ 2024 2.5 28.3 3.19 2025-05-07 ⓘ 1 1 6-DoF pose estimation; similarity measure; deep learning; CAD model retrieval ⓘ ⓘ 6-DoF pose estimation; CAD model retrieval; deep learning; similarity measure ⓘ 3D modeling; Augmented reality; Computer aided logic design; Computer vision; Deep learning; Image matching; Image retrieval; Industrial robots; Online searching; RGB color model; Three dimensional computer graphics; CAD model retrieval; CAD models; Deep learning; Matchings; Pose-estimation; RGB images; Similarity measure; Similarity measurements; Six degree of freedom pose estimation; Six degrees of freedom; Rendering (computer graphics) ⓘ English 2025 2025-02 10.3390/app15031501 ⓘ 바로가기 바로가기 바로가기 바로가기
○ ○ Article ⓘ A CNN-Based Indoor Positioning Algorithm for Dark Environments: Integrating Local Binary Patterns and Fast Fourier Transform with the MC4L-IMU Device ⓘ In our previous study, we proposed a vision-based ranging algorithm (LRA) that utilized a monocular camera with four lasers (MC4L) for indoor positioning in dark environments. The LRA achieved a positioning error within 2.4 cm using a logarithmic regression algorithm to establish a linear relationship between the illuminated area and real distance. However, it cannot distinguish between obstacles and walls. Hence, it results in severe errors in complex environments. To address this limitation, we developed an LBP-CNNs model that combines local binary patterns (LBPs) and self-attention mechanisms. The model effectively identifies obstacles based on the laser reflectivity of different material surfaces. It reduces positioning errors to 1.27 cm and achieves an obstacle recognition accuracy of 92.3%. In this paper, we further enhance LBP-CNNs by combining it with fast Fourier transform (FFT) to create an LBP-FFT-CNNs model that significantly improves the recognition accuracy of obstacles with similar textures to 96.3% and reduces positioning errors to 0.91 cm. In addition, an inertial measurement unit (IMU) is integrated into the MC4L device (MC4L-IMU) to design an inertial-based indoor positioning algorithm. Experimental results show that the LBP-FFT-CNNs model achieves the highest determination coefficient (R2 = 0.9949), outperforming LRA (R2 = 0.9867) and LBP-CNN (R2 = 0.9934). In addition, all models show strong stability, and the prediction standard index (PSI) values are always below 0.02. To evaluate model robustness and MC4L-IMU work reliably under different conditions, the experiments were conducted in a controlled indoor environment with different obstacle materials and lighting conditions. ⓘ Yin, Nan; Sun, Yuxiang; Kim, Jae-Soo ⓘ Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu 41566, South Korea ⓘ ⓘ 59143277000; 57202927837; 59863623600 ⓘ yinnan.lisa@gmail.com; syx921120@gmail.com; kjs@knu.ac.kr; ⓘ APPLIED SCIENCES-BASEL ⓘ APPL SCI-BASEL ⓘ 2076-3417 15 7 SCIE CHEMISTRY, MULTIDISCIPLINARY;ENGINEERING, MULTIDISCIPLINARY;MATERIALS SCIENCE, MULTIDISCIPLINARY;PHYSICS, APPLIED ⓘ 2024 2.5 28.3 0 2025-05-07 ⓘ 0 0 local binary pattern; fast Fourier transform; self-attention mechanism; CNNs; inertia-based indoor positioning algorithm; visual localization; obstacle recognition; dark environment ⓘ ⓘ CNNs; dark environment; fast Fourier transform; inertia-based indoor positioning algorithm; local binary pattern; obstacle recognition; self-attention mechanism; visual localization ⓘ Inertial navigation systems; Local binary pattern; Regression analysis; Time difference of arrival; Attention mechanisms; Dark environment; Fast fourier; Indoor positioning; Inertia-based indoor positioning algorithm; Local binary patterns; Obstacle recognition; Positioning algorithms; Self-attention mechanism; Visual localization; Fast Fourier transforms ⓘ English 2025 2025-04-07 10.3390/app15074043 ⓘ 바로가기 바로가기 바로가기 바로가기
○ ○ Article ⓘ A Secure and Efficient Authentication Scheme for Fog-Based Vehicular Ad Hoc Networks ⓘ Recently, the application of fog-computing technology to vehicular ad hoc networks (VANETs) has rapidly advanced. Despite these advancements, challenges remain in ensuring efficient communication and security. Specifically, there are issues such as the high communication and computation load of authentications and insecure communication over public channels between fog nodes and vehicles. To address these problems, a lightweight and secure authenticated key agreement protocol for confidential communication is proposed. However, we found that the protocol does not offer perfect forward secrecy and is vulnerable to several attacks, such as privileged insider, ephemeral secret leakage, and stolen smart card attacks. Furthermore, their protocol excessively uses elliptic curve cryptography (ECC), resulting in delays in VANET environments where authentication occurs frequently. Therefore, this paper proposes a novel authentication protocol that outperforms other related protocols regarding security and performance. The proposed protocol reduced the usage frequency of ECC primarily using hash and exclusive OR operations. We analyzed the proposed protocol using informal and formal methods, including the real-or-random (RoR) model, Burrows-Abadi-Nikoogadam (BAN) logic, and automated validation of internet security protocols and applications (AVISPA) simulation to show that the proposed protocol is correct and secure against various attacks. Moreover, We compared the computational cost, communication cost, and security features of the proposed protocol with other related protocols and show that the proposed methods have better performance and security than other schemes. As a result, the proposed scheme is more secure and efficient for fog-based VANETs. ⓘ Lee, Sangjun; Son, Seunghwan; Kwon, Deokkyu; Park, Yohan; Park, Youngho ⓘ Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea; Keimyung Univ, Sch Comp Engn, Daegu 42601, South Korea ⓘ ⓘ 59557779500; 57221744477; 57221739597; 55660095600; 56962990300 ⓘ gumoning9010@knu.ac.kr; sonshawn@knu.ac.kr; kdk145@knu.ac.kr; yhpark@kmu.ac.kr; parkyh@knu.ac.kr; ⓘ APPLIED SCIENCES-BASEL ⓘ APPL SCI-BASEL ⓘ 2076-3417 15 3 SCIE CHEMISTRY, MULTIDISCIPLINARY;ENGINEERING, MULTIDISCIPLINARY;MATERIALS SCIENCE, MULTIDISCIPLINARY;PHYSICS, APPLIED ⓘ 2024 2.5 28.3 0 2025-05-07 ⓘ 1 1 fog computing; vehicular ad hoc network; lightweight; key agreement; perfect forward secrecy; BAN logic; RoR model; AVISPA simulation ⓘ KEY AGREEMENT PROTOCOL; PRIVACY; DESIGN ⓘ AVISPA simulation; BAN logic; fog computing; key agreement; lightweight; perfect forward secrecy; RoR model; vehicular ad hoc network ⓘ Authentication; Authentication Protocol; Cryptography; Fog computing; Polynomial approximation; Program debugging; Secure communication; Application simulation; Automated validation of internet security protocol and application simulation; Burrow–abadi–nikoogadam logic; Internet security; Key agreement; Lightweight; Perfect forward secrecy; Protocol simulation; Random Model; Real-or-random model; Security application; Security protocols; Vehicular Adhoc Networks (VANETs); Vehicular ad hoc networks ⓘ English 2025 2025-02 10.3390/app15031229 ⓘ 바로가기 바로가기 바로가기 바로가기
○ ○ Article ⓘ Cross-Database Learning Framework for Electrocardiogram Arrhythmia Classification Using Two-Dimensional Beat-Score-Map Representation ⓘ Cross-database electrocardiogram (ECG) classification remains a critical challenge due to variations in patient populations, recording conditions, and annotation granularity. Existing methodologies for ECG arrhythmia classification have primarily utilized datasets with either fine-grained or coarse-grained labels, but seldom both simultaneously. Fine-grained labels provide beat-level annotations, whereas coarse-grained labels offer only record-level labels. In this study, we propose an innovative cross-database learning framework that utilizes both fine-grained and coarse-grained labels in tandem, thereby enhancing classification performance across heterogeneous datasets. Specifically, our approach begins with the pretraining of a CNN-based beat classifier that takes ECG signals as the input and predicts beat types on a finely labeled dataset, namely the MIT-BIH Arrhythmia Database (MITDB). The pretrained model is then fine-tuned using weakly supervised learning on two coarsely labeled datasets: the SPH one, which contains four rhythm classes, and the PTB-XL one, which involves binary classification between the sinus rhythm (SR) and atrial fibrillation (AFIB). Once the beat classifier is adapted to a new dataset, it generates a two-dimensional beat-score-map (BSM) representation from the input ECG signal. This 2D BSM is subsequently utilized as the input for arrhythmia rhythm classification. The proposed method achieves F1 scores of 0.9301 on the SPH dataset and 0.9267 on the PTB-XL dataset, corresponding to the multi-class and binary rhythm classification tasks described above. These results demonstrate a robust cross-database classification of complex cardiac arrhythmia rhythms. Furthermore, t-SNE visualizations of the 2D BSM representations, after adaptation to the coarsely labeled SPH and PTB-XL datasets, validate how our method significantly enhances the ability to differentiate between various arrhythmia rhythm types, thus highlighting its effectiveness in cross-database ECG analysis. ⓘ Lee, Jaewon; Shin, Miyoung ⓘ Kyungpook Natl Univ, Sch Elect & Elect Engn, Biointelligence & Data Min Lab, Daegu 41566, South Korea ⓘ ⓘ 58377059800; 7401536642 ⓘ realjaewon94@gmail.com; shinmy@knu.ac.kr; ⓘ APPLIED SCIENCES-BASEL ⓘ APPL SCI-BASEL ⓘ 2076-3417 15 10 SCIE CHEMISTRY, MULTIDISCIPLINARY;ENGINEERING, MULTIDISCIPLINARY;MATERIALS SCIENCE, MULTIDISCIPLINARY;PHYSICS, APPLIED ⓘ 2024 2.5 28.3 0 2025-06-11 ⓘ 0 0 ECG; arrhythmia classification; cross-database; weakly supervised learning ⓘ ⓘ arrhythmia classification; cross-database; ECG; weakly supervised learning ⓘ Image coding; Image compression; Image enhancement; Image segmentation; Support vector machines; Arrhythmia classification; Coarse-grained; Cross-database; Electrocardiogram signal; Fine grained; Labeled dataset; Learning frameworks; Map representations; Two-dimensional; Weakly supervised learning; Labeled data ⓘ English 2025 2025-05-15 10.3390/app15105535 ⓘ 바로가기 바로가기 바로가기 바로가기
○ ○ Article ⓘ Digital Analysis Using 3D Intraoral Scanner on Gingival Contour Changes Following the Roll Flap Technique ⓘ The study aimed to evaluate changes in buccal gingival contour following implant surgery using the simultaneous roll technique on Seibert class I defects, as determined by 3D intraoral scan data. Three patients requiring implant placement were recruited, and implants were placed using the roll flap technique. Digital impressions of the surgical site were obtained with a 3D intraoral scanner before surgery, after suture removal, and 4 months postoperatively. The results showed an overall increase in buccal gingival contour, with a maintained increase in soft tissue contour after 4 months. The study concluded that 3D scanning is a suitable method for assessing small changes in gingival contour, making it ideal for evaluating these changes. The roll flap technique was also found to effectively enhance the buccal gingival contour and soft tissue appearance around the implant collar. ⓘ Shin, Ye-Jin; Do, Woo-Seok; Hwang, Sung-Min; Kim, Yong-Gun; Lee, Jae-Mok ⓘ Kyungpook Natl Univ, Sch Dent, Dept Periodontol, Daegu 41940, South Korea ⓘ ⓘ 59730805900; 59072915500; 57870525500; 55622694400; 17346330000 ⓘ shjean24@naver.com; jd06hanmail@naver.com; lhwangl89@naver.com; periokyg@knu.ac.kr; leejm@knu.ac.kr; ⓘ APPLIED SCIENCES-BASEL ⓘ APPL SCI-BASEL ⓘ 2076-3417 15 7 SCIE CHEMISTRY, MULTIDISCIPLINARY;ENGINEERING, MULTIDISCIPLINARY;MATERIALS SCIENCE, MULTIDISCIPLINARY;PHYSICS, APPLIED ⓘ 2024 2.5 28.3 0 2025-05-07 ⓘ 0 0 digital dentistry; 3D scanner; dental implants; clinical cases; connective tissue pedicle graft; roll technique ⓘ LOCALIZED RIDGE AUGMENTATION; SOFT-TISSUES ⓘ 3D scanner; clinical cases; connective tissue pedicle graft; dental implants; digital dentistry; roll technique ⓘ Rolls (machine components); Transplantation (surgical); 3D-scanners; Class I; Clinical case; Connective tissue pedicle graft; Connective tissues; Contour following; Digital analysis; Digital dentistry; Roll technique; Soft tissue; Dental prostheses ⓘ English 2025 2025-03-25 10.3390/app15073578 ⓘ 바로가기 바로가기 바로가기 바로가기
○ ○ Article ⓘ Digital Twin Framework for Road Infrastructure Management ⓘ Digital twin (DT) technology has garnered increasing attention across various sectors, particularly in the construction and road infrastructure domains. To fully realize its potential and systematically apply it in practice, adherence to a formalized approach is necessary. However, numerous DT-related standards and models currently exist, creating uncertainty in the selection of appropriate frameworks. Moreover, no widely accepted standard or reference model has yet been developed in the field of road infrastructure management. Therefore, this study examined the current standards and models employed in the adoption and implementation of DTs in road infrastructure management, focusing on their dimensions (layers) and functional components. A bottom-up approach was adopted by comprehensively reviewing the existing literature on road networks, bridges, tunnels, and other civil infrastructures and urban DTs. Ultimately, a DT framework was developed, comprising five core layers with their respective components and functionalities, to facilitate network-level integrated road infrastructure management. Moreover, the proposed framework's implementation scenario enhances its applicability in the field. Overall, this study provides valuable insights for researchers and practitioners involved in DT implementation in infrastructure management and supports future standardization efforts in this domain. ⓘ Buuveibaatar, Munkhbaatar; Shin, Sungpil; Lee, Wonhee ⓘ Kyungpook Natl Univ, Res Inst Artificial Intelligent Diag Technol Multi, Sangju 37224, South Korea; Korea Inst Civil Engn & Bldg Technol, Integrated Rd Management Res Ctr, Goyang 10223, South Korea; Kyungpook Natl Univ, Dept Locat Based Informat Syst, Sangju 37224, South Korea ⓘ Buuveibaatar, Munkhbaatar/ISU-9533-2023 ⓘ 57219182724; 57045111800; 57190774365 ⓘ munkh@knu.ac.kr; spshin@kict.re.kr; wlee33@knu.ac.kr; ⓘ APPLIED SCIENCES-BASEL ⓘ APPL SCI-BASEL ⓘ 2076-3417 15 10 SCIE CHEMISTRY, MULTIDISCIPLINARY;ENGINEERING, MULTIDISCIPLINARY;MATERIALS SCIENCE, MULTIDISCIPLINARY;PHYSICS, APPLIED ⓘ 2024 2.5 28.3 0 2025-06-11 ⓘ 0 0 digital twin; road infrastructure digital twin; digital twin framework; digital twin reference model; digital twin standardization; intelligent road infrastructure management; road infrastructure digitalization ⓘ ⓘ digital twin; digital twin framework; digital twin reference model; digital twin standardization; intelligent road infrastructure management; road infrastructure digital twin; road infrastructure digitalization ⓘ Calibration; Digital twin framework; Digital twin reference model; Digital twin standardization; Infrastructure managements; Intelligent road infrastructure management; Intelligent roads; Reference modeling; Road infrastructure digital twin; Road infrastructure digitalization; Road infrastructures; Highway administration ⓘ English 2025 2025-05-21 10.3390/app15105765 ⓘ 바로가기 바로가기 바로가기 바로가기
○ ○ Article ⓘ Enhancing Small Language Models for Graph Tasks Through Graph Encoder Integration ⓘ Small language models (SLMs) are increasingly utilized for on-device applications due to their ability to ensure user privacy, reduce inference latency, and operate independently of cloud infrastructure. However, their performance is often limited when processing complex data structures such as graphs, which are ubiquitous in real-world datasets like social networks and system interactions. Graphs inherently encode intricate structural dependencies, requiring models to effectively capture both local and global relationships. Traditional language models, designed primarily for text data, struggle to address these requirements, leading to suboptimal performance in graph-related tasks. To overcome this limitation, we propose a novel graph encoder-based prompt tuning framework which integrates a graph convolutional network (GCN) with a graph transformer. By leveraging the complementary strengths of the GCN for local structural modeling and the graph transformer for capturing global relationships, our method enables SLMs to effectively process graph data. This integration significantly enhances the ability of SLMs to handle graph-centric tasks while maintaining the efficiency required for resource-constrained devices. The experimental results show that our approach not only improves the performance of SLMs on various graph benchmarks but also achieves results which closely approach the performance of a large language model (LLM). This work highlights the potential of extending SLMs for graph-based applications and advancing the capabilities of on-device artificial intelligence. ⓘ Oh, Dongryul; Kang, Sujin; Kim, Heejin; Oh, Dongsuk ⓘ Hyundai Motors, AVP Div, Vehicle Dev DX Team, AI Engn Part, 150 HyundaiYeonguso Ro, Hwaseong 18280, South Korea; Kyungpook Natl Univ, Dept English Language & Literature, Daegu 41566, South Korea ⓘ ⓘ 59693741900; 59393450000; 57205485740; 57211283137 ⓘ dongryul.oh@hyundai.com; kangsujin@knu.ac.kr; hkim1596@knu.ac.kr; inow3555@knu.ac.kr; ⓘ APPLIED SCIENCES-BASEL ⓘ APPL SCI-BASEL ⓘ 2076-3417 15 5 SCIE CHEMISTRY, MULTIDISCIPLINARY;ENGINEERING, MULTIDISCIPLINARY;MATERIALS SCIENCE, MULTIDISCIPLINARY;PHYSICS, APPLIED ⓘ 2024 2.5 28.3 0 2025-05-07 ⓘ 0 0 small language model (SLM); on-device AI; graph neural network (GNN); graph transformer; graph convolutional network (GCN); prompt tuning; graph representation learning ⓘ ⓘ graph convolutional network (GCN); graph neural network (GNN); graph representation learning; graph transformer; on-device AI; prompt tuning; small language model (SLM) ⓘ Convolutional neural networks; Data privacy; Economic and social effects; Encoding (symbols); Convolutional networks; Graph convolutional network; Graph neural network; Graph neural networks; Graph representation; Graph representation learning; Graph transformer; Language model; On-device AI; Prompt tuning; Small language model; Graph neural networks ⓘ English 2025 2025-03 10.3390/app15052418 ⓘ 바로가기 바로가기 바로가기 바로가기
○ ○ Article ⓘ Evaluating Creativity: Can LLMs Be Good Evaluators in Creative Writing Tasks? ⓘ The evaluation of creative writing has long been a complex and subjective process, made even more intriguing by the rise of advanced Artificial Intelligence (AI) tools like Large Language Models (LLMs). This study evaluates the potential of LLMs as reliable and consistent evaluators of creative texts, directly comparing their performance with traditional human evaluations. The analysis focuses on key creative criteria, including fluency, flexibility, elaboration, originality, usefulness, and specific creativity strategies. Results demonstrate that LLMs provide consistent and objective evaluations, achieving higher Inter-Annotator Agreement (IAA) compared with human evaluators. However, LLMs face limitations in recognizing nuanced, culturally specific, and context-dependent aspects of creativity. Conversely, human evaluators, despite lower consistency and higher subjectivity, exhibit strengths in capturing deeper contextual insights. These findings highlight the need for the further refinement of LLMs to address the complexities of creative writing evaluation. ⓘ Kim, Sungeun; Oh, Dongsuk ⓘ Kyungpook Natl Univ, Dept English Language & Literature, Daegu 41566, South Korea ⓘ ⓘ 59710082300; 57211283137 ⓘ emilykim@knu.ac.kr; inow3555@knu.ac.kr; ⓘ APPLIED SCIENCES-BASEL ⓘ APPL SCI-BASEL ⓘ 2076-3417 15 6 SCIE CHEMISTRY, MULTIDISCIPLINARY;ENGINEERING, MULTIDISCIPLINARY;MATERIALS SCIENCE, MULTIDISCIPLINARY;PHYSICS, APPLIED ⓘ 2024 2.5 28.3 0 2025-05-07 ⓘ 0 0 large language models (LLMs) evaluation; creative writing evaluation; creativity; AI evaluation; human evaluation ⓘ ⓘ AI evaluation; creative writing evaluation; creativity; human evaluation; large language models (LLMs) evaluation ⓘ Artificial intelligence evaluation; Artificial intelligence tools; Creative writing evaluation; Creative writings; Creatives; Creativity; Human evaluation; Language model; Large language model evaluation; Model evaluation ⓘ English 2025 2025-03-10 10.3390/app15062971 ⓘ 바로가기 바로가기 바로가기 바로가기
○ ○ Article ⓘ Expectorant Effects of Atractylodes japonica Koidz. ex Kitam Root Extracts on Particulate Matter-Induced Pulmonary Injury in Mice ⓘ This study investigated the growing environmental concern of particulate matter (PM)-induced pulmonary injury and explored novel preventive strategies. In particular, it evaluated the protective effects of Atractylodes japonica Koidz. ex. Kitam root extract (AJ), which is known for its anti-inflammatory and antioxidant properties, against PM2.5-induced subacute pulmonary injuries in Balb/c mice. The experimental design involved administering AJ at a concentration from 400 to 100 mg/kg over a ten-day period, with comparisons made to the mucolytic agent ambroxol hydrochloride (AX). The results revealed that AJ significantly alleviated PM2.5-induced pulmonary injuries, mucus overproduction, and respiratory acidosis in a dose-dependent manner. Notably, body surface redness was reduced by up to 55% at a concentration of 100 mg/kg compared to the control. These effects were evidenced by reduced mRNA expression of the mucus-associated genes MUC5B and MUC5AC and increased concentrations of substance P (up to 475%) and acetylcholine (up to 355%) in the lungs at 400 mg/kg, compared to the intact vehicle control. Particularly, the 400 mg/kg dose of AJ demonstrated comparable effectiveness to AX, highlighting its potent mucolytic and expectorant activities. The results of this study highlight the fact that AJ could act as a promising alternative for respiratory protection, with potential applications as a functional food ingredient. This study substantiates AJ's role in enhancing respiratory health, emphasizing its capacity as a candidate for further development into therapeutic agents against toxic environmental exposure. ⓘ Lee, Junho; Mansoor, Sana; Lee, Jeongjun; Chung, Hunsuk; Kwon, Young-Sam; Bashir, Khawaja Muhammad Imran; Choi, Jae-Suk; Ku, Sae-Kwang ⓘ Kyungpook Natl Univ, Coll Vet Med, Dept Vet Surg, Daegu 41566, South Korea; Gyeongsang Natl Univ, Inst Marine Ind, Dept Seafood Sci & Technol, Tongyeong 53064, South Korea; GAPI BIO Co Ltd, Hwaseong 18622, South Korea; German Engn Res & Dev Ctr Life Sci Technol Med & E, Busan 46742, South Korea; Daegu Haany Univ, Coll Korean Med, Dept Anat & Histol, Gyongsan 38610, South Korea ⓘ BASHIR, KHAWAJA MUHAMMAD IMRAN/J-9192-2018 ⓘ 57219032336; 57205331915; 57214357024; 59403883000; 59540546300; 56488376400; 35104615200; 7006331005 ⓘ 2009045032@knu.ac.kr; sanamansoorahmad@gmail.com; orglab@gapibio.co.kr; hunsukchung@dongbangchem.co.kr; kwon@knu.ac.kr; imranbashir@gnu.ac.kr; jsc1008@gnu.ac.kr; gucci200@dhu.ac.kr; ⓘ APPLIED SCIENCES-BASEL ⓘ APPL SCI-BASEL ⓘ 2076-3417 15 1 SCIE CHEMISTRY, MULTIDISCIPLINARY;ENGINEERING, MULTIDISCIPLINARY;MATERIALS SCIENCE, MULTIDISCIPLINARY;PHYSICS, APPLIED ⓘ 2024 2.5 28.3 3.19 2025-05-07 ⓘ 1 1 antioxidant activity; anti-inflammatory; Atractylodes japonica; herbal medicine; mucolytic expectorant; respiratory protection ⓘ PRO-INFLAMMATORY CYTOKINES; LUNG EPITHELIAL-CELLS; CHEMICAL-COMPOSITION; ATRACTYLENOLIDE-III; OXIDATIVE STRESS; PM2.5; INHIBITION; EXPRESSION; POLLUTION; APOPTOSIS ⓘ anti-inflammatory; antioxidant activity; Atractylodes japonica; herbal medicine; mucolytic expectorant; respiratory protection ⓘ Bioremediation; Lung cancer; Medicinal chemistry; Ambroxol hydrochloride; Anti-inflammatories; Antioxidant activities; Atractylode japonicum; Environmental concerns; Herbal medicines; Mucolytic expectorant; Particulate Matter; Respiratory protection; Root extracts; Pulmonary diseases ⓘ English 2025 2025-01 10.3390/app15010099 ⓘ 바로가기 바로가기 바로가기 바로가기
○ ○ Article ⓘ Exploring the Potential of Desmodesmus sp. KNUA231 for Bioenergy and Biofertilizer Applications and Its Adaptability to Environmental Stress ⓘ As global energy demand continues to rise, microalgae have gained attention as a promising feedstock for biofuel production due to their environmental adaptability and renewable nature. This study investigated the growth performance and stress tolerance of Desmodesmus sp. KNUA231 under varying pH and salinity conditions to evaluate its potential as a biofuel candidate. The strain was cultivated under controlled laboratory conditions and exhibited stable growth across a broad pH range (4-10) and moderate salinity levels (up to 5 g L-1 NaCl), indicating its resilience to diverse environmental conditions. Fatty acid methyl ester (FAME) analysis revealed that the biodiesel properties of Desmodesmus sp. KNUA231 comply with ASTM and EN standards in specific parameters, reinforcing its feasibility as a renewable biofuel feedstock. Additionally, its high calorific value (CV) suggests its potential as an energy-dense biomass source. The results of inductively coupled plasma mass spectrometry (ICP) analysis show that the soil is supplied with essential nutrients while minimizing heavy metal contamination, suggesting the possibility of biofertilizers. Although Desmodesmus sp. KNUA231 demonstrated promising characteristics for biofuel applications, further research is required to optimize large-scale cultivation and improve productivity for industrial applications. These findings highlight the potential of Desmodesmus sp. KNUA231 as a biofuel resource, particularly in non-optimal environmental conditions where pH and salinity fluctuations are common, contributing to the ongoing search for sustainable bioenergy solutions. ⓘ Shin, Yeon-Su; Do, Jeong-Mi; Noh, Hae-Seo; Yoon, Ho-Sung ⓘ Kyungpook Natl Univ, Dept Biol, Daegu 41566, South Korea; Kyungpook Natl Univ, Sch Life Sci, BK21 FOUR KNU Creat BioRes Grp, Daegu 41566, South Korea; Kyungpook Natl Univ, Integrated Blue Carbon Res Ctr, Adv Bioresource Res Ctr, Daegu 41566, South Korea ⓘ ⓘ 59902659600; 57208562245; 59670381700; 7402990205 ⓘ 58sus95@naver.com; jmdoe09@knu.ac.kr; noj224@naver.com; hsy@knu.ac.kr; ⓘ APPLIED SCIENCES-BASEL ⓘ APPL SCI-BASEL ⓘ 2076-3417 15 9 SCIE CHEMISTRY, MULTIDISCIPLINARY;ENGINEERING, MULTIDISCIPLINARY;MATERIALS SCIENCE, MULTIDISCIPLINARY;PHYSICS, APPLIED ⓘ 2024 2.5 28.3 0 2025-06-11 ⓘ 0 0 microalgae; biomass productivity; bioenergy; biofertilizer; environmental stress adaptation ⓘ DIVERSITY ⓘ bioenergy; biofertilizer; biomass productivity; environmental stress adaptation; microalgae ⓘ Acetobacter; Feedstocks; Phytoplankton; Seaweed; Bio-energy; Biofertilizers; Biomass productivity; Environmental conditions; Environmental stress; Environmental stress adaptation; Global energy demand; Micro-algae; Microalga; Renewables; Microalgae ⓘ English 2025 2025-05-03 10.3390/app15095097 ⓘ 바로가기 바로가기 바로가기 바로가기
○ ○ Article ⓘ Implementation of a Parametric Ultrasonic Receiver Using Multilayer Lead Zirconate Titanate for a Feasibility Study of an Ultrasonic-Beam-Focused Hearing Aid ⓘ We demonstrated that focusing an ultrasonic beam on the eardrum can overcome the high-frequency sensitivity limitations and acoustic distortion of conventional hearing aid receivers. Multilayer PZT was used for an ultrasonic receiver that operates at low voltage and enters the external auditory canal, and a 3 mm radius radiator was designed to radiate the focused parametric acoustic signal to the center of the eardrum based on an acoustic analysis according to the frequency. To this end, an ultrasonic earphone consisting of a radiator attached to multilayer PZT and a 130 kHz parametric ultrasonic modulator was implemented; vibration and sound pressure were measured using a laser vibrometer and a tube-type microphone. The proposed parametric ultrasonic receiver generates an average sound pressure of 70 dB SPL at a frequency of 1 similar to 10 kHz with a 10 V-peak applied voltage; this was implemented to provide a higher output in the range of 5 kHz and above, which is difficult to cover with existing receivers. ⓘ Seong, Ki Woong; Cho, Jin Ho; Kim, Myoung Nam; Shin, Dong Ho; Lee, Jyung Hyun ⓘ Kyungpook Natl Univ Hosp, Dept Biomed Engn, 130 Dongdeok Ro, Daegu 41944, South Korea; Kyungpook Natl Univ, Inst Biomed Engn, 680 Gukchaebosang Ro, Daegu 41944, South Korea; Kyungpook Natl Univ, Sch Med, Dept Biomed Engn, 680 Gukchaebosang Ro, Daegu 41944, South Korea ⓘ ⓘ 59917565300; 59917804200; 57212315655; 59917804300; 59918046100 ⓘ seongkw@gmail.com; jinhocho53@gmail.com; kimmn@knu.ac.kr; swap9552@naver.com; pung@knu.ac.kr; ⓘ APPLIED SCIENCES-BASEL ⓘ APPL SCI-BASEL ⓘ 2076-3417 15 10 SCIE CHEMISTRY, MULTIDISCIPLINARY;ENGINEERING, MULTIDISCIPLINARY;MATERIALS SCIENCE, MULTIDISCIPLINARY;PHYSICS, APPLIED ⓘ 2024 2.5 28.3 0 2025-06-11 ⓘ 0 0 hearing aid receiver; ultrasound speaker; focused ultrasound; piezoelectric element ⓘ ⓘ focused ultrasound; hearing aid receiver; piezoelectric element; ultrasound speaker ⓘ Acoustic emissions; Acoustic noise; Acoustic variables measurement; Piezoelectric materials; Ultrasonic sensors; Ultrasonic testing; Ultrasonic waves; Focused ultrasound; Hearing aid receiver; Hearing-aids; Lead zirconate-titanate; Piezoelectric elements; PZT; Sound pressures; Ultrasonic beams; Ultrasonic receivers; Ultrasound speaker; Ultrasonic distortion ⓘ English 2025 2025-05-19 10.3390/app15105679 ⓘ 바로가기 바로가기 바로가기 바로가기
○ ○ Article ⓘ MAIL: Micro-Accelerator-in-the-Loop Framework for MCU Integrated Accelerator Peripheral Fast Prototyping ⓘ The resource-constrained MCU-based platform is unable to use high-performance accelerators such as GPUs or servers due to insufficient resources for ML applications. We define a Micro-Accelerator (MA) that can accelerate ML operations by being connected to the on-chip bus peripheral of the MCU core. ML applications using general-purpose accelerators have a well-equipped SDK environment, making design and verification flow straightforward. In contrast, MA must be connected to the MCU core and on-chip bus interface within the chip. However, evaluating the interaction between the MCU core and an MA is challenging, as it requires the MA to connect with the core and the on-chip bus interface during target software execution. The cost of fabricating physical MA hardware is enormous, compounded by licensing issues with commercial cores. We propose a MA-in-the-loop (MAIL) framework that integrates a custom-designed MA into an emulation platform. This platform enables virtual execution by loading software onto the MCU, allowing observation of hardware-software interactions during ML execution. The proposed framework in this paper is a mixture of software that can emulate the environment in which general ML applications run on the MCU and RTL simulations to profile the acceleration on the MA. To evaluate the flow of ML software execution and performance changes according to the various architectures of MA in the framework, the MA can be reconfigured at runtime to explore the design space. To benchmark our proposed framework, we compared TinyML application profiles to the pure software execution. Experimental results show that the MA-accelerated framework performs comparably to actual MCUs, validating the efficacy of the proposed approach. ⓘ Kwon, Jisu; Park, Daejin ⓘ Kyungpook Natl Univ, Sch Elect & Elect Engn, Daegu 41566, South Korea ⓘ ⓘ 57215531728; 55463943600 ⓘ kjisu96@knu.ac.kr; boltanut@knu.ac.kr; ⓘ APPLIED SCIENCES-BASEL ⓘ APPL SCI-BASEL ⓘ 2076-3417 15 3 SCIE CHEMISTRY, MULTIDISCIPLINARY;ENGINEERING, MULTIDISCIPLINARY;MATERIALS SCIENCE, MULTIDISCIPLINARY;PHYSICS, APPLIED ⓘ 2024 2.5 28.3 0 2025-05-07 ⓘ 0 0 tiny machine learning; embedded system; microcontroller unit (MCU); accelerator; system emulator ⓘ HARDWARE ⓘ accelerator; embedded system; microcontroller unit (MCU); system emulator; tiny machine learning ⓘ Benchmarking; Hardware-in-the-loop simulation; Mice (computer peripherals); Microcontrollers; Bus interfaces; Embedded-system; Fast prototyping; Machine-learning; Microcontroller unit; On-chip bus; Software execution; System emulator; Tiny machine learning; Computer software selection and evaluation ⓘ English 2025 2025-02 10.3390/app15031056 ⓘ 바로가기 바로가기 바로가기 바로가기
○ ○ Article ⓘ Pharmacokinetics and Tissue Distribution of Enavogliflozin in Mice Using a Validated Liquid Chromatography-Tandem Mass Spectrometry Method ⓘ Enavogliflozin, a sodium-glucose cotransporter 2 inhibitor, was approved in 2022 by the Korean Ministry of Food and Drug Safety as a therapeutic agent for type 2 diabetes mellitus and has been investigated for expanded therapeutic efficacy in diabetic retinopathy and cardioprotection. In this study, we developed and validated an analytical method to precisely detect enavogliflozin in mouse plasma, employing liquid-liquid extraction combined with liquid chromatography-tandem mass spectrometry. Overall, the analytical method, covering a range of 5-3000 ng/mL, is reliable for investigating the time-concentration profiles of enavogliflozin, demonstrating acceptable accuracy, precision, extraction recovery, and minimal matrix effects without stability concerns as evidenced by assessments of post-treatment stability, freeze-thaw stability, and short-term stability of enavogliflozin. Pharmacokinetic profiles and all pharmacokinetic parameters of enavogliflozin in mice did not differ between fed and fasted states after oral administration of enavogliflozin (1 mg/kg). Additionally, no differences in the pharmacokinetic profiles of enavogliflozin were observed among single, 7-day repeated, and 14-day repeated oral administrations at 1 mg/kg. In the tissue distribution study, enavogliflozin showed the highest distribution in the kidneys, followed by the large intestine, stomach, small intestine, liver, heart, lungs, spleen, and testes after oral administration at both 1 and 3 mg/kg doses. Dose proportionality in tissue distribution was observed except for the kidneys. In conclusion, enavogliflozin can be administered without concern for pharmacokinetic changes, regardless of single or multiple dosing and whether in fed or fasted states. Furthermore, the tissue distribution profile may offer valuable insights into the therapeutic potential of this drug. ⓘ Pang, Minyeong; Lee, Jihoon; Choi, Min-Koo; Song, Im-Sook ⓘ Dankook Univ, Coll Pharm, Cheonan 31116, South Korea; Kyungpook Natl Univ, BK21 FOUR Community Based Intelligent Novel Drug, Vessel Organ Interact Res Ctr VOICE, Inst Pharmaceut Sci,Coll Pharm & Res, Daegu 41566, South Korea ⓘ ⓘ 57488599500; 57195979045; 8695781400; 7201564500 ⓘ mignon@dankook.ac.kr; legadema0905@naver.com; minkoochoi@dankook.ac.kr; isssong@knu.ac.kr; ⓘ APPLIED SCIENCES-BASEL ⓘ APPL SCI-BASEL ⓘ 2076-3417 15 3 SCIE CHEMISTRY, MULTIDISCIPLINARY;ENGINEERING, MULTIDISCIPLINARY;MATERIALS SCIENCE, MULTIDISCIPLINARY;PHYSICS, APPLIED ⓘ 2024 2.5 28.3 0 2025-05-07 ⓘ 0 0 enavogliflozin; SGLT2 inhibitor; LC-MS/MS; analytical validation; pharmacokinetics; tissue distribution ⓘ GLUCOSE COTRANSPORTER 2; INHIBITORS ⓘ analytical validation; enavogliflozin; LC-MS/MS; pharmacokinetics; SGLT2 inhibitor; tissue distribution ⓘ Pharmacokinetics; Analytical method; Analytical validation; Enavogliflozin; LC-MS-MS; Lc.ms/ms; Liquid chromatography-tandem mass spectrometry; Liquid chromatography/tandem mass spectrometry; Oral administration; SGLT2 inhibitor; Tissue distributions; Liquid chromatography ⓘ English 2025 2025-02 10.3390/app15031445 ⓘ 바로가기 바로가기 바로가기 바로가기
페이지 이동: