期刊,IEEE Access 2025年13卷1期_国家学术搜索

Editorial Board

xi-xix页

查看更多>>摘要：Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.

原文链接:

NETL
NSTL

IEEE Access™ Editorial Board

i-x页

查看更多>>摘要：Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.

原文链接:

NETL
NSTL

MVS-GS: High-Quality 3D Gaussian Splatting Mapping via Online Multi-View Stereo

Byeonggwon LeeJunkyu ParkKhang Truong GiangSungho Jo...

1-13页

查看更多>>摘要：This study addresses the challenge of online 3D model generation for neural rendering using an RGB image stream. Previous research has tackled this issue by incorporating Neural Radiance Fields (NeRF) or 3D Gaussian Splatting (3DGS) as scene representations within dense SLAM methods. However, most studies focus primarily on estimating coarse 3D scenes rather than achieving detailed reconstructions. Moreover, depth estimation based solely on images is often ambiguous, resulting in low-quality 3D models that lead to inaccurate renderings. To overcome these limitations, we propose a novel framework for high-quality 3DGS modeling that leverages an online multi-view stereo (MVS) approach. Our method estimates MVS depth using sequential frames from a local time window and applies comprehensive depth refinement techniques to filter out outliers. The refinement method produces temporally consistent depths by checking sequential geometric consistency, enabling accurate initialization of Gaussians in 3DGS. Furthermore, we introduce a parallelized backend module that optimizes the 3DGS model efficiently, ensuring timely updates with each new keyframe. Experimental results demonstrate that our method outperforms state-of-the-art dense SLAM methods, achieving an average PSNR improvement of approximately 2 dB on indoor scenes. Moreover, our method reliably produces consistent 3D models in complex outdoor scenes, where existing methods often fail due to tracking errors and depth noise. It also reconstructs large-scale aerial scenes effectively, achieving an average PSNR gain of about 10.28 dB over existing methods.

原文链接:

NETL
NSTL

MVS-GS: High-Quality 3D Gaussian Splatting Mapping via Online Multi-View Stereo

Byeonggwon LeeJunkyu ParkKhang Truong GiangSungho Jo...

1-13页

查看更多>>摘要：This study addresses the challenge of online 3D model generation for neural rendering using an RGB image stream. Previous research has tackled this issue by incorporating Neural Radiance Fields (NeRF) or 3D Gaussian Splatting (3DGS) as scene representations within dense SLAM methods. However, most studies focus primarily on estimating coarse 3D scenes rather than achieving detailed reconstructions. Moreover, depth estimation based solely on images is often ambiguous, resulting in low-quality 3D models that lead to inaccurate renderings. To overcome these limitations, we propose a novel framework for high-quality 3DGS modeling that leverages an online multi-view stereo (MVS) approach. Our method estimates MVS depth using sequential frames from a local time window and applies comprehensive depth refinement techniques to filter out outliers. The refinement method produces temporally consistent depths by checking sequential geometric consistency, enabling accurate initialization of Gaussians in 3DGS. Furthermore, we introduce a parallelized backend module that optimizes the 3DGS model efficiently, ensuring timely updates with each new keyframe. Experimental results demonstrate that our method outperforms state-of-the-art dense SLAM methods, achieving an average PSNR improvement of approximately 2 dB on indoor scenes. Moreover, our method reliably produces consistent 3D models in complex outdoor scenes, where existing methods often fail due to tracking errors and depth noise. It also reconstructs large-scale aerial scenes effectively, achieving an average PSNR gain of about 10.28 dB over existing methods.

原文链接:

NETL
NSTL

Retentive Time Series: A Scalable Machine Learning Model for Traffic Prediction in Elastic Optical Networks

Faranak KhosraviMehdi Shadaram

1-17页

查看更多>>摘要：Accurate traffic prediction is crucial for elastic optical networks (EONs) as it improves network scalability, performance, and operational efficiency. High accuracy is fundamental for performing long-term traffic management and network planning, while time-sensitive predictions allow efficient real-time adaptability. In this study, we propose a new RNN-based model, retentive time series (Ret-TS), which overcomes some of the limitations of traditional RNNs in EONs scenarios. Compared to RNNs, which successively consider data and always suffer from problematic vanishing gradients, Ret-TS can handle long-term dependencies efficiently through parallel computation; hence, it is more suitable for large-scale and real-time applications. In contrast to the Transformer models, Ret-TS is computationally more efficient, with a lower time and memory complexity of $O(L)$ , making it more suitable for resource-limited devices. This research demonstrates that Ret-TS is robust for both short- and long-term traffic forecasting with better prediction accuracy and computational efficiency than traditional models based on RNNs and Transformers. Extensive simulations performed on traffic datasets have shown that Ret-TS reduces prediction errors and network blocking probabilities under different traffic loads in three network topologies: NSFNET, Janos-US, and US100. The results confirm Ret-TS’s robustness and scalability, making it an effective solution for real-world applications in modern optical networks, including both telecommunications and data center networks.

原文链接:

NETL
NSTL

SafeRespirator: Comprehensive Database for N95 Filtering Facepiece Respirator Leakage Detection Including Infrared, RGB Videos, and Quantitative Fit Testing

Geoffrey MarchaisMohamed ArbaneBarthelemy TopilkoJean Brousseau...

1-12页

查看更多>>摘要：The COVID-19 pandemic underscored the challenges of performing mandatory Quantitative Fit Tests (QNFT) for healthcare professionals and the limitations of self-administered fit checks. To address this, it is crucial to develop faster and more efficient methods for detecting, locating, and quantifying Filtering Facepiece Respirators (FFRs) leakage, providing wearers with immediate feedback on their safety. Infrared (IR) technology, which relies on temperature variation analysis around the face seal, has proven effective for locating leakage but has not yet achieved automated quantification. This paper introduces a validated protocol for creating a comprehensive database to advance automatic leakage detection. The database includes synchronized and calibrated IR and RGB video data, along with QNFT results, collected from 62 participants wearing four different N95 FFR models in four distinct positions. High-performance IR and RGB cameras were used to precisely capture temperature variations, while a PortaCount® instrument served as the reference for fit quantification. Preliminary results using the MediaPipe approach with synchronized and calibrated RGB and IR videos demonstrate that precise tracking of the human face is achievable even with an FFR. The normalized cross-correlation methods further highlight the capability of IR imaging to accurately monitor and detect leakage. This breakthrough paves the way for real-time, automated detection of N95 FFR leakage, potentially deployable at operator workstations. This large, high-quality, open-access database is available to the scientific community to drive innovation in respiratory protection research and beyond.

原文链接:

NETL
NSTL
IEEE

Balancing Profit and Cultural Heritage: Multi-Objective Dynamic Pricing for Hanfu Using Deep Deterministic Policy Gradient

Qingcong ZhaoGuanghui MaoShen Wang

1-15页

查看更多>>摘要：Dynamic pricing is a critical strategy in e-commerce, enabling merchants to optimize sales profit while adapting to varying market conditions. However, existing approaches often fall short in balancing commercial objectives with the preservation of cultural heritage, particularly in niche markets like Hanfu apparel. To address this challenge, we developed a dynamic pricing simulation environment based on a Markov Decision Process (MDP) and introduced a novel multi-objective hybrid particle swarm optimization algorithm combined with Deep Deterministic Policy Gradient (DDPG), referred to as MOHPSO-DDPG. By applying principal component analysis (PCA) to consumer preference data and constructing utility functions and Logit choice models, we accurately simulated consumer behavior. MOHPSO-DDPG, Multi-Objective Particle Swarm Optimization (MOPSO), and Multi-Objective Hybrid Particle Swarm Optimization (MOHPSO) were each deployed to interact with the environment to explore the Pareto front of pricing decisions. Experimental results demonstrate that MOHPSO-DDPG significantly outperforms other algorithms in terms of solution diversity and convergence efficiency. After 3,000 iterations, its Generation Distance (GD) reached 0.023 and the Diversity Metric $\Delta $ was 0.594, whereas GD and Diversity Metric $\Delta $ values remained larger for MOPSO and MOHPSO. Moreover, MOHPSO-DDPG continued to maintain a leading position in later iterations, underscoring its superiority in identifying comprehensive and near-optimal Pareto fronts. These findings validate that MOHPSO-DDPG provides an efficient multi-objective dynamic pricing decision-making framework for the Hanfu market, effectively balancing profit maximization with the demands of cultural heritage preservation.

原文链接:

NETL
NSTL
IEEE

Optimized Identification of Sentence-Level Multiclass Events on Urdu-Language-Text Using Machine Learning Techniques

Somia AliUzma JamilMuhammad YounasBushra Zafar...

1-25页

查看更多>>摘要：In today’s digital world, social media platforms generate a plethora of unstructured information. However, for low-resource languages like Urdu, there is a scarcity of well-structured data for specific tasks such as event classification. Urdu, a language prominent in South Asia, has boasted a complex morphological structure with unique features but has lacked standard linguistic resources like datasets. Long-text classification has demanded more effort than short-text classification due to its expansive vocabulary, information redundancy, and noise. Text processing has been the latest trend in research, with many machine learning and deep learning techniques widely used for it. Multiclass classification has been utilized to classify different languages for various purposes. In this research, a multiclass classification for the Urdu language was performed using a text dataset taken from five different social media platforms including Geo News, Samaa News, Dawn News, Express News, and Urdu Blogs totaling 103,771 sentences. We used sentence-level classification to categorize sentences including terrorist attacks, national news, sports, entertainment, politics, safety, earthquakes, fraud and corruption, sexual assault, weather, accidents, forces, inflation, murder and death, education, and international news. Deep learning, transformer-based and machine learning classifiers are used for event classification. The SMFCNN classifier achieved the greatest accuracy of 88.29%. We incorporated transformer-based models, with the proposed XLM-R+ model demonstrating superior performance with an accuracy of 89.8%. Our results were compared to previously reported techniques that used traditional models, highlighting the significant improvements offered by our approaches. The novelty of this research lies in the inclusion of 16 event categories to broaden coverage and the implementation of the SMFCNN and transformer-based algorithms. This study highlights the potential of deep learning and transformer-based models in enhancing the accuracy and generalizability of multiclass classification in low-resource languages Urdu.

原文链接:

NETL
NSTL
IEEE

Dual-Band Absorptive Bandpass Filters Using a Dual-Behavior Matching Section

Young-Ho ChoCheolsoo Park

1-6页

查看更多>>摘要：This study introduces a dual-band absorptive bandpass filter that employs a dual-behavior matching section. The proposed design utilizes a filter methodology based on a low-pass filter prototype, enabling the development of higher-order distributed dual-band absorptive bandpass filters with the control of two center frequencies and bandwidths. The proposed filter requires fewer resonators than the existing dual-band absorptive filters owing to the dual-band matching section design based on an image parameter method. The proposed configuration is implemented to design and fabricate two filter prototypes with center frequencies of 1.3 GHz and 1.6 GHz on a substrate characterized by a relative permittivity $\varepsilon _{\mathrm {r}}=3.42$ and a thickness $h=30$ mil. The first filter (two-pole configuration) demonstrated a measured return loss exceeding 11.3 dB at 0.8–2.2 GHz, and the second filter with three-pole exhibited a measured return loss exceeding 10.2 dB at 0.8–2.2 GHz. These dual-band absorptive bandpass filters are suitable for application in cognitive radio and carrier aggregation systems.

原文链接:

NETL
NSTL
IEEE