Presents corrections to the paper, Corrections to “Design of Compact Dual-Band Eighth-Mode SIW Antenna for On-Body ISM Band Application”.
{"title":"Corrections to “Design of Compact Dual-Band Eighth-Mode SIW Antenna for On-Body ISM Band Application”","authors":"Muthukumara Rajaguru Kattiakara Muni Samy;Abhishek Gudipalli","doi":"10.1109/ACCESS.2025.3546694","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3546694","url":null,"abstract":"Presents corrections to the paper, Corrections to “Design of Compact Dual-Band Eighth-Mode SIW Antenna for On-Body ISM Band Application”.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"39033-39034"},"PeriodicalIF":3.4,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10916531","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143564076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Quality of 3D point cloud maps is essential for navigation and localization in Autonomous Mobile Robots, yet creating these maps for large-scale areas presents challenges, stemming from the processing of numerous points. In such situations, constructing a 3D map can be accomplished by dividing it into smaller regions and then merging them to generate a complete map by performing a 3D map stitching algorithm. Currently, these overlapping areas are manually selected, which leads to potential errors. In response, a novel method to automatically identify overlapping areas is proposed to perform map stitching based on the overlapping areas only instead of the entire maps. Utilizing the proposed method results in a significant reduction in time consumption. The proposed automatic method incorporates the DBSCAN algorithm for clustering, template matching for identifying corresponding clusters, and a binary-search algorithm for parameter optimization. The proposed method was evaluated on several large-scale 3D maps, including the KITTI dataset, and compared against manual selection and the use of entire maps in the map-merge-3D algorithm. The method achieves a significant reduction in the time required for the 3D map stitching process, amounting to a 38.64% decrease compared to using the entire maps. In terms of accuracy, the proposed method reduces translation error to 0.1723m and rotation error to 0.1763°, representing decreases of 5.28% and 16.16%, respectively, while manual selection results in a translation error of 0.4278m and rotation error of 0.7123°, increases of 135.25% and 238.75% respectively, compared to the entire maps 0.1819m and 0.2103°.
{"title":"An Efficient Large-Scale 3D Map Stitching Algorithm Using Automatic Overlapping Area Identification","authors":"Hsien-I Lin;Muhammad Ahsan Fatwaddin Shodiq;An-Kai Jeng;Chun-Wei Chang","doi":"10.1109/ACCESS.2025.3548859","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548859","url":null,"abstract":"Quality of 3D point cloud maps is essential for navigation and localization in Autonomous Mobile Robots, yet creating these maps for large-scale areas presents challenges, stemming from the processing of numerous points. In such situations, constructing a 3D map can be accomplished by dividing it into smaller regions and then merging them to generate a complete map by performing a 3D map stitching algorithm. Currently, these overlapping areas are manually selected, which leads to potential errors. In response, a novel method to automatically identify overlapping areas is proposed to perform map stitching based on the overlapping areas only instead of the entire maps. Utilizing the proposed method results in a significant reduction in time consumption. The proposed automatic method incorporates the DBSCAN algorithm for clustering, template matching for identifying corresponding clusters, and a binary-search algorithm for parameter optimization. The proposed method was evaluated on several large-scale 3D maps, including the KITTI dataset, and compared against manual selection and the use of entire maps in the map-merge-3D algorithm. The method achieves a significant reduction in the time required for the 3D map stitching process, amounting to a 38.64% decrease compared to using the entire maps. In terms of accuracy, the proposed method reduces translation error to 0.1723m and rotation error to 0.1763°, representing decreases of 5.28% and 16.16%, respectively, while manual selection results in a translation error of 0.4278m and rotation error of 0.7123°, increases of 135.25% and 238.75% respectively, compared to the entire maps 0.1819m and 0.2103°.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"42587-42607"},"PeriodicalIF":3.4,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10915654","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-06DOI: 10.1109/ACCESS.2025.3548974
Min-Seong Kim;Dong-Hwan Park;Mohamed Elhefnawy;Wang-Sang Lee
In this paper, a rectenna array system using decoupling slots with a defected ground structure (DGS) is proposed to improve received power in wireless power transfer (WPT) applications. The proposed rectenna array features a $4times 4$ configuration with an antenna spacing of $lambda _{0}/3$ and introduces decoupling slots based on a meander line DGS structure between the H-plane arrays. The proposed rectenna array operates at 5.8 GHz and has dimensions of $78times 78times 0.76$ mm3. The rectenna array achieves miniaturization, enhanced gain, and the ability to receive power regardless of the antenna polarization, through the high isolation formed by the decoupling slots. For performance validation, the operating principle of the proposed rectenna array system was theoretically analyzed and simulated. Additionally, the received power was measured based on the polarization of the transmitting antenna, and the results were compared with a conventional rectenna array and a proposed rectenna array without decoupling slots, both with the same area. The measurements show that the rectenna array with decoupling slots improves the power reception in environments with polarization mismatch, compared to the conventional rectenna arrays.
{"title":"Densely Placed Rectenna Array With Decoupling Slots for Enhanced Received Power in Far-Field Wireless Power Transfer","authors":"Min-Seong Kim;Dong-Hwan Park;Mohamed Elhefnawy;Wang-Sang Lee","doi":"10.1109/ACCESS.2025.3548974","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548974","url":null,"abstract":"In this paper, a rectenna array system using decoupling slots with a defected ground structure (DGS) is proposed to improve received power in wireless power transfer (WPT) applications. The proposed rectenna array features a <inline-formula> <tex-math>$4times 4$ </tex-math></inline-formula> configuration with an antenna spacing of <inline-formula> <tex-math>$lambda _{0}/3$ </tex-math></inline-formula> and introduces decoupling slots based on a meander line DGS structure between the H-plane arrays. The proposed rectenna array operates at 5.8 GHz and has dimensions of <inline-formula> <tex-math>$78times 78times 0.76$ </tex-math></inline-formula> mm3. The rectenna array achieves miniaturization, enhanced gain, and the ability to receive power regardless of the antenna polarization, through the high isolation formed by the decoupling slots. For performance validation, the operating principle of the proposed rectenna array system was theoretically analyzed and simulated. Additionally, the received power was measured based on the polarization of the transmitting antenna, and the results were compared with a conventional rectenna array and a proposed rectenna array without decoupling slots, both with the same area. The measurements show that the rectenna array with decoupling slots improves the power reception in environments with polarization mismatch, compared to the conventional rectenna arrays.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"43249-43258"},"PeriodicalIF":3.4,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10915655","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-06DOI: 10.1109/ACCESS.2025.3548875
Anh-Tuan Tran;Van Van Huynh;Jae Woong Shim;Chee Peng Lim
This paper proposes an adaptive-based single-phase higher-order sliding mode controller (SMC) optimized by the honey badger algorithm (HBA). The developed control method is employed for load frequency control (LFC) in electrical power systems (EPSs) that incorporates a battery energy storage system (BESS) with droop control. Unlike conventional SMCs, the proposed higher-order SMC eliminates the reaching phase by utilizing the second derivative of the sliding motion and embedding the sliding surface directly within the original system, significantly reducing oscillations and chattering effects. Furthermore, an adaptive mechanism dynamically estimates the unknown bound of system uncertainties, enabling real-time compensation and minimizing steady-state errors. The system’s global stability is rigorously analyzed through linear matrix inequality (LMI) and Lyapunov stability theory, highlighting the robustness and practicality of the proposed method. To further enhance the system performance, the HBA is employed to optimize controller parameters, providing a balance between fast response and low overshoot. Additionally, a coordinated BESS control strategy integrating droop control and state-of-charge management is introduced, enabling seamless interaction between the energy storage system and generators to mitigate large disturbances in uncertain EPSs. Finally, extensive case studies under various configurations and conditions demonstrate the superior performance of the proposed controller compared to other related methods. Simulation results consistently confirm that the proposed solution outperforms alternative approaches across all scenarios. This is demonstrated by the minimal over/undershoot value in frequency deviations: $1.913times 10^{-3}$ for the isolated EPS, $3.3134times 10^{-4}$ and $0.6476times 10^{-4}$ for two-area EPS equipped with ten BESS units. In the final case, the presence of BESS results in a significant reduction in peak value by approximately 22.9%, 16.5%, and 22.3% of each respective area of EPS.
{"title":"Optimized Sliding Mode Frequency Controller for Power Systems Integrated Energy Storage System With Droop Control","authors":"Anh-Tuan Tran;Van Van Huynh;Jae Woong Shim;Chee Peng Lim","doi":"10.1109/ACCESS.2025.3548875","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548875","url":null,"abstract":"This paper proposes an adaptive-based single-phase higher-order sliding mode controller (SMC) optimized by the honey badger algorithm (HBA). The developed control method is employed for load frequency control (LFC) in electrical power systems (EPSs) that incorporates a battery energy storage system (BESS) with droop control. Unlike conventional SMCs, the proposed higher-order SMC eliminates the reaching phase by utilizing the second derivative of the sliding motion and embedding the sliding surface directly within the original system, significantly reducing oscillations and chattering effects. Furthermore, an adaptive mechanism dynamically estimates the unknown bound of system uncertainties, enabling real-time compensation and minimizing steady-state errors. The system’s global stability is rigorously analyzed through linear matrix inequality (LMI) and Lyapunov stability theory, highlighting the robustness and practicality of the proposed method. To further enhance the system performance, the HBA is employed to optimize controller parameters, providing a balance between fast response and low overshoot. Additionally, a coordinated BESS control strategy integrating droop control and state-of-charge management is introduced, enabling seamless interaction between the energy storage system and generators to mitigate large disturbances in uncertain EPSs. Finally, extensive case studies under various configurations and conditions demonstrate the superior performance of the proposed controller compared to other related methods. Simulation results consistently confirm that the proposed solution outperforms alternative approaches across all scenarios. This is demonstrated by the minimal over/undershoot value in frequency deviations: <inline-formula> <tex-math>$1.913times 10^{-3}$ </tex-math></inline-formula> for the isolated EPS, <inline-formula> <tex-math>$3.3134times 10^{-4}$ </tex-math></inline-formula> and <inline-formula> <tex-math>$0.6476times 10^{-4}$ </tex-math></inline-formula> for two-area EPS equipped with ten BESS units. In the final case, the presence of BESS results in a significant reduction in peak value by approximately 22.9%, 16.5%, and 22.3% of each respective area of EPS.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"43749-43766"},"PeriodicalIF":3.4,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10915636","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-06DOI: 10.1109/ACCESS.2025.3549377
Xiangyang Cao;Yaojie Zheng;Hanbin Xiao;Min Xiao
To enhance the multi-target path planning and tracking performance of Unmanned Surface Vehicles (USVs), a combined control strategy integrating the Serret-Frenet Line-of-Sight (SFLOS) algorithm and an incremental PID controller is proposed to achieve precise path tracking in complex environments. Additionally, a novel finite-time observer is presented to compensate for the sideslip angle caused by environmental disturbances in real time. The heading controller of the USV is designed using incremental PID control, and an improved Particle Swarm Optimization (PSO) algorithm is proposed to optimize the PID parameters. The stability and effectiveness of the proposed method are validated through simulations. Furthermore, a USV equipped with a crane-assisted experimental platform is constructed to conduct verification experiments for course control, guidance law, and planned path tracking control. Both simulation and real-world tests demonstrate the effectiveness and feasibility of the proposed approach.
{"title":"Multi-Target Point Path Planning and Tracking of Unmanned Surface Vehicle Using SFLOS Algorithm and Incremental PID Control With Crane-Assisted","authors":"Xiangyang Cao;Yaojie Zheng;Hanbin Xiao;Min Xiao","doi":"10.1109/ACCESS.2025.3549377","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3549377","url":null,"abstract":"To enhance the multi-target path planning and tracking performance of Unmanned Surface Vehicles (USVs), a combined control strategy integrating the Serret-Frenet Line-of-Sight (SFLOS) algorithm and an incremental PID controller is proposed to achieve precise path tracking in complex environments. Additionally, a novel finite-time observer is presented to compensate for the sideslip angle caused by environmental disturbances in real time. The heading controller of the USV is designed using incremental PID control, and an improved Particle Swarm Optimization (PSO) algorithm is proposed to optimize the PID parameters. The stability and effectiveness of the proposed method are validated through simulations. Furthermore, a USV equipped with a crane-assisted experimental platform is constructed to conduct verification experiments for course control, guidance law, and planned path tracking control. Both simulation and real-world tests demonstrate the effectiveness and feasibility of the proposed approach.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"44620-44635"},"PeriodicalIF":3.4,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10916642","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bearing fault diagnosis is essential for ensuring the reliable and stable operation of mechanical equipment. While Convolutional Neural Networks (CNNs) have demonstrated significant advancements in fault diagnosis, challenges such as varying operational conditions and feature extraction complexity persist. This paper introduces an innovative method that synergistically combines multiple CNN architectures to enhance the accuracy and robustness of bearing fault diagnosis. Specifically, we design five distinct convolutional network structures: SerConv, ResConv, One-Shot Aggregation Convolution (OSAConv), Cross-Stage Aggregation Convolution (CSAConv), and Multi-Domain Dual-Aggregation Convolution (MD-DAConv). These architectures integrate multi-directional, multi-scale, and residual connections to optimize feature extraction depth and breadth. Furthermore, we implement advanced feature fusion and information transmission mechanisms to bolster the model’s generalization and resilience against data variability. Experimental results on the Case Western Reserve University (CWRU) bearing dataset and SJTU-SY bearing fault diagnosis dataset demonstrate that the proposed method significantly outperforms existing approaches, achieving higher diagnostic accuracy and enhanced robustness. The findings highlight the critical role of architectural diversity and effective feature integration in advancing bearing fault diagnosis, offering a comprehensive solution to current limitations in the field.
{"title":"Research on Bearing Fault Diagnosis Methods Based on Various Convolutional Neural Network Architectures","authors":"Mingshen Xu;Po Guan;Xinyu Shi;Runji Jiang;Jingjia Tian;Jianghai Geng;Gaoxian Xiong","doi":"10.1109/ACCESS.2025.3548693","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548693","url":null,"abstract":"Bearing fault diagnosis is essential for ensuring the reliable and stable operation of mechanical equipment. While Convolutional Neural Networks (CNNs) have demonstrated significant advancements in fault diagnosis, challenges such as varying operational conditions and feature extraction complexity persist. This paper introduces an innovative method that synergistically combines multiple CNN architectures to enhance the accuracy and robustness of bearing fault diagnosis. Specifically, we design five distinct convolutional network structures: SerConv, ResConv, One-Shot Aggregation Convolution (OSAConv), Cross-Stage Aggregation Convolution (CSAConv), and Multi-Domain Dual-Aggregation Convolution (MD-DAConv). These architectures integrate multi-directional, multi-scale, and residual connections to optimize feature extraction depth and breadth. Furthermore, we implement advanced feature fusion and information transmission mechanisms to bolster the model’s generalization and resilience against data variability. Experimental results on the Case Western Reserve University (CWRU) bearing dataset and SJTU-SY bearing fault diagnosis dataset demonstrate that the proposed method significantly outperforms existing approaches, achieving higher diagnostic accuracy and enhanced robustness. The findings highlight the critical role of architectural diversity and effective feature integration in advancing bearing fault diagnosis, offering a comprehensive solution to current limitations in the field.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"44445-44465"},"PeriodicalIF":3.4,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10915663","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-06DOI: 10.1109/ACCESS.2025.3549279
Abol Basher;Jani Boutellier
Learning 3D shape directly from raw data (i.e., un-oriented meshes, raw point clouds or triangle soups) and reconstructing high fidelity surfaces are still a difficult problem in computer vision and graphics. Several approaches have been proposed to learn from raw data, however, their reconstruction quality is somewhat limited in capturing small detail. Moreover, they introduce surface sheet in case of big gaps and empty spaces, and struggle in reconstructing small openings and thin structure. In this study, we address these problems by proposing a novel attention-based variational autoencoder architecture, ADR-SALD where the encoder and decoder are constructed based on the idea of residual feature learning and inception-like neural structure. We have adopted two different self attention mechanisms for sign agnostic learning in the encoder, which allow the proposed approach to learn the global spatial contextual dependencies and local features simultaneously for the 3D shape. This novel architecture solves the surface sheet problem of previous approaches such as SALD. Moreover, our experimental results show that ADR-SALD is more successful in reconstructing thin structure than the state-of-the-art approaches SALD and DC-DFFN, and has significant performance in separating small gaps. The proposed approach outperforms the baseline state-of-the-art approaches by reconstruction quality and quantitative measures.
{"title":"ADR-SALD: Attention-Based Deep Residual Sign Agnostic Learning With Derivatives for Implicit Surface Reconstruction","authors":"Abol Basher;Jani Boutellier","doi":"10.1109/ACCESS.2025.3549279","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3549279","url":null,"abstract":"Learning 3D shape directly from raw data (i.e., un-oriented meshes, raw point clouds or triangle soups) and reconstructing high fidelity surfaces are still a difficult problem in computer vision and graphics. Several approaches have been proposed to learn from raw data, however, their reconstruction quality is somewhat limited in capturing small detail. Moreover, they introduce surface sheet in case of big gaps and empty spaces, and struggle in reconstructing small openings and thin structure. In this study, we address these problems by proposing a novel attention-based variational autoencoder architecture, ADR-SALD where the encoder and decoder are constructed based on the idea of residual feature learning and inception-like neural structure. We have adopted two different self attention mechanisms for sign agnostic learning in the encoder, which allow the proposed approach to learn the global spatial contextual dependencies and local features simultaneously for the 3D shape. This novel architecture solves the surface sheet problem of previous approaches such as SALD. Moreover, our experimental results show that ADR-SALD is more successful in reconstructing thin structure than the state-of-the-art approaches SALD and DC-DFFN, and has significant performance in separating small gaps. The proposed approach outperforms the baseline state-of-the-art approaches by reconstruction quality and quantitative measures.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"44243-44259"},"PeriodicalIF":3.4,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10916624","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-06DOI: 10.1109/ACCESS.2025.3549316
André F. R. Guarda;Nuno M. M. Rodrigues;Fernando Pereira
Efficient point cloud coding has become increasingly critical for multiple applications such as virtual reality, autonomous driving, and digital twin systems, where rich and interactive 3D data representations may functionally make the difference. Deep learning has emerged as a powerful tool in this domain, offering advanced techniques for compressing point clouds more efficiently than conventional coding methods while also allowing effective computer vision tasks performed in the compressed domain thus, for the first time, making available a common compressed visual representation effective for both man and machine. Taking advantage of this potential, JPEG has recently finalized the JPEG Pleno Learning-based Point Cloud Coding (PCC) standard offering efficient lossy coding of static point clouds, targeting both human visualization and machine processing by leveraging deep learning models for geometry and color coding. The geometry is processed directly in its original 3D form using sparse convolutional neural networks, while the color data is projected onto 2D images and encoded using the also learning-based JPEG AI standard. The goal of this paper is to provide a complete technical description of the JPEG PCC standard, along with a thorough benchmarking of its performance against the state-of-the-art, while highlighting its main strengths and weaknesses. In terms of compression performance, JPEG PCC outperforms the conventional MPEG PCC standards, especially in geometry coding, achieving significant rate reductions. Color compression performance is less competitive but this is overcome by the power of a full learning-based coding framework for both geometry and color and the associated effective compressed domain processing.
{"title":"The JPEG Pleno Learning-Based Point Cloud Coding Standard: Serving Man and Machine","authors":"André F. R. Guarda;Nuno M. M. Rodrigues;Fernando Pereira","doi":"10.1109/ACCESS.2025.3549316","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3549316","url":null,"abstract":"Efficient point cloud coding has become increasingly critical for multiple applications such as virtual reality, autonomous driving, and digital twin systems, where rich and interactive 3D data representations may functionally make the difference. Deep learning has emerged as a powerful tool in this domain, offering advanced techniques for compressing point clouds more efficiently than conventional coding methods while also allowing effective computer vision tasks performed in the compressed domain thus, for the first time, making available a common compressed visual representation effective for both man and machine. Taking advantage of this potential, JPEG has recently finalized the JPEG Pleno Learning-based Point Cloud Coding (PCC) standard offering efficient lossy coding of static point clouds, targeting both human visualization and machine processing by leveraging deep learning models for geometry and color coding. The geometry is processed directly in its original 3D form using sparse convolutional neural networks, while the color data is projected onto 2D images and encoded using the also learning-based JPEG AI standard. The goal of this paper is to provide a complete technical description of the JPEG PCC standard, along with a thorough benchmarking of its performance against the state-of-the-art, while highlighting its main strengths and weaknesses. In terms of compression performance, JPEG PCC outperforms the conventional MPEG PCC standards, especially in geometry coding, achieving significant rate reductions. Color compression performance is less competitive but this is overcome by the power of a full learning-based coding framework for both geometry and color and the associated effective compressed domain processing.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"43289-43315"},"PeriodicalIF":3.4,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10916627","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-06DOI: 10.1109/ACCESS.2025.3548720
Mengya Liu;Xu Cheng;Yu Cao;Qian Zhou
Remaining shelf-life prediction of blueberries is crucial in reducing economic losses and enhancing market competitiveness. To meet the demand for high accuracy in predicting the remaining shelf-life of blueberries, this paper proposes a fusion model (PSO-CNN-BiLSTM-MHA) that combines Particle Swarm Optimization (PSO), Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory network (BiLSTM), and Multi-Head Attention (MHA) mechanisms for predicting the remaining shelf-life of ‘Emerald’ blueberries under two temperature conditions, $4^{circ } text {C}$ and $25^{circ } text {C}$ . In this study, seven key features were selected from fifteen quality indicators of blueberries using the embedded method, and the PSO algorithm was used to determine the optimal hyperparameter combination of the model, which effectively improved its prediction performance. The experimental results show that our model outperforms other models in all evaluation metrics under both temperature conditions and demonstrates excellent prediction ability and stability. This study provides an effective technical approach for the accurate prediction of the remaining shelf-life of blueberries and other fruits.
{"title":"Blueberry Remaining Shelf-Life Prediction Based on the PSO-CNN-BiLSTM-MHA Model","authors":"Mengya Liu;Xu Cheng;Yu Cao;Qian Zhou","doi":"10.1109/ACCESS.2025.3548720","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548720","url":null,"abstract":"Remaining shelf-life prediction of blueberries is crucial in reducing economic losses and enhancing market competitiveness. To meet the demand for high accuracy in predicting the remaining shelf-life of blueberries, this paper proposes a fusion model (PSO-CNN-BiLSTM-MHA) that combines Particle Swarm Optimization (PSO), Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory network (BiLSTM), and Multi-Head Attention (MHA) mechanisms for predicting the remaining shelf-life of ‘Emerald’ blueberries under two temperature conditions, <inline-formula> <tex-math>$4^{circ } text {C}$ </tex-math></inline-formula> and <inline-formula> <tex-math>$25^{circ } text {C}$ </tex-math></inline-formula>. In this study, seven key features were selected from fifteen quality indicators of blueberries using the embedded method, and the PSO algorithm was used to determine the optimal hyperparameter combination of the model, which effectively improved its prediction performance. The experimental results show that our model outperforms other models in all evaluation metrics under both temperature conditions and demonstrates excellent prediction ability and stability. This study provides an effective technical approach for the accurate prediction of the remaining shelf-life of blueberries and other fruits.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"43238-43248"},"PeriodicalIF":3.4,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10915596","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-06DOI: 10.1109/ACCESS.2025.3548631
Felipe Ramos;Alexandre Costa;Mirko Perkusich;Luiz Silva;Dalton Valadares;Ademar de Sousa Neto;Felipe Cunha;Hyggo Almeida;Angelo Perkusich
Context: Agile software development, particularly Scrum, enables teams to manage evolving requirements by emphasizing face-to-face communication and incremental deliveries. Although effective in addressing functional requirements, agile methods often overlook non-functional requirements during the initial stages of software projects, potentially leading to cost overruns on software and hardware and project failures exceeding 60%. Objective: In this article, we introduce a data-driven recommendation system to assist Scrum teams in eliciting NFRs effectively and early in the development lifecycle. Method: Our proposed solution applies the k-nearest neighbors algorithm to recommend non-functional requirements by leveraging historical project data structured through a taxonomy of user stories. We evaluated the system through offline experiments under the cross-validation protocol, utilizing datasets from 13 real-world projects. Results: Our recommendation system achieved an F-measure of up to 79%, demonstrating its ability to provide accurate and context-aware non-functional requirements suggestions. Conclusion: These findings suggest that our solution supports agile teams by automating non-functional requirement elicitation and enhancing decision-making processes, thereby addressing critical gaps in non-functional requirement integration within Scrum-based projects.
{"title":"A Data-Driven Recommendation System for Enhancing Non-Functional Requirements Elicitation in Scrum-Based Projects","authors":"Felipe Ramos;Alexandre Costa;Mirko Perkusich;Luiz Silva;Dalton Valadares;Ademar de Sousa Neto;Felipe Cunha;Hyggo Almeida;Angelo Perkusich","doi":"10.1109/ACCESS.2025.3548631","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548631","url":null,"abstract":"<bold>Context:</b> Agile software development, particularly Scrum, enables teams to manage evolving requirements by emphasizing face-to-face communication and incremental deliveries. Although effective in addressing functional requirements, agile methods often overlook non-functional requirements during the initial stages of software projects, potentially leading to cost overruns on software and hardware and project failures exceeding 60%. <bold>Objective:</b> In this article, we introduce a data-driven recommendation system to assist Scrum teams in eliciting NFRs effectively and early in the development lifecycle. <bold>Method:</b> Our proposed solution applies the k-nearest neighbors algorithm to recommend non-functional requirements by leveraging historical project data structured through a taxonomy of user stories. We evaluated the system through offline experiments under the cross-validation protocol, utilizing datasets from 13 real-world projects. <bold>Results:</b> Our recommendation system achieved an F-measure of up to 79%, demonstrating its ability to provide accurate and context-aware non-functional requirements suggestions. <bold>Conclusion:</b> These findings suggest that our solution supports agile teams by automating non-functional requirement elicitation and enhancing decision-making processes, thereby addressing critical gaps in non-functional requirement integration within Scrum-based projects.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"44000-44023"},"PeriodicalIF":3.4,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10915619","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}