IEEE Access最新文献_第10页

Height-Adaptive Deformable Multi-Modal Fusion for 3D Object Detection

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-03-21 DOI: 10.1109/ACCESS.2025.3553372

Jiahao Li;Lingshan Chen;Zhen Li

{"title":"Height-Adaptive Deformable Multi-Modal Fusion for 3D Object Detection","authors":"Jiahao Li;Lingshan Chen;Zhen Li","doi":"10.1109/ACCESS.2025.3553372","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3553372","url":null,"abstract":"LiDAR-Camera fusion has demonstrated remarkable potential in 3D object detection for autonomous vehicles, leveraging complementary information from both modalities. Recent state-of-the-art approaches primarily make use of projection matrices to achieve cross-modal data alignment. However, these methods often struggle with poor performance when faced with sensor misalignment or calibration errors, resulting in suboptimal fusion quality and limited robustness. In this paper, we propose a novel framework for 3D object detection, called Height-Adaptive Deformable Multi-Modal Fusion, which leverages Deformable Attention to enhance the fusion process. Specifically, we introduce a Deformable-based Cross-Modal Spatial Attention that dynamically fuse image features through learnable offsets, allowing for more flexible and precise alignment between the LiDAR and camera modalities. To further improve the fusion quality, we design a Height-Adaptive Aggregation strategy that mitigates the risk of incorrect fusion from background points while emphasizing the aggregation of foreground object features. In addition, we introduce projection noise to simulate misalign scenarios. To tackle these issues, an extra supervision loss is added. Extensive experiments on the nuScenes benchmark demonstrate the effectiveness and robustness of our proposed framework. Specifically, our methods significantly outperforms the LiDAR-only method and exhibits reduced precision degradation under sensor misalignment, outperforming other fusion-based approaches. Our results validate the potential of proposed framework for improving 3D object detection accuracy, particularly in real-world, imperfect sensor environments.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"52385-52396"},"PeriodicalIF":3.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10935618","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740382","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}

引用次数: 0

A Low-Cost Environment-Interactive Patrol Inspection System With Navigation Based on Sensor-Fusion and Robotic Arm Contact Pose Feedback

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-03-21 DOI: 10.1109/ACCESS.2025.3553521

Zhesheng Zhang;Long Chen

{"title":"A Low-Cost Environment-Interactive Patrol Inspection System With Navigation Based on Sensor-Fusion and Robotic Arm Contact Pose Feedback","authors":"Zhesheng Zhang;Long Chen","doi":"10.1109/ACCESS.2025.3553521","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3553521","url":null,"abstract":"In this paper, we introduce a cost-effective mobile-robot-based patrol inspection system that navigates using sensor fusion and arm contact feedback, bypassing the need for 3D LiDAR, physical odometry, and external positioning systems. Our system utilizes a height-adjustable, four-wheel platform equipped with a 6-DOF robotic arm, achieving nine degrees of freedom with the platform’s height adjustability and planar movement. Within the Robot Operating System (ROS) framework, the system employs 2D LiDAR and a depth camera for SLAM-based mapping and pose estimation. The primary challenge during the implementation of this system is to obtain reliable pose updates of the mobile platform without physical odometry and a direct positioning source while maintaining affordability. To address this challenge, a lightweight deep neural network (DNN) object detection model is trained to identify the specific interactive items at checkpoints. By integrating a contact sensor and knowing the position of the button on the map, the acquisition of the pose of the end effector is achieved upon contact. This allows a precise update of the position of the mobile platform on the map through transforms. Experimental results indicate that our system can efficiently patrol designated routes, interact with the environment at checkpoints, and recalibrate pose using robotic arm feedback. In real-world evaluations, the system achieves a 24.35% improvement in positional accuracy and a 26.70% improvement in orientation accuracy, demonstrating its effectiveness and robustness.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"54547-54560"},"PeriodicalIF":3.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10937195","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748920","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}

引用次数: 0

Machine Learning-Based Differential Diagnosis of Parkinson’s Disease Using Kinematic Feature Extraction and Selection

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-03-21 DOI: 10.1109/ACCESS.2025.3553528

Masahiro Matsumoto;Abu Saleh Musa Miah;Nobuyoshi Asai;Jungpil Shin

{"title":"Machine Learning-Based Differential Diagnosis of Parkinson’s Disease Using Kinematic Feature Extraction and Selection","authors":"Masahiro Matsumoto;Abu Saleh Musa Miah;Nobuyoshi Asai;Jungpil Shin","doi":"10.1109/ACCESS.2025.3553528","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3553528","url":null,"abstract":"Parkinson’s disease (PD) is the second most common neurodegenerative disorder and is characterized by dopaminergic neuron loss and the accumulation of abnormal synuclein. PD presents both motor and non-motor symptoms that progressively impair daily functioning. The severity of these symptoms is typically assessed using the MDS-UPDRS rating scale, which is subjective and dependent on the physician’s experience. Additionally, PD shares symptoms with other neurodegenerative diseases, such as progressive supranuclear palsy (PSP) and multiple system atrophy (MSA), complicating accurate diagnosis. We propose a machine learning-based system for differential diagnosis of PD, PSP, MSA, and healthy controls (HC) to address these diagnostic challenges. This system utilizes a kinematic feature-based hierarchical feature extraction and selection approach. Initially, 18 kinematic features are extracted, including two newly proposed features: Thumb-to-index vector velocity and acceleration, which provide insights into motor control patterns. In addition, 41 statistical features were extracted here from each kinematic feature, including some new approaches such as Average Absolute Change, Rhythm, Amplitude, Frequency, Standard Deviation of Frequency, and Slope. Feature selection is performed using One-way ANOVA to rank features, followed by Sequential Forward Floating Selection (SFFS) to identify the most relevant ones, aiming to reduce the computational complexity. The final feature set is used for classification, achieving a classification accuracy of 66.67% for each dataset and 88.89% for each patient, with particularly high performance for the MSA and HC groups using the SVM algorithm. This system shows potential as a rapid and accurate diagnostic tool in clinical practice, though further data collection and refinement are needed to enhance its reliability.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"54090-54104"},"PeriodicalIF":3.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10937116","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748831","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}

引用次数: 0

Phase Code Integration Using Interpulse Techniques for Enhanced Radar Performance

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-03-21 DOI: 10.1109/ACCESS.2025.3553308

Basmah Ahmad;Faran Awais Butt;Ijaz Haider Naqvi;Saqib Ejaz;Saqib Ali;Ali Hussein Muqaibel;Saleh A. Alawsh;Muhammad Arif Anwar

{"title":"Phase Code Integration Using Interpulse Techniques for Enhanced Radar Performance","authors":"Basmah Ahmad;Faran Awais Butt;Ijaz Haider Naqvi;Saqib Ejaz;Saqib Ali;Ali Hussein Muqaibel;Saleh A. Alawsh;Muhammad Arif Anwar","doi":"10.1109/ACCESS.2025.3553308","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3553308","url":null,"abstract":"Phase coding plays an important role in radar systems, affecting signal modulation, target detection, and interference rejection. This study assesses various phase codes, including Gold, Kasami, Barker, Frank, and Chaotic codes, by analyzing performance metrics like cross-correlation and peak-to-sidelobe ratio (PSLR). The study highlights certain limitations, suggesting the need for new waveform solutions. It integrates component-based and Kronecker product-based interpulse coding to combine different codes and improve overall system performance. By merging phase codes effectively, interpulse coding leverages the strengths of individual codes to produce a composite waveform with enhanced autocorrelation and cross-correlation properties, improving radar performance. An optimization problem is formulated using a weighted performance metric to identify the best waveform, considering factors such as cross-correlation and PSLR. The approach, utilizing simple Kronecker and element-wise multiplication techniques, offers significant benefits with minimal complexity. The Barker-Gold interpulse code stands out as highly effective for spread spectrum-based applications due to its favorable correlation properties.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"51680-51692"},"PeriodicalIF":3.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10934989","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143735347","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}

引用次数: 0

A Novel Similarity Score for Link Prediction Approach Using Financial Transaction Networks and Firms’ Attribute

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-03-21 DOI: 10.1109/ACCESS.2025.3553795

Aparajita Bose;Byunghoon Kim

{"title":"A Novel Similarity Score for Link Prediction Approach Using Financial Transaction Networks and Firms’ Attribute","authors":"Aparajita Bose;Byunghoon Kim","doi":"10.1109/ACCESS.2025.3553795","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3553795","url":null,"abstract":"Financial transaction networks represent inter-firm relationships, where firms and transactions act as nodes and edges, respectively. Link prediction in these networks aims to identify potential future or missing transactions or links, providing valuable insights for decision-making and market analysis. While several link prediction studies exist for general networks, limited research has specifically addressed the unique characteristics of financial transaction networks. Existing studies often overlook important features such as the direction of transactions between firms, the hierarchical nature of transaction networks, and the significance of node attributes, thereby hindering accurate link prediction. In this study, we propose a novel similarity score, the “Attribute-Transaction Similarity (ATS) Score,” for link prediction in financial transaction networks. The ATS Score integrates both transaction network topology and firm attributes, such as the Standard Industrial Classification (SIC) codes, to predict unobserved links between firms. Our method not only forecasts future transactions but also preserves the hierarchical structure of transaction networks. By leveraging both network topology and firm attribute frequencies, our method results in more accurate and reliable predictions. Experimental evaluations on real-world financial transaction network datasets demonstrate that the ATS Score-based link prediction method outperforms existing similarity-based link prediction techniques, achieving superior results in terms of the area under the receiver operating characteristic curve (AUC). This highlights the effectiveness of the ATS Score in capturing the intricate relationships and dynamics of financial transaction networks.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"52051-52068"},"PeriodicalIF":3.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10937185","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143716366","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}

引用次数: 0

Handwritten Amharic Character Recognition Through Transfer Learning: Integrating CNN Models and Machine Learning Classifiers

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-03-21 DOI: 10.1109/ACCESS.2025.3553199

Natenaile Asmamaw Shiferaw;Zefree Lazarus Mayaluri;Prabodh Kumar Sahoo;Ganapati Panda;Prince Jain;Adyasha Rath;Md. Shabiul Islam;Mohammad Tariqul Islam

{"title":"Handwritten Amharic Character Recognition Through Transfer Learning: Integrating CNN Models and Machine Learning Classifiers","authors":"Natenaile Asmamaw Shiferaw;Zefree Lazarus Mayaluri;Prabodh Kumar Sahoo;Ganapati Panda;Prince Jain;Adyasha Rath;Md. Shabiul Islam;Mohammad Tariqul Islam","doi":"10.1109/ACCESS.2025.3553199","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3553199","url":null,"abstract":"Handwritten Amharic character recognition presents significant challenges due to the script’s syllabic nature and variations in handwriting styles. This study investigates a hybrid approach that integrates convolutional neural networks (CNNs) with machine learning classifiers to enhance recognition accuracy. Transfer learning is applied using four CNN architectures: AlexNet, VGG16, VGG19, and ResNet50 as feature extractors. Initially, their performance is evaluated with softmax classifiers. Subsequently, the softmax layer is replaced with machine learning classifiers, including Random Forest, XGBoost, and Support Vector Machine (SVM), while freezing the pretrained feature extractors. The Hybrid ResNet50 + SVM model achieves the highest accuracy of 91.89%, with a precision of 92.46%, recall of 91.15%, and an F1-score of 91.80%. These results indicate that SVM serves as a potential alternative to softmax, offering robust classification performance for complex handwritten scripts. This research contributes to advancements in handwritten character recognition systems for underrepresented languages.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"52134-52148"},"PeriodicalIF":3.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10935359","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143716391","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}

引用次数: 0

Spatial Resolution Ensured Configuration Planning for Visual Inspection Using Pan-Tilt-Zoom Camera-Equipped Robots

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-03-21 DOI: 10.1109/ACCESS.2025.3553517

Weitong Wu;Masaya Haneda;Yuki Funabora;Shinji Doki;Kae Doki

引用次数: 0

(Q, S, R)-Dissipativity Analysis of Large-Scale Networked Singular Systems With Time Delays

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-03-20 DOI: 10.1109/ACCESS.2025.3553131

Lingze Zhang;Huabo Liu

引用次数: 0

Contextual Regularization-Based Energy Optimization for Segmenting Breast Tumor in DCE-MRI

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-03-20 DOI: 10.1109/ACCESS.2025.3553035

Priyadharshini Babu;Mythili Asaithambi;Sudhakar Mogappair Suriyakumar

{"title":"Contextual Regularization-Based Energy Optimization for Segmenting Breast Tumor in DCE-MRI","authors":"Priyadharshini Babu;Mythili Asaithambi;Sudhakar Mogappair Suriyakumar","doi":"10.1109/ACCESS.2025.3553035","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3553035","url":null,"abstract":"Accurate breast tumor segmentation is crucial for precise diagnosis, effective treatment planning, and the development of automated decision-support systems in clinical practice. The imprecision of trending segmentation models in differentiating tumors from their surrounding tissues, particularly in weighing the boundary pixels across tumor regions poses a significant challenge in precise tumor delineation. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) effectively captures tumor vascularity and perfusion dynamics and is a reliable modality for extracting the region of interest (ROI). Nevertheless, the intricate intensity variations in DCE-MRI owing to heterogeneous tumor morphology pose considerable challenges in tumor delineation, necessitating a highly adaptive and robust model for precise tumor segmentation. Accordingly, this manuscript presents a Contextual Regularization-Based Energy Optimization (CRBEO) model that effectively captures these intensity variations in the form of energies contributed by data fidelity and regularization terms. The formulated non-linear energy-based convex optimizer is adaptively tuned by a variational Minimax principle to achieve the desired solution. An iterative gradient descent algorithm is engaged to minimize the energy-based cost function, obtaining stable convergence towards the optimal solution. The extensive relative analysis of CRBEO on complex breast DCE-MRI datasets including QIN breast DCE-MRI, TCGA-BRCA, BreastDM, RIDER, and ISPY1 has recorded significant dice improvements of 30.16%, 11.48%, 20.66%, 1.012%, and 28.107%, respectively on par with trending SOTA methods. The complexity analysis of CRBEO with time and space has justified its extension to real-time clinical diagnosis.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"51986-52005"},"PeriodicalIF":3.4,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10935791","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143716372","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}

引用次数: 0

Optimum Selection of Lithium Iron Phosphate Battery Cells for Electric Vehicles

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-03-20 DOI: 10.1109/ACCESS.2025.3553081

Arda Akyildiz;Bati E. Ergun;Ege Uzun;Mustafa A. Zehir;Cavit F. Kucuktezcan;Ilhan Kocaarslan;Mehmet O. Gulbahce

{"title":"Optimum Selection of Lithium Iron Phosphate Battery Cells for Electric Vehicles","authors":"Arda Akyildiz;Bati E. Ergun;Ege Uzun;Mustafa A. Zehir;Cavit F. Kucuktezcan;Ilhan Kocaarslan;Mehmet O. Gulbahce","doi":"10.1109/ACCESS.2025.3553081","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3553081","url":null,"abstract":"This paper presents a systematic approach to selecting lithium iron phosphate (LFP) battery cells for electric vehicle (EV) applications, considering cost, volume, aging characteristics, and overall performance. A battery selection algorithm is developed, and to investigate its functionality, a case study to evaluate four different LFP battery cell models based on their long-term behavior in a 40 kWh battery pack is conducted. The algorithm integrates a vehicle energy consumption model to better account for the aging impacts of different cell choices, where battery performance is analyzed based on the Worldwide Harmonised Light Vehicles Test Procedure (WLTP) over a 10-year simulated period, considering five driving cycles per day. In order to ensure a fair assessment, the model accounts for variations in battery pack weight as the sole influencing factor on vehicle dynamics. The results compare vehicle range, battery pack mass, cost, cell degradation, and volume for each battery option. The case study findings indicate that the developed method found A123 Systems ANR 26650m1 battery cell superior among the considered four options offering the best trade-off between longevity and cost-effectiveness, making it a highly suitable choice for durable and efficient EV battery packs. This study underscores the importance of considering several critical factors including aging based on detailed driving cycles, together for the most suitable battery selection in designing cost-effective, long-lasting EV energy storage solutions.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"55070-55080"},"PeriodicalIF":3.4,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10935344","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748849","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}

引用次数: 0