IEEE Access最新文献_第6页

A Comprehensive Approach to Residual Value Analysis in the Luxury Automotive Market 豪华汽车市场残值分析的综合方法

IF 3.6 3区计算机科学

IEEE Access Pub Date : 2025-07-23 DOI: 10.1109/ACCESS.2025.3591765

A. Ghibellini;A. Scioletti;M. Coletto;L. Bononi;M. Gabbrielli

{"title":"A Comprehensive Approach to Residual Value Analysis in the Luxury Automotive Market","authors":"A. Ghibellini;A. Scioletti;M. Coletto;L. Bononi;M. Gabbrielli","doi":"10.1109/ACCESS.2025.3591765","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3591765","url":null,"abstract":"Global automotive markets have introduced new complexities, from the surge in powertrain diversity to evolving consumer purchasing habits. In the luxury car segment, residual value (RV), the car’s actual value at the end of ownership, is particularly significant. A high RV translates into lower overall ownership costs, as the car retains more of its value over time, which can boost demand as well as leasing margin. For this reason, the analysis of RV offers key insights for strategic decision-making. The present study leverages a large-scale global dataset spanning a 10-year period, capturing both internal vehicle features and three available external market conditions (CPI, unemployment rate, and 10-year bond yield). Our approach employs machine learning techniques, particularly CatBoost, achieving a mean absolute percentage error of around 5%, deemed highly acceptable within the industry. Moreover, a novel method to enhance the reliability and interpretability of RV estimations is proposed by quantifying depreciation thresholds and mitigating distortions related to sample composition via a “Standard Vehicle” concept. The approach has been validated by Ferrari S.p.A., the provider of the data, serving as a robust tool for automotive industry stakeholders.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"131733-131743"},"PeriodicalIF":3.6,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11091377","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144725210","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

Accelerated ElasticTrainer With Elastic Layer Selection 加速ElasticTrainer与弹性层选择

IF 3.6 3区计算机科学

IEEE Access Pub Date : 2025-07-23 DOI: 10.1109/ACCESS.2025.3591772

Sangho Ha;Hyungshin Kim

引用次数: 0

High-Performance Modeling and Optimization of Wireless Networks Using Bottleneck Structures 基于瓶颈结构的无线网络高性能建模与优化

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-23 DOI: 10.1109/ACCESS.2025.3586752

Aleix Torres-Camps;Alex Batlle Casellas;Yuyang Wang;Mauro Filomeno Rivero;Naga Bhushan;Jordi Ros-Giralt

{"title":"High-Performance Modeling and Optimization of Wireless Networks Using Bottleneck Structures","authors":"Aleix Torres-Camps;Alex Batlle Casellas;Yuyang Wang;Mauro Filomeno Rivero;Naga Bhushan;Jordi Ros-Giralt","doi":"10.1109/ACCESS.2025.3586752","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3586752","url":null,"abstract":"Bottleneck structures have been recently introduced as an efficient mathematical framework for modeling communication systems. Leveraging fast computational graph algorithms from the field of automatic differentiation such as backpropagation, these structures can solve certain wired network problems two to three orders of magnitude faster than traditional network simulators, without losing significant precision. In this paper, we extend the theory of bottleneck structures to incorporate channel interference, enabling their application to wireless network modeling. This generalization leads to the development of a novel mathematical simulator for wireless networks. By introducing a new class of water-filling algorithms that exploit the structure of the computational graph, we demonstrate that bottleneck structures can simulate wireless networks with thousands of user equipments (UEs) in just a few seconds—achieving speedups of two to four orders of magnitude compared to state-of-the-art linear and non-linear programming solvers. For example, in a network with approximately 3000 UEs and 30 base stations, our approach reduces computation time from 145 to 1.08 seconds when assuming generalized processor sharing (GPS) schedulers, and from 2470 to 0.04 seconds when assuming proportional fair (PF) schedulers. To showcase the practical utility of this framework in network optimization, we also integrate bottleneck structures into a mixed-integer linear programming solver and apply it to the antenna placement problem, demonstrating scalability to networks with thousands of UEs.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"130363-130392"},"PeriodicalIF":3.4,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11091392","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144716140","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

ML-Augmented Optimization of LoRa Antennas for Drone Telemetry 无人机遥测LoRa天线的ml增强优化

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-23 DOI: 10.1109/ACCESS.2025.3592096

Pothala Chaya Devi;Ramarakula Madhu

{"title":"ML-Augmented Optimization of LoRa Antennas for Drone Telemetry","authors":"Pothala Chaya Devi;Ramarakula Madhu","doi":"10.1109/ACCESS.2025.3592096","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3592096","url":null,"abstract":"A compact printed monopole antenna for drone telemetry communication, operating at 433 MHz, with a gain of 2.2 dBi, is designed. The antenna is fabricated on an FR-4 substrate with dimensions of <inline-formula> <tex-math>$0.116~lambda _{0} times 0.073~lambda _{0}$ </tex-math></inline-formula> and is optimized for long-range communication. A Machine Learning-augmented Optimization (MLaO) method is proposed to reduce the antenna design time compared to traditional electromagnetic simulation techniques. Typically, antenna design involves complex computer simulations like CST and computationally intensive parameter sweeps. However, in this work a surrogate Artificial Neural Network (ANN) model trained on 1080 antenna designs replaces the heavy CST simulations. This ANN model is then coupled with a Simulated Annealing (SA) optimizer to generate antennas with the desired characteristics, reducing the total design time to 57% compared to traditional techniques. Three antenna designs were simulated using MLaO for different long-range (LoRa) frequency bands, with Ata1 (433 MHz) achieved a return loss (S11) of −23.3 dB, Ata2 (865 MHz) had an S11 of −30.6 dB, and Ata3 (dual band at 433 MHz and 865 MHz) with S11 of −15.6 dB and −35.4 dB respectively. The fabricated antenna (433 MHz) was mounted on a drone and tested with a 3DR-433 telemetry transceiver, recording an average Received Signal Strength Indicator (RSSI) of −57.8 dBm up to 470 m. These results demonstrate the proposed antenna’s efficiency, compactness, and the effectiveness of the MLaO approach for fast and accurate antenna design.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"130353-130362"},"PeriodicalIF":3.4,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11091312","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144716217","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 Multilayer Residual Dendritic Neural Model for Predicting Stroke Prognosis 预测脑卒中预后的多层残差树突状神经模型

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-23 DOI: 10.1109/ACCESS.2025.3591799

Yuxi Wang;Haochang Jin;Maocheng Cao;Xiong Xiao;Li Wang

引用次数: 0

Hypergraph Neural Sheaf Diffusion: A Symmetric Simplicial Set Framework for Higher-Order Learning 超图神经束扩散：用于高阶学习的对称简单集框架

IF 3.6 3区计算机科学

IEEE Access Pub Date : 2025-07-23 DOI: 10.1109/ACCESS.2025.3592104

Seongjin Choi;Gahee Kim;Yong-Geun Oh

{"title":"Hypergraph Neural Sheaf Diffusion: A Symmetric Simplicial Set Framework for Higher-Order Learning","authors":"Seongjin Choi;Gahee Kim;Yong-Geun Oh","doi":"10.1109/ACCESS.2025.3592104","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3592104","url":null,"abstract":"The absence of intrinsic adjacency relations and orientation systems in hypergraphs creates fundamental challenges for constructing sheaf Laplacians of arbitrary degrees. We resolve these limitations through symmetric simplicial sets derived directly from hypergraphs, called symmetric simplicial lifting, which encode all possible oriented subrelations within each hyperedge as ordered tuples. This construction canonically defines adjacency via facet maps while inherently preserving hyperedge provenance. We establish that the normalized degree zero sheaf Laplacian on our symmetric simplicial lifting reduces exactly to the traditional graph normalized sheaf Laplacian when restricted to graphs, validating its mathematical consistency with prior graph-based sheaf theory. Furthermore, the induced structure preserves all structural information from the original hypergraph, ensuring that every multi-way relational detail is faithfully retained. Leveraging this framework, we introduce Hypergraph Neural Sheaf Diffusion (HNSD), the first principled extension of neural sheaf diffusion to hypergraphs. HNSD operates via normalized degree zero sheaf Laplacian over symmetric simplicial lifting, resolving orientation ambiguity and adjacency sparsity inherent to hypergraph learning. Experimental evaluations demonstrate HNSD’s competitive performance across established benchmarks.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"131823-131838"},"PeriodicalIF":3.6,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11091307","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144725257","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

WISP: Workframe for Interferogram Signal Phase-Unwrapping 干涉图信号相位展开的工作框架

IF 3.6 3区计算机科学

IEEE Access Pub Date : 2025-07-23 DOI: 10.1109/ACCESS.2025.3591959

Timofey F. Khirianov;Aleksandra I. Khirianova;Egor V. Parkevich;Ilya Makarov

{"title":"WISP: Workframe for Interferogram Signal Phase-Unwrapping","authors":"Timofey F. Khirianov;Aleksandra I. Khirianova;Egor V. Parkevich;Ilya Makarov","doi":"10.1109/ACCESS.2025.3591959","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3591959","url":null,"abstract":"This paper proposes an iterative framework WISP (Workframe for Interferogram Signal Phase-unwrapping for phase reconstruction from interferograms of complex phase objects. The framework processes each interferogram through the sequential stages: dark fringe tracing, isophase distribution, local gradient direction estimation, anisotropic (local direction dependent) diffusion smoothing, phase unwrapping, and convergence testing. Iterations continue until the difference between the reconstructed and experimental phase distributions reaches an asymptotic minimum. A key contribution is the proposed loss function for isophase fitting, which directly optimizes curve quality and enhances reconstruction accuracy. Experimental results confirm the algorithm’s highest precision. A study of the framework’s resistance to noise was conducted, showing high stability even in the case of noise with an amplitude half the amplitude of the image brightness. Comparative analysis against established baselines reveals that the WISP consistently outperforms alternative approaches in accurately unwrapping the phase, particularly under high noise conditions. Evaluated using RMSD metrics, WISP achieves the lowest reconstruction errors, reducing them by 39.7% compared to the next best method (Deep Convolutional Neural Network), highlighting its superior robustness and accuracy.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"131757-131771"},"PeriodicalIF":3.6,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11091281","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144725258","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

AAV Parameters Estimation Based on Improved Time-Frequency Ridge Extraction and Hough Transform 基于改进时频脊提取和霍夫变换的AAV参数估计

IF 3.6 3区计算机科学

IEEE Access Pub Date : 2025-07-23 DOI: 10.1109/ACCESS.2025.3591787

Yongji Yu;Yonghong Ruan;Junjie Zhong

{"title":"AAV Parameters Estimation Based on Improved Time-Frequency Ridge Extraction and Hough Transform","authors":"Yongji Yu;Yonghong Ruan;Junjie Zhong","doi":"10.1109/ACCESS.2025.3591787","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3591787","url":null,"abstract":"The micro-Doppler effect caused by the rotation of autonomous aerial vehicle (AAV) rotors plays a crucial role in AAV detection and identification, as it can reflect the micro-movement characteristics of the target, enabling the estimation of the blade length and rotation speed. However, existing methods are prone to noise interference and exhibit poor performance in extracting multi-rotor and multi-component signals. In this paper, we first construct a AAV rotor echo model for frequency-modulated radar systems and derive the mapping relationship between rotor parameters and micro-Doppler characteristic components. First-Order short-time Fourier transform synchrosqueezed transform (FSST) is proposed for extracting micro-Doppler features. Specifically, a novel AAV parameter estimation method is investigated, which is based on an improved time-frequency ridge extraction and Hough transform, following a detailed analysis of the micro-Doppler time-frequency spectrum. Finally, the effectiveness of the method is validated through experimental data. Compared to traditional methods, this approach improves the accuracy of multi-rotor, multi micro-Doppler signal parameter estimation.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"131074-131087"},"PeriodicalIF":3.6,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11091279","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144725250","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

Scalable Nonparametric Supervised Learning for Streaming and Massive Data: Applications in Healthcare Monitoring and Credit Risk 流和海量数据的可扩展非参数监督学习：在医疗监控和信用风险中的应用

IF 3.6 3区计算机科学

IEEE Access Pub Date : 2025-07-23 DOI: 10.1109/ACCESS.2025.3591883

Mohamed Chaouch;Omama M. Al-Hamed

{"title":"Scalable Nonparametric Supervised Learning for Streaming and Massive Data: Applications in Healthcare Monitoring and Credit Risk","authors":"Mohamed Chaouch;Omama M. Al-Hamed","doi":"10.1109/ACCESS.2025.3591883","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3591883","url":null,"abstract":"This paper introduces novel nonparametric supervised learning techniques for classifying massive datasets, addressing key limitations of existing methods in Big and Streaming Data framework. We propose an offline kernel-based classifier enhanced by Batch Principal Component Analysis (PCA) for dimensionality reduction to mitigate the “curse of dimensionality”. Additionally, an online classifier is developed for streaming data, combining online PCA with a kernel-based recursive classifier using a stochastic approximation algorithm. Application to fetal well-being monitoring demonstrates that the online classifier achieves a competitive median misclassification rate (11.92%), comparable to the offline classifier (11.54%) and Random Forest (11.31%), while requiring only 1/15th of the offline classifier’s computation time. Receiver Operating Characteristic (ROC) analysis shows superior Area Under the Curve (AUC) for the offline classifier but at a significant computational cost. A second study on larger database of credit scoring confirms these findings, showing that the online classifier achieves an F1-score of 96.40% and an accuracy of 93.08%, closely matching the performance of neural networks (96.46%, 93.22%) and boosting (96.51%, 93.31%). Notably, the online classifier accomplishes this with a CPU time of only 0.87 seconds per classification - over 600 times faster than neural networks - demonstrating its effectiveness for high-frequency, real-time financial decision-making.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"131716-131732"},"PeriodicalIF":3.6,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11091306","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144725251","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

An Accurate and Reliable Behavioral Modeling Technique for Fully Printed Vanadium Dioxide RF Switches Using Model Ensembling Approach 基于模型集成方法的全印刷二氧化钒射频开关准确可靠的行为建模技术

IF 3.6 3区计算机科学

IEEE Access Pub Date : 2025-07-23 DOI: 10.1109/ACCESS.2025.3591890

Saddam Husain;Bagylan Kadirbay;Mohammad Vaseem;Atif Shamim;Mohammad Hashmi

{"title":"An Accurate and Reliable Behavioral Modeling Technique for Fully Printed Vanadium Dioxide RF Switches Using Model Ensembling Approach","authors":"Saddam Husain;Bagylan Kadirbay;Mohammad Vaseem;Atif Shamim;Mohammad Hashmi","doi":"10.1109/ACCESS.2025.3591890","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3591890","url":null,"abstract":"This paper develops and showcases a model ensembling-based accurate, reliable and computer-aided design integrable behavioral modeling technique for emerging fully printed Vanadium dioxide (VO2) based Radio Frequency (RF) switches. Initially, separate and independent models are trained using Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Light Gradient Boosting Machine (LightGBM) gradient boosting frameworks. The hyperparameters of the standalone XGBoost, CatBoost, and LightGBM based models are optimized using random search optimization coupled with a cross-validation scheme. Subsequently, weighted ensemble models are constructed by leveraging the optimally trained XGBoost, CatBoost, and LightGBM based models. It is vital to carefully calibrate the ensembling weights; therefore, an optimization algorithm, namely Tuna Swarm Optimization (TSO), is employed. Finally, all the developed models are tried and validated on standard regression tests, including mean relative error across all operating temperature conditions. The proposed weighted ensemble models have achieved remarkable accuracy and efficiency in simulating the behavior of VO2 RF switches.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"131638-131653"},"PeriodicalIF":3.6,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11091287","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144725211","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