检索结果-内蒙古大学图书馆

AR-Light: Enabling Fast and Lightweight Multi-User Augmented Reality via Semantic Segmentation and Collaborative View Synchronization

引用

IEEE Transactions on computers 2025年第6期74卷 2073-2086页

作者： Wen, Yu Shah, Aamir Bader Cao, Ruizhi Zhang, Chen Chen, Jiefu Wu, Xuqing Xie, Chenhao Fu, Xin University of Houston Department of Electrical and Computer Engineering HoustonTX77204 United States Beihang University School of Computer Science and Engineering Beijing100191 China University of Houston Department of Information Science Technology HoustonTX77204 United States

Multi-user Augmented Reality (MuAR) allows multiple users to interact with shared virtual objects, facilitated by exchanging environment information. Current MuAR systems rely on 3D point clouds for real-world analysis, view synchronization, object rendering, and movement tracking. However, the complexity of 3D point clouds leads to significant processing delays, with approximately 80% of overhead in commercial frameworks. This hampers usability and degrades user experience. Our analysis reveals that maintaining the facing side of the real-world scene in a stable environment provides sufficient information for virtual object placement and rendering. To address this, we introduce a lightweight quadtree structure, representing 2D scenes through semantic segmentation and geometry, as an alternative to 3D point clouds. Additionally, we propose a novel correction method to handle potential shifts in virtual object placement during view synchronization among users. Combining all designs, we implement a fast and lightweight MuAR framework named AR-Light and test our framework on commercial AR devices. The evaluation results on real-world applications demonstrate that AR-Light can achieve high performance in various real-world scenes while maintaining a comparable virtual object placement accuracy. © 1968-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Enhancing English accent identification in automatic speech recognition using spectral features and hybrid CNN-BiLSTM model

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Ahmed, Ghayas Lawaye, Aadil Ahmad Jain, Vishal Chatterjee, Jyotir Moy Mahajan, Shubham Department of Computer Sciences Baba Ghulam Shah Badshah University J&K Rajouri India Department of Computer Science & Engineering Sharda University Noida India Dehradun India Department of Computer Science & Engineering Amity University Haryana India

Automatic Speech Recognition (ASR) has been the regnant research area in the domain of Natural Language Processing for the last few decades. Past years’ advancement provides progress in this area of research. The accent of spoken is the prominent factor affecting the performance of ASR. Accent is the pronunciation of a word in a distinct way which may vary from specimen to specimen depending upon their social class, formality, age, vocal property, gender, geography, and influence of native or other language. Recognizing an accent requires various complex characteristics and features of voice such as voice quality, prosody, and phoneme pronunciation which are difficult to extract and analyze. To solve these difficulties, the researchers focus their attention on spectral representation such as Mel Spectrogram and Mel-Frequency Cepstral Coefficient (MFCC). In this study, we will analyze which features achieve maximum accuracy for the English accent classification task. Here in this work, we perform our experiments on Log Mel filter bank and MFCC features with four different window function. We extract features from raw audio with various windowing function and train a hybrid model of Convolutional Neural Network and Bidirectional Long Short-term Memory network (CNN-BiLSTM) on a custom dataset having nine different accents of English language namely American, Australian, British, Indian (Oriya, Bangla, Telegu, Malayalam), and Welsh. The accuracy of each feature is evaluated and compared. The log Mel filter bank outputs the highest accuracy of 99.75% and 99.91% of training and validation with Han window function while MFCC with Bartlett window function achieves 99.98% of training and 99.33% of validation accuracy. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Feature-Based Federated Transfer Learning: Communication Efficiency, Robustness and Privacy

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2024年 2卷 823-840页

作者： Wang, Feng Gursoy, M. Cenk Velipasalar, Senem Syracuse University Department of Electrical Engineering and Computer Science SyracuseNY13244 United States

In this paper, we propose feature-based federated transfer learning as a novel approach to improve communication efficiency by reducing the uplink payload by multiple orders of magnitude compared to that of existing approaches in federated learning and federated transfer learning. Specifically, in the proposed feature-based federated learning, we design the extracted features and outputs to be uploaded instead of parameter updates. For this distributed learning model, we determine the required payload and provide comparisons with the existing schemes. Subsequently, we analyze the robustness of feature-based federated transfer learning against packet loss, data insufficiency, and quantization. Finally, we address privacy considerations by defining and analyzing label privacy leakage and feature privacy leakage, and investigating mitigating approaches. For all aforementioned analyses, we evaluate the performance of the proposed learning scheme via experiments on an image classification task and a natural language processing task to demonstrate its effectiveness (https://***/wfwf10/Feature-based-Federated-Transfer-Learning). © 2023 CCBY.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

M22: A Communication-Efficient Algorithm for Federated Learning Inspired by Rate-Distortion

引用

IEEE Transactions on Communications 2024年第2期72卷 845-860页

作者： Liu, Yangyi Rini, Stefano Salehkalaibar, Sadaf Chen, Jun McMaster University Department of Electrical and Computer Engineering HamiltonONL8S 4L8 Canada Department of Electrical and Computer Engineering Hsinchu30010 Taiwan University of Toronto Department of Electrical and Computer Engineering TorontoONM5A 4T4 Canada

In federated learning (FL), the communication constraint between the remote clients and the Parameter Server (PS) is a crucial bottleneck. For this reason, model updates must be compressed so as to minimize the loss in accuracy resulting from the communication constraint. This paper proposes 'M-magnitude weighted L2 distortion + 2 degrees of freedom' (M22) algorithm, a rate-distortion inspired approach to gradient compression for federated training of deep neural networks (DNNs). In particular, we propose a family of distortion measures between the original gradient and the reconstruction we referred to as ' M-magnitude weighted L{2} ' distortion, and we assume that gradient updates follow an i.i.d. distribution-generalized normal or Weibull, which have two degrees of freedom. In both the distortion measure and the gradient distribution, there is one free parameter for each that can be fitted as a function of the iteration number. Given a choice of gradient distribution and distortion measure, we design the quantizer to minimize the expected distortion in gradient reconstruction. To measure the gradient compression performance under a communication constraint, we define the per-bit accuracy as the optimal improvement in accuracy that one bit of communication brings to the centralized model over the training period. Using this performance measure, we systematically benchmark the choice of gradient distribution and distortion measure. We provide substantial insights on the role of these choices and argue that significant performance improvements can be attained using such a rate-distortion inspired compressor. © 1972-2012 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Making Sense of Big Data in Intelligent Transportation Systems: Current Trends, Challenges and Future Directions

引用

ACM Computing Surveys 2025年第8期57卷 1-43页

作者： Ahmad Jan, Mian Adil, Muhammad Brik, Bouziane Harous, Saad Abbas, Sohail Department of Computer Science University of Sharjah Sharjah27272 United Arab Emirates Department of Computer Science and Engineering University at Buffalo BuffaloNY United States

Intelligent Transportation Systems (ITS) generate massive amounts of Big Data through both sensory and non-sensory platforms. The data support batch processing as well as stream processing, which are essential for reliable operations on the roads and connected vehicles in ITS. Despite the immense potential of Big Data intelligence in ITS, autonomous vehicles are largely confined to testing and trial phases. The research community is working tirelessly to improve the reliability of ITS by designing new protocols, standards, and connectivity paradigms. In the recent past, several surveys have been conducted that focus on Big Data Intelligence for ITS, yet none of them have comprehensively addressed the fundamental challenges hindering the widespread adoption of autonomous vehicles on the roads. Our survey aims to help readers better understand the technological advancements by delving deep into Big Data architecture, focusing on data acquisition, data storage, and data visualization. We reviewed sensory and non-sensory platforms for data acquisition, data storage repositories for archival and retrieval of large datasets, and data visualization for presenting the processed data in an interactive and comprehensible format. To this end, we discussed the current research progress by comprehensively covering the literature and highlighting challenges that urgently require the attention of the research community. Based on the concluding remarks, we argued that these challenges hinder the widespread presence of autonomous vehicles on the roads. Understanding these challenges is important for a more informed discussion on the future of self-driven technology. Moreover, we acknowledge that these challenges not only affect individual layers but also impact the functionality of subsequent layers. Finally, we outline our future work that explores how resolving these challenges could enable the realization of innovations such as smart charging systems on the roads and data centers

关键词： Intelligent transportation systems big data sensors storage visualization data centers on the wheels smart computers on the roads

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware DRL for Autonomous Vehicle Crowd Navigation in Shared Space

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Golchoubian, Mahsa Ghafurian, Moojan Dautenhahn, Kerstin Azad, Nasser Lashgarian Department of Systems Design Engineering University of Waterloo Canada Department of Electrical and Computer Engineering University of Waterloo Canada

Safe, socially compliant, and efficient navigation of low-speed autonomous vehicles (AVs) in pedestrian-rich environments necessitates considering pedestrians' future positions and interactions with the vehicle and others. Despite the inevitable uncertainties associated with pedestrians' predicted trajectories due to their unobserved states (e.g., intent), existing deep reinforcement learning (DRL) algorithms for crowd navigation often neglect these uncertainties when using predicted trajectories to guide policy learning. This omission limits the usability of predictions when diverging from ground truth. This work introduces an integrated prediction and planning approach that incorporates the uncertainties of predicted pedestrian states in the training of a model-free DRL algorithm. A novel reward function encourages the AV to respect pedestrians' personal space, decrease speed during close approaches, and minimize the collision probability with their predicted paths. Unlike previous DRL methods, our model, designed for AV operation in crowded spaces, is trained in a novel simulation environment that reflects realistic pedestrian behaviour in a shared space with vehicles. Results show a 40% decrease in collision rate and a 15% increase in minimum distance to pedestrians compared to the state of the art model that does not account for prediction uncertainty. Additionally, the approach outperforms model predictive control methods that incorporate the same prediction uncertainties in terms of both performance and computational time, while producing trajectories closer to human drivers in similar scenarios. IEEE

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

A Graph-Assisted Digital-Twin-Driven Multiagent Shared Offloading for Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第11期12卷 17349-17363页

作者： Zahangir Alam, Md Rahman, Suryaia Asif Bin Khaled, Md Islam, Ashraful Jamalipour, Abbas Independent University Bangladesh Department of Computer Science and Engineering Center for Computational and Data Sciences Dhaka1229 Bangladesh The University of Sydney School of Electrical and Computer Engineering SydneyNSW2006 Australia

Vehicular edge computing (VEC) allows vehicles to process part of the tasks locally at the network edge while offloading the rest of the tasks to a centralized cloud server for processing. A massive volume of tasks generated by the Internet of Vehicles (IoV) leads to buffer overflow that causes higher latency. Elevating latency, in turn, can increase network energy consumption. Both higher latency and energy consumption lead to a degradation of network performance. Therefore, VEC design requires a balance between latency and energy consumption tradeoff. To reduce overwhelming amount of offloading to edge servers, a cooperative cluster-based shared offloading strategy has been proposed in this work. We use digital twin technology in VEC for managing and adapting to environmental dynamic changes. Then, we leverage Lyapunov (Ly) optimization to transform the stochastic offloading problem into a more manageable deterministic form. Finally, we present a decentralized coordination graph (CG)-driven Ly-based multiagent deep deterministic policy gradient (CG-LyMADDPG) algorithm that trains agents toward energy efficient optimal offloading policy while maintaining queue stability at a maximum delay constraint. The experimental result shows that the proposed learning significantly outperforms the baseline algorithms for energy savings while maintain queue stability. © 2014 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

SAFED: secure and adaptive framework for edge-based data aggregation in IoT applications

引用

Discover Internet of Things 2025年第1期5卷 1-28页

作者： Naaz, Zaineb Joshi, Gamini Sharma, Vidushi Department of Computer Science and Engineering School of ICT Gautam Buddha University Greater Noida India Department of Computer Science and Engineering PES University Electronic City Campus Bangalore India

The paper proposed a secured and efficient data aggregation mechanism leveraging the edge computing paradigm and homomorphic data encryption technique. The paper used a unique combination of Paillier cryptosystem and RSA digital signature mechanism to preserve data privacy, confidentiality, and integrity while maintaining the efficiency of the IoT network. The efficiency and implementation of the proposed scheme have been demonstrated through a case study, showcasing how the scheme can be effectively applied in real-world scenarios, such as in a smart grid network. Additionally, the future scope has been outlined, with potential techniques to address challenges that the scheme may face. © The Author(s) 2025.

关键词： Data aggregation Edge computing Internet of things Paillier cryptosystem Privacy-preserving Security

来源：评论

学校读者我要写书评

暂无评论

A Developer-Focused Genetic Algorithm for IoT Application Placement in the Computing Continuum

引用

IEEE Transactions on Services Computing 2025年第03期18卷 1185-1198页

作者： Herrera, Juan Luis Moya, Alejandro Berrocal, Javier Murillo, Juan Manuel Navarro, Elena University of Bologna Department of Computer Science Engineering Italy University of Castilla-La Mancha LoUISE Research Group Spain University of Extremadura Department of Computer Science and Communications Engineering Spain

The rise of the Internet of Things (IoT) paradigm has led to an interest in applying it not only in tasks for the general public but also to stringent domains such as healthcare. However, the developers of these next-generation IoT applications must consider additional non-functional requirements related to the criticality of the processes they automate, such as low response times or low deployment costs, as well as technical constraints, which include organizational, legal and policy-related constraints on where data can be processed or stored. While the Computing Continuum paradigm emerges as a valuable alternative for placing such applications, identifying the deployments that satisfy all these requirements becomes a tough challenge. The NP-hard nature of the problem makes it impractical to manually find such a deployment, and traditional approaches fail to consider the technical constraints. In this paper, we present the Genetic Algorithm for Application Placement (GAAP), an evolutionary computing-based meta-heuristic designed to help IoT application developers find deployments that satisfy their Quality of Service, business and technical constraints. Our evaluation of an Internet of Medical Things use case shows that GAAP supports larger scenarios than traditional approaches and gives IoT application developers more options while providing better scalability. © 2008-2012 IEEE.

关键词： Internet Of Things Microservice Architectures Quality Of Service Costs Time Factors Electrocardiography Biomedical Monitoring Blood Pressure Genetic Algorithms Business Internet Of Things Computing Continuum Quality Of Service Service Placement Deployment Genetic Algorithm Internet Of Things Internet Of Things Applications Response Time Service Quality Technical Constraints Deployment Cost Low Response Time Internet Of Medical Things Heuristic Objective Function Replica Decision Variables Solution Space Quality Of Experience Internet Of Things Devices Pareto Front Multi Objective Algorithm Capital Expenditure Crossover Operator Quality Of Service Requirements Operational Expenditure Set Of Hosts Workflow Dijkstras Algorithm Non Dominated Solutions Average Response Time Pareto Optimal Solutions Response Cost Multi Objective Genetic Algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhanced WPT structures via EC-SRR-based metasurfaces

引用

COMPEL - The International Journal for Computation and Mathematics in electrical and Electronic engineering 2023年第3期42卷 757-775页

作者： Karatzidis, Dimitrios I. Zygiridis, Theodoros T. Kantartzis, Nikolaos V. Department of Electrical and Computer Engineering Aristotle University of Thessaloniki Thessaloniki Greece Department of Electrical and Computer Engineering University of Western Macedonia Kozani Greece

Purpose: The purpose of this paper is to present a family of robust metasurface-oriented wireless power transfer systems with improved efficiency and size compactness. The effect of geometric and structural features on the overall efficiency and miniaturisation is elaborately studied, while the presence of substrate losses is, also, considered. Moreover, to further enhance the performance, possible means for reducing the operating frequency, without comprising the unit-cell size, are proposed. Design/methodology/approach: The key element of the design technique is the edge-coupled split-ring resonators patterned in various metasurface configurations and optimally placed to increase the total efficiency. To this goal, a rigorous three-dimensional algorithm, launching a new high-order prism macroelement, is developed in this paper for the fast evaluation of the required quantities. The featured scheme can host diverse approximation orders, while it is drastically more economical than existing methods. Hence, the demanding wireless power transfer systems are precisely modelled via reduced degrees of freedom, without the need to conduct large-scale simulations. Findings: Numerical results, compared with measured data from fabricated prototypes, validate the design methodology and prove its competence to provide enhanced metasurface wireless power transfer systems. An assortment of optimized 3 x 3 and 5 x 5 metamaterial setups is investigated, and interesting deductions, regarding the impact of the inter-element gaps, the distance between the transmitting and receiving components and the substrate losses, are derived. Also, the proposed vector macroelement technique overwhelms typical implementations in terms of computational burden, particularly when combined with the relevant commercial software packages. Originality/value: Systematic design of advanced real-world wireless power transfer structures through optimally selected metasurfaces with fully controllable electro

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：