检索结果-内蒙古大学图书馆

Molecular-Guided Surgery: Molecules, Devices, and Applications XI 2025

作者： Lediju Bell, Muyinatu A. Department of Electrical & Computer Engineering Johns Hopkins University BaltimoreMD United States Department of Biomedical Engineering Johns Hopkins University BaltimoreMD United States Department of Computer Science Johns Hopkins University BaltimoreMD United States Department of Oncology Johns Hopkins University School of Medicine BaltimoreMD United States

ISBN: (纸本)9781510683501

This invited contribution discusses recent applications in breast imaging and hysterectomy guidance from the Photoacoustic & Ultrasonic Systems engineering (PULSE) Lab at Johns Hopkins University. Challenges with breast imaging and hysterectomy guidance are discussed. Solutions to the discussed challenges that incorporate multispectral photoacoustic imaging are summarized. In particular, diagnostic imaging innovations in coherence-based beamforming ultimately enabled molecular imaging innovations for surgical guidance, relying on training data, principal component analyses, and acoustic-based approaches to spectral unmixing. These new innovations are promising for breast imaging and hysterectomy procedures. © 2025 SPIE.

关键词： Molecular imaging

来源：评论

学校读者我要写书评

暂无评论

Intelligent Cooperative Sensing for Connected and Autonomous Vehicles: An Improved Decision Transformer Approach

引用

IEEE Internet of Things Journal 2025年第11期12卷 15424-15437页

作者： Pincan Zhao Changle Li Xinrui Zhang F. Richard Yu Yuchuan Fu State Key Laboratory of Integrated Services Networks Xidian University Xi’an China School of Information Technology Carleton University Ottawa ON Canada Department of Systems and Computer Engineering Carleton University Ottawa ON Canada

Effective sensing capabilities are crucial for the safe and reliable operation of Connected and autonomous vehicles (CAVs). While traditional approaches focus on enhancing onboard sensors, the integration of road sensor networks (RSNs) into the CAV ecosystem presents a promising solution to improve sensing performance, but also introduces significant challenges, including heterogeneous sensing requirements, inconsistencies in multisource sensor data, and efficient resource utilization. To address these challenges, this article proposes a novel cooperative sensing framework that leverages multisource and multilevel sensing information from RSNs to optimize CAV sensing performance in resource-constrained scenarios. We develop an improved decision transformer (DT)-based approach that dynamically adapts to diverse driving conditions and efficiently fuses sensor data at various abstraction levels. To tackle the issue of long-delayed rewards, we introduce a reshaped reward function and a bi-level optimization framework that enables effective propagation of rewards along decision sequences. An advanced gradient approximation technique is employed to efficiently solve the optimization problem. Extensive simulations demonstrate the superior performance of our improved DT approach compared to state-of-the-art reinforcement learning (RL) methods in terms of sensing accuracy, coverage, and data efficiency under various traffic conditions.

关键词： Connected vehicles Fuses Thermal sensors Sensor fusion Transformers Data models Sensors Resource management Optimization Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Diffusion Model for Multiple Antenna Communications

arXiv

引用

arXiv 2025年

作者： Guo, Jia Xu, Xiaoxia Liu, Yuanwei Nallanathan, Arumugam School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

The potential of applying diffusion models (DMs) for multiple antenna communications is discussed. A unified framework of applying DM for multiple antenna tasks is first proposed. Then, the tasks are innovatively divided into two categories, i.e., decision-making tasks and generation tasks, depending on whether an optimization of system parameters is involved. For each category, it is conceived 1) how the framework can be used for each task and 2) why the DM is superior to traditional artificial intelligence (TAI) and conventional optimization tasks. It is highlighted that the DMs are well-suited for scenarios with strong interference and noise, excelling in modeling complex data distribution and exploring better actions. A case study of learning beamforming with a DM is then provided, to demonstrate the superiority of the DMs with simulation results. Finally, the applications of DM for emerging multiple antenna technologies and promising research directions are discussed. Copyright © 2025, The Authors. All rights reserved.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

QMix: Quality-aware Learning with Mixed Noise for Robust Retinal Disease Diagnosis

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Hou, Junlin Xu, Jilan Feng, Rui Chen, Hao Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai China HKUST Department of Chemical and Biological Engineering Division of Life Science Hong Kong HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen China

Due to the complex nature of medical image acquisition and annotation, medical datasets inevitably contain noise. This adversely affects the robustness and generalization of deep neural networks. Previous noise learning methods mainly considered noise arising from images being mislabeled, i.e., label noise, assuming all mislabeled images were of high quality. However, medical images can also suffer from severe data quality issues, i.e., data noise, where discriminative visual features for disease diagnosis are missing. In this paper, we propose QMix, a noise learning framework that learns a robust disease diagnosis model under mixed noise scenarios. QMix alternates between sample separation and quality-aware semisupervised training in each epoch. The sample separation phase uses a joint uncertainty-loss criterion to effectively separate (1) correctly labeled images, (2) mislabeled high-quality images, and (3) mislabeled low-quality images. The semi-supervised training phase then learns a robust disease diagnosis model from the separated samples. Specifically, we propose a sample-reweighing loss to mitigate the effect of mislabeled low-quality images during training, and a contrastive enhancement loss to further distinguish them from correctly labeled images. QMix achieved state-of-the-art performance on six public retinal image datasets and exhibited significant improvements in robustness against mixed noise. © 1982-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Circular LPDA Array Design for Efficient Microwave Treatment of Palm Weevil Infestation

Circular LPDA Array Design for Efficient Microwave Treatment...

引用

Microwave, Antennas & Circuits (ICMAC), International Conference on

作者： Asad Masood Muhammad Ali Zubair Mehmood Zunair Ahmad Faizan Ramzan Rifaqat Hussain Muhammad Qasim Mehmood Department of Electrical Engineering MicroNano Lab Information Technology University (ITU) Lahore Pakistan Department of Electrical Engineering Hafiz Hayat Campus University of Gujrat (UOG) Gujrat Pakistan Antenna and Electromagnetics Research Group School of Electronic Engineering and Computer Science Queen Mary University of London London UK

ISBN: (数字)9798331518424

ISBN: (纸本)9798331518431

The Red Palm Weevil (RPW) is one of the most harmful pests to palms globally. Various strategies have been used to killing this pest which includes Phyto sanitation, chemical pesticides, pheromone traps, and biological management, however the use of microwave energy for heat disinfestation appears to be a potential alternative. This article describes the method to develop a microwave antenna system that uses a circular array of Log-Periodic Dipole Antennas (LPDAs) to disinfect date palms. The simulation results are performed in FDTD solver. The proposed antenna covers a wide frequency range spanning 1.3 GHz − 3 GHz. The reflection coefficient is well below to −10 dB over the whole resonant frequency band, having a peak gain of 9.5 dBi for a single antenna. A circular LPDA antenna array is proposed to perform the thermal analysis for particular area of the palm tree to mitigate the RPW.

关键词： Electromagnetic heating Microwave integrated circuits Dipole antennas Resonant frequency Microwave theory and techniques Microwave circuits Microwave antenna arrays Thermal analysis Reflection coefficient Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

HeadSonic: Usable Bone Conduction Earphone Authentication via Head-conducted Sounds

引用

IEEE Transactions on Mobile Computing 2025年

作者： He, Zhixiang Chen, Jing He, Kun Gu, Yangyang Deng, Qiyi Zhang, Zijian Du, Ruiying Zhao, Qingchuan Wu, Cong Wuhan University School of Cyber Science and Engineering Wuhan430072 China State Key Lab of Intelligent Transportation System Beijing China Beijing Institute of Technology School of Cyberspace Science and Technology China City University of Hong Kong Department of Computer Science Hong Kong The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong

Earables (ear wearables) are rapidly emerging as a new platform encompassing a diverse of personal applications, prompting the development of authentication schemes to protect user privacy. Existing earable authentication methods are all specifically designed for air-conduction earphones, which are not suited for bone conduction earphones (BCEs) that rely on bone conduction mechanisms. In this paper, we propose HeadSonic, a usable BCE authentication system based on the unique head-conducted sounds, which can be acquired when the user wears the BCE device. Specifically, the system emits a millisecond-level sound to initiate the authentication session. The signal captured by the BCE microphone is propagated through the user’s head, which is unique in density, geometry, and bone-tissue ratio. It operates implicitly, while maintaining robustness across different behaviors. Extensive experiments involving 60 subjects demonstrate that HeadSonic achieves a commendable balanced accuracy of 96.59%, proving its efficacy and resilience against replay and synthesis attacks. Our dataset and source codes are available at https://***/r/HeadSonic1CE4. © 2025 IEEE. All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

HOpenCls: Training Hyperspectral Image Open-Set Classifiers in Their Living Environments

arXiv

引用

arXiv 2025年

作者： Zhao, Hengwei Wang, Xinyu Zheng, Zhuo Li, Jingtao Zhong, Yanfei State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University China Department of Computer Science Stanford University United States School of Remote Sensing and Information Engineering Wuhan University China

Hyperspectral image (HSI) open-set classification is critical for HSI classification models deployed in real-world environments, where classifiers must simultaneously classify known classes and reject unknown classes. Recent methods utilize auxiliary unknown classes data to improve classification performance. However, the auxiliary unknown classes data is strongly assumed to be completely separable from known classes and requires labor-intensive annotation. To address this limitation, this paper proposes a novel framework, HOpenCls, to leverage the unlabeled wild data—that is the mixture of known and unknown classes. Such wild data is abundant and can be collected freely during deploying classifiers in their living environments. The key insight is reformulating the open-set HSI classification with unlabeled wild data as a positive-unlabeled (PU) learning problem. Specifically, the multi-label strategy is introduced to bridge the PU learning and open-set HSI classification, and then the proposed gradient contraction and gradient expansion module to make this PU learning problem tractable from the observation of abnormal gradient weights associated with wild data. Extensive experiment results demonstrate that incorporating wild data has the potential to significantly enhance open-set HSI classification in complex real-world scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Beamforming Design for Continuous Aperture Array (CAPA)-Based MIMO Systems

arXiv

引用

arXiv 2025年

作者： Wang, Zhaolin Ouyang, Chongjun Liu, Yuanwei The School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom The Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

An efficient beamforming design is proposed for continuous aperture array (CAPA)-based point-to-point multiple-input multiple-output (MIMO) systems. In contrast to conventional spatially discrete array (SPDA)-MIMO systems, whose optimal beamforming can be obtained using singular-value decomposition, CAPA-MIMO systems require solving the eigendecomposition of a Hermitian kernel operator, which is computationally prohibitive. To address this challenge, an explicit closed-form expression for the achievable rate of CAPA-MIMO systems is first derived as a function of the continuous transmit beamformer. Subsequently, an iterative weighted minimum mean-squared error (WMMSE) algorithm is proposed, directly addressing the CAPA-MIMO beamforming optimization without discretization approximation. Closed-form updates for each iteration of the WMMSE algorithm are derived via the calculus of variations (CoV) method. For low-complexity implementation, an equivalent matrix-based iterative solution is introduced using Gauss-Legendre quadrature. Our numerical results demonstrate that 1) CAPA-MIMO achieves substantial performance gain over the SPDA-MIMO, 2) the proposed WMMSE algorithm enhances performance while significantly reducing computational complexity compared to state-of-the-art Fourier-based approaches, and 3) the proposed WMMSE algorithm enables practical realization of parallel, non-interfering transmissions. Copyright © 2025, The Authors. All rights reserved.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Hybrid Quantum Computing and Deep Learning Approaches for Enhancing Wireless Communication Security

Hybrid Quantum Computing and Deep Learning Approaches for En...

引用

Emerging Systems and Intelligent Computing (ESIC), International Conference on

作者： Ramu V Kalyan Barla Kavitha V Srinivas Aluvala Sankepally Chandrasekhar A.Athiraja Department of CSE (AI&ML) KITS Warangal Hanamkonda Telangana Department of IT Bannari Amman Institute of Technology Erode School of Computer Science & Artificial Intelligence SR University Warangal Department of Mechanical Engineering Malla Reddy Engineering College (Autonomous) Telangana Department of CSE (AI&ML) Malla Reddy Engineering College (Autonomous) Telangana

ISBN: (数字)9798331522100

ISBN: (纸本)9798331522117

A potential way to improve wireless communication security in the face of increasingly complex cyberthreats is to combine deep learning techniques with hybrid quantum computing. By combining the processing benefits of quantum algorithms with the pattern recognition powers of deep learning, this article tackles the crucial problems of protecting wireless networks, which are vulnerable to eavesdropping, spoofing, and data breaches. The research uses a hybrid framework in which deep learning models like convolutional neural networks (CNNs) identify and stop possible invasions in real time, while quantum key distribution (QKD) guarantees safe data transfer. Simulations and experimental validation in a 5G network environment show that the proposed system has a 40% reduction in latency and a 35% increase in intrusion detection accuracy compared to traditional security methods, like standard encryption techniques and rule-based intrusion detection systems that lack quantum cryptographic mechanisms and advanced AI-driven pattern recognition. The findings demonstrate that integrating quantum and AI-driven methods to build a more robust wireless communication infrastructure is feasible. The study concludes by highlighting the potential of hybrid quantum-AI systems as a critical first step in protecting next-generation networks.

关键词： Deep learning 5G mobile communication Computational modeling Wireless networks Intrusion detection Real-time systems Quantum key distribution Security Artificial intelligence Optimization

来源：评论

学校读者我要写书评

暂无评论

Palantir: Towards Efficient Super Resolution for Ultra-high-definition Live Streaming 25

Palantir: Towards Efficient Super Resolution for Ultra-high-...

引用

16th ACM Multimedia Systems Conference, MMSys 2025

作者： Jin, Xinqi Zhu, Zhui Sun, Xikai Dang, Fan Liu, Jiangchuan Xu, Jingao Liu, Kebin Chen, Xinlei Liu, Yunhao School of Software & BNRist Tsinghua University Beijing China Department of Automation & BNRist Tsinghua University Beijing China School of Software Engineering Beijing Jiaotong University Beijing China School of Computing Science Simon Fraser University Burnaby Canada Computer Science Department Carnegie Mellon University Pittsburgh United States Global Innovation Exchange Tsinghua University Beijing China Shenzhen International Graduate School Tsinghua University Shenzhen China

ISBN: (纸本)9798400714672

Neural enhancement through super-resolution (SR) deep neural networks (DNNs) opens up new possibilities for ultra-high-definition (UHD) live streaming. Yet, the heavy SR DNN inference overhead leads to severe deployment challenges. To reduce the overhead, existing systems propose to apply DNN-based SR only on carefully selected anchor frames while upscaling non-anchor frames via the lightweight reusing-based SR approach. However, frame-level scheduling is coarse-grained and fails to deliver optimal efficiency. In this work, we propose Palantír, the first neural-enhanced UHD live streaming system with fine-grained patch-level *** the core of Palantír is its SR video quality estimation strategy which guides the low-delay selection of the most beneficial anchor patches. Although existing systems propose estimation strategies for anchor frame selection, these strategies heavily rely on empirical insights that cannot be transferred to our context, making fine-grained scheduling a challenging problem that requires a fundamentally new solution. Facing the challenge, we follow the first-principles approach and derive a directed acyclic graph (DAG) model to address the problem. The model can also be generalized to various settings due to its first-principles nature. Compared to the state-of-the-art real-time frame-level scheduling strategy for live streaming, Palantír reduces the anchor size by 80.1% at most and 38.4% on average without compromising the quality gain. Furthermore, Palantír incurs a scheduling latency accounting for only 0.6-3.9% of the end-to-end latency requirement for UHD live streaming. © 2025 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Deep neural networks

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：