检索结果-内蒙古大学图书馆

MR Spatiospectral Reconstruction Integrating Subspace Modeling and Self-Supervised Spatiotemporal Denoising

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Zhao, Ruiyang Wang, Zepeng Anderson, Aaron Huesmann, Graham Lam, Fan University of Illinois Urbana-Champaign Department of Electrical and Computer Engineering Beckman Institute for Advanced Science and Technology United States University of Illinois Urbana-Champaign Department of Bioengineering Beckman Institute for Advanced Science and Technology United States University of Illinois Urbana-Champaign Beckman Institute for Advanced Science and Technology United States Carle Foundation Hospital United States University of Illinois Urbana-Champaign Department of Bioengineering Beckman Institute for Advanced Science and Technology IL61801 United States

We present a new method that integrates subspace modeling and a pre-learned spatiotemporal denoiser for reconstruction from highly noisy magnetic resonance spectroscopic imaging (MRSI) data. The subspace model imposes an explicit low-dimensional representation of the high-dimensional spatiospectral functions of interest for noise reduction, while the denoiser serves as a complementary spatiotemporal prior to constrain the subspace reconstruction. A self-supervised learning strategy was proposed to train a denoiser that can distinguish the spatio-temporally correlated signals from uncorrelated noise. An iterative reconstruction formalism was developed based on the Plug-and-Play (PnP)-ADMM framework to synergize the subspace constraint, plug-in denoiser and spatiospectral encoding model. We evaluated the proposed method using numerical simulations and in vivo data, demonstrating improved performance over state-of-the-art subspacebased methods. We also provided theoretical analysis on the utility of combining subspace projection and iterative denoising in terms of both algorithm convergence and performance. Our work demonstrated the potential of integrating self-supervised denoising priors and low-dimensional representations for high-dimensional imaging problems. © 2025 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Adaptive Vehicle Control System for Improved Safety With Image Processing 5

Adaptive Vehicle Control System for Improved Safety With Ima...

引用

5th IEEE International Conference on Electro-Computing Technologies for Humanity, NIGERCON 2024

作者： Vijayalakshmi, N. Priya, L. Ramaraj, S. Nanjundan, Menakadevi Palanisamy, Satheesh Kumar Olalekan Salau, Ayodeji Braide, Sepiribo Lucky Alliance University Alliance School of Advanced Compuitng Department of Computer Science and Engineering Bangalore India Department of Ece Kinathukadavu Tamilnadu Coimbatore641202 India Karpagam College of Engineering Department of Computer Science and Engineering India Karpagam Institute of Technology Department of Ece Coimbatore India Bms Institute of Technology and Management Department of Ece Karnataka Bengaluru India Afe Babalola University Department of Electrical/Electronics and Computer Engineering Ado-Ekiti Nigeria Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Chennai India Rivers State University Department of Electrical and Electronics Engineering Port Harcourt Nigeria

ISBN: (纸本)9798331542559

We propose the development of an Adaptive Vehicle Control (AVC) system using readily available components such as a Raspberry Pi microcontroller, a motor, a motor driver, and a Raspberry Pi camera. This system aims to enhance safety and convenience by automatically adjusting vehicle speed based on surrounding traffic conditions and recognizing relevant road signs like school zones, speed limits, and hospital zones. The process begins with real-time image capture using the Raspberry Pi camera module. These images are then analyzed using Python-based computer vision algorithms, primarily leveraging OpenCV. The image processing pipeline employs techniques such as object detection and template matching to identify specific road signs within the captured frames. Upon sign detection, the system interprets their meanings and determines the appropriate speed limits associated with them. Using the information from the detected signs and their corresponding speed limits, the system regulates the motor connected to the vehicle's throttle through GPIO pins on the Raspberry Pi. By adjusting the motor's speed, the AVC system ensures compliance with the specified speed limits across various road conditions. Safety measures are paramount, with fail-safe mechanisms implemented to prevent accidents in case of system errors or malfunctions. This AVC system offers a cost-effective and adaptable solution for integrating intelligent cruise control capabilities into vehicles. Leveraging the computational power of the Raspberry Pi and the versatility of image processing techniques, the system can adapt to diverse driving environments, thereby enhancing overall driving safety. This project contributes to the progression of smart transportation systems and lays the foundation for further advancements in autonomous driving technologies. © 2024 IEEE.

关键词： Adaptive cruise control

来源：评论

学校读者我要写书评

暂无评论

Longitudinal velocity control of autonomous driving based on extended state observer

引用

CAAI Transactions on Intelligence Technology 2025年第1期10卷 36-46页

作者： Hongbo Gao Hanqing Yang Xiaoyu Zhang Xiangyun Ren Fenghua Liang Ruidong Yan Qingchao Liu Mingmao Hu Fang Zhang Jiabing Gao Siyu Bao Keqiang Li Deyi Li Danwei Wang Department of Automation University of Science and Technology of ChinaHefeiChina State Key Laboratory of Intelligent Vehicle Safety Technology ChongqingChina Institute of Advanced Technology University of Science and Technology of ChinaHefeiChina School of Electrical and Electronic Engineering Nanyang Technological UniversitySingaporeSingapore School of Traffic and Transportation Beijing Jiaotong UniversityBeijingChina Automotive Engineering Research Institute Jiangsu UniversityZhenjiangChina School of Mechanical and Aerospace Engineering Nanyang Technological UniversitySingaporeSingapore School of Automotive Engineering Hubei University of Automotive TechnologyShiyanChina Beijing Idriverplus Technology Co. Ltd.BeijingChina Chery Automobile Co. Ltd.WuhuChina State Key Laboratory of Automotive Safety and Energy Tsinghua UniversityBeijingChina Department of Computer Science and Technology Tsinghua UniversityBeijingChina

Active Disturbance Rejection Control(ADRC)possesses robust disturbance rejection capabilities,making it well-suited for longitudinal velocity ***,the conventional Extended State Observer(ESO)in ADRC fails to fully exploit feedback from first-order and higher-order estimation errors and tracking error simultaneously,thereby diminishing the control performance of *** address this limitation,an enhanced car-following algorithm utilising ADRC is proposed,which integrates the improved ESO with a feedback *** comparison to the conventional ESO,the enhanced version effectively utilises multi-order estimation and tracking ***,it enhances convergence rates by incorporating feedback from higher-order estimation errors and ensures the estimated value converges to the reference value by utilising tracking error *** improved ESO significantly enhances the disturbance rejection performance of ***,the effectiveness of the proposed algorithm is validated through the Lyapunov approach and experiments.

关键词： active disturbance rejection control(ADRC) autonomous vehicle extended state observer(ESO) intelligent control longitudinal velocity control

来源：评论

学校读者我要写书评

暂无评论

Ferro-floating memory:Dual-mode ferroelectric floating memory and its application to in-memory computing

引用

InfoMat 2022年第11期4卷 93-105页

作者： Sangyong Park Seyong Oh Dongyoung Lee Jin-Hong Park Department of Semiconductor and Display Engineering Sungkyunkwan UniversitySuwonRepublic of Korea Flash Process Architecture Team Flash Development TeamMemory BusinessSamsung Electronics CompanyPyeongtaekRepublic of Korea Department of Electrical and Computer Engineering Sungkyunkwan University(SKKU)SuwonRepublic of Korea SKKU Advanced Institute of Nanotechnology(SAINT) Sungkyunkwan UniversitySuwonRepublic of KoreagBeijingPeople's Republic of China

Various core memory devices have been proposed for utilization in future inmemory computing technology featuring high energy *** memory is considered as a viable choice owing to its high integration density,stability,and reliability,which has been verified by commercialized ***,its high operating voltage and slow operation speed issues caused by the tunneling mechanism make its adoption in in-memory computing applications *** this paper,we introduce a dual-mode memory device named“ferro-floating memory”,fabricated using van der Waals(vdW)materials(h-BN,MoS2,andα-In2Se3).The vdW material,α-In2Se3,acts as a polarization control layer for the ferroelectric memory operation and charge storage layer for the conventional flash memory *** to the tunnelingbased memory operation,the ferro-floating memory operates 1.9 and 3.3 times faster at 6.7 and 5.8 times lower operating voltages for programming and erasing operations,*** dual-mode operation improves the linearity of conductance change by 5 times and the dynamic range by 48%through achieving conductance variation ***,we assess the effects of the variation in device operating voltage on neural networks and suggest a memory array operating scheme for maximizing the networks'performance through various training/inference simulations.

关键词： artificial synaptic device dual-mode operation mechanism ferroelectric floating memory inmemory computing multi-stages conductance reconfigurable operation range

来源：评论

学校读者我要写书评

暂无评论

Power Supply Induced Jitter (PSIJ) Modeling, Analysis, and Optimization of High Bandwidth Memory (HBM) I/O Interface

Power Supply Induced Jitter (PSIJ) Modeling, Analysis, and O...

引用

IEEE International Symposium on Electromagnetic Compatibility (EMC)

作者： Hyunwook Park Taein Shin Seongguk Kim Keeyoung Son Keunwoo Kim Boogyo Sim Hyungmin Kang Seonguk Choi Jiwon Yoon Hyunwoo Kim Chulsoon Hwang Joungho Kim School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon South Korea Department of Electrical and Computer Engineering Missouri University of Science and Technology (MST) Rolla MO USA

Power supply induced jitter (PSIJ) in high bandwidth memory (HBM) I/O interface is modeled, analyzed, and optimized for different HBM generations. Precise models for VDDQ power distribution networks (PDNs), simultaneous switching current (SSC), and jitter sensitivities of the clock and I/O buffers are implemented for PSIJ estimation. Compared to the SPICE, the average error rate of the estimated PSIJ is 4.26 %. The critical frequency bands in the jitter spectrum where large jitters occur are derived by comparing the relative impact of the modeled interface factors in the frequency domain. For the optimization, on-chip and on-interposer decoupling capacitor (decap) placement strategies using machine learning (ML) are applied. The decap effects in the critical ranges are analyzed. Finally, based on the integrated analysis of the limitation of the decap solution and all the I/O interface factors, the major challenges of high-frequency PSIJ are characterized.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient and Practical Multi-party Computation under Inconsistent Trust in TEEs

Towards Efficient and Practical Multi-party Computation unde...

引用

IEEE Symposium on Security and Privacy

作者： Xuanwei Hu Rujia Li Yi Liu Qi Wang Department of Computer Science and Engineering Southern University of Science and Technology Institute for Advanced Study Tsinghua Univesity College of Cyber Security Jinan University National Center for Applied Mathematics Shenzhen Southern University of Science and Technology

ISBN: (数字)9798331522360

ISBN: (纸本)9798331522377

Secure multi-party computation (MPC) allows joint computations on sensitive data while guaranteeing privacy and correctness. In recent years, a series of MPC protocols assisted by trusted execution environments (TEEs) have been proposed to reduce overhead brought by costly cryptographic techniques. However, existing protocols either generally assume consistent trust in TEEs among all participating parties, or require dedicated designs for different applications. This prevents the protocols from being deployed in practice. To address these challenges, in this work, we propose a generic MPC protocol without assuming consistent trust in TEEs while fully utilizing heterogeneous TEEs to improve efficiency. To this end, we propose a security model to capture parties' inconsistent trust in TEEs and prove the security of our protocol under a simpler variant of the UC framework (SUC framework). In addition, we instantiate our protocol for secure aggregation based on a state-of-the-art information-theoretically secure protocol SwiftAgg+. Evaluation results among 64 parties deployed on Azure virtual machines show that our protocol reduces the running time of SwiftAgg+ by 66%. The running time of parties in our protocol is reduced by at most 91% compared to that required in SwiftAgg+.

关键词： Analytical models Privacy Data privacy Protocols Computational modeling Multi-party computation Virtual machines Security

来源：评论

学校读者我要写书评

暂无评论

GRU: MITIGATING THE TRADE-OFF BETWEEN UNLEARNING AND RETENTION FOR LARGE LANGUAGE MODELS

arXiv

引用

arXiv 2025年

作者： Wang, Yue Wang, Qizhou Liu, Feng Huang, Wei Du, Yali Du, Xiaojiang Han, Bo TMLR Group Department of Computer Science Hong Kong Baptist University Hong Kong The University of Melbourne Australia RIKEN Center for Advanced Intelligence Project Japan King’s College London United Kingdom Department of Electrical and Computer Engineering Stevens Institute of Technology United States

Large language model (LLM) unlearning has demonstrated its essential role in removing privacy and copyright-related responses, crucial for their legal and safe applications. However, the pursuit of complete unlearning often comes with substantial costs due to its compromises in their general functionality, leading to a notorious trade-off between unlearning and retention. In examining the update process for unlearning dynamically, we find gradients hold essential information for revealing this trade-off. In particular, we look at the varying relationship between retention performance and directional disparities between gradients during unlearning. It motivates the sculpting of an update mechanism derived from gradients from two sources, i.e., harmful for retention and useful for unlearning. Accordingly, we propose Gradient Rectified Unlearning (GRU), an enhanced unlearning framework controlling the updating gradients in a geometry-focused and optimization-driven manner such that their side impacts on other, unrelated responses can be minimized. Specifically, GRU derives a closed-form solution to project the unlearning gradient onto the orthogonal space of that gradient harmful for retention, ensuring minimal deviation from its original direction under the condition that overall performance is retained. Comprehensive experiments are conducted to demonstrate that GRU, as a general framework, is straightforward to implement and efficiently enhances a range of baseline methods through its adaptable and compatible characteristics. Additionally, experimental results show its broad effectiveness across a diverse set of benchmarks for LLM unlearning. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiscale multi-functional phase imaging platform for cell and tissue characterization

Multiscale multi-functional phase imaging platform for cell ...

引用

IEEE Photonics Conference (IPC)

作者： Hongqiang Ma Phuong Nguyen Yang Liu Department of Bioengineering Beckman Institute for Advanced Science and Technology University of Illinois Urbana-Champaign Urbana IL USA Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign Urbana IL USA

ISBN: (数字)9798350361957

ISBN: (纸本)9798350361964

Phase Imaging offers a label-free approach to non-invasively characterize cellular processes and tissue architecture by exploiting their refractive index based intrinsic contrast in their natural states. In this study, we present a multiscale phase imaging system that bridges mesoscale and nanoscale imaging. This system shows the capability for large-scale, simultaneous tracking of live-cell morphodynamics, capturing sub-cellular details across thousands of cells as they develop resistance to chemotherapy drugs and the ability to reveal sub-cellular features in pathological tissue.

关键词： Pathology Chemotherapy Optical microscopy Imaging Refractive index Optical variables control Optical imaging Nanoscale devices Optical refraction Photonics

来源：评论

学校读者我要写书评

暂无评论

Q2oE: Balancing QoE Fairness and Preference for Video Streaming from Cooperative Edge Servers

Q2oE: Balancing QoE Fairness and Preference for Video Stream...

引用

IEEE Internatonal Conference on Mobile Adhoc and Sensor Systems (MASS)

作者： Xinwei Huang Yin Xu Jinbo Cai He Sun Jie Wu Mingjun Xiao School of Software Engineering University of Science and Technology of China China Suzhou Institute for Advanced Study University of Science and Technology of China China School of Computer Science and Technology University of Science and Technology of China China Department of Computer and Information Sciences Temple University USA

ISBN: (数字)9798350363999

ISBN: (纸本)9798350364002

Quality of Experience (QoE) is a pivotal factor that defines the overall quality within the realm of video streaming services. To improve users' QoE indicators, existing methods have proposed many QoE models and Adaptive Bitrate (ABR) algorithms. However, these advanced methods do not account for the tradeoff between users' personalized preferences and fairness, leading to resource wastage on the edge server and an inefficient bitrate allocation. Given resource constraints, non-cooperative edge servers frequently request the cloud to enhance user QoE, consequently resulting in high-latency transmissions. In this paper, we address this issue by introducing collaborative edge servers, which alleviate the burden of video chunk transcoding and caching on individual servers. Specifically, we design a novel QoE model named Q 2 0E that incorporates user-level QoE preference and QoE fairness in this scenario. Furthermore, we propose Q2D3, a Q 2 oE-aware reinforcement learning algorithm based on a video chunk transcoding strategy for mobility-aware vehicular networks, to improve Q 2 oE model performance.

关键词： Measurement Simulation Bit rate Transcoding Reinforcement learning Streaming media Smart systems Quality of experience Servers Resource management

来源：评论

学校读者我要写书评

暂无评论

Cyclic Sensing: An Orbital Spectrum Sensing Method for Uplink NOMA IoT Systems

Cyclic Sensing: An Orbital Spectrum Sensing Method for Uplin...

引用

IEEE International Conference on Communications (ICC)

作者： Tianheng Xu Yinjun Xu Jingyi Wu Haijun Zhang Ting Zhou Honglin Hu Victor C.M. Leung Shanghai Advanced Research Institute Chinese Academy of Sciences Shanghai China Shanghai Frontier lnnovation Research Institute Shanghai China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China School of Microelectronics Shanghai University Shanghai China Department of Electrical and Computer Engineering The University of British Columbia Canada College of Computer and Software Engineering Shenzhen University China

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

The upcoming sixth-generation (6G) of ubiquitous connectivity communications systems is driven by the next-generation of Internet of Things (IoT) technology. Accordingly, the demand for spectrum resources is growing exponentially. Spectrum sensing, which dynamically explores spectrum holes, is expected to be crucial in the 6G era. In the meantime, Non-Orthogonal Multi-Access (NOMA), an efficient means of reusing resources, can enable multiple users to share the same frequency band stably. The combination of both technologies holds promise for more effective use of spectrum resources in future commu-nications. In this paper, we present a spectrum sensing method for the uplink communication scenario in NOMA with multi-user interference, which aims to make effective use of both static and dynamic gain on spectrum efficiency. Firstly, the sensing criterion and workflow are outlined. The closed-form solution for the sensing threshold configuration is derived thereafter. The simulation results demonstrate the feasibility of the proposed approach, which can increase the system throughput up to 19.7%, when compared to NOMA without spectrum sensing.

关键词： 6G mobile communication NOMA Closed-form solutions Simulation Throughput Orbits Sensors

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：