检索结果-内蒙古大学图书馆

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Deng, Yongheng Ren, Ju Tang, Cheng Lyu, Feng Liu, Yang Zhang, Yaoxue Tsinghua University Department of Computer Science and Technology BNRist Beijing China Zhongguancun Laboratory Beijing China Central South University School of Computer Science and Engineering Changsha China Beijing China

ISBN: (纸本)9798350334142

Federated learning (FL) enables distributed clients to collaboratively learn a shared model while keeping their raw data private. To mitigate the system heterogeneity issues of FL and overcome the resource constraints of clients, we investigate a novel paradigm in which heterogeneous clients learn uniquely designed models with different architectures, and transfer knowledge to the server to train a larger server model that in turn helps to enhance client models. For efficient knowledge transfer between client models and server model, we propose FedHKT, a Hierarchical Knowledge Transfer framework for FL. The main idea of FedHKT is to allow clients with similar data distributions to collaboratively learn to specialize in certain classes, then the specialized knowledge of clients is aggregated to a super knowledge covering all specialties to train the server model, and finally the server model knowledge is distilled to client models. Specifically, we tailor a hybrid knowledge transfer mechanism for FedHKT, where the model parameters based and knowledge distillation (KD) based methods are respectively used for client-edge and edge-cloud knowledge transfer, which can harness the pros and evade the cons of these two approaches in learning performance and resource efficiency. Besides, to efficiently aggregate knowledge for conducive server model training, we propose a weighted ensemble distillation scheme with server-assisted knowledge selection, which aggregates knowledge by its prediction confidence, selects qualified knowledge during server model training, and uses selected knowledge to help improve client models. Extensive experiments demonstrate the superior performance of FedHKT compared to state-of-the-art baselines. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Improving Signal-to-Noise Ratio (SNR) for Readout Signals Using Adaptive Filters on Reconfigurable Controls Hardware 4

Improving Signal-to-Noise Ratio (SNR) for Readout Signals Us...

引用

4th IEEE International Conference on Quantum Computing and engineering, QCE 2023

作者： Johnson, Hans Zorzetti, Silvia Saniie, Jafar Research Laboratory Department of Electrical and Computer Engineering ChicagoIL United States Fermi National Accelerator Laboratory BataviaIL60510 United States

ISBN: (纸本)9798350343236

This study investigates the optimization of Signal-to-Noise Ratio (SNR) in superconducting quantum computing readout signals through adaptive filtering. Quantum computing technology has the potential to revolutionize various fields by delivering exponential speedup in solving certain computational problems. However, the technology's practical implementation is hindered by the difficulty of extracting clean, reliable signals during the readout phase, with various sources of noise presenting a significant barrier to clean signals. This noise, often present in readout profiles due to imperfect isolation, degrades the system's overall SNR, thus impeding the ability to extract the quantum state accurately. The research leverages the power of adaptive filtering to improve the SNR of quantum computing readout signals. Specifically, an adaptive filter is implemented in a PYNQ overlay on an FPGA, and eventually will be connected to a quantum computing system. The system models the noise with a Least Mean Squares (LMS) adaptive filter, and then subtracts the estimated noise from the received signal to improve the SNR. A Direct Memory Access (DMA) channel is used to handle the signal processing, delivering efficient, high-speed data transfer between the PYNQ system and the hardware. The study explores the benefits of this adaptive filtering technique, potentially providing a significant contribution to practical and fast quantum computing. © 2023 IEEE.

关键词： Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

Incorporating Graph Permanent in Forecasting Financial Performance

Incorporating Graph Permanent in Forecasting Financial Perfo...

引用

作者： Das, Sujoy Khatun, Mossa. Anisa Rahman, Md. Saidur Graph Drawing and Information Visualization Laboratory Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh Department of Operations and Supply Chain Management American International University-Bangladesh Dhaka Bangladesh

Forecasting financial performance metrics plays a pivotal role in guiding decision-making processes for the management, investors, creditors, regulators and other stakeholders of every business entity. Multiple linear regression is a widely used popular method to forecast financial performance metrics. But multiple linear regression fails to capture the interrelationships and correlations among various factors influencing financial performance metrics. It’s a notable limitation of multiple linear regression. In this research paper, we have proposed a graph permanent based technique named networked regression that integrates graph theory with regression analysis to model the dynamic relationships among the explanatory variables and to offer a more comprehensive understanding of their collective impact on the response variable. We demonstrate that networked regression, when combined with multiple linear regression, can offer more comprehensive insights and predictive capability. Thus by integrating graph theoretic concepts in regression analysis, our proposed approach contributes to advancing the field of financial performance forecasting in dynamic financial environments. In this research work, we have conducted experiments on the financial datasets of various companies like PepsiCo, P&G and Nestlé. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

Examining the economic feasibility of hybrid Photovoltaic - Battery Energy Storage System in public building with flexible demand: Cyprus case study 3

Examining the economic feasibility of hybrid Photovoltaic - ...

引用

3rd International Conference on Energy Transition in the Mediterranean Area, SyNERGY MED 2024

作者： Chatzigeorgiou, Nikolas G. Makrides, George Theocharides, Spyros Georghiou, George E. University of Cyprus PV Technology Laboratory Department of Electrical and Computer Engineering Cyprus PHAETHON Centre of Excellence for Intelligent Efficient and Sustainable Energy Solutions Nicosia Cyprus

ISBN: (纸本)9798350375923

Photovoltaic - Battery Energy Storage Systems (PVBESS) are a promising solution against technical bottlenecks of high PV penetration. Public buildings are suitable for installation, although currently underexploited, while high BESS costs limit technology diffusion. This paper assesses the economic feasibility of PV-BESS in public buildings with flexible demand, through simulations showcasing BESS subsidisation impact and self-sufficiency contribution. The results derived that smaller PV-BESS sizes are more attractive investments, as larger systems are characterised by reduced profitability, while BESS subsidisation enhances system profitability. Shifting a small portion of load demand improves economic feasibility by decreasing BESS size, while combining PV production, energy storage, and energy flexibility is the optimal solution for public buildings against electricity prices. Finally, a trade-off between economic feasibility and energy self-sufficiency is observed. The results can be utilised by policymakers to design strategies for BESS promotion, while professionals can perform accurate system sizing, thus avoiding excess system capacities. © 2024 IEEE.

关键词： Battery storage

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Safety System for Treadmill Users

Machine Learning Safety System for Treadmill Users

引用

2022 IEEE International Conference on Electro Information Technology, eIT 2022

作者： Natarajan, Ravishankar Yu, Xinrui Saniie, Jafar Department of Electrical and Computer Engineering Research Laboratory ChicagoIL United States

ISBN: (纸本)9781665480093

In this paper, we present an AI-based treadmill assistant that employs computer vision and Deep learning algorithms to offer a comprehensive safety net for treadmill users. The system is designed and implemented with minimal components including an off-the-shelf camera, speaker, an IoT smart plug, and Jetson Nano (a single board GPU-based embedded computing device). To provide an extensive set of safety features such as face recognition, facial stress detection, object detection, and distance and aspect measurement to the treadmill user, the system uses CNN architectures based on ResNet, MobileNet SSD, and customized fully connected neural networks. This set of features monitored in real-time will play a crucial role in mitigating treadmill user falls and injuries. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Advanced extended-term simulation approach with flexible quas-isteady-state and dynamic semi-analytical simulation engines

iEnergy

引用

iEnergy 2022年第1期1卷 124-132页

作者： Rui Yao Dongbo Zhao A.P.Sakis Meliopoulos Chanan Singh Joydeep Mitra Feng Qiu Division of Energy Systems Argonne National LaboratoryLemontIL 60439USA School of Electrical and Computer Engineering Georgia Institute of TechnologyAtlantaGA 30332USA Department of Electrical and Computer Engineering Texas A&M UniversityCollege Sta-tionTX 77843USA Department of Electrical and Computer Engineering Michigan State UniversityEast LansingMI 48824USA

Power system simulations that extend over a time period of minutes,hours,or even longer are called extendedterm *** power systems evolve into complex systems with increasing interdependencies and richer dynamic behaviors across a wide range of timescales,extendedterm simulation is needed for many power system analysis tasks(e.g.,resilience analysis,renewable energy integration,cascading failures),and there is an urgent need for efficient and robust extendedterm simulation *** conventional approaches are insufficient for dealing with the extendedterm simulation of multitimescale *** paper proposes an extendedterm simulation approach based on the semianalytical simulation(SAS)*** accuracy and computational efficiency are backed by SAS's high accuracy in eventdriven simulation,larger and adaptive time steps,and flexible switching between fulldynamic and quasisteadystate(QSS)*** used this proposed extendedterm simulation approach to evaluate bulk power system restoration plans,and it demonstrates satisfactory accuracy and efficiency in this complex simulation task.

关键词： Extended-term simulation resilience multi-timescale simulation event-driven simulation dynamics quasi-steady-state(QSS) hybrid simulation holomorphic embedding(HE) semi-analytical simulation(SAS)

来源：评论

学校读者我要写书评

暂无评论

Staggered Microstrip Grating Structure for Sheet-Beam TWTs 25

Staggered Microstrip Grating Structure for Sheet-Beam TWTs

引用

25th Joint IEEE International Vacuum Electronics Conference and 15th International Vacuum Electron Sources Conference, IVEC + IVESC 2024

作者： Marosi, Robert Zuboraj, Muhammed Capolino, Filippo University of California Department of Electrical Engineering and Computer Science IrvineCA United States Los Alamos National Laboratory Los AlamosNM United States

ISBN: (纸本)9798350348705

We introduce a simple geometry for slow-wave structures (SWSs) in sheet-beam traveling-wave tubes (TWTs). The staggered microstrip grating SWS is a space harmonic structure with geometry and bandwidth with analogous to the staggered vane SWS commonly used for sheet beam TWTs. The staggered microstrip grating TWT is designed to operate in V-band with a center frequency of 74 GHz and electron beam voltage of 20 kV. © 2024 IEEE.

关键词： Slow wave structures

来源：评论

学校读者我要写书评

暂无评论

Autonomous Robotic Arm for Object Sorting and Motion Compensation using Kalman Filter

Autonomous Robotic Arm for Object Sorting and Motion Compens...

引用

2022 IEEE International Conference on Electro Information Technology, eIT 2022

作者： Ndambani, Melanie Acelor Fang, Tianyang Saniie, Jafar Department of Electrical and Computer Engineering Research Laboratory ChicagoIL United States

ISBN: (纸本)9781665480093

Robotic arm has played a key role in the industry for more than a half-century. Although robotic arms have superior accuracy and efficiency, they are not always cost-effective, especially for small-scale applications. This paper proposes an autonomous robotic arm system that can identify, sort, and interact with different objects, using IoT devices. For precision robotic arm movement, we have developed a Kalman filter-based motion compensation system. The embedded computing system is used for real-time object recognition and motion compensation. Experimental results show that the proposed high precision autonomous robotic arm system can recognize objects with 95% accuracy, and locate and sort the moving objects with a mean error of 1.1mm. © 2022 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Practical FSS-Based Sensor Sensitivity

Practical FSS-Based Sensor Sensitivity

引用

2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022

作者： Mahmoodi, Mahboobeh Donnell, Kristen M. Laboratory Department of Electrical and Computer Engineering RollaMO65409 United States

ISBN: (数字)9781665496582

ISBN: (纸本)9781665496582

Frequency selective surfaces are a periodic array of unit cells that, when illuminated externally, have a specific frequency response that depends on element geometry, spacing, and substrate properties. Theoretically, FSS is assumed as an infinite array of unit cells with a plane wave excitation. However, in practice, an FSS is finite and hence, due to edge effects, the limited number of unit cells, and non-uniform illumination, the response will deviate from the theoretical. As it relates to FSS-based sensing in particular, a localized illumination is often used in order to improve the sensing resolution. However, due to the aforementioned factors, the sensitivity of the sensor may suffer as a result. Hence, the effect of these factors is studied on the FSS sensor response. Then, taking strain measurement as an example, the degradation in the sensor sensitivity to strain is evaluated in comparison with that of a theoretical FSS. The simulation results show that a finite FSS with non-uniform illumination has reduced sensitivity to strain. This degradation in sensitivity of reduces as the number of illuminated unit cells increases. However, the sensitivity of a finite FSS with uniform illumination is nearly constant with respect to the number of illuminated unit cells. © 2022 IEEE.

关键词： Frequency selective surfaces

来源：评论

学校读者我要写书评

暂无评论

Stereolithography 3D printing of an accelerometer embedded nightguard for TMD monitoring 12

Stereolithography 3D printing of an accelerometer embedded n...

引用

Laser 3D Manufacturing XII 2025

作者： McLaughlin, Elizabeth M. Gerding, Maya Wu, Yongji Xiao, Hai Yao, Hai Department of Bioengineering Clemson University ClemsonSC29631 United States Photonics Technology Laboratory Holcombe Department of Electrical and Computer Engineering Clemson University AndersonSC29625 United States

ISBN: (纸本)9781510684560

There are currently no effective take-home jaw motion tracking devices to monitor the symptoms in temporomandibular joint disorder (TMD). Existing methods consist of bulky lab equipment that lack a standard for TMD diagnosis. These devices are unable to provide critical data that occurs within a patient’s natural day-to-day life which can lead to inadequate management of TMD. This study presents the fabrication techniques explored to create a take-home wearable device capable of detecting jaw movements to aid in remote patient monitoring of TMD symptoms. The nightguard prototypes are 3D modeled using denture model STL files and printed in various dental and biomedical resins on a Form 3B+ stereolithography 3D printer by Formlabs. Embedded accelerometers are used to quantify jaw movements, and a CAD-modeled, 3D-printed denture model is used to simulate these movements. Extensive testing is conducted throughout the fabrication process to ensure accuracy and reliability. This proof-of-concept study aims to establish the feasibility of the device for future clinical trials, where AI integration for data analysis and further optimization of manufacturing methods will be explored to validate the device’s efficacy and user requirements. The potential impact of this device includes improved TMD management through continuous, at-home monitoring, leading to better patient outcomes. Future work will focus on refining the design and expanding the testing to a larger cohort to further validate the device’s performance and reliability. © 2025 SPIE.

关键词： Stereolithography

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：