检索结果-内蒙古大学图书馆

32nd International Conference on electrical engineering, ICEE 2024

作者： Fard, E. Karimpour Nouri, M. Behroozi, H. Sobhi-Givi, S. Sharif University of Technology Dept. of Electrical Engineering Tehran Iran University of Mohaghegh Ardabili Dept. of Electrical and Computer Engineering Ardabil Iran

ISBN: (纸本)9798350376340

Fast and accurate methods for spectrum sensing (SS) are the key elements in cognitive radio networks (CRNs) that achieve high SS. This paper proposes a reinforcement learning (RL) scheme for secondary users (SUs) in a massive multiple-input multiple-output (MIMO) CRN to determine occupation and emptiness of scanned wideband channels. In the proposed H-learning method, the clustered neighboring SUs collect data to check the status of channels that improve reliability of measured sensing. Then, they share information about different frequency channels with other clusters and the status of channel occupation is determined for all SUs. This model-based learning method increases finding free channels and enhances spectral efficiency (SE) in presence of large probability of missing detection. Furthermore, each SU learns the presence pattern of primary user (PU) and gather a dynamic scan priority list to decrease scan overhead and access delays. Simulation results demonstrate the multi-agent reinforcement modified H-learning (MH-learning) method can achieve better performance in terms of PU usage percent, number of attempts, call block rate, and probability of detection in comparison to H-learning and some state-of-art learning methods. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Simplifying Digital Streaming: An Innovative Cross-Platform Streaming Solution 15

Simplifying Digital Streaming: An Innovative Cross-Platform ...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Muduli, Debendra Sahoo, Saroj Kumar Mishra, Jayanta Kumar Pradhan, Debasish Sharma, Santosh Kumar C.V Raman Global University Dept. of Computer Science Engineering Odisha Bhubaneswar India Centurion University of Technology and Management Dept. of Computer Science Engineering India GITA Autonomous College Dept. of Computer Science Engineering Odisha Bhubaneswar India

ISBN: (纸本)9798350370249

Our research aims to investigate how reinforcement learning methods can be applied to develop a movie recommendation system. We frame the issue of interactive recommendation as a contextual multi-armed bandit, where the system learns user preferences by suggesting new movies and receiving feedback. Through reinforcement learning, we address challenges such as balancing exploitation and exploration and tackling the coldstart problem. Additionally, we incorporate the novelty factor of movies into our model. We evaluate both content-based and collaborative filtering approaches which achieved accuracy 72.33(%), both of which demonstrate effective recommendation outcomes. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deliberating with AI: Improving Decision-Making for the Future through Participatory AI Design and Stakeholder Deliberation

引用

Proceedings of the ACM on Human-computer Interaction 2023年第CSCW1期7卷 1-32页

作者： Zhang, Angie Walker, Olympia Nguyen, Kaci Dai, Jiajun Chen, Anqing Lee, Min Kyung School of Information The University of Texas Austin United States Dept. of Computer Science The University of Texas Austin United States School of Business The University of Texas Austin United States Dept. of Electrical and Computer Engineering The University of Texas Austin United States

Research exploring how to support decision-making has often used machine learning to automate or assist human decisions. We take an alternative approach for improving decision-making, using machine learning to help stakeholders surface ways to improve and make fairer decision-making processes. We created "Deliberating with AI", a web tool that enables people to create and evaluate ML models in order to examine strengths and shortcomings of past decision-making and deliberate on how to improve future decisions. We apply this tool to a context of people selection, having stakeholders - -decision makers (faculty) and decision subjects (students) - -use the tool to improve graduate school admission decisions. Through our case study, we demonstrate how the stakeholders used the web tool to create ML models that they used as boundary objects to deliberate over organization decision-making practices. We share insights from our study to inform future research on stakeholder-centered participatory AI design and technology for organizational decision-making. © 2023 ACM.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A 4x4 MIMO Antenna Array for the Wi-Fi7Access Point on a Metal Wall Application

A 4x4 MIMO Antenna Array for the Wi-Fi7Access Point on a Met...

引用

2024 International Symposium on Antennas and Propagation, ISAP 2024

作者： Su, Hsin-Lung Zhan, You-Sheng Dept. of Computer and Communication National Pingtung University Taiwan Dept. of Computer Science and Information Engineering National Pingtung University Taiwan

ISBN: (纸本)9798350364774

A 4×4 CPW MIMO Antenna array with an artificial magnetic conductor (AMC) reflector is presented for Wi-Fi7 access point on a metal wall application in the study. The 10-dB impedance of the integrated MIMO antenna array covers the Wi-Fi 7 operating bands, and the transmission coefficients are under -15 dB in the whole Wi-Fi7 bands. This proposed integrated MIMO antenna is low profile and has good total radiation efficiency (over 60%). The height of the integrated MIMO antenna array is 6.325 mm. © 2024 IEEE.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

Authentication and Authorization in Zero Trust IoT: A Survey 35

Authentication and Authorization in Zero Trust IoT: A Survey

引用

35th Irish Systems and Signals Conference, ISSC 2024

作者： James, Meha Newe, Thomas O'Shea, Donna O'Mahony, George D. Munster Technological University Dept. Computer Science Cork Ireland University of Limerick Dept. Electronic and Computer Engineering Limerick Ireland

ISBN: (纸本)9798350352986

A critical challenge in implementing Zero trust (ZT) in Internet of Things (IoT) environments is ensuring secure authentication and authorization mechanisms. The work in this article delves into the intricate realm of ZT by critically examining the state-of-the-art authentication and authorization processes within the ZT framework for IoT. Despite the wealth of work on ZT and Zero Trust Architecture (ZTA), notable research gaps persist, specifically in identity authentication and fine-grained access control. Given the vast and diverse ecosystem of IoT devices, device identification complexities arise from a lack of unique hardware identifiers, rendering traditional methods susceptible to cyber-attacks, such as, spoofing. For dynamic IoT environments, achieving the optimal implementation in access policies poses a significant challenge. Numerous ZTA methodologies, integrating access controls, blockchain frameworks, and advancements in Artificial Intelligence (AI) and Machine Learning (ML), have been implemented to tackle these challenges. However, research gaps remain, particularly in understanding the behavioral aspects within these frameworks. As a result, this article focuses on identifying how device behavioral aspects can improve authentication and authorization in ZT for IoT. Finally, the article concludes by highlighting how these challenges can serve as future research directions. © 2024 IEEE.

关键词： Authorization

来源：评论

学校读者我要写书评

暂无评论

BERN-NN: Tight Bound Propagation For Neural Networks Using Bernstein Polynomial Interval Arithmetic 26

BERN-NN: Tight Bound Propagation For Neural Networks Using B...

引用

26th ACM International Conference on Hybrid Systems: Computation and Control, HSCC 2023, Part of CPS-IoT Week 2023

作者： Fatnassi, Wael Khedr, Haitham Yamamoto, Valen Shoukry, Yasser University of California Irvine United States Dept. of Electrical Engineering and Computer Science

ISBN: (纸本)9798400700330

In this paper, we present BERN-NN as an efficient tool to perform bound propagation of Neural Networks (NNs). Bound propagation is a critical step in wide range of NN model checkers and reachability analysis tools. Given a bounded input set, bound propagation algorithms aim to compute tight bounds on the output of the NN. So far, linear and convex optimizations have been used to perform bound propagation. Since neural networks are highly non-convex, state-of-the-art bound propagation techniques suffer from introducing large errors. To circumvent such drawback, BERN-NN approximates the bounds of each neuron using a class of polynomials called Bernstein polynomials. Bernstein polynomials enjoy several interesting properties that allow BERN-NN to obtain tighter bounds compared to those relying on linear and convex approximations. BERN-NN is efficiently parallelized on graphic processing units (GPUs). Extensive numerical results show that bounds obtained by BERN-NN are orders of magnitude tighter than those obtained by state-of-the-art verifiers such as linear programming and linear interval arithmetic. Moreoveer, BERN-NN is both faster and produces tighter outputs compared to convex programming approaches like alpha-CROWN. © 2023 Copyright held by the owner/author(s).

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

A Single-Weight Neural Network for MIMO Signal Detection: Algorithm and Implementation 10

A Single-Weight Neural Network for MIMO Signal Detection: Al...

引用

10th International Conference on engineering and Emerging Technologies, ICEET 2024

作者： Ho, Yi-Cheng Yen, Mao-Hsu Lu, Hoang-Yang National Taiwan Ocean University Dept. of Computer Science and Engineering Keelung Taiwan National Taiwan Ocean University Dept. of Electrical and Engineering Keelung Taiwan

ISBN: (纸本)9798331532895

Existing deep learning-based MIMO detectors often face substantial memory demands due to the need to store neural network weights, posing a significant challenge to practical implementation. To address this issue, we propose a single-weight neural network, namely SW-Net. By reducing each layer's weight vector to a scalar, the required hardware storage is significantly reduced. Simulation results demonstrate that hardware requirements can be reduced while maintaining bit error rate (BER) performance. Additionally, we present the corresponding VLSI hardware architecture, implemented using TSMC's 90-nm CMOS technology, operating at 707 MHz. This design requires 1109 kGEs and achieves a throughput of 707 Mbps. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

AI-Enabled Cyber Physical System And Battery Life Estimation For Smart Grid Applications 49

AI-Enabled Cyber Physical System And Battery Life Estimation...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： N.k, Anantha Padmanabhan Kumar, Aman Chitransh, Varun Singh, Rajeev Kumar Lal, Vivek Nandan Singh, Sanjay Kumar Dept. of Computer Science and Engineering Varanasi India Dept. of Electrical Engineering Varanasi India

ISBN: (纸本)9798350331820

In this paper, the development of an efficient three- layer Cyber Physical System (CPS) using a multi-output power electronic interface integrated with IoT-enabled modules and AI- based algorithms is presented. The power electronic interface layer of the proposed CPS eliminates the need of bulky electrolytic capacitors and reduces the switching loss. This layer facilitates DC to DC and DC to three-phase AC power conversion for battery charging and smart-grid applications respectively. AI-based algorithms are utilized for accurately predicting the Remaining Useful Life (RUL) of batteries. The performance of the proposed CPS is validated through simulation and experimental measurement results using a 700 W prototype system. The measurement results show that the proposed CPS enables real-time monitoring, accurate prediction of RUL, predictive maintenance decisions, data analytics, and optimized power flow. © 2023 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

EV Allocation and Charging within Parking Lots Using a Locational Marginal Pricing Mechanism

EV Allocation and Charging within Parking Lots Using a Locat...

引用

2023 IEEE PES Innovative Smart Grid Technologies Europe, ISGT EUROPE 2023

作者： Arias, Nataly Bañol Giraldo, Juan S. López, Juan Camilo Hoogsteen, Gerwin Hurink, Johann Dept. of Electrical Engineering Mathematics and Computer Science University of Twente Netherlands Netherlands

ISBN: (纸本)9798350396782

Electrifying parking lots (PLs) is becoming increasingly challenging as the number of electric vehicle (EV) chargers operating within PLs increases, putting a strain on the internal electricity grid. Reinforcing the local grid can be an expensive solution. Therefore, an alternative approach is to design a mechanism that optimizes the distribution of incoming EVs along the PL infrastructure, minimizing operating costs for the PL owner and the charging costs for EV users. This paper proposes a user-aware pricing mechanism for EV charging in PLs based on locational marginal prices (LMPs), which consists of a base tariff and a location-dependent tariff. A mixed-integer second-order programming model is developed to determine the optimal charging spot for each EV upon arrival at the PL. Results show that the proposed LMP-based allocation mechanism distributes the strain more evenly throughout the local grid, increasing the EV hosting capacity of the PL, while minimizing charging costs for users. Compared to a random allocation approach, the proposed mechanism resulted in 30.9% less energy not served and 17.5% lower charging costs. © 2023 IEEE.

关键词： Electric vehicles locational marginal prices optimization parking lots pricing mechanism

来源：评论

学校读者我要写书评

暂无评论

Robust and Predictive Charging of Large Electric Vehicle Fleets in Grid Constrained Parking Lots 14

Robust and Predictive Charging of Large Electric Vehicle Fle...

引用

14th IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, SmartGridComm 2023

作者： Hoogsteen, Gerwin Winschermann, Leoni Nijenhuis, Bart Arias, Nataly Banol Hurink, Johann L. University of Twente Dept. of Electrical Engineering Mathematics and Computer Science Enschede Netherlands

ISBN: (纸本)9781665455541

Grid congestion forms an obstacle for the adoption of electric vehicles (EVs) by companies for their sustainability goals. This paper presents a robust approach to smart charging of large fleets of EVs that only utilizes currently available technologies and data, such that it can be applied in practice. The method relies only on available data at charge point operators. The presented approach uses offline aggregated planning to determine a robust fill-level. Subsequently, this fill-level is used in online control to maximise the quality of service to users while being able to provide flexibility to the energy system. Simulation results using real data show that the self-consumption of PV energy can be improved from 72.0% to 85.4%. Furthermore, the energy not served is reduced from 5.9% to 2.8%. © 2023 IEEE.

关键词： Charging (batteries)

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：