检索结果-内蒙古大学图书馆

2022 International Joint Conference on Neural Networks, IJCNN 2022

作者： Yue, Zhixiong Lin, Baijiong Zhang, Yu Liang, Christy Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology China Southern University of Science and Technology Department of Computer Science and Engineering China School of Computer Science University of Technology Sydney Australia Peng Cheng Laboratory China

ISBN: (数字)9781728186719

ISBN: (纸本)9781728186719

Designing neural network architecture for embedded devices is practical but challenging because the models are expected to be not only accurate but also enough lightweight and robust. However, it is challenging to balance those trade-offs manually because of the large search space. To solve this problem, we propose an Effective, Efficient, and Robust Neural Architecture Search (E2RNAS) method to automatically search a neural network architecture that balances the performance, robustness, and resource consumption. Unlike previous studies, the objective function of the proposed E2RNAS method is formulated as a multi-objective bi-level optimization problem with the upper-level subproblem as a multi-objective optimization problem that considers the performance, robustness, and resource consumption. To solve the proposed objective function, we integrate the multiple-gradient descent algorithm, a widely studied gradient-based multi-objective optimization algorithm, with the bi-level optimization. Experiments on benchmark datasets show that the proposed E2RNAS method can find robust architecture with low resource consumption and comparable classification accuracy. © 2022 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Effective Handover Process for Reliable Video Streaming Over Software-Defined Wireless Networking 12th

Effective Handover Process for Reliable Video Streaming Over...

引用

12th EAI International Conference on Simulation Tools and Techniques, SIMUtools 2020

作者： Puttaswami, Kavyashree Lung, Chung-Horng Department of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada Department of Systems and Computer Engineering Carleton University OttawaON Canada

ISBN: (纸本)9783030727918

Handover process plays a crucial role in a Wireless Local Area Network (WLAN) with multiple Access Points (APs). To meet Quality of Service (QoS) or Quality of Experience (QoE) requirements for end-users, especially during video transmissions, such as real-time multimedia streaming or VoIP, the time required for handovers from one AP to another AP should be highly efficient;otherwise, end users may likely experience packet losses or longer delay, which leads to loss of significant information and degraded QoS/QoE. This paper discusses handover mechanisms using Software Defined Networking (SDN) for AP selection in a WLAN. The proposed approach enhances the existing handover process by considering both the received signal strength and load balancing of APs in order to provide better QoS/QoE during video transmissions over a Software-defined WLAN with multiple APs. A number of experiments have been performed using the Mininet-WiFi environment and the Ryu SDN controller. The results show that the proposed method improves QoS/QoE with lower delay, higher transmitted bytes, and visually higher quality video images. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2021.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Assessing the Performance of AI-Generated Code: A Case Study on GitHub Copilot

Assessing the Performance of AI-Generated Code: A Case Study...

引用

International Symposium on Software Reliability engineering (ISSRE)

作者： Shuang Li Yuntao Cheng Jinfu Chen Jifeng Xuan Sen He Weiyi Shang School of Computer Science Wuhan University Wuhan China Department of Systems and Industrial Engineering University of Arizona Tucson United States Department of Electrical and Computer Engineering University of Waterloo Waterloo Canada

ISBN: (数字)9798350353884

ISBN: (纸本)9798350353891

The integration of Large Language Models (LLMs) into software development tools like GitHub Copilot holds the promise of transforming code generation processes. While AI-driven code generation presents numerous advantages for software development, code generated by large language models may introduce challenges related to security, privacy, and copyright issues. However, the performance implications of AI-generated code remain insufficiently explored. This study conducts an empirical analysis focusing on the performance regressions of code generated by GitHub Copilot across three distinct datasets: HumanEval, AixBench, and MBPP. We adopt a comprehensive methodology encompassing static and dynamic performance analyses to assess the effectiveness of the generated code. Our findings reveal that although the generated code is functionally correct, it frequently exhibits performance regressions compared to code solutions crafted by humans. We further investigate the code-level root causes responsible for these performance regressions. We identify four major root causes, i.e., inefficient function calls, inefficient looping, inefficient algorithm, and inefficient use of language features. We further identify a total of ten sub-categories of root causes attributed to the performance regressions of generated code. Additionally, we explore prompt engineering as a potential strategy for optimizing performance. The outcomes suggest that meticulous prompt designs can enhance the performance of AI-generated code. This research offers valuable insights contributing to a more comprehensive understanding of AI-assisted code generation.

关键词： Privacy Codes Large language models Focusing Software reliability Performance analysis Prompt engineering Security Software development management

来源：评论

学校读者我要写书评

暂无评论

Large-signal Stability Analysis of Grid-forming Inverters with Equivalent-circuit Models

引用

IEEE Transactions on Energy Conversion 2025年

作者： Baeckeland, Nathan Pal, Diptak Seo, Gab-Su Johnson, Brian Dhople, Sairaj National Renewable Energy Laboratory Power Systems Engineering Center GoldenCO80401 United States Hitachi Energy Ltd United States University of Texas Chandra Family Department of Electrical and Computer Engineering AustinTX United States University of Minnesota Department of Electrical and Computer Engineering MN United States

This paper proposes an energy function-based direct method for large-signal stability assessment of grid-forming (GFM) inverters leveraging an equivalent-circuit representation of all involved control- and physical-layer dynamics. Three different primary controls, a standard inner-current outer-voltage cascaded-control architecture, output CL filter, and reference-current saturation limiting are featured in the modeling and analysis framework. A composite energy function for the GFM inverter is obtained by summing up individual energy contributions gleaned from the circuit representation. The approach can readily be generalized to different primary controls, output-filter arrangements, and current limiters since it is based on a circuit-theoretic foundation. Numerical simulations validate the efficacy of the approach in estimating the critical clearing time following a large-signal disturbance. © 1986-2012 IEEE.

关键词： Electric network analysis

来源：评论

学校读者我要写书评

暂无评论

Design Optimization of NOMA Aided Multi-STAR-RIS for Indoor Environments: A Convex Approximation Imitated Reinforcement Learning Approach

引用

IEEE Transactions on Mobile Computing 2025年

作者： Park, Yu Min Hassan, Sheikh Salman Tun, Yan Kyaw Huh, Eui-Nam Saad, Walid Hong, Choong Seon Kyung Hee University Department of Computer Science and Engineering Yongin-si Gyeonggi-do17104 Korea Republic of Bradley Department of Electrical and Computer Engineering Virginia Tech VA22203 United States Aalborg University Department of Electronic Systems Kobenhavn2450 Denmark

Non-orthogonal multiple access (NOMA) enables multiple users to share the same frequency band, and simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) provides 360-degree full-space coverage, optimizing both transmission and reflection for improved network performance and dynamic control of the indoor environment. However, deploying STAR-RIS indoors presents challenges in interference mitigation, power consumption, and real-time configuration. In this work, a novel network architecture utilizing multiple access points (APs), STAR-RISs, and NOMA is proposed for indoor communication. To address these, we formulate an optimization problem involving user assignment, access point (AP) beamforming, and STAR-RIS phase control. A decomposition approach is used to solve the complex problem efficiently, employing a many-to-one matching algorithm for user-AP assignment and K-means clustering for resource management. Additionally, multi-agent deep reinforcement learning (MADRL) is leveraged to optimize the control of the STAR-RIS. Within the proposed MADRL framework, a novel approach is introduced in which each decision variable acts as an independent agent, enabling collaborative learning and decision making. The MADRL framework is enhanced by incorporating convex approximation (CA), which accelerates policy learning through suboptimal solutions from successive convex approximation (SCA), leading to faster adaptation and convergence. Simulations demonstrate significant improvements in network utility compared to baseline approaches. © 2025 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

A Mixed-Integer Linear Programming Approach to Maintenance Budgeting in electrical Distribution Networks Considering Repair Time Uncertainty

A Mixed-Integer Linear Programming Approach to Maintenance B...

引用

2023 International Conference on Future Energy Solutions, FES 2023

作者： Mirsaeedi, Hamed Hassankashi, Alireza Sajjadi, Mahsa Siano, Pierluigi University of Tehran Tehran Iran Iran University of Science and Technology Tehran Iran University of Tennessee Department of Electrical and Computer Engineering KnoxvilleTN United States University of Salerno Department of Management & Innovation Systems Salerno84084 Italy

ISBN: (纸本)9798350332308

As a component of asset management strategies, maintenance management is essential for improving the reliability of the electrical Distribution Networks (EDNs). To increase system efficiency, electricity companies invest a significant effort to assign their financial sources to important system components. In this paper, a mixed-integer linear programming approach to maintenance budgeting considering restoration time uncertainty is suggested. The suggested technique finds the optimal budget for doing maintenance tasks in distribution network feeders. The objective is to reduce overall cost, which includes total interruption cost of customer (TCCIC), total energy not supplied cost TCENS), total cost of materials and labor for repair (TCREP), and total cost of maintenance (TCPM). Three cases are also taken into account to observe the effectiveness of the suggested maintenance method: Case I assumes that no maintenance actions are performed in the system, in Case II, maintenance budget for each distribution feeder is taken into consideration equally, in Case III, according to constraints, the suggested formulation allocates the optimal maintenance budget. The Roy Billinton test system's bus number two (RBTS2) is subjected to the proposed reliability improvement approaches, and the results are discussed. © 2023 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Training Graph Neural Networks on Growing Stochastic Graphs

Training Graph Neural Networks on Growing Stochastic Graphs

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Juan Cerviño Luana Ruiz Alejandro Ribeiro Department of Electrical and Systems Engineering University of Pennsylvania Philadelphia USA Computer Science & Artificial Intelligence Laboratory MIT Cambridge USA

Graph Neural Networks (GNNs) rely on graph convolutions to exploit meaningful patterns in networked data. Based on matrix multiplications, convolutions incur in high computational costs leading to scalability limitations in practice. To overcome these limitations, proposed methods rely on training GNNs in smaller number of nodes, and then transferring the GNN to larger graphs. Even though these methods are able to bound the difference between the output of the GNN with different number of nodes, they do not provide guarantees against the optimal GNN on the very large graph. In this paper, we propose to learn GNNs on very large graphs by leveraging the limit object of a sequence of growing graphs, the graphon. We propose to grow the size of the graph as we train, and we show that our proposed methodology – learning by transference – converges to a neighborhood of a first order stationary point on the graphon data. A numerical experiment validates our proposed approach.

关键词： Training Convolution Scalability Signal processing algorithms Graph neural networks Acoustics Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

How Much Reserve Fuel: Quantifying the Maximal Energy Cost of System Disturbances 63

How Much Reserve Fuel: Quantifying the Maximal Energy Cost o...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Padmanabhan, Ram Bakker, Craig Dinkar, Siddharth Abhijit Ornik, Melkior University of Illinois Urbana-Champaign Department of Electrical and Computer Engineering UrbanaIL United States University of Illinois UrbanaChampaign Coordinated Science Laboratory UrbanaIL United States National Security Directorate Pacific Northwest National Laboratory RichlandWA United States University of Illinois UrbanaChampaign Department of Aerospace Engineering UrbanaIL United States

ISBN: (纸本)9798350316339

Motivated by the design question of additional fuel needed to complete a task in an uncertain environment, this paper introduces metrics to quantify the maximal additional energy used by a control system in the presence of bounded disturbances when compared to a nominal, disturbance-free system. In particular, we consider the task of finite-time stabilization for a linear time-invariant system. We first derive the nominal energy required to achieve this task in a disturbance-free system, and then the worst-case energy over all feasible disturbances. The latter leads to an optimal control problem with a least-squares solution, and then an infinited-imensional optimization problem where we derive an upper bound on the solution. The comparison of these energies is accomplished using additive and multiplicative metrics, and we derive analytical bounds on these metrics. Simulation examples on an ADMIRE fighter jet model demonstrate the practicability of these metrics, and their variation with the task hardness, a combination of the distance of the initial condition from the origin and the task completion time. © 2024 IEEE.

关键词： Linear time-invariant system

来源：评论

学校读者我要写书评

暂无评论

Deep nonparametric estimation of operators between infinite dimensional spaces

引用

The Journal of Machine Learning Research 2024年第1期25卷 1239-1305页

作者： Hao Liu Haizhao Yang Minshuo Chen Tuo Zhao Wenjing Liao Department of Mathematics Hong Kong Baptist University Hong Kong Department of Mathematics and Department of Computer Science University of Maryland College Park Department of Electrical and Computer Engineering Princeton University School of Industrial and Systems Engineering Georgia Institute of Technology School of Mathematics Georgia Institute of Technology

Learning operators between infinitely dimensional spaces is an important learning task arising in machine learning, imaging science, mathematical modeling and simulations, etc. This paper studies the nonparametric estimation of Lipschitz operators using deep neural networks. Non-asymptotic upper bounds are derived for the generalization error of the empirical risk minimizer over a properly chosen network class. Under the assumption that the target operator exhibits a low dimensional structure, our error bounds decay as the training sample size increases, with an attractive fast rate depending on the intrinsic dimension in our estimation. Our assumptions cover most scenarios in real applications and our results give rise to fast rates by exploiting low dimensional structures of data in operator estimation. We also investigate the influence of network structures (e.g., network width, depth, and sparsity) on the generalization error of the neural network estimator and propose a general suggestion on the choice of network structures to maximize the learning efficiency quantitatively.

关键词： deep neural networks nonparametric estimation operator learning generalization error analysis

来源：评论

学校读者我要写书评

暂无评论

NeuroMorse: A Temporally Structured Dataset For Neuromorphic Computing

arXiv

引用

arXiv 2025年

作者： Walters, Ben Bethi, Yeshwanth Kergan, Taylor Nguyen, Binh Amirsoleimani, Amirali Eshraghian, Jason K. Afshar, Saeed Azghadi, Mostafa Rahimi College of Science and Engineering James Cook University Townsville Australia International Centre for Neuromorphic Systems Western Sydney University Australia Department of Electrical Engineering and Computer Science York University Toronto Canada Department of Electrical and Computer Engineering University of California Santa Cruz United States

Neuromorphic engineering aims to advance computing by mimicking the brain’s efficient processing, where data is encoded as asynchronous temporal events. This eliminates the need for a synchronisation clock and minimises power consumption when no data is present. However, many benchmarks for neuromorphic algorithms primarily focus on spatial features, neglecting the temporal dynamics that are inherent to most sequence-based tasks. This gap may lead to evaluations that fail to fully capture the unique strengths and characteristics of neuromorphic systems. In this paper, we present NeuroMorse, a temporally structured dataset designed for benchmarking neuromorphic learning systems. NeuroMorse converts the top 50 words in the English language into temporal Morse code spike sequences. Despite using only two input spike channels for Morse dots and dashes, complex information is encoded through temporal patterns in the data. The proposed benchmark contains feature hierarchy at multiple temporal scales that test the capacity of neuromorphic algorithms to decompose input patterns into spatial and temporal hierarchies. We demonstrate that our training set is challenging to categorise using a linear classifier and that identifying keywords in the test set is difficult using conventional methods. The NeuroMorse dataset is available at 10.5281/zenodo.12702379, with our accompanying code at https://***/jc427648/NeuroMorse. © 2025, CC BY.

关键词： Spatio-temporal data

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：