检索结果-内蒙古大学图书馆

Improving Performance of Recurrent Neural Networks Using Simulated Annealing for Vertical Wind Speed Estimation

Energy engineering 2023年第4期120卷 775-789页

作者： Shafiqur Rehman HilalH.Nuha Ali Al Shaikhi Satria Akbar Mohamed Mohandes Interdisciplinary Research Center for Renewable Energy and Power Systems(IRC-REPS) KFUPMDhahran31261Saudi Arabia HUMIC Engineering School of ComputingTelkom UniversityBandung40257Indonesia Electrical Engineering Department King Fahd University of Petroleum&Minerals(KFUPM)Dhahran31261Saudi Arabia

An accurate vertical wind speed(WS)data estimation is required to determine the potential for wind farm *** general,the vertical extrapolation of WS at different heights must consider different parameters fromdifferent locations,such as wind shear coefficient,roughness length,and atmospheric *** novelty presented in this article is the introduction of two steps optimization for the Recurrent Neural Networks(RNN)model to estimate WS at different heights using measurements from lower *** first optimization of the RNN is performed to minimize a differentiable cost function,namely,mean squared error(MSE),using the Broyden-Fletcher-Goldfarb-Shanno ***,the RNN is optimized to reduce a non-differentiable cost function using simulated annealing(RNN-SA),namely mean absolute error(MAE).Estimation ofWS vertically at 50 m height is done by training RNN-SA with the actualWS data a 10–40 m *** estimatedWS at height of 50 m and the measured WS at 10–40 heights are further used to train RNN-SA to obtain WS at 60 m *** procedure is repeated continuously until theWS is estimated at a height of 180 *** RNN-SA performance is compared with the standard RNN,Multilayer Perceptron(MLP),Support Vector Machine(SVM),and state of the art methods like convolutional neural networks(CNN)and long short-term memory(LSTM)networks to extrapolate theWS *** estimated values are also compared with realWS dataset acquired using LiDAR and tested using four error metrics namely,mean squared error(MSE),mean absolute percentage error(MAPE),mean bias error(MBE),and coefficient of determination(R2).The numerical experimental results show that the MSE values between the estimated and actualWS at 180mheight for the RNN-SA,RNN,MLP,and SVM methods are found to be 2.09,2.12,2.37,and 2.63,respectively.

关键词： Vertical wind speed estimation recurrent neural networks simulated annealing multilayer perceptron support vector machine

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient joint user association and power allocation using Parameterized Deep DQN 9

Energy Efficient joint user association and power allocation...

引用

9th International Conference on Computer and Communication engineering, ICCCE 2023

作者： Mughees, Amna Tahir, Mohammad Sheikh, Muhammad Aman Amphawan, Angela Yap, Kian Meng Habaebi, Mohamed Hadi Islam, Md. Rafiqul Sunway University Dept. of Computing and Information Systems Petaling Jaya Malaysia University of Turku Dept. of Computing Turku Finland Cardiff Metropolitan University Dept. of Electronics and Computer Systems Engineering Cardiff United Kingdom International Islamic University Dept. of Electrical and Computer Engineering Kuala Lumpur Malaysia

ISBN: (纸本)9798350325218

Using small cells to create an ultra-dense network for 5G and beyond is a promising strategy to improve network coverage, data demands and reduce latency. Despite using small cells, these dense wireless networks result in performance degradation and increased energy consumption. Energy consumption is a crucial parameter for sustainable future wireless networks. In order to improve quality of service (QoS) and Energy Efficiency (EE), efficient resource allocation strategies are required. This paper investigates a Parameterized Double Deep Q-Network (PDDQN) based framework for joint user association and power allocation to improve EE and throughput. Apart from other conventional machine learning approaches, considering single state space of the joint optimization problem, our proposed framework considers both discrete and continuous state spaces. Our proposed PDDQN technique also solves the generalization problem that occurs due to similar states. The simulation results indicate that the proposed work significantly improves energy EE and throughput in large-scale learning problems. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Edge-Driven Industrial computing Power Networks: Digital Twin-Empowered Service Provisioning by Hybrid Soft Actor-Critic

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8095-8109页

作者： Zhang, Long Song, Deng-Ao Zhang, Hongliang Tian, Ni Zhuang, Zirui Niyato, Dusit Han, Zhu Hebei University of Engineering School of Information and Electrical Engineering Handan056038 China Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

With the proliferation of data-intensive industrial applications, the collaboration of computing powers among standalone edge servers is vital to provision such services for smart devices. In this paper, we propose an edge-driven industrial computing power network (CPN) by orchestrating the computing and network resources of edge servers through the centralized resource scheduling and decentralized task computing. However, efficient task offloading and collaborative processing is challenging, which requires higher degrees of network automation and intelligence. Therefore, we incorporate digital twins (DTs) into the edge-driven CPN architecture, where the DTs are created as the digital replicas to assist both the computation offloading and collaborative processing. A joint optimization problem of the computing power assignment, service association, task partition, and transmit power control is formulated for maximizing the system average weighted utility. Due to the temporal-spatial variability of tasks and the resulted dynamic environment, we transform the original problem as a Markov decision process aiming at maximizing the long-term average weighted utility. To efficiently handle the high-dimensional discrete-continuous action space, a hybrid soft actor-critic based deep reinforcement learning algorithm is developed for optimizing the joint design. Simulation results validate the superiority of our proposed algorithm over the benchmarks, showing the significant gains obtained by integrating DTs into the edge-driven CPN. © 1967-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

SNNGX: Securing Spiking Neural Networks with Genetic XOR Encryption on RRAM-based Neuromorphic Accelerator 24

SNNGX: Securing Spiking Neural Networks with Genetic XOR Enc...

引用

43rd International Conference on Computer-Aided Design, ICCAD 2024

作者： Wong, Kwunhang Wang, Songqi Huang, Wei Zhang, Xinyuan He, Yangu Lai, Karl M.H. Jiao, Yuzhong Lin, Ning Qi, Xiaojuan Chen, Xiaoming Wang, Zhongrui ACCESS – AI Chip Center for Emerging Smart Systems InnoHK Centers Hong Kong Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798400710773

Biologically plausible Spiking Neural Networks (SNNs), characterized by spike sparsity, are growing tremendous attention over intellectual edge devices and critical bio-medical applications as compared to artificial neural networks (ANNs). However, there is a considerable risk from malicious attempts to extract white-box information (i.e., weights) from SNNs, as attackers could exploit well-trained SNNs for profit and white-box adversarial concerns. There is a dire need for intellectual property (IP) protective measures. In this paper, we present a novel secure software-hardware co-designed RRAM-based neuromorphic accelerator for protecting the IP of SNNs. Software-wise, we design a tailored genetic algorithm with classic XOR encryption to target the least number of weights that need encryption. From a hardware perspective, we develop a low-energy decryption module, meticulously designed to provide zero decryption latency. Extensive results from various datasets, including NMNIST, DVSGesture, EEGMMIDB, Braille Letter, and SHD, demonstrate that our proposed method effectively secures SNNs by encrypting a minimal fraction of stealthy weights, only 0.00005% to 0.016% weight bits. Additionally, it achieves a substantial reduction in energy consumption, ranging from ×59 to ×6780, and significantly lowers decryption latency, ranging from ×175 to ×4250. Moreover, our method requires as little as one sample per class in dataset for encryption and addresses hessian/gradient-based search insensitive problems. This strategy offers a highly efficient and flexible solution for securing SNNs in diverse applications1 © 2024 Copyright is held by the owner/author(s).

关键词： Medical computing

来源：评论

学校读者我要写书评

暂无评论

TRANSMISSION SYSTEM MODEL IN THE TRACK-VEHICLE RELATIONSHIP BASED ON LONG TERM EVOLUTION TECHNOLOGY

引用

Archives of Transport 2023年第2期66卷 89-108页

作者： Chrzan, Marcin Pirosz, Pawel Paś, Jacek Faculty of Transport Electrical Engineering and Information Technology Kazimierz Pulaski University of Technology and Humanities in Radom Radom Poland Faculty of Computing and Telecommunications Poznan University of Technology Poznań Poland Division Electronic Systems Exploitations Manager Military University of Technology Warszawa Poland

Because of degradations of the wired infrastructure connecting the element of railroad control systems, and related primarily to their destruction, the use of the radio transmission medium for independent management of railroad traffic control devices is increasingly being considered. An undoubted problem in implying such solutions is the security of transmission in such systems. It should be noted that security at a certain level of transmission is currently already offered by the radio transmission systems themselves, which has also been used in the GSM-R standard. The creation of a separate dedicated system for railroads involves huge expenditures for the design, testing, certification and, finally, construction and implementation of such technology. Therefore, in the opinion of the author of this dissertation, it is possible to use public open radio networks for the needs of railroads, which significantly reduces costs, since such a system is based on existing infrastructure. It is necessary to develop a way of transmitting information that meets the requirements of secure transmission in the sense of railroad traffic control systems. The task is to develop a general model for open radio transmission in traffic control systems based on the latest public radio standard, which is LTE, 5G or Future Railway Mobile Communications System (FRMCS). The article will present the concept of data transmission in the track – vehicle relationship with the use of LTE (Long Term Evolution) technology. It will show the concept of transmission based on the PNEN50159:2011 standard and the results of the tests conducted during control trips on the railway route. The main element that will be subject to the research will include the transmission safety and its delay. The impact of a type of transmission encryption on its delay will be estimated with the assumed blocks of data sent during the transmission. A probability distribution and density functions of the transmission delay pro

关键词： Radio transmission

来源：评论

学校读者我要写书评

暂无评论

Modified pentagonal fractal antenna for ultra-wideband applications in communication systems

引用

International Journal of Electronics Letters 2024年第4期12卷 413-421页

作者： Singh, Gurmeet Kumar, Ashish Jit Singh, Mandeep Singh, A.P. School of Computing Science and Engineering Galgotias University Greater Noida India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Electrical Electronic and Systems Engineering Faculty of Engineering and Built Environment Universiti Kebangsaan Malaysia UKM Selangor Bangi Malaysia Department of Electronics and Communication Engineering Sant Longowal Institute of Engineering and Technology Punjab Longowal India

Due to the recent expansion in the generations of the communications systems, it is utmost priority to transmit a large amount of data over a wideband frequency spectrum. For this single ultra-wideband (UWB) antennas are the prime choice as compared to the multiple narrow band antennas. A modified pentagonal fractal patch antenna with a modified ground plane covering ultra-wideband has been proposed. The antenna has a compact size of 25 mm × 25 mm × 1.6 mm with peak gain of 2.2 dB. The UWB coverage of the design is achieved by implementing modified co-planar ground, modified fractal geometry and coplanar feed. The proposed design possesses the significant resonance and radiation performance with very compact size on low-cost substrate while covering the whole UWB. Finally, the simulated resonating and radiation characteristics have been validated with the measured characteristics of the fabricated prototype and the results are quite promising. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： antenna co-planer feed fractal Ultra-wideband

来源：评论

学校读者我要写书评

暂无评论

Human Decisions versus Multi-agent Reinforcement Learning in a Pursuit-evader Game

引用

IFAC-PapersOnLine 2024年第30期58卷 260-265页

作者： Takuma A. Adams Andrew C. Cullen Tansu Alpcan Department of Electrical and Electronic Engineering The University of Melbourne Parkville Australia School of Computing and Information Systems The University of Melbourne Parkville Australia

The modelling and analysis of nonlinear cyber-physical systems is integral to applications ranging from social networks to defence strategy. However, conventional linear-quadratic methods inadequately capture the complex nonlinear behaviour of human decision-makers in these systems. Utilising game theory and multi-agent reinforcement learning (MARL), we explore dynamic interactions between humans and machines within a cyber-physical environment, using a swarmalator to represent strategic humans in a pursuit-evader game. Preliminary results indicate that MARL inadequately captures the nonlinear behaviour of human decision-making, with pursuers and evaders exhibiting human behaviours achieving the highest utilities.

关键词： Decision-support for human operators Potential impact of automation open problems Advanced control design-linear non-linear stochastic large scale control systems

来源：评论

学校读者我要写书评

暂无评论

Converting Vocal Performances into Sheet Music Leveraging Large Language Models 24

Converting Vocal Performances into Sheet Music Leveraging La...

引用

24th IEEE International Conference on Data Mining Workshops, ICDMW 2024

作者： Jiang, Jinjing Teo, Nicole Pen, Haibo Ho, Seng-Beng Wang, Zhaoxia Mastercard Research and Development Singapore Singapore Singapore Management University School of Computing and Information Systems Singapore Singapore Tianjin University China School of Electrical and Information Engineering China AI Institute Global 139955 Singapore

ISBN: (纸本)9798331530631

Advanced natural language processing (NLP) models are increasingly applied in music composition and performance, particularly in generating vocal melodies and simulating singing voices. While NLP techniques have been successfully used to analyze vocal performance data, providing insights into performance quality and style, the automatic transcription of vocal performances into sheet music remains a complex challenge. Existing tools for manual transcription are often insufficient due to the intricate dynamics of vocal expression. This study addresses the challenge of automating the conversion of vocal performances into sheet music using a combination of novel techniques, including large language models (LLMs). We present a method that successfully translates vocal audio input into display-ready sheet music. Our findings highlight the strengths and limitations of various approaches, particularly in the transcription of a cappella performances into notes and lyrics. This research contributes to the expanding field of NLP-driven music analysis and showcases the potential of these models to revolutionize vocal transcription in the future. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Do we need watchful eyes on our workers? Ethics of using computer vision for workplace surveillance

AI and Ethics

引用

AI and Ethics 2025年 1-21页

作者： Sebastian, Rinu Ann Ehinger, Kris Miller, Tim School of Computing and Information Systems The University of Melbourne Carlton Australia School of Electrical Engineering and Computer Science The University of Queensland St Lucia Australia

In this paper, we critically examine the relevant ethical concerns of using computer vision-based surveillance in workplaces and propose an intent—and priority-based ethical framework for such systems. With the growing capabilities of computer vision technologies, its application in monitoring workplaces brings forth significant concerns. Organisations increasingly leverage computer vision for workplace surveillance to improve productivity, safety, and security. Unlike electronic surveillance techniques that monitor workers’ wire or electronic communication, computer vision-based workplace surveillance (CVWS) captures highly detailed visual and personal information about workers, including body language, emotional state, and actions. This makes CVWS potentially more intrusive than traditional electronic surveillance, raising a more comprehensive range of ethical considerations. However, this topic has received minimal attention in the current literature. Our proposed framework combines the intention for deploying surveillance with the moral notions of privacy, data security, fairness, transparency, explainability, autonomy, beneficence, nonmaleficence, dignity, and reliability to morally scrutinise CVWS systems. The paper proposes a second framework that aims to establish accountability among key stakeholders of the CVWS system. Further, we discuss two critical questions to consider when evaluating the necessity for CVWS systems in a work environment. In practice, this work will serve as a groundwork for stakeholders such as technical developers, employers, and regulatory and advocacy teams to make ethical design decisions during the developmental, operational, and maintenance stages of CVWS systems and devise proactive strategies to minimise potential harm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Coalitional Model Predictive Control of Building Zones Temperatures

Coalitional Model Predictive Control of Building Zones Tempe...

引用

European Control Conference (ECC)

作者： Filip Vrbanc Vinko Lešić Anita Banjac Mario Vašak University of Zagreb Faculty of Electrical Engineering and Computing Laboratory for Renewable Energy Systems Zagreb Croatia

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

This paper deals with the potential benefits of coalition-based modelling and control of building zones heating and cooling to enhance the overall energy efficiency of the building. The paper applies model predictive control for tracking of setpoint temperature in building zones. To tackle the complexity of the model, the approach utilizes semi-physical independent thermal models of building zones and models thermal connections between adjacent zones based on resistive-capacitive analogy. Such coupled models are formed into coalitions and are used in model predictive control of zone temperature. Realistic two 5-day simulations are conducted to compare the performance of the coalitional control. Results indicate that the coalitional control approach reduces energy consumption by up to 14.96% in comparison to decentralized approach of independent model predictive control of each zone while providing consumption increase of 1.38% compared to a centralized floor-based model predictive control. The paper provides evaluation of coalitional control performance based on trade-off between energy savings, user comfort, and computational complexity.

关键词： Heating systems Computational modeling Thermal resistance Buildings Europe Predictive models Energy efficiency

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：