检索结果-内蒙古大学图书馆

IEEE International conference on Communications (ICC)

作者： Yingshuo Gu Shuqi Chai Bowen Sun Yi Chen Qingjiang Shi School of Science and Engineering The Chinese University of Hong Kong Shenzhen Shenzhen Research Institute of Big Data China School of Software Engineering Tongji University Shanghai China

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Optimizing antenna parameters like azimuth, down-tilt, and power is crucial for coverage and capacity optimization (CCO) in next-generation wireless networks. However, traditional expert knowledge-based methods struggle to maintain optimal results when faced with changing environments. To address this, we propose a guided deep reinforcement learning (DRL) algorithm that learns a policy to dynamically adjust antenna parameters based on the evolving environment. Our approach employs proximal policy optimization-based DRL and integrates a problem-specific pretraining process using zero-order gradient descent. The pretrain policy serves as a guiding policy, enabling the agent to explore and discover high-reward regions, thus accel-erating the learning process. The performance of our solution is validated by numerical experiments conducted on a 5G simulation platform with real-world topological properties. The results show that our approach achieves significantly faster convergence and outperforms baseline methods in terms of CCO performance.

关键词： Heuristic algorithms Wireless networks Neural networks Knowledge based systems Deep reinforcement learning Numerical models Antennas

来源：评论

学校读者我要写书评

暂无评论

Design of Generalized Hopfield Neural Network based Fractional Order PI controller for Average Current mode control of Synchronous SEPIC Converter

Design of Generalized Hopfield Neural Network based Fraction...

引用

IEEE UP Section conference on Electrical Computer and Electronics (UPCON)

作者： Sundaramoorthy Sridhar M.G. Umamaheswari Rajalakshmi Engineering College Chennai India

ISBN: (数字)9781665403733

ISBN: (纸本)9781665447478

Synchronous rectified DC-DC Converters are widely used to power devices requiring low voltage and high current, including computer power supplies and PV-systems. This paper proposes Fractional Order Proportional Integral (FOPI) controllers for Average Current Mode (ACM) Control of synchronous SEPIC converter. The parameters of the FOPI controllers used in the inner and outer loop for given specifications are found by means of the Generalized Hopfield Neural Network (GHNN) based optimization technique. The converter's state-space model is derived using the state-space averaging technique by considering the parasitic resistance in each component. The transient and steady-state performances of the closed-loop system are analyzed and compared with conventional Proportional Integral(PI) controllers tuned using other optimization techniques such as Genetic Algorithm(GA) and Particle Swarm optimization(PSO) for variations in the input, reference voltage, and load variations using Matlab/ Simulink software tool. It is observed that the proposed GHNN based FOPI controller have better performance in terms of indices like less settling time, overshoot, steady-state error than conventional PI controllers tuned using GA and PSO based optimization techniques.

关键词： PI control Hopfield neural networks DC-DC power converters Steady-state Voltage control optimization Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on control of DC speed-regulated electric energy vehicle based on PSO optimization

Research on control of DC speed-regulated electric energy ve...

引用

IEEE International conference on Automation, Electronics and Electrical Engineering (AUTEEE)

作者： Xiaolong Li Jibao Pan Qingao Zhao College of Electrical and Information Engineering Anhui University of Science and Technology Huainan China College of Electrical Information Engineering Wanjiang University of Technology Huainan China College of Electrical Engineering and Automation Qilu University of Technology Jinan China

ISBN: (数字)9781665471978

ISBN: (纸本)9781665471985

Aiming at the problem that the traditional electric energy vehicle speed control system is challenging to meet its application in high speed, high precision, and large disturbance, a particle swarm optimization PID energy vehicle control algorithm is proposed in this paper. Firstly, the DC motor speed regulation system controlled by the STC89C52 microcontroller is designed to realize its speed regulation function, and the PID control algorithm optimizes the graph curve to realize the design of the controller. Then the composition and operation principle of the servo motor model is introduced, and its mathematical model is analyzed under ideal conditions. Then, the simulation model of PID self-tuning is built under the Simulink platform to obtain the characteristics of each PID link. Because the traditional PID parameter tuning process is generally time-consuming and laborious, and some complex systems have certain hysteresis, nonlinear and other factors, which makes the PID parameter tuning difficult. To this end, the basic principle, composition, and structure of the PSO algorithm are analyzed, and it is combined with the PID algorithm, and the particle swarm algorithm is innovatively applied to the optimization problem of each parameter of the PID regulator and is based on the MATLAB/Simulink platform. Simulation experiments are carried out, and the results show that the PID regulator optimized by particle swarm optimization has excellent control performance in all aspects, which makes the speed control system have the advantages of rapid response, high control accuracy, anti-interference, and good adaptability.

关键词： Regulators software packages Velocity control DC motors Mathematical models Regulation Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Incorporating invariants in Mahalanobis distance based classifiers: application to face recognition

Incorporating invariants in Mahalanobis distance based class...

引用

International Joint conference on Neural Networks (IJCNN)

作者： A.M. Fraser N.W. Hengartner K.R. Vixie B.E. Wohlberg Los Alamos National Laboratory Portland State University USA Los Alamos National Laboratory Los Alamos NM USA

We present a technique for combining prior knowledge about transformations that should be ignored with a covariance matrix estimated from training data to make an improved Mahalanobis distance classifier. Modern classification problems often involve objects represented by high-dimensional vectors or images (for example, sampled speech or human faces). The complex statistical structure of these representations is often difficult to infer from the relatively limited training data sets that are available in practice. Thus, we wish to efficiently utilize any available a priori information, such as transformations or the representations with respect to which the associated objects are known to retain the same classification (for example, spatial shifts of an image of a handwritten digit do not alter the identity of the digit). These transformations, which are often relatively simple in the space of the underlying objects, are usually nonlinear in the space of the object representation, making their inclusion within the framework of a standard statistical classifier difficult. Motivated by prior work of Simard et al. (1998; 2000), we have constructed a new classifier which combines statistical information from training data and linear approximations to known invariance transformations. When tested on a face recognition task, performance was found to exceed by a significant margin that of the best algorithm in a reference software distribution.

关键词： Face recognition Training data Laboratories Covariance matrix State estimation Speech Humans Linear approximation software testing software algorithms

来源：评论

学校读者我要写书评

暂无评论

Joint Computing Offloading and Resource Allocation in MEC-Enabled IoT: A Diffusion-Based Reinforcement Learning Approach

Joint Computing Offloading and Resource Allocation in MEC-En...

引用

IEEE International conference on Systems, Man and Cybernetics

作者： Huimin Cao Bo Xiao MoE Engineering Research Center for Software/Hardware Co-Design Technology and Application East China Normal University Shanghai China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

The integration of the Internet of Things (IoT) with mobile edge computing (MEC) has come out to be a promising solution to address the requirements of high computing capabilities and low latency services, enabling user equipments(UE) to migrate the computation of tasks onto edge servers. This paper focuses on optimizing the performance of MEC-enabled IoT system by formulating a joint computing offloading and resource allocation problem. The objective is to minimize the total delay of the system consisting of multiple servers and multiple users. The denoising network of a diffusion model with capabilities of generation can be trained to obtain optimal solution given the changed environment conditions. Therefore, we propose the diffusion-based deep deterministic policy gradient (DiffDDPG) algorithm which utilizes a diffusion model as the policy to learn optimal decisions jointly. Simulation results exhibits the superior performance of the DiffDDPG algorithm.

关键词： Heuristic algorithms Simulation Training data Reinforcement learning Diffusion models Delays Resource management Servers Internet of Things optimization

来源：评论

学校读者我要写书评

暂无评论

Detection of Errors in Jumping Landing Form of Basketball Players Using Support Vector Machine

Detection of Errors in Jumping Landing Form of Basketball Pl...

引用

International conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM)

作者： Jessie R. Balbin Royce D. Bumagat Sebastian Paul O. Uy School of Electrical Electronics and Computer Engineering Mapua University Manila Philippines

ISBN: (数字)9798350381177

ISBN: (纸本)9798350381184

With its frequent direction changes, rapid acceleration, and high jumps, basketball poses an elevated risk of landing-related injuries, such as ankle sprains and ACL tears. This research aims to create a detection system for evaluating a basketball player's jump-landing technique to mitigate injury risks. The system leverages an image processing algorithm, specifically employing Support Vector Machine and Image Processing techniques. The system is subject to assessment by experienced basketball coaches to validate its accuracy. Data is collected using a Kinect sensor and a laptop webcam, and specialized software processes this data to extract pertinent features. The system's results are then compared with coach assessments, with the data and analysis outcomes securely stored. The system effectively identifies optimal jump-landing techniques by assessing joint angles and critical landing components, as demonstrated through solid statistical correlations with reference postures. The potential impact of this system extends to reducing injury risks and enhancing player performance in basketball, offering promising implications for the sport's safety and performance optimization.

关键词： Support vector machines Correlation Webcams software algorithms Solids Feature extraction Vectors

来源：评论

学校读者我要写书评

暂无评论

SADP: A State-Aware Domain Partition Approach in Large Scale software Defined Networking 2017

SADP: A State-Aware Domain Partition Approach in Large Scale...

引用

Proceedings of the 2017 2nd International conference on Communication and Information Systems

作者： Jie Gao Jiangxing Wu Tao Hu National Digital Switching System Engineering & Technology Research Center Zhengzhou Henan

ISBN: (纸本)9781450353489

Distributed multi-domain network architecture has improved the reliability and scalability of software defined networking (SDN). However, it also introduces a new challenge to domain partition because of the uncertainty of network state. In the multi-domain SDN, both excessive and few switch deployments in each domain will bring about the load imbalance of domain controllers and the poor network stability. To address the above problems, for a given large scale SDN network, this paper proposes a State-Aware Domain Partition (SADP) approach. Firstly, through collecting the information of distance, delay and traffic in the network, SADP perceives the network state of all devices, and builds the corresponding state-aware lists of switches and controllers, respectively. Then, according to the specific sequencing of elements in the lists, the awareness connections between switches and controllers are implemented to partition multiple domains and construct the distributed SDN network. Finally, simulation shows that, compared with the typical algorithms, SADP can achieve the better performance of SDN domain partition, which has low processing delay and high load balancing rate.

关键词： controller domain partition software defined networking network optimization

来源：评论

学校读者我要写书评

暂无评论

FPGA-based feedback control of quantum optics experiments with the open source software package PyRPL

arXiv

引用

arXiv 2023年

作者： Neuhaus, Leonhard Croquette, Michaël Metzdorff, Rémi Chua, Sheon Jacquet, Pierre-Edouard Journeaux, Alexandre Heidmann, Antoine Briant, Tristan Jacqmin, Thibaut Cohadon, Pierre-François Deléglise, Samuel Laboratoire Kastler Brossel Sorbonne Université ENS - Université PSL Collège de France CNRS 4 place Jussieu ParisF-75005 France

We present PyRPL, an open source software package that allows the implementation of automatic digital feedback controllers for quantum optics experiments on commercially available, affordable FPGA boards. Our software implements the digital generation of various types of error signals, from an analog input through the application of loop filters of high complexity and real-time gain adjustment for multiple analog output signals, including different algorithms for resonance search, lock acquisition sequences and in-loop gain optimization. Furthermore, all necessary diagnostic instruments such as an oscilloscope, a network analyzer and a spectrum analyzer are integrated into our software. Apart from providing a quickly scalable, automatic feedback controller, the lock performance that can be achieved by using PyRPL with imperfect equipment such as piezoelectric transducers and noisy amplifiers is better than the one achievable with standard analog controllers due to the higher complexity of implementable filters and possibilities of nonlinear operations in the FPGA. This drastically reduces the cost of added complexity when introducing additional feedback loops to an experiment. The open-source character also distinguishes PyRPL from commercial solutions, as it allows users to customize functionalities at various levels, ranging from the easy integration of PyRPL-based feedback controllers into existing setups to the modification of the FPGA functionality. A community of developers provides fast and efficient implementation and testing of software modifications. © 2023, CC BY.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Joint End-to-End Image Compression and Denoising: Leveraging Contrastive Learning and Multi-Scale Self-Onns

Joint End-to-End Image Compression and Denoising: Leveraging...

引用

IEEE International conference on Image Processing

作者： Yuxin Xie Li Yu Farhad Pakdaman Moncef Gabbouj School of Software Nanjing University of Information Science and Technology Nanjing China School of Computer Science Nanjing University of Information Science and Technology Nanjing China Faculty of Information Technology and Communication Sciences Tampere University Finland

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Noisy images are a challenge to image compression algorithms due to the inherent difficulty of compressing noise. As noise cannot easily be discerned from image details, such as high-frequency signals, its presence leads to extra bits needed for compression Since the emerging learned image compression paradigm enables end-to-end optimization of codecs, recent efforts were made to integrate denoising into the compression model, relying on clean image features to guide denoising. However, these methods exhibit suboptimal performance under high noise levels, lacking the capability to generalize across diverse noise types. In this paper, we propose a novel method integrating a multi-scale denoiser comprising of Self Organizing Operational Neural Networks, for joint image compression and denoising. We employ contrastive learning to boost the network ability to differentiate noise from high frequency signal components, by emphasizing the correlation between noisy and clean counterparts. Experimental results demonstrate the effectiveness of the proposed method both in rate-distortion performance, and codec speed, outperforming the current state-of-the-art.

关键词： Training Image coding Codecs Noise reduction Noise Rate-distortion Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Speed Control of Six-Phase Permanent Magnet Synchronous Motor Based on a Brand New Approach Law Integral Sliding Mode Structure

Speed Control of Six-Phase Permanent Magnet Synchronous Moto...

引用

Power and Energy Engineering (ICPEE), International conference on

作者： Yunkai Guo Wei Xie Lin Tan Department of Electrical Automation Shanghai Maritime University Shanghai China

ISBN: (纸本)9781665464765

As a nonlinear multivariable strongly coupled variable-parameter complex object, the six-phase permanent magnet synchronous motor is sensitive to external disturbances and internal parameter variations. In order to heighten the dynamic quality of the motor speed control system, an integral sliding mode variable structure speed control algorithm based on a brand new variable exponential convergence law is proposed. The convergence law is based on the conventional exponential convergence law, and introduces a variable speed convergence term, and combines the integral sliding mode surface to overcome the shortcomings of the conventional exponential convergence law, heighten the sliding mode convergence rate, and effectively suppress the inherent chattering of the sliding mode control. The stability of the new exponential convergence law is analyzed by using Lyapunov function, and the new convergence law is used to design the sliding mode speed regulator for six-phase permanent magnet synchronous motor control system and compare it with the conventional exponential convergence law and PI controller. As illustrated by the simulation tests, the designed sliding mode controller has better anti-load disturbance performance, no overshoot, very small chattering, and high robustness.

关键词： PI control Heuristic algorithms Velocity control software algorithms Permanent magnet motors Synchronous motors Robustness

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：