检索结果-内蒙古大学图书馆

Image Processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Tusongjiang Kari Ziwei Zhang Yufeng He Dejin Wang Jing Jia Xiaojing Ma School of Electrical Engineering Xinjiang University Urumqi China Sichuan Energy Internet Research Institute Tsinghua University Chengdu China Ultra High Voltage Branch State Grid Sichuan Electric Power Company Chengdu China YGSOFT INC. Zhuhai China China Qiyuan Engineering Corporation Xi’an China

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

To preserve the image details more precisely and fully after image filtering, a directional mean filtering algorithm based on the edge direction of noise points is proposed. Firstly, pepper and salt noise recognizer model based on single hidden layer neural network is established. Afterwards, pepper and salt noise recognizer is trained to detect noise points, respectively. Then, according to the neighborhood pixel value of the noise point, the direction with the smallest pixel difference is regarded as the edge direction. Finally, the pixel value of the noise point is replaced by the average value of the pixel in the edge direction. The experimental results indicates that the filtering effect of the algorithm is superior to other algorithms on low and medium noise concentrations, with a PSNR value up to 82.0dB. While for the high concentration of noise, the PSNR value and consumed computational time are less than 3.2dB and 3.91s, respectively. According to the experimental results, the proposed algorithm provides a better capability of filtering and displaying detailed information of the image, and significant guidance on promoting the construction of the energy Internet and digital grid.

关键词： Salt filtering Image edge detection Noise Energy Internet Artificial neural networks Machine learning filtering algorithms Power grids Power transformers

来源：评论

学校读者我要写书评

暂无评论

Study of Wind Power Fluctuation Based on Simulated Annealing Algorithm and Each filtering Algorithm

Study of Wind Power Fluctuation Based on Simulated Annealing...

引用

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

作者： Zhihui Jiao Chuanshi Cui Zhiyuan Gao Youyao Li Tianyi Zhang Xinjiang University Urumqi China

ISBN: (数字)9798350377033

ISBN: (纸本)9798350377040

This paper investigates the wind power fluctuation problem based on the simulated annealing algorithm and multiple filtering algorithms, aiming to improve the output stability of wind farms and enhance the grid's ability to absorb wind energy. To this end, this paper proposes an energy storage system that makes use of decommissioned power batteries in a gradual manner, and constructs a cooperative scheduling model for wind farms and energy storage systems to optimise charging and discharging operations. Firstly, this paper applies low-pass filtering, Gaussian filtering and sliding average filtering algorithms to process the raw wind power data in order to weaken the noise interference and smooth the power output. Secondly, a simulated annealing algorithm is used to optimally configure the capacity of the energy storage system and finally determine the optimal solution for the rated capacity. The study makes gradual use of retired power batteries, combines multiple filtering algorithms and optimal configurations, systematically solves the problem of wind power fluctuation, and improves the ultimate benefit of wind power grid integration.

关键词： Fluctuations filtering Noise Simulated annealing Wind power generation filtering algorithms Wind farms Power system stability Stability analysis Batteries

来源：评论

学校读者我要写书评

暂无评论

Multipath Ghost Suppression Based on Frequency Domain filtering for Through-the-Wall Radar

Multipath Ghost Suppression Based on Frequency Domain Filter...

引用

Signal, Information and Data Processing (ICSIDP), IEEE International Conference on

作者： Feiyang Liu Xiaolong Sun Hao Zhang Yiming Wang Xiaodong Qu Xiaopeng Yang School of Information and Electronics Beijing Institute of Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Moving target detection based on unmanned aerial vehicle (UAV)-borne multichannel through-the-wall radar has found wide applications in military and civilian domains. However, multipath reflections within indoor environments lead to multipath ghost in imaging results, which cause the generation of false alarms. To address this issue, this article proposes a method for suppressing multipath artifacts in UAV-borne multichannel through-the-wall radar based on frequency-domain filtering. In the proposed method, the differences between the multipath echoes and the direct path echoes in the range-Doppler domain are analyzed. Subsequently, a frequency domain filtering method is proposed to filter out multipath echoes. Finally, the back-projection algorithm is used to achieve through-the-wall imaging. Simulations demonstrate the feasibility and effectiveness of the proposed method.

关键词： filtering Frequency-domain analysis Imaging Radar detection Object detection Radar imaging filtering algorithms Logic gates Reflection Indoor environment

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Collaborative filtering Recommendation Algorithm Based on Graph Neural Network

Design and Implementation of Collaborative Filtering Recomme...

引用

Information and Communication Technology (ICTech), International Conference of

作者： Li Zhao Yujiang Liu Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Shenyang Institute of Computing Technology Chinese Academy of Science University of Chinese Academy of Science Beijing China

ISBN: (数字)9798350376258

ISBN: (纸本)9798350376265

We propose the Deep-INTN-NGCF algorithm, which is an innovative recommendation algorithm that solves the problem of modelling relationships that exists in graph neural network based recommendation algorithms, which aims to solve the smoothing problem and the problem of ignoring fine-grained interaction intent in traditional collaborative filtering methods. The algorithm combines the ideas of deep graph neural networks and interaction intent modelling. In order to avoid the problem of graph neural networks falling into oversmoothing after performing multiple graph convolution operations, the Deep-INTN-NGCF algorithm employs initial residual connectivity and constant mapping. The initial embeddings of users and items are obtained through their interaction history. In the aggregation propagation layer, the initial residual connection and constant mapping are used to fuse the different orders of synergistic signals of users and items, and the predicted scores are obtained through linear representation. By adjusting the weights in the initial residual connection and constant mapping, the flexibility and recommendation performance of the model can be improved. In addition, the Deep-INTN-NGCF algorithm introduces fine-grained modelling of interaction intentions, in order to identify potential intentions and determine their importance, in order to solve this problem, we adopt the method of decomposing edges into multiple potential spaces and combine it with an interaction intention fusion layer. Ultimately, the user's predicted score for the item is generated. Experiments demonstrate that the Deep-INTN-NGCF algorithm performs well on the Gowalla, Yelp-2018, and Amazon-Book datasets, with higher recall and normalised discount cumulative gain (NDCG) than existing graph neural network recommendation algorithms. This validates the effectiveness and performance benefits of the proposed algorithm.

关键词： Smoothing methods Fuses Convolution Collaborative filtering filtering algorithms Prediction algorithms Information filters Graph neural networks Information and communication technology History

来源：评论

学校读者我要写书评

暂无评论

Enhanced Deep SORT with Class filtering for ID Switches Minimization in Visual Object Tracking

Enhanced Deep SORT with Class Filtering for ID Switches Mini...

引用

Computer Applications (ICCA), IEEE Conference on

作者： Khin Ohnmar Maung Theingi Myint Department of Computer Engineering and Information Technology Mandalay Technological University Mandalay Myanmar

ISBN: (数字)9798350353624

ISBN: (纸本)9798350353631

A new approach for tracking the visual objects is proposed to enhance Deep SORT with class filtering in this system. Currently, visual object tracking systems are most popular in real life. But there are still challenging tasks such as illumination change, occlusion and reappearing on camera's view, and the tracked objects’ ID switching. Moreover, in the tracking process, false positive tracks are changed the tracking object's ID, and different detection class and tracking class are also problems for ID switching cases. The main emphasis of this paper is to minimize IDs’ changes of objects. In this paper, low-confidence, and proposed class filters are implemented and tested on own dataset to enhance Deep SORT. In the experimental results, the changes in tracking specified objects’ ID of the two filtering can minimize by 10% and 67% respectively rather than that of the Deep SORT. Therefore, we found that a new approach can significantly minimize the IDs’ changes of objects.

关键词： YOLO Visualization Filters Lighting Switches filtering algorithms Minimization

来源：评论

学校读者我要写书评

暂无评论

Research on filtering Algorithm of Bridge Vibration Signal Based on Millimeter Wave Radar

Research on Filtering Algorithm of Bridge Vibration Signal B...

引用

Intelligent Communications and Computing (ICC), International Conference on

作者： Huachao Zhuang Chen Gao Zhenyu Li Yanbo Zhang Guang Yan Xingwen Zhao Institute of Automation Shandong Academy of Sciences Qilu University of Technology (Shandong Academy of Sciences) Jinan Shandong China

ISBN: (数字)9798331530365

ISBN: (纸本)9798331530372

Bridges play a crucial role in transportation networks, but accidents due to bridge health issues pose serious threats to safety. Millimeter-wave radar, a non-contact detection technology, is increasingly used for monitoring bridge health. This paper proposes a PSO-VMD-SWT algorithm to optimize VMD parameters using PSO, filter radar echo signals with SWT, and analyze bridge vibration signals through phase detection. Experimental validation using millimeter-wave radar and accelerometers confirmed the algorithm's effectiveness in detecting bridge health.

关键词： Bridges Vibrations Accelerometers Phase measurement Transportation Radar detection Millimeter wave radar filtering algorithms Vibration measurement Safety

来源：评论

学校读者我要写书评

暂无评论

Dual filtering Based Decentralized Learning Against Byzantine Attack

Dual Filtering Based Decentralized Learning Against Byzantin...

引用

Fully Actuated System Theory and Applications (CFASTA), Conference on

作者： Jiansong Qing Lizong Zhang Dongcheng Zhou Jianjun Wan Wei Zheng Qiang He Yanjun Lin Shaoxing Jianyuan Electric Power Group Co. Ltd Shaoxing P. R. China Hangzhou Applied Acoustics Research Institute Hangzhou P. R. China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

Decentralized deep learning improves upon centralized methods by reducing failure risks but faces challenges from Byzantine attacks that can disrupt model integrity. In Byzantine defense models, the main approach is to rank neighboring node scores, which places strict demands on network *** paper proposes a Dual filtering based Parameter Aggregation Rule (DF-PAR). It primarily focuses on the parameter cosine similarity and distance, employing predefined thresholds to filter out the outliers. Additionally, an evaluation mechanism rooted in the credibility of historical information is introduced to determine the weight value of each node. Eventually, the impact of the suspicious node is gradually reduced and eliminated. The experimental results demonstrate the algorithm’s ability and convergence even when some benign nodes are surrounded by Byzantine nodes.

关键词： Deep learning filtering algorithms Information filters filtering theory Faces Convergence

来源：评论

学校读者我要写书评

暂无评论

Signal Adaptive filtering Algorithm to Eliminate White Noise of Stationary and Non-Stationary Signals

Signal Adaptive Filtering Algorithm to Eliminate White Noise...

引用

International Russian Automation Conference (RusAutoCon)

作者： Kirill A. Shabanov Sergey M. Vlasov Control Systems and Robotics Faculty ITMO University Saint-Petersburg Russia

ISBN: (数字)9798350349818

ISBN: (纸本)9798350349825

This article aims to research and evaluate existing adaptive signal filtering algorithms. filtering of signals removes noise and distortion, which is a crucial scientific and technical challenge. the authors specifically consider the problem of white noise filtering using an adaptive filter approach. To address this problem, classical adaptive filtering algorithms are selected as the primary techniques for investigation. the efficiency of the least mean squares and recursive least squares with forgetting factor algorithms is compared in white noise filtering tasks for stationary and non-stationary signals. As a result, the authors have successfully filtered multi-harmonic signals from white noise using both the least mean squares and recursive least squares with forgetting factor algorithms.

关键词： Automation filtering Simulation Adaptive filters Interference filtering algorithms White noise Distortion

来源：评论

学校读者我要写书评

暂无评论

Fusion filtering Algorithm Based on Edge Point Judgment

引用

Chinese Journal of Electronics 2023年第1期21卷 165-168页

作者： Xuanming Wang Xiaolin Zhang Xiaojun Jing Beihang University Beijing China Beijing University of Posts and Telecommunications Beijing China

For defects of image filtering algorithm based on the modified Information entropy (IIE), a novel fusion image filtering algorithm based on edge point judgment by fusion entropy is proposed in this paper. IIE algorithm only fuses the decision of edge point and it still uses single method (linear or nonlinear filters) for image pixel. So it is not a real fusion filtering algorithm. Therefore, the proposed algorithm not only applies fusion theory to edge point judgment, but also uses fusion theory for fusion filtering which can improve the performance of filtering. The experimental results indicate that the proposed algorithm is effective.

关键词： Maximum likelihood detection filtering Fuses Image edge detection Nonlinear filters filtering algorithms Image filtering

来源：评论

学校读者我要写书评

暂无评论

An improved variable step size LMS adaptive filtering algorithm based on hyperbolic sine function and its application

An improved variable step size LMS adaptive filtering algori...

引用

Big Data & Artificial Intelligence & Software Engineering (ICBASE), International Conference on

作者： Zhengang Wan Yonghao Zhou Jiangsu University of Science and Technology Zhenjiang China

ISBN: (数字)9798331506612

ISBN: (纸本)9798331506629

This paper presents an enhanced variable step-size LMS (VSS-LMS) algorithm using a hyperbolic tangent function to address the poor performance of traditional VSS-LMS algorithms in non-Gaussian environments. The conventional VSS-LMS struggles with adaptability and convergence speed under non-Gaussian noise. To overcome this, a parameter-free VSS-LMS algorithm based on the hyperbolic tangent function is proposed. This new algorithm introduces a nonlinear step-size error model with five adaptive coefficients ($\beta,\text k,\text b,\text a, \text m$). It analyzes convergence and algorithmic complexity and compares performance with traditional LMS, VSS-LMS, and an improved VSS-LMS under various non-Gaussian noise conditions. Simulation results demonstrate that the proposed algorithm significantly improves convergence speed and steady-state characteristics, achieving near-theoretical SNR performance.

关键词： Adaptation models Simulation Software algorithms filtering algorithms Steady-state Complexity theory Application software Convergence Signal to noise ratio

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：