检索结果-内蒙古大学图书馆

7th International Conference on Signal Processing and Machine Learning, SPML 2024

作者： Sun, Wei Wu, Jianli Hu, Changdi Wanjiang University of Technology China Ma'anshan Engineering Technology Research Center for Wireless Sensor Network and IntelliSense China

ISBN: (纸本)9798400717192

In image enhancement technology, there is a spatial domain method that changes a certain grayscale value or neighboring grayscale value of an image in the spatial domain to achieve the enhancement effect. This article proposes an improvement on the traditional double histogram equalization by using threshold segmentation to perform equalization processing on subgraphs. The values obtained from K-means clustering are used as thresholds to segment images according to different thresholds. After histogram equalization, the two subgraphs are merged into a new image. After simulation testing, the improved algorithm has improved the image enhancement effect, making it more convenient to observe the edge features and contrast of the image. © 2024 Owner/Author.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Power Quality Disturbances Classification Based on WOA-SVM Algorithm

Power Quality Disturbances Classification Based on WOA-SVM A...

引用

2023 International Conference on Power Energy Systems and Applications, ICoPESA 2023

作者： Ji, Ping Zhu, Quan Maanshan Wireless Sensor Network and Intelligent Perception Engineering Technology Research Center Maanshan China Wanjiang University of Technology Maanshan China

ISBN: (纸本)9798350345605

With the rapid development of new energy technology, all kinds of distributed power grids are connected to the main power grid, generating a large number of complex disturbance signals. In order to ensure the safety of the power grid and solve the difficult problem of power grid disturbance identification, this paper proposes a classification recognition algorithm based on the combination of energy difference (ED) and support vector machine (SVM) optimized by the Whale optimization algorithm (WOA). Firstly, the disturbance signal is decomposed with multi-resolution, and the energy difference of each layer is calculated as the characteristic quantity of the disturbance signal. Then, WOA algorithm was used to optimize SVM, and the optimal solutions of penalty parameters and kernel parameters were obtained. Finally, the feature vector is input into the WOA-SVM model, and the output disturbance signal type is automatically identified. Experimental results show that this method can accurately identify single and complex disturbance signals. In the noise environment, it shows strong robustness. The overall recognition rate of ED-WOA-SVM is over 99%. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Design of Intelligent Clothes Hanger System Based on Rainfall Data Analysis 10th

Design of Intelligent Clothes Hanger System Based on Rainfal...

引用

10th International Conference on Computer engineering and networks, CENet 2020

作者： Tao, Binbin Zhang, Jing Hu, Xusheng Wu, Jingmei Maanshan Engineering Technology Research Center for Wireless Sensor Network and IntelliSense Maanshan243031 China Wanjiang Institute of Technology Maanshan243031 China

ISBN: (纸本)9789811584619

Rainfall plays a vital role in guiding clothes drying. This paper proposes an intelligent clothes hanger system based on the analysis of rainfall data. The system consists of an electric mechanism, weather monitoring module, wireless communication module, central control module, network server, and user APP. The weather data monitored by the local weather monitoring module is uploaded to the network server in real-time, users can monitor and control the clothes hanger through the APP. Besides, the web server constructs a two-dimensional rainfall map based on the weather data provided by the clothes hangers in different geographic locations. Using the weight matrix to perform convolution operation on the rainfall map, the weighted average of the rainfall conditions at any point and its surrounding points is realized. The result is used as the rainfall risk prediction of the area corresponding to this point, used to guide drying. Finally, the feasibility of the algorithm is verified by Labview simulation. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Image Enhancement Algorithm of Foggy Sky with Sky based on Sky Segmentation

Image Enhancement Algorithm of Foggy Sky with Sky based on S...

引用

2023 Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2023

作者： Sun, Wei Wu, Jianli Rashid, Haroon Wanjiang University of Technology Ma'anshan243031 China Ma'Anshan Engineering Technology Research Center for Wireless Sensor Network and IntelliSense Ma'anshan243031 China The Islamia University of Bahawalpur Punjab Pakistan

In recent years, image defogging has become a research hotspot in the field of digital image processing. Through defogging enhancement processing, the visual quality of foggy images can be significantly improved, and it is also an important part of subsequent image processing. To overcome the limitations of traditional image dehazing, an image enhancement algorithm for foggy image with sky based on sky segmentation is proposed. Firstly, based on K-means clustering and sky feature analysis, sky region recognition is performed for fog image with sky. Secondly, according to the pixels of sky region, the rough transmittance is corrected, and the dehazing image is obtained by dark channel prior image dehazing based on guided filter. Finally, the dehazing image is equalized by bi-histogram equalization. This algorithm effectively avoids the problem of color distortion and halo caused by the traditional dark channel prior dehazing algorithm in the sky area, and makes the restored foggy image have better global and local contrast. © Published under licence by IOP Publishing Ltd.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Improved decoy-state quantum key distribution with uncharacterized heralded single-photon sources

引用

Chinese Physics B 2024年第2期33卷 204-208页

作者：徐乐辰张春辉周星宇王琴 Institute of Quantum Information and Technology Nanjing 210003China Broadband Wireless Communication and Sensor Network Technology Key Laboratory of Ministry of EducationNanjing University of Posts and TelecommunicationsNanjing 210003China Telecommunication and Networks National Engineering Research Center Nanjing University of Posts and TelecommunicationsNanjing 210003China

Encoding system plays a significant role in quantum key distribution(QKD).However,the security and performance of QKD systems can be compromised by encoding misalignment due to the inevitable defects in realistic *** alleviate the influence of misalignments,a method exploiting statistics from mismatched basis is proposed to enable uncharacterized sources to generate secure keys in *** this work,we propose a scheme on four-intensity decoy-state quantum key distribution with uncharacterized heralded single-photon *** only requires the source states are prepared in a two-dimensional Hilbert space,and can thus reduce the complexity of practical ***,we carry out corresponding numerical simulations and demonstrate that our present four-intensity decoy-state scheme can achieve a much higher key rate compared than a three-intensity decoy-state method,and meantime it can obtain a longer transmission distance compared than the one using weak coherent sources.

关键词： quantum key distribution heralded single-photon source decoy-state method

来源：评论

学校读者我要写书评

暂无评论

Highly efficient twin-field quantum key distribution with neural networks

引用

Science China(Information Sciences) 2023年第8期66卷 281-282页

作者： Jingyang LIU Qingqing JIANG Huajian DING Xiao MA Mingshuo SUN Jiaxin XU Chun-Hui ZHANG Shipeng XIE Jian LI Guigen ZENG Xingyu ZHOU Qin WANG Institute of Quantum Information and Technology Nanjing University of Posts and Telecommunications Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Telecommunication and Networks National Engineering Research Center Nanjing University of Posts and Telecommunications

Quantum key distribution(QKD) allows two legitimate parties, Alice and Bob, to share a series of random bits that are secured by the laws of quantum mechanics. As a remarkable theoretical progress towards longer distances, the proposal of twin-field QKD(TF-QKD) [1] shows the capability to break a repeaterless bound and provides a key rate in the square-root scale of channel transmittance(i.e.,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of UAV obstacle avoidance based on STM32 3

Design and implementation of UAV obstacle avoidance based on...

引用

3rd International Conference on Mechatronics and Mechanical engineering, ICMME 2024

作者： Hu, Xusheng Liu, Juan Ma'anshan Engineering Technology Research Center for Wireless Sensor Network and IntelliSense Ma’anshan243031 China Anhui Provincial Engineering Laboratory on Information Fusion and Control of Intelligent Robot Wuhu241002 China Ma'anshan Technical College Ma'anshan243030 China

ISBN: (纸本)9781510681651

With the development of remote control and telemetry technology, the application of UAV is more and more extensive, and the requirement of UAV flight control is higher and higher. In order to enhance the stability of UAV hardware system, the power supply part is protected in various ways;a spare chip is added to ensure the effectiveness of attitude calculation;SPI peripheral interface is reserved to expand GPS, ultrasonic and other sensors. Through the mathematical model, the calibration method of accelerometer and gyroscope is introduced, and the importance of this step for flight control system is emphasized. The software flow chart of the system is designed, and the mathematical model of obstacle avoidance algorithm is given. The classic PID control algorithm and simulation method are used to realize the obstacle avoidance of UAV. Considering the problems that may be encountered in UAV obstacle avoidance, the mathematical model is established, the evaluation index is given, and the control experiment is designed. Experimental results show that the algorithm has good obstacle avoidance effect and strong robustness in low speed and complex environment. © 2024 SPIE.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

Application research of Webshell detection system based on deep learning

Application research of Webshell detection system based on d...

引用

2024 International Applied Computational Electromagnetics Society Symposium, ACES-China 2024

作者： Zhang, Liting Zhu, Jinrui Wanjiang University of Technology Ma'anshan Wireless Sensor Network and Intelligent Perception Engineering Technology Research Center Ma'anshan243031 China Wanjiang University of Technology Ma'anshan243031 China

ISBN: (纸本)9798350355581

Aiming at the limitations of traditional Webshell detection methods, such as relying on static rule matching, easy to be affected by confusing technologies, and difficult to cope with constantly evolving attack means. A Webshell detection method based on deep learning is proposed. This method not only integrates convolutional neural network (CNN) algorithm and recurrent neural network (RNN) algorithm, but also introduces multi-dimensional strategies of opcode analysis, regular detection and entropy detection to enrich the detection means. It is proved that this algorithm greatly improves the accuracy and real-time of Webshell detection. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Application research on Blockchain-based Asynchronous Federated Learning in Data Security Sharing in Vehicle network

Application Research on Blockchain-based Asynchronous Federa...

引用

2024 International Applied Computational Electromagnetics Society Symposium, ACES-China 2024

作者： Zhang, Liting Wang, Yunfei Wanjiang University of Technology Ma'anshan Wireless Sensor Network and Intelligent Perception Engineering Technology Research Center Ma'anshan243031 China Wanjiang University of Technology Ma'anshan243031 China

ISBN: (纸本)9798350355581

In the vehicle-connected environment of intelligent transportation systems, although data sharing brings new development opportunities, it is also accompanied by challenges such as privacy and security (such as data leaks) and upload efficiency. These issues reduce the enthusiasm of data providers to participate. In order to solve the above problems, this research aims to propose a new architecture based on asynchronous federated learning, focusing on solving bandwidth, security and privacy issues encountered in IoT vehicle data sharing, and is committed to improving the reliability of data sharing. and efficiency. By adopting blockchain technology to enhance the security and reliability of model parameters, reducing transmission loads and alleviating privacy concerns. At the same time, the research also uses a distributed, efficient and secure data sharing architecture based on blockchain to select nodes and further optimizes the asynchronous federated learning scheme to improve overall efficiency. Experimental results show that the proposed scheme not only improves the learning accuracy, but also significantly accelerates the convergence speed, and at the same time enhances privacy protection and service quality, fully verifying the effectiveness and practicality of this research method. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

research on network Intrusion Detection System Based on Independent Q-learning

Research on Network Intrusion Detection System Based on Inde...

引用

2024 International Applied Computational Electromagnetics Society Symposium, ACES-China 2024

作者： Zhang, Liting Zhou, Enxiang Wanjiang University of Technology Ma'anshan Wireless Sensor Network and Intelligent Perception Engineering Technology Research Center Ma'anshan243031 China Wanjiang University of Technology Ma'anshan243031 China

ISBN: (纸本)9798350355581

Aiming at the problem that traditional network intrusion detection systems have low accuracy in identifying complex and changeable network attack patterns, a multi-agent network intrusion detection system based on independent Q-learning is proposed. The system adopts a multi-agent architecture, and each agent uses an independent Q learning algorithm to monitor and assess network behavior, and improves the efficiency and accuracy of network intrusion detection through intelligent methods. The experimental results show that compared with traditional intrusion detection methods, the detection accuracy, response speed and robustness of this system are significantly improved. It can show good adaptability and generalization ability. It provides a new solution for the field of network security and has certain theoretical and practical value for building a more intelligent and reliable network security protection system. © 2024 IEEE.

关键词： network intrusion

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：