检索结果-内蒙古大学图书馆

2022 International Conference on Signal processing, Computer Networks, and Communications, SPCNC 2022

作者： Ge, Qiang Jiang, Kejian Han, Hongyu Liu, Huaizhou Zhang, Jing Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475001 China School of Computer and Information Engineering Henan University Kaifeng475001 China

ISBN: (纸本)9781510664616

Aiming at a series of problems such as low evaluation efficiency of traditional algorithms, cumbersome process operation, high use cost and no complete algorithm inspection process system, this paper proposes an algorithm flow technology inspection processing system and method based on remote sensing applications, mainly including satellite product processing, algorithm processing, sample feature selection, sample extraction, and algorithm processing results comparison, It mainly realizes the functions of input, output and parameter adjustment required by different function functions, and designs an interface interaction system that adapts to the input and output elements required by different function modules. It realizes the modular, plug-in and componentized design of interface interaction of function modules, and obtains the evaluation system of algorithm credibility. © 2023 SPIE.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

An effective global learning framework for hyperspectral image classification based on encoder-decoder architecture

引用

International Journal of Digital Earth 2022年第1期15卷 1350-1376页

作者： Lanxue Dang Chongyang Liu Weichuan Dong Yane Hou Qiang Ge Yang Liu Henan Key Laboratory of Big Data Analysis and Processing Henan UniversityKaifengChina School of Computer and Information Engineering Henan UniversityKaifengChina Department of Geography Kent State UniversityKentOHUSA

Most deep learning methods in hyperspectral image(HSI)classification use local learning methods,where overlapping areas between pixels can lead to spatial redundancy and higher computational *** paper proposes an efficient global learning(EGL)framework for HSI *** EGL framework was composed of universal global random stratification(UGSS)sampling strategy and a classification model *** UGSS sampling strategy was used to solve the problem of insufficient gradient variance resulted from limited training *** fully extract and explore the most distinguishing feature representation,we used the modified linear bottleneck structure with spectral attention as a part of the BrsNet network to extract spectral spatial *** a type of spectral attention,the shuffle spectral attention module screened important spectral features from the rich spectral information of HSI to improve the classification accuracy of the ***,we also designed a double branch structure in BrsNet that extracted more abundant spatial information from local and global perspectives to increase the performance of our classification *** were conducted on three famous datasets,IP,PU,and *** with other classification methods,our proposed method produced competitive results in training time,while having a greater advantage in test time.

关键词： Deep learning global learning feature representation hyperspectral image classification spectral attention

来源：评论

学校读者我要写书评

暂无评论

Multimodal Identity Recognition of Spiking Neural Network Based on Brain-Inspired Reward Propagation 22

Multimodal Identity Recognition of Spiking Neural Network Ba...

引用

22nd IEEE International Symposium on Parallel and Distributed processing with Applications, ISPA 2024

作者： Liu, Yang Zhang, Hongxia Li, Yahui Wang, Quanqiang Liu, Cheng Henan University Henan Key Laboratory of Big Data Analysis and Processing Henan Kaifeng475004 China Henan University School of Computer and Information Engineering Henan Kaifeng475004 China Huaihe Hospital of Henan University Department of Clinical Laboratory Henan Kaifeng475004 China

ISBN: (纸本)9798331509712

Deep learning has strongly promoted the research progress of unimodal feature learning such as face recognition and speech recognition, but it still needs to be strengthened in multimodal data representation learning, especially the problem of high power consumption, which is not conducive to the real-time application of mobile devices under limited resources. In order to realize multimodal identity recognition for low-energy edge smart devices, this paper proposes a multimodal identity recognition method of spiking neural network based on brain-like mechanism (SNN-MIR-BiM). Simulating the attention mechanism of the cognitive system to specific information improves the response of multimodal features, mimics the regulation mechanism of the neurotransmitter dopamine in the nervous system, and releases reward signals from the recognition results, which affects the neuronal state and regulates the synaptic weights through global propagation, and then optimizes the network structure. Experimental results on large-scale audio and video datasets show that the proposed method can reach 98.94% recognition accuracy, and the energy consumption of the model is about 1/10 of that of CNN under the same architecture, which verifies the effectiveness of the attention mechanism and reward propagation in network design. This research is of great practical significance in the industry applications of unmanned autonomous systems such as human-computer interaction of intelligent machines and intelligent security. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Application of CPU Parallel Computing in MATLAB Environment for analysis of Anti-Saturation and Gain Effects in PID Controller 13

Application of CPU Parallel Computing in MATLAB Environment ...

引用

13th IEEE data Driven Control and Learning Systems Conference, DDCLS 2024

作者： Huang, Ruirui Wu, Zhenhui Hou, Yandong Cheng, Qianshuai Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Technology and Media University of Henan Kaifeng Kaifeng475004 China School of Artificial Intelligence Henan University Zhengzhou450000 China

ISBN: (纸本)9798350361674

With the continuous increase in data size and model complexity, the computational workload has grown rapidly, posing a significant challenge to the capabilities of computer data processing and simulation calculations. Therefore, parallel programming based on multicore and cluster architectures has become one of the mainstream technologies to enhance program execution efficiency and numerical computation efficiency. The theoretical foundations of parallel program computing have been applied in various aspects of engineering applications and theoretical simulations. In this paper, a new parallel PID anti-integral saturation controller is designed for a second-order closed-loop control system of unmanned aerial vehicles (UAVs). It compares and analyzes the runtime, execution efficiency, and speedup ratio of parallel programs and general serial programs under the same scenario. The experimental results demonstrate that parallel computing significantly improves the simulation program's efficiency for PID controller anti-saturation control systems under identical scenarios, exhibiting a high speedup ratio on the existing computing platform. Additionally, this study consolidates common issues encountered in MATLAB parallel program design, offering valuable insights into overcoming challenges in this domain. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

PG-YOLO: A Lightweight Vehicle Detection Method for Drones 22

PG-YOLO: A Lightweight Vehicle Detection Method for Drones

引用

22nd IEEE International Symposium on Parallel and Distributed processing with Applications, ISPA 2024

作者： Liu, Yang Fan, Tengyu Mei, Kun Zhou, Liming Henan University Henan Key Laboratory of Big Data Analysis and Processing Henan Kaifeng475004 China Henan University School of Computer and Information Engineering Henan Kaifeng475004 China Huaihe Hospital of Henan University Department of Clinical Laboratory Henan Kaifeng475004 China

ISBN: (纸本)9798331509712

With the rapid development of drone technology, object detection technology is widely applied in the field of drone intelligent transportation. In response to the problems of low accuracy and high computational complexity in vehicle detection tasks on resource limited drones, this paper proposes a lightweight and efficient improved model PG-YOLO for drone vehicle detection based on the YOLOv7-tiny model. Firstly, replace the LeakyReLU activation function with the SiLU activation function to compensate for the lack of nonlinear expression in the LeakyReLU activation function, and improve the convergence speed and generalization of the model during training;Secondly, the feature extraction and fusion modules were optimized to enhance the network's perception and capture capabilities of the target, improve detection accuracy, and reduce the number of parameters;Then, lightweight convolution PConv and GSConv are introduced, and a lightweight module PPC based on PConv is proposed to improve the network's Neck layer, reducing the number of parameters and computation while maintain detection performance;Finally, the CBAM attention mechanism is introduced to improve the detection performance for the problem of dense vehicle targets. The improved network achieved an average detection accuracy of 60.1%, an increase of 12.1 percentage points compared to the original network, a reduction of 73.6% in parameter count, a reduction of 15.9% in computational complexity, and a detection speed of 154 FPS. Compared to the original network, the network is more lightweight and achieves higher detection accuracy, which can more effectively perform unmanned aerial vehicle detection tasks. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

A Review of Detection-Related Multiple Object Tracking in Recent Times 26

A Review of Detection-Related Multiple Object Tracking in Re...

引用

26th International Conference on Advanced Communications Technology, ICACT 2024

作者： Li, Suya Cao, Ying Xie, Xin Henan University School of Computer and Information Engineering Jinming Campus Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Jinming Campus Kaifeng China

ISBN: (纸本)9791188428120

Multi-object tracking (MOT) is garnering more attention due to its widespread application in the area of autonomous driving, human-computer interaction, and intelligent video surveillance. Especially in recent years, MOT has rapidly developed thanks to related technologies such as object detection, which has helped in handling interfering factors such as crowded scene occlusion, small objects, and similar appearances. Among these, Detection-based MOT is the mainstream for accurately forming objects' trajectories. Therefore, according to the analysis of the last three years' research, this paper particularly focuses on discussing the continuous optimization strategies of MOT around the development of object detection at each stage. In addition, this article also introduces the commonly used benchmark datasets and related applications of MOT. © 2024 Global IT Research Institute - GIRI.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Discrete Multi-Attributed Network Releasing

Differentially Private Discrete Multi-Attributed Network Rel...

引用

2022 International Conference on Signal processing, Computer Networks, and Communications, SPCNC 2022

作者： Lin, Yinghao Wang, Yuye Zhao, Shihao Qiao, Baojun Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Henan University Kaifeng China Shenzhen Research Institute of Henan University ShenZhen China

ISBN: (纸本)9781510664616

In the area of social network, different attributes have different effects on the structure of network. Most of the existing privacy protection methods for attributed networks ignore the situation which different attributes have different effects on the network structure. They protect the privacy of the attributes indiscriminately. In respect of the issues above, a differentially private discrete multi-attributed network releasing method is proposed. Firstly, a probability model of discrete multi-attributed network is structured and the correlation parameter between multiple attributes and network structure is defined. The factor with different effects of different attributes on network structure is added into the model. Then, the algorithm uses the correlation parameter to establish the partition model of metadata and divides the metadata into different groups. As the group has different network model and attribute between each other, the groups are independence. The differential privacy of discrete multi-attributed network is realized through sanitizing parameters of the model and allocating metadata using exponential mechanism. Finally, experiment on real datasets verifies that the algorithm can satisfy the characteristics of the discrete multi-attributed network. It can also improve the efficiency and data availability. © 2023 SPIE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Fault Estimation for Nonlinear Systems with Disturbance Based on Reinforcement Iterative Learning Strategy 13

Fault Estimation for Nonlinear Systems with Disturbance Base...

引用

13th IEEE data Driven Control and Learning Systems Conference, DDCLS 2024

作者： Chen, Zhengquan Huang, Ruirui Zhang, Zhiheng Hou, Yandong Henan University School of Computer and Information Engineering Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China School of Artificial Intelligence Henan University Zhengzhou450000 China

ISBN: (纸本)9798350361674

This paper addresses the problem of low fault estimation accuracy in Lipschitz nonlinear systems with external disturbances, presenting an innovative strategy based on a Reinforcement Iterative Learning (RIL) framework. Initially, we conducted precise mathematical modeling, comprehensively considering the impact of Lipschitz non-linearity and external disturbances. Subsequently, an iterative learning fault observer was designed, and the optimization problem for its parameters was reformulated into a reinforcement learning task, clearly defining the states, actions, and reward functions. Employing the Advantage Actor-Critic (A2C) reinforcement learning method, we optimized the gain parameters of the iterative learning fault estimator to approximate non-linearity. Simultaneously, with the increase in iteration count, the neural network weights were continually optimized, achieving accurate fault estimation. Experimental results demonstrate a significant improvement in fault estimation using the proposed method. © 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

Semantic Segmentation of Remote Sensing Images Based on Swin Transformer 3

Semantic Segmentation of Remote Sensing Images Based on Swin...

引用

3rd International Conference on Artificial Intelligence, big data and Algorithms, CAIBDA 2023

作者： Lin, Yinghao Zhao, Shihao Wang, Yuye Xie, Yi Qiao, Baojun Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Henan University Kaifeng China Shenzhen Research Institute of Henan University Shenzhen China

ISBN: (纸本)9781643684444

With the evolution of Earth observation technology and remote sensing technologies, the amount of data available for high-resolution remote sensing images has exploded, and high-precision image segmentation has become a current research hotspot. Semantic segmentation technology is becoming increasingly important in fields such as urban planning, land use management, and autonomous driving. Large disparities within intraclass and modest differences intraclass are hallmarks of high resolution remote sensing pictures. Traditional image semantic segmentation methods rely on human-computer interaction and have poor generalization ability. When facing remote sensing images with rich types of ground objects and significant differences in target scales, the segmentation accuracy is not high. In this paper, we suggest an UperSwin decoder structure. The decoder includes several Swin transformer blocks and a fusion upsampling module, where the multi head contextual attention module in the Swin transformer block simultaneously uses multi-scale features and upsampling output features from the backbone network. In addition, the fusion upsampling module concatenates the backbone network features with the output features of the Swin transformer block, and then performs upsampling operations, preserving more detailed information. This article evaluates the accuracy and intersection ratio indicators on the Potsdam and Vaihingen datasets, verifying the feasibility and effectiveness of the model. © 2023 The Authors.

关键词： Land use

来源：评论

学校读者我要写书评

暂无评论

Fusion Attention-ASPP and Context Semantic for Complex Scene Semantic Segmentation

Fusion Attention-ASPP and Context Semantic for Complex Scene...

引用

2022 International Conference on Signal processing, Computer Networks, and Communications, SPCNC 2022

作者： Lin, YingHao Zhao, ShiHao Cai, Kun Qiao, BaoJun Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Henan University Kaifeng China Shenzhen Research Institute of Henan University ShenZhen China

ISBN: (纸本)9781510664616

Semantic segmentation is widely used in remote sensing data extraction and classification. Existing semantic segmentation networks focus on capturing contextual information in many different ways, simply fusing features at different levels, and ultimately improving the accuracy of semantic segmentation. However, low-level semantic features lack spatial context guidance, and high-level semantic features tend to encode large objects with coarse spatial details, making segmentation results prone to losing fine details. In this paper, we analyze the advantages and disadvantages of different levels of feature maps, and enhance the feature representation from two aspects to solve this problem. On the one hand, inspired by the architectural idea of atrous spatial pyramic pooling (ASPP), we adjust the structure of ASPP module and add the attention module to ASPP, and a new Attention-ASPP(AASPP) module is constructed in this paper. On the other hand, feature information such as boundary contours is enhanced by channel attention modeling, thereby improving local detail representation. Comprehensive experimental results show that our model framework achieves excellent segmentation performance on two public datasets, WHU building dataset and ISPRS Potsdam dataset. © 2023 SPIE.

关键词： Semantic Segmentation

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：