检索结果-内蒙古大学图书馆

6th International Conference on Geoscience and Remote Sensing Mapping, GRSM 2024

作者： Deng, Fengying Qiao, Baojun Li, Kaitao Zhao, Limin Chen, Xingfeng Li, Jiaguo Liu, Jun Sun, Yuan Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China Aerospace Information Research Institute Chinese Academy of Science Beijing China School of Space Information Space Engineering University Beijing China

ISBN: (纸本)9781510688018

Wind turbine detection is essential for the power industry and regulatory agencies to efficiently and accurately determine their number and spatial distribution. Under complex underlying surface conditions, the detection accuracy of conventional methods is low, especially when dealing with multi-scale wind turbine targets. In addition, the underutilization of the near-infrared (NIR) band limits the capability of optical remote sensing sensors in wind turbine detection. To address the above problems, this paper proposes a wind turbine detection algorithm YOLOv8m-BD based on high spatial resolution four-band reflectance images using YOLOv8m as the baseline model. Firstly, the four-band image is input through channel adaptation modification. Next, the CSPDarknet53 to 2-stage FPN (C2f) module is enhanced by introducing deformable convolution (DCN) to expand the receptive field. Finally, the effectiveness of our design was validated through extensive experiments on a self-built wind turbine dataset. Compared to the YOLOv8m baseline model that only inputs RGB three bands, the improved YOLOv8m-BD achieves an accuracy of 96.4% and a false alarm rate of 2.0%, an increase of 3.4% in accuracy and a decrease of 2.5% in false alarm rate. © 2025 SPIE.

关键词： Proximity sensors

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

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

Few-Shot Node Classification on Attributed Networks Based on Prototypical Network 19

Few-Shot Node Classification on Attributed Networks Based on...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Zhao, Yaliang Zhang, Guangming Wang, Jinke Henan University Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Kaifeng China

ISBN: (纸本)9798350346558

In today's society, the interactions between various entities form complicated attributed networks. The node classification task as the core task of analyzing attribute networks has gained a considerable amount of attention from researchers. The existing graph neural network-based node classification approaches all demand lots of labeled data, but a high percentage of node classes in practical scenarios contain only restricted labeled data. So their classification effect is not good. In response to this problem, we put forward an improved graph prototypical network (IGPN) to enhance the few-shot node classification's accuracy. In particular, we start by obtaining the embedding representations of nodes on the attributed network through a graph attention network. Then combined with the node's degree information and neighbor information, the importance coefficient of all nodes in the support set is learned. After that, we can obtain the prototype representation of every class. Finally, the node classification can be completed by the distance of the query nodes' representation from all class prototypes. Our method is preferable to the baseline method on three datasets according to a large number of experiments. © 2022 IEEE.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

A MAB-based Hyper-heuristic for Vehicle Routing Problem with Time Window

A MAB-based Hyper-heuristic for Vehicle Routing Problem with...

引用

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

作者： Hou, Yan-E Liu, Bingbing Fan, Gaojuan Henan Key Laboratory of Big Data Analysis and Processing Henan University Henan Kaifeng475004 China School of Computer and Information Engineering Henan University Kaifeng475004 China

ISBN: (纸本)9781510664616

In order to efficiently solve the vehicle routing problem with time window (VRPTW), a hyper-heuristic algorithm based on reinforcement learning was proposed. Firstly, the performance of the underlying heuristic algorithm was evaluated, and then a multi-armed bandit (MAB) algorithm was used to select the low-level heuristic algorithm. At the same time, a simulated annealing-based acceptance rule was used to determine whether to accept the solution obtained by each low-level heuristic to ensure the diversity of solutions. Experiments was carried out on some VRPTW benchmark instances, and the results show that the proposed algorithm is effective and stable. © 2023 SPIE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised PolSAR image classification method based on contrastive learning 6

Semi-supervised PolSAR image classification method based on ...

引用

6th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Hua, Wenqiang Sun, Nan Liu, Lin The Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an Key Laboratory of Big Data and Intelligent Computing School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an China School of Computer Technology Xi'an University of Posts and Telecommunications Xi'an China

ISBN: (纸本)9798400707674

Polarimetric synthetic aperture radar (PolSAR) image classification has important application value and a wide range of application scenarios in many fields. Supervised classification methods, which need to use a large amount of labeled data to improve classification accuracy, have achieved satisfactory classification performance. However, it is difficult and expensive to obtain sufficient labeled data for PolSAR images. The problem to be solved is how to obtain high classification accuracy with a limited number of labeled samples. Semi-supervised PolSAR image classification method based on contrastive learning is proposed. Firstly, a supervised PolSAR image classification method based on meta-learning is introduced. Prototypical network based on meta-learning ideas is used as the basic classification model, and a prototypical representation is created for each category. Classification is performed by computing the similarity between the prototypical representation and samples to be classified. Secondly, a method of training feature extractor based on contrastive learning is designed. By maintaining the consistency of features between the same data and distinguishing the differences between different data after data augmentation, the method enables the feature extractor to obtain accurate feature representation. By co-training with meta-learning, so as to improve the classification performance. Finally, experiments on real PolSAR data prove the effectiveness of the proposed method. © 2023 ACM.

关键词： image classification

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

Exploiting Multiple Features for Hash Codes Learning with Semantic-Alignment-Promoting Variational Auto-encoder 12th

Exploiting Multiple Features for Hash Codes Learning with Se...

引用

12th National CCF Conference on Natural Language processing and Chinese Computing, NLPCC 2023

作者： Chen, Jiayang Su, Qinliang School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Beijing China

ISBN: (纸本)9783031446924

Semantic hashing is an effective technique to empower information retrieval. Currently, considerable efforts have been dedicated to generating high-quality hash codes by modeling document features using generative models and other approaches. However, most of these methods rely solely on a single type of feature, such as TFIDF features, BERT embeddings, etc. As different types of features have distinct but complementary information of documents, e.g. TFIDF mainly contains the keywords information and BERT focuses on the semantics, hash codes generated solely from either may not capture the full essence of the documents. To overcome this challenge, we propose a semantic-alignment-promoting variational auto-encoder to generate hash codes from multiple document features. Specifically, a VAE-based generative model is first developed to model the multiple features. Then, we propose a semantic-alignment-promoting inference network to estimate the parameters of the variational posterior from multiple features. Additionally, the quality of hash codes is further improved by promoting the semantic alignment between the hash codes of connected documents in a constructed connection graph. The results of extensive experiments on three public datasets demonstrate that our proposed model significantly outperforms current state-of-the-art models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Intention Recognition Method Based on Resting-state and P300 Task-state Dynamic Brain Functional Network Features 15

Intention Recognition Method Based on Resting-state and P300...

引用

15th International Conference on Measurement Technology and Mechanical Automation, ICMTMA 2023

作者： Yi, X. Wang, Z.M. Heng, X. School of Computer Science and Technology Xi'An University of Posts and Telecommunications Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi 'An Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

In order to reconfigure its structure from the static state in the vision odd ball task, so as to realize the intention recognition based on the characteristics of the brain functional network. The thesis proposes the intention recognition method based on resting state and P300 task state dynamic brain functional network features. First, the brain connectivity in each time window is constructed into a brain functional network using phase lock value (PLV). Then, extract the global features (global efficiency, transitivity) of the brain functional network, and use Louvain algorithm to obtain the brain functional network community. The experimental results show that in the (100-200) ms of P300 task status, the core nodes are mainly concentrated in the forehead region and the central region, while in the (300-500) ms of P300, the core nodes are concentrated in the temporal lobe. The recognition accuracy based on this method reaches 93%. © Published under licence by IOP Publishing Ltd.

关键词： Brain Function Network Intention Recognition P300 PLV Sliding Windows

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：