检索结果-内蒙古大学图书馆

2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021

作者： Wang, Kuan Chen, Bingxu Li, Ning Guo, Zhengwei Fu, Zewen College of Computer and Information Engineering Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng China

The propagation of spaceborne synthetic aperture radar (SAR) signal is affected by the ionosphere, which will lead to the degradation of the imaging quality, especially in the conditions of low-frequency and wide-bandwidth. This paper analyzed the influence of ionosphere on SAR imaging under different carrier frequency, different bandwidth, different ionosphere total electron content (TEC), different azimuth resolution and different scintillation strength by time-domain simulation. The results show that the ionospheric dispersion effect leads to SAR image defocusing, which is closely related to the radar carrier frequency, signal bandwidth, azimuth resolution and TEC value on the propagation path. At the same time, due to the influence of time delay, the dispersion effect also leads to the range displacement of SAR image. The ionospheric scintillation effect reduces the azimuth resolution significantly and in extreme cases imaging is not possible. © 2021 IEEE

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Acceleration Method for Remote Sensing Image processing Based on CUDA 12th

A Dynamic Acceleration Method for Remote Sensing Image Proce...

引用

12th EAI International Conference on Simulation Tools and Techniques, SIMUtools 2020

作者： Zuo, Xianyu Zhang, Zhe Qiao, Baojun Tian, Junfeng Zhou, Liming Zhang, Yunzhou Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Henan Engineering Laboratory of Spatial Information Processing Henan University Kaifeng475004 China College of Computer and Information Engineering Henan University Kaifeng475004 China National Cultural Heritage Administration Beijing100010 China

ISBN: (纸本)9783030727918

The incredible increase in the volume of remote sensing data has made the concept of Remote Sensing as Big data reality with recent technological developments. Remote sensing image processing is characterized with features of massive data processing and intensive computation, which makes the processes difficult. To optimize the remote sensing image processing for GPU, compute unified device architecture (CUDA) is widely used to implement remote sensing algorithms. However, the usage of GPU in remote sensing image processing has been constrained by the complexity of its implementation and configuration. Therefore, how to take fully advantage of the parallel organization of GPU architecture is awfully challenging. In this paper, a dynamic adaptive acceleration (DAA) method is proposed to determine calculation parameters of GPU adaptively and preprocess the input remote sensing images on host dynamically. By this method, we determine calculation parameters according to the hardware parameters of GPU firstly. And then, the input remote sensing images are reconstructed based on the calculation parameters. Finally, the preprocessed image blocks are arranged to stream tasks and executed on GPU respectively. Effectiveness of the proposed DAA method in accelerate remote sensing algorithm with point operations were verified by experiments in this paper, and the experimental results indicated that the DAA method can obtain better performance than traditional methods. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2021.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

A Hybrid BiLSTM-ATT Model for Improved Accuracy Sentiment analysis

A Hybrid BiLSTM-ATT Model for Improved Accuracy Sentiment An...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Lanxue Dang Chunyu Wang Hongyu Han Yan-E Hou Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer Science and Information Engineering Henan University Kaifeng China

Sentiment analysis is an important and challenging task in the field of natural language processing. Researchers have used vocabulary-based methods and machine learning methods to conduct research on sentiment analysis tasks. In recent years, deep learning has achieved great success in the field of sentiment analysis. However, for complex textual data, using a single model is often insufficient. Inspired by deep learning models, in this study, we proposed a hybrid model using BiLSTM and attention mechanism, called BiLSTM-ATT model, to solve the problem of sentiment analysis. First, we adopted the GloVe method to train the initialized word embeddings. GloVe converts textual information into word vectors, which can calculate the distance between words. Next, we used a convolutional neural network that can extract local features, and a BiLSTM that can extract long-range semantic features of text with bidirectional extraction of long-term dependencies. Finally, the attention mechanism was used to improve the performance of the model by calculating the weight of the data. Experimental results demonstrate that our proposed hybrid BiLSTM-ATT model outperforms traditional deep learning methods in Accuracy, Recall, and Fl-Score. Our method was compared with deep learning methods on the IMDB movie review dataset.

关键词： Deep learning Analytical models Sentiment analysis Semantics Feature extraction Motion pictures data models

来源：评论

学校读者我要写书评

暂无评论

Insider trading and government intervention

引用

International Review of Economics and Finance 2025年 101卷

作者： Li, Zhihua Liu, Hong Yang, Qingshan School of Mathematics and Statistics Henan University of Technology Zhengzhou 450001 China KLAS Key Laboratory of Big Data Analysis of Jilin Province School of Mathematics and Statistics Northeast Normal University Changchun China

This paper studies an insider trading model with government intervention aiming to stabilize price volatility, in one-period and multi-period scenarios. In a single-period model, we identify a threshold for the strength of government intervention that determines the interplay among market characteristics contingent on whether this threshold is exceeded or not. Furthermore, we find that government intervention effectively stabilizes price fluctuation in the multi-period model. Meanwhile, the insider adopts alternating increasing trading strategies (V-shaped) while the government adopts corresponding hedging strategies. Finally, empirical analysis is used to verify the effectiveness of government intervention. © 2025 The Authors

关键词： Government intervention Hedging strategy Insider trading Price disclosure Price stability

来源：评论

学校读者我要写书评

暂无评论

Prediction model of physical activity level and hypertension based on artificial neural network 4

Prediction model of physical activity level and hypertension...

引用

2021 4th International Conference on Advanced Algorithms and Control Engineering, ICAACE 2021

作者： Hua, Liang Yu, Wang Jinying, Li Wanjun, Zhang Yiting, Wang School of Physical Education Henan University Kaifeng Henan475001 China Department of Health Management People's Hospital of Henan Province People's Hospital of Henan University People's Hospital of Zhengzhou University Zhengzhou450003 China Key Laboratory of Big Data Analysis and Processing of Henan Province Henan University Kaifeng475004 China School of Foreign Language Henan University Kaifeng Henan475001 China

Purpose: Taking the population of henan Provincial People's Hospital Chronic Disease Control Center from July 1, 2020 to December 31, 2020 who came to the hospital for physical examination as the research object, analyze and explore the role and contribution of physical activity level in the prediction of hypertension by using the LSTM network model, which can provide references for the clinical diagnosis of hypertension. Methods: Randomly select 2000 physical examination data, remove missing and invalid data, and preprocess them. Finally, select factors such as gender, age, body mass index, weight grade, waist-to-hip ratio, physical activity level, body fat percentage and other factors to establish a neural network prediction model. Then test and study the model, focusing on exploring the contribution of physical activity level to prediction. Result: The level of physical activity has certain advantages in predicting the prevalence of hypertension, but the predictive ability in the later stage is insufficient © Published under licence by IOP Publishing Ltd.

关键词： Disease control

来源：评论

学校读者我要写书评

暂无评论

DOA Estimation Based on Intelligent FMCW Radar with Triangle Array Antenna 15th

DOA Estimation Based on Intelligent FMCW Radar with Triangle...

引用

15th EAI International Conference on Communications and Networking, ChinaCom 2020

作者： Du, Xiaoyu Jiang, Guoping Han, Chong Wang, Chunsong Zhou, Yi College of Automation and College of Artificial Intelligence Nanjing University of Posts and Telecommunications Nanjing China International Joint Research Laboratory for Cooperative Vehicular Networks of Henan Zhengzhou China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

ISBN: (纸本)9783030677190

In this paper, we propose a target Direction of Arrival (DOA) estimation algorithm through the triangular array antenna to improve the perception accuracy of intelligent vehicular millimeter-wave radar. Firstly, we utilize Total Least Square- Estimation of Signal Parameters to obtain the solution set of target azimuth with the geometrical advantages of the triangular array. Subsequently, the preliminary optimal target azimuth can be derived based on the power spectrum function of the improved Multiple Signal Classification algorithm, which is used to estimate the DOA solution set. Finally, we could estimate the optimal azimuth parameters accurately through searching the preliminary optimal target azimuth. The proposed algorithm avoids a wide range of power spectrum search, and reduces the error of azimuth estimation. Compared with both TLS-ESPRIT and MMUSIC algorithm, the spatial resolution is further improved. The evaluation results indicate that the proposed algorithm reduces the root mean square error and the computational complexity, and meanwhile improves the target azimuth estimation accuracy. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Direction of arrival

来源：评论

学校读者我要写书评

暂无评论

A Deletable and Modifiable Blockchain Scheme Based on Record Verification Trees and the Multisignature Mechanism

引用

Computer Modeling in Engineering & Sciences 2021年第7期128卷 223-245页

作者： Daojun Han Jinyu Chen Lei Zhang Yatian Shen Yihua Gao Xueheng Wang Henan Key Laboratory of Big Data Analysis and Processing Henan UniversityKaifeng47500China Institute of Data and Knowledge Engineering Henan UniversityKaifeng47500China School of Computer and Information Engineering Henan UniversityKaifeng47500China Department of Network and Finance Agricultural Bank of China Limited Xuchang BranchXuchang461000China School of Software Pingdingshan UniversityPingdingshan467000China Department of Network and Finance Agricultural Bank of China Limited Nanyang BranchNanyang473000China

As one of the most valuable technologies,blockchains have received extensive attention from researchers and industry circles and are widely applied in various ***,data on a blockchain cannot be *** a result,it is impossible to clean invalid and sensitive data and correct erroneous ***,to a certain extent,hinders the application of blockchains in supply chains and Internet of *** address this problem,this study presents a deletable and modifiable blockchain scheme(DMBlockChain)based on record verification trees(RVTrees)and the multisignature scheme.(1)In this scheme,an RVTree structure is designed and added to the block *** RVTree can not only ensure that a record is true and valid but,owing to its unique binary structure,also verify whether modification and deletion requests are valid.(2)In DMBlockChain,the multisignature mechanism is also *** mechanism requires the stakeholders’signatures for each modification or deletion request and thus ensures that a record will not be modified arbitrarily.A user’s request is deemed valid only if it is dually verified by the RVTree and the multisignature *** analysis finds that DMBlockChain can provide a secure and valid means for modifying and deleting records in a block while ensuring the integrity of the block and that DMBlockChain can effectively save space in some scenarios that require frequent records modification.

关键词： Blockchain record verification trees multisignature DMBlockChain

来源：评论

学校读者我要写书评

暂无评论

Multi-level Relation Learning for Cross-domain Few-shot Hyperspectral Image Classification

arXiv

引用

arXiv 2023年

作者： Liu, Chun Yang, Longwei Li, Zheng Yang, Wei Han, Zhigang Guo, Jianzhong Yu, Junyong School of Computer and Information Engineering Henan University Henan Zhengzhou450046 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Henan Zhengzhou450046 China Henan Engineering Laboratory of Spatial Information Processing Henan University Henan Zhengzhou450046 China Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan University Henan Zhengzhou450046 China College of Geography and Environmental Science Henan University Henan Zhengzhou450046 China Henan DeFan High-tech Software Co. Ltd Henan Zhengzhou450046 China

Cross-domain few-shot hyperspectral image classification focuses on learning prior knowledge from a large number of labeled samples from source domains and then transferring the knowledge to the tasks which contain few labeled samples in target domains. Following the metric-based manner, many current methods first extract the features of the query and support samples, and then directly predict the classes of query samples according to their distance to the support samples or prototypes. The relations between samples have not been fully explored and utilized. Different from current works, this paper proposes to learn sample relations on different levels and take them into the model learning process, to improve the cross-domain few-shot hyperspectral image classification. Building on current method of"Deep Cross-Domain Few-Shot Learning for Hyperspectral Image Classification" which adopts a domain discriminator to deal with domain-level distribution difference, the proposed method applies contrastive learning to learn the class-level sample relations to obtain more discriminable sample features. In addition, it adopts a transformer based cross-attention learning module to learn the set-level sample relations and acquire the attention from query samples to support samples. Our experimental results have demonstrated the contribution of the multi-level relation learning mechanism for few-shot hyperspectral image classification when compared with the state of the art methods. All the codes are available at github https://***/HENULWY/STBDIP. © 2023, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review on Long-Tailed Learning

arXiv

引用

arXiv 2024年

作者： Zhang, Chongsheng Almpanidis, George Fan, Gaojuan Deng, Binquan Zhang, Yanbo Liu, Ji Kamel, Aouaidjia Soda, Paolo Gama, João Henan University Henan Key Lab of Big Data Analysis and Processing Kaifeng China Baidu Inc. Beijing China University Campus Bio-Medico di Roma Rome Italy The Laboratory of Artificial Intelligence and Decision Support Faculty of Economics University of Porto Porto Portugal

Long-tailed data is a special type of multi-class imbalanced data with a very large amount of minority/tail classes that have a very significant combined influence. Long-tailed learning aims to build high-performance models on datasets with long-tailed distributions, which can identify all the classes with high accuracy, in particular the minority/tail classes. It is a cutting-edge research direction that has attracted a remarkable amount of research effort in the past few years. In this paper, we present a comprehensive survey of latest advances in long-tailed visual learning. We first propose a new taxonomy for long-tailed learning, which consists of eight different dimensions, including data balancing, neural architecture, feature enrichment, logits adjustment, loss function, bells and whistles, network optimization, and post hoc processing techniques. Based on our proposed taxonomy, we present a systematic review of long-tailed learning methods, discussing their commonalities and alignable differences. We also analyze the differences between imbalance learning and long-tailed learning approaches. Finally, we discuss prospects and future directions in this field. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Two-Step Approach for Pulse RFI Detection in SAR data

A Two-Step Approach for Pulse RFI Detection in SAR Data

引用

IEEE SENSORS

作者： Zongsen Lv Hengrui Zhang Ning Li Zhengwei Guo Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

The existence of pulse radio frequency interference (PRFI) severely affects the signal processing and image interpretation of synthetic aperture radar (SAR), which cannot be ignored. In SAR data processing, the detection accuracy directly affects the performance of the PRFI mitigation algorithm. However, most of the existing detectors can only detect the occurrence of PRFI, but cannot locate the PRFI. Based on a two-step process combining eigenvalue decomposition (EVD) with short-time Fourier transform (STFT), in this paper, a novel PRFI detector, which has the capability to detecting and locating PRFI, is proposed. In the proposed detector, the first step is the detection of PRFI occurrence, which is based on the Hankel structure and EVD. The second step is the location of PRFI, which is based on the STFT and a simple ratio operator. Experimental results, which are based on simulated and measured SAR data, validate the performance of the proposed PRFI detector.

关键词： Fourier transforms Signal processing algorithms Detectors Radar imaging Signal processing Time measurement Sensors

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：