检索结果-内蒙古大学图书馆

A Gaussian process regression-based sea surface temperature interpolation algorithm

Journal of Oceanology and Limnology 2021年第4期39卷 1211-1221页

作者： Yongshun ZHANG Miao FENG Weimin ZHANG Huizan WANG Pinqiang WANG College of Meteorology and Oceanography National University of Defense TechnologyChangsha 410073China Key Laboratory of Software Engineering for Complex Systems National University of Defense TechnologyChangsha 410073China

The resolution of ocean reanalysis datasets is generally low because of the limited resolution of their associated numerical ***-resolution ocean reanalysis datasets are therefore usually interpolated to provide an initial or boundary field for higher-resolution regional ocean ***,traditional interpolation methods(nearest neighbor interpolation,bilinear interpolation,and bicubic interpolation)lack physical constraints and can generate significant errors at land-sea boundaries and around *** this paper,a machine learning method is used to design an interpolation algorithm based on Gaussian process *** method uses a multiscale kernel function to process two-dimensional space meteorological ocean processes and introduces multiscale physical feature information(sea surface wind stress,sea surface heat flux,and ocean current velocity).This greatly improves the spatial resolution of ocean features and the interpolation *** eff ectiveness of the algorithm was validated through interpolation experiments relating to sea surface temperature(SST).The root mean square error(RMSE)of the interpolation algorithm was 38.9%,43.7%,and 62.4%lower than that of bilinear interpolation,bicubic interpolation,and nearest neighbor interpolation,*** interpolation accuracy was also significantly better in off shore area and around *** algorithm has an acceptable runtime cost and good temporal and spatial generalizability.

关键词： Gaussian process regression sea surface temperature(SST) machine learning kernel function spatial interpolation

来源：评论

学校读者我要写书评

暂无评论

Boosting Adversarial Training with Learnable Distribution

引用

Computers, Materials & Continua 2024年第3期78卷 3247-3265页

作者： Kai Chen Jinwei Wang James Msughter Adeke Guangjie Liu Yuewei Dai School of Electronics and Information Engineering Nanjing University of Information Science and TechnologyNanjing210044China Key Laboratory of Intelligent Support Technology for Complex Environments Ministry of EducationNanjing210044China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China Nanjing Center for Applied Mathematics Nanjing211135China

In recent years,various adversarial defense methods have been proposed to improve the robustness of deep neural *** training is one of the most potent methods to defend against adversarial ***,the difference in the feature space between natural and adversarial examples hinders the accuracy and robustness of the model in adversarial *** paper proposes a learnable distribution adversarial training method,aiming to construct the same distribution for training data utilizing the Gaussian mixture *** distribution centroid is built to classify samples and constrain the distribution of the sample *** natural and adversarial examples are pushed to the same distribution centroid to improve the accuracy and robustness of the *** proposed method generates adversarial examples to close the distribution gap between the natural and adversarial examples through an attack algorithm explicitly designed for adversarial *** algorithm gradually increases the accuracy and robustness of the model by scaling ***,the proposed method outputs the predicted labels and the distance between the sample and the distribution *** distribution characteristics of the samples can be utilized to detect adversarial cases that can potentially evade the model *** effectiveness of the proposed method is demonstrated through comprehensive experiments.

关键词： Adversarial training feature space learnable distribution distribution centroid

来源：评论

学校读者我要写书评

暂无评论

ISAR Image-based Spatial Target Recognition 3

ISAR Image-based Spatial Target Recognition

引用

3rd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023

作者： Zhou, Yongjing Zhu, Weigang He, Yonghua Li, Yonggang University of Aerospace Engineering Department of Electronics and Optics Beijing China Key Laboratory of Complex Electronic Systems Simulation Beijing China Graduate School of Aerospace Engineering Beijing China

ISBN: (纸本)9781665490788

With the increasing demand for space situational awareness and space environment monitoring, space target discovery, tracking, identification and classification technologies have been developed accordingly. At present, the integrated development of machine learning, artificial intelligence and other multidisciplinary disciplines has greatly promoted the progress of space target detection and identification technology. The inverse synthetic aperture radar image can reflect the fine structural features of space targets, which is important for feature extraction and recognition and classification of space targets. In this paper, three aspects of target recognition technologies based on RCS, HRRP and ISAR imaging are reviewed respectively, and the target recognition methods based on ISAR images are mainly discussed and validated. First, the basic problems and common methods of current RCS, HRRP, and ISAR image target recognition are introduced;then, a summary is made for ISAR image target recognition techniques;finally, the still existing problems of current ISAR image target recognition and the next development prospects are discussed. © 2023 IEEE.

关键词： Inverse synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

CASKA-CRT: Chinese Remainder Theorem Empowered Certificateless Aggregate Signcryption Scheme with key Agreement in IoVs

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-16页

作者： Hou, Yingzhe Cao, Yue Xiong, Hu Sun, Zhili Mumtaz, Shahid Tian, Daxin School of Cyber Science and Engineering Wuhan University Wuhan China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Institute of Communication Systems University of Surrey Guildford U.K Department of Applied Informatics Silesian University of Technology Akademicka Gliwice Poland State Key Laboratory of Vehicle-Infrastructure Integrated ITS the State Key Laboratory of Intelligent Transportation System and the School of Transportation Science and Engineering Beihang University Beijing China

To enhance the privacy of messages in Internet of Vehicles (IoVs), it is critical to preserve the communication security between Road Side Unit (RSU) and numerous vehicles. The primitive of signcryption is introduced to guarantee the confidentiality, integrity and unforgeability of transmitted messages. Nevertheless, the existing signcryption schemes fail to achieve a balance between security and efficiency. In this paper, we construct a Chinese remainder theorem (CRT) empowered certificateless aggregate signcryption scheme with key agreement (CASKA-CRT). As the vehicle joins and leaves dynamically, the proposed scheme can ensure the dynamic security via one modulo division operation. Besides, the certificateless aggregate signcryption and key agreement mechanisms are embedded. The former idea can both address the certificate management and key escrow problems, while the latter technology can create authentication as a premise of secure communication. Based on this construction, the hash-to-group operation and bilinear pairing are avoided, to realize a faster verification with the increased number of messages. Moreover, the security of proposed scheme is proved under the random oracle model. Finally, the performance analysis demonstrates the advantage of CASKA-CRT in terms of security and reliability over related works. IEEE

关键词： Public key cryptography

来源：评论

学校读者我要写书评

暂无评论

Special Issue for the 14th Global Chinese Chemical engineering Symposium

引用

Frontiers of Chemical Science and engineering 2023年第10期17卷 1321-1322页

作者： Jesse Zhu Junwu Wang Particle Technology Research Centre Western UniversityLondonOntario N6A 5B9Canada State Key Laboratory of Multiphase Complex Systems Institute of Process EngineeringChinese Academy of SciencesBeijing 100190China

The Global Chinese Chemical engineering Symposium(GCCES)is a prestigious and world-wide platform for the communication and academic exchange of chemical science and *** special issue is a collection of the keynote lectures presented by the winners of Future Chemical engineering Scholars,the Global Award for Outstanding Young Female Chemical Engineers,and the International Award for Outstanding Young Chemical Engineers,selected by the International Scientific Committee of the GCCES.

关键词： engineering. Global Engineers

来源：评论

学校读者我要写书评

暂无评论

Nonlinear wave in granular systems based on elastoplastic dashpot model

引用

International Journal of Mechanical System Dynamics 2021年第1期1卷 132-142页

作者： Gengxiang Wang Caishan Liu State Key Laboratory for Turbulence and Complex Systems College of EngineeringPeking UniversityBeijingChina

The dynamic dashpot models are widely used in EDEM commercial ***,most dashpot models suffer from a serious numerical issue in calculating the granular chain because the denominator of damping force includes the initial impact ***,the existing dynamic dashpot models extended from the original Hertz contact law overestimated the contact stiffness in the elastoplastic contact *** two reasons above result in most dynamic dashpot models confronting some issues in calculating the multiple collision of the granular ***,this investigation aims to propose a new composite dynamic dashpot model for the dynamic simulation of granular ***,the entire contact process is divided into three different phases:elastic,elastoplastic,and full plastic *** Hertz contact stiffness is still used in the elastic contact phase when the contact comes into the elastoplastic or full plastic *** contact stiffness in the dynamic dashpot model is replaced by linearizing the contact stiffness from the Ma‐Liu(ML)model in each time ***,the whole contact behavior is treated as a linear mass‐spring‐damper model,and the damping factor is obtained by solving the single‐degree‐freedom underdamped vibration *** new dynamic dashpot model is proposed by combining the contact stiffnesses in different contact phases and corresponding damping factors,which not only removes the initial im-pact velocity from the denominator of damping force but also updates the contact stiffness based on the constitutive relation of the contact body when the contact comes into the elastoplastic or full plastic ***,a granular chain is treated as numerical examples to check the reasonability and effectiveness of the new dynamic dashpot model by comparing it to the experimental *** simulation shows that the solitary waves obtained using the new dashpot model are more accurate than the dashpot model used in EDEM software.

关键词： dynamic dashpot model granular chain numerical singularity solitary wave

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Prompts: Few-Shot Multi-Label Recognition With Single-Label Training

引用

IEEE Transactions on Multimedia 2025年 27卷 3023-3033页

作者： Ding, Zixuan Zhou, Zihan Chen, Hui Hao, Tianxiang Xiong, Yizhe Zhao, Sicheng Zhang, Qiang Han, Jungong Xidian University State Key Laboratory of Electromechanical Integrated Manufacturing of High-Performance Electronic Equipments Xi'an710071 China Xidian University Center for Complex Systems School of Mechano-Electronic Engineering Xi'an710071 China Tsinghua University School of Software Beijing100190 China Tsinghua University Beijing National Research Center for Information Science and Technology Beijing100190 China Tsinghua University Department of Automation Beijing100190 China

Few-shot multi-label recognition (FS-MLR) presents a significant challenge due to the need to assign multiple labels to images with limited examples. Existing methods often struggle to balance the learning of novel classes and the retention of knowledge from base classes. To address this issue, we propose a novel Cross-Modality Prompts (CMP) approach. Unlike conventional methods that rely on additional semantic information to mitigate the impact of limited samples, our approach leverages multimodal prompts to adaptively tune the feature extraction network. A new FS-MLR benchmark is also proposed, which includes single-label training and multi-label testing, accompanied by benchmark datasets constructed from MS-COCO and NUS-WIDE. Extensive experiments on these datasets demonstrate the superior performance of our CMP approach, highlighting its effectiveness and adaptability. Our results show that CMP outperforms CoOp on the MS-COCO dataset with a maximal improvement of 19.47% and 23.94% in mAPharmonic for 5-way 1-shot and 5-way 5-shot settings, respectively. © 1999-2012 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Capturing the baroclinic effect in non-Boussinesq gravity currents

引用

Theoretical & Applied Mechanics Letters 2022年第1期12卷 10-16页

作者： Shengqi Zhang Zhenhua Xia State Key Laboratory for Turbulence and Complex Systems College of EngineeringPeking UniversityBeijing 100871China Department of Engineering Mechanics Zhejiang UniversityHangzhou 310027China

Direct numerical simulations of two-dimensional gravity currents with small and medium density variations are performed using different non-Boussinesq buoyancy approximations. Taking the full low-Machnumber approximation as the reference, the accuracy of several buoyancy terms are examined. It is found that all considered buoyancy terms performed well in the cases with small density variation. In the cases with medium density variation, the classical gravitational Boussinesq’s buoyancy term showed the lack of accuracy, and a simple correction did not make any improvement. In contrast, the recently introduced second-order buoyancy term showed a significantly higher accuracy. The present results and our previous derivations indicate that simple algebraic buoyancy approximations extended from the Boussinesq’s gravitational buoyancy are unlikely to achieve an accuracy beyond first order. Instead, it seems necessary to solve at least one extra Poisson equation for buoyancy terms to capture the higher-order baroclinic effect. An approximate analysis is also provided to show the leading term of the non-Boussinesq effect corresponding to gravity.

关键词： Baroclinic effect Gravity current

来源：评论

学校读者我要写书评

暂无评论

Quantum software Testing: A Brief Introduction

Quantum Software Testing: A Brief Introduction

引用

International Conference on software engineering - Companion, ICSE, Companion

作者： Shaukat Ali Tao Yue Engineering Complex Software Systems Simula Research Laboratory Oslo Norway

Quantum software testing concentrates on testing quantum programs to discover quantum faults in the programs cost-effectively. Given the foundations in quantum mechanics, the way quantum computations are performed is significantly different than classical computing. Therefore, quantum software testing also differs from classical software testing. There has been quite an interest in building quantum software testing techniques since 2019 in the software engineering (SE) community. Thus, we aim to introduce quantum software testing to the SE community. In particular, we will present the basic foundations of quantum computing and quantum programming as circuits, followed by the current state of the art on quantum software testing. Next, we will present some basic quantum software testing techniques and finally give the research directions that deserve attention from the SE community.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Person Re-identification Based on Dual-channel Attention and Local Feature Fusion

Person Re-identification Based on Dual-channel Attention and...

引用

2022 International Conference on Electrical, Control and Information Technology, ECITech 2022

作者： Ning, Xinkuang Shao, Jiayu Lin, Wenjie Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China

ISBN: (纸本)9783800759170

Aiming at improving low accuracy of existing person re-identification algorithms in dealing with low image resolution, different illumination, diverse poses, and viewing angles, this paper proposes a person re-id algorithm based on dual-channel attention and local feature fusion. After ResNet50, it is followed by the spatial attention and the channel attention to extract the global features. Then the feature map segmentation is performed to extract the local features, and a fusion feature with strong judgment is obtained. In addition, this paper adds the central loss constraint item to the triplet hard loss. The triplet_center loss joint cross-entropy loss function further to improve adaptability of the model in complex scenarios. The proposed method is compared and tested on the CUHK03, DukeMTMC-reID and Market-1501 data sets, and the accuracy of Rank-1 reached 96.1%, 89.8% and 79.8%. This algorithm makes full use of the features of different depths and the key information of interest. The module has a solid discriminative ability. Also the accuracy of mean average precision of the proposed method is better than other advanced algorithms. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Image resolution

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：