检索结果-内蒙古大学图书馆

3rd URSI Atlantic and Asia Pacific Radio science Meeting, AT-AP-RASC 2022

作者： Gulati, Ishita Atul, Jyoti Kumar Kravchenko, Oleg V Dlay, Satnam Newcastle University United Kingdom Indian Institute of Geomagnetism Navi Mumbai India Federal Research Center Computer Science and Control Ras Moscow Russia

ISBN: (纸本)9789463968058

It has been established that polar cap patches are capable of triggering phase scintillation via various convective instabilities such as Gradient Drift, Gravitational Interchange, Current Convective, and Kelvin-Helmholtz Instabilities coupled with turbulent plasma processes in the cold and warm approximation. These multiple instabilities provide a qualitative density peaking mechanism which ultimately leads to the formation of highly dense and coherent nonlinear structures such as polar patches and auroral blobs at high latitudes. It is important to note that the nonlinear evolution of these polar patches/blobs and their associated plasma number density in-homogeneities are primarily controlled by dominant magnetospheric (inertial) or ionospheric (collisional) current systems. Moreover, intense observational studies on the trans-polar movement of these polar patches/blobs and their associated morphology further classify these structures as Type 1 and Type 2 blobs depending upon their density estimates and ionisation sources. In this study, a correlation between inherent polar patches plasma parameters and phase scintillation metrics is discussed in terms of Total Electron Content (TEC) and ROTI measurements at a localised region Ny-Alesund [78.93N, 11.86E], Svalbard which is more sensitive to the polar patch mobilisation driven by dayside polar cusp dynamics. Moreover, it is concluded that phase scintillation studied in terms of TEC and ROTI local estimations could be used as proxies for the polar ionosphere. © 2022 URSI.

关键词： Plasma diagnostics

来源：评论

学校读者我要写书评

暂无评论

Decoupling While Coupling: Towards More Accurate Stereo Image Sand Removal Beyond Certainty

Decoupling While Coupling: Towards More Accurate Stereo Imag...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wei, Bingcai Liu, Hui Qian, Chuang Jia, Yi Wu, Wangyu Li, Zhishan School of Computer Science Wuhan University Wuhan China GNSS Research Center Wuhan Unicersity Wuhan China Intelligent Transport Systems Research Center Wuhan University of Technology Wuhan China College of Information and Control Engineering Jilin Institute of Chemical Technology Jilin China University of Liverpool Liverpool United Kingdom School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798350368741

Stereo image sand removal is crucial to improve the perceptual quality for autonomous driving perception. Existing methods often fall short in accurately estimating the uncertainty inherent in degraded images, leading to suboptimal outcomes. To address this, we introduce a novel framework named Decoupling While Coupling(DWC). DWC pioneers the integration of inter-view uncertainty estimation, cross-view uncertainty-aware interaction and block-wise uncertainty representation for superior stereo image sand removal. For cross-view information interaction, we propose an Uncertainty-aware Cross-view Attentive Interaction module(UCAI) to cope with the lack of uncertainty estimation ability in the existing cross-view information interaction mechanism. For the uncertainty perception and information interaction within the inter-view, we propose a Distribution Modeling Coupling Block(DMCB), which transmits the representation of uncertainty between each backbone module. For block-wise uncertainty estimation, we use our proposed Uncertainty-aware Distribution Feature Modulator(UDFM) as the backbone of DWC to modulate the uncertainty inside the neural network itself. Extensive experimental validations on our proposed stereo image sand removal dataset SandST confirm the efficacy of DWC. Our method not only achieves higher PSNR and SSIM, but also exhibits enhanced robustness against various sand degrees and patterns. © 2025 IEEE.

关键词： Cross-view Inter-view Sand removal Stereo image Uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

Solar Wind Density Forecasting with U-Net and LSTM-based Neural Networks 8

Solar Wind Density Forecasting with U-Net and LSTM-based Neu...

引用

8th International Conference of Yearly Reports on Informatics, Mathematics, and Engineering, ICYRIME 2023

作者： Iacobelli, Emanuele Fiani, Francesca Napoli, Christian Department of Computer Control and Management Engineering Sapienza University of Rome Roma00185 Italy Institute for Systems Analysis and Computer Science Italian National Research Council Roma00185 Italy Department of Computational Intelligence Czestochowa University of Technology Czestochowa42-201 Poland

Forecasting changes in solar wind properties accurately is crucial for predicting space weather, as it significantly impacts the majority of space operations and the telecommunication system. To meet this challenge, we introduce an architecture that combines U-Net’s capabilities for segmenting coronal holes from high-resolution sun images with the predictive abilities of Long Short-Term Memory (LSTM) and ConvLSTM models. This architecture predicts solar wind density using sun surface images obtained from the AIA 193 Å dataset (provided by NASA) and historical electron and proton density data from the OMNI and ELM2 datasets (also provided by NASA), covering the entire year 2012. Our findings demonstrate the system’s ability to generate reliable coronal hole segmentation maps and achieve good accuracy in forecasting solar wind density. © 2023 Copyright for this paper by its authors.

关键词： NASA

来源：评论

学校读者我要写书评

暂无评论

Rethinking Guidance Information to Utilize Unlabeled Samples: A Label Encoding Perspective 41

Rethinking Guidance Information to Utilize Unlabeled Samples...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, Yulong Yao, Yuan Chen, Shuhao Jin, Pengrong Zhang, Yu Jin, Jian Lu, Jiangang Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China College of Control Science and Engineering Zhejiang University Hangzhou China Beijing Teleinfo Technology Company Ltd. China Academy of Information and Communications Technology Beijing China Research Institute of Industrial Internet of Things China Academy of Information and Communications Technology Beijing China

Empirical Risk Minimization (ERM) is fragile in scenarios with insufficient labeled samples.A vanilla extension of ERM to unlabeled samples is Entropy Minimization (EntMin), which employs the soft-labels of unlabeled samples to guide their ***, EntMin emphasizes prediction discriminability while neglecting prediction *** alleviate this issue, in this paper, we rethink the guidance information to utilize unlabeled *** analyzing the learning objective of ERM, we find that the guidance information for labeled samples in a specific category is the corresponding label *** by this finding, we propose a Label-Encoding Risk Minimization (LERM).It first estimates the label encodings through prediction means of unlabeled samples and then aligns them with their corresponding ground-truth label *** a result, the LERM ensures both prediction discriminability and diversity, and it can be integrated into existing methods as a ***, we analyze the relationships between LERM and ERM as well as ***, we verify the superiority of the LERM under several label insufficient *** codes are available at https://***/zhangyl660/LERM. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model-Based Policy Optimization with Neural Differential Equations for Robotic Arm control 8th

Model-Based Policy Optimization with Neural Differential Equ...

引用

Proceedings of the 8th International Conference on Interactive Collaborative Robotics, ICR 2023

作者： Gorodetskiy, Andrey Mironov, Konstantin Panov, Aleksandr Center of Cognitive Modeling Moscow Institute of Physics and Technology 9 Institutskij per. Dolgoprudny141701 Russia Artificial Intelligence Research Institute Moscow105064 Russia Federal Research Center "Computer Science and Control" 9 60-letiya Oktyabrya pr. Moscow117312 Russia

ISBN: (纸本)9783031431104

Applying learning-based control methods to real robots presents hard challenges, including the low sample efficiency of model-free reinforcement learning algorithms. The widely adopted approach to tackling this problem uses an environment dynamics model. We propose to use the Neural Ordinary Differential Equations to approximate transition dynamics as this allows for finer control of a trajectory generation process. NODE offers a continuous-time formulation that captures the temporal dependencies. We evaluate our approach on various tasks from simulation environment including learning 6-DoF robotic arm to open the door, which represents particular challenges for policy search. The NODE model is trained to predict movement of the arm and the door, and is used to generate trajectories for the model-based policy optimization. Our method shows better sample efficiency on this task comparing to the model-free and model-based baseline. It also shows comparable results on several other tasks. The application of NODE to model-based reinforcement learning enables more precise modeling of robotic system dynamics and enhances the sample efficiency of learning-based control methods. The empirical evaluation on various tasks demonstrates the efficacy of our approach, offering promising prospects for improving the performance and efficiency of real-world robotic systems. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

3D printed-electrospun PCL/hydroxyapatite/MWCNTs scaffolds for the repair of subchondral bone

引用

Regenerative Biomaterials 2023年第1期10卷 294-305页

作者： Yanyan Cao Lei Sun Zixian Liu Zhizhong Shen Wendan Jia Peiyi Hou Shengbo Sang College of Information Science and Engineering Hebei North UniversityZhangjiakou 075000China Shanxi Key Laboratory of Micro Nano Sensors&Artificial Intelligence Perception College of Information and ComputerTaiyuan University of TechnologyTaiyuan 030024China Key Lab of Advanced Transducers and Intelligent Control System of the Ministry of Education Taiyuan University of TechnologyTaiyuan 030024China Shanxi Research Institute of 6D Artificial Intelligence Biomedical Science Taiyuan 030031China

Osteochondral defect caused by trauma or osteoarthritis exhibits a major challenge in clinical treatment with limited symptomatic effects at *** regeneration and remodeling of subchondral bone play a positive effect on cartilage regeneration and further promotes the repair of osteochondral *** use of the strengths of each preparation method,the combination of 3D printing and electrospinning is a promising method for designing and constructing multi-scale scaffolds that mimic the complexity and hierarchical structure of subchondral bone at the microscale and nanoscale,*** this study,the 3D printed-electrospun poly(ɛ-caprolactone)/nano-hydroxyapatites/multi-walled carbon nanotubes(PCL/nHA/MWCNTs)scaffolds were successfully constructed by the combination of electrospinning and layer-by-layer 3D *** resulting dual-scale scaffold consisted of a dense layer of disordered nanospun fibers and a porous microscale 3D scaffold layer to support and promote the ingrowth of subchondral ***,the biomimetic PCL/nHA/MWCNTs scaffolds enhanced cell seeding efficiency and allowed for higher cell-cell interactions that supported the adhesion,proliferation,activity,morphology and subsequently improved the osteogenic differentiation of bone marrow mesenchymal stem cells in ***,this study elucidates that the construction of 3D printed-electrospun PCL/nHA/MWCNTs scaffolds provides an alternative strategy for the regeneration of subchondral bone and lays a foundation for subsequent in vivo studies.

关键词： additive manufacturing 3D printing electrospinning subchondral bone

来源：评论

学校读者我要写书评

暂无评论

Long Short-Term Memory Neural Equalizer

IEEE Transactions on Signal and Power Integrity

引用

IEEE Transactions on Signal and Power Integrity 2023年第1期2卷 13-22页

作者： Wang, Zihao Xu, Zhifei He, Jiayi Delingette, Hervé Fan, Jun The French National Institute for Research in Computer Science and Control Le Chesnay-Rocquencourt78150 France Université Côte d’Azur Nice06000 France The Detoolic Technology Co. Ltd Ningbo China The Missouri University of Science and Technology RollaMO65401 United States The Electromagnetic Compatibility Laboratory Missouri University of Science and Technology RollaMO65401 United States The Université Côte d’Azur FranceFrench Interdisciplinary Institutes of Artificial Intelligence Université Côte d’Azur 06000 Nice Nice06000 France

A trainable neural equalizer based on the long short-term memory (LSTM) neural network architecture is proposed in this article to recover the channel output signal. The current widely used solution for the transmission line signal recovery is generally realized through a decision feedback equalizer (DFE) or: Feed forward equalizer (FFE) combination. The novel learning-based equalizer is suitable for highly nonlinear signal restoration, thanks to its recurrent design. The effectiveness of the LSTM equalizer (LSTME) is shown through an advance design system simulation channel signal equalization task, including a quantitative and qualitative comparison with an FFE–DFE combination. The LSTM neural network shows good equalization results compared with that of the FFE–DFE combination. The advantage of a trainable LSTME lies in its ability to learn its parameters in a flexible manner and to tackle complex scenarios without any hardware modification. This can reduce the equalizer implantation cost for variant transmission channels and bring additional portability in practical applications. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Enhancing Object Detection Robustness for Cross-Depiction Through Neural Style Transfer 8

Enhancing Object Detection Robustness for Cross-Depiction Th...

引用

8th International Conference of Yearly Reports on Informatics, Mathematics, and Engineering, ICYRIME 2023

作者： Fiani, Francesca Puglisi, Adriano Napoli, Christian Department of Computer Control and Management Engineering Sapienza University of Rome Roma00185 Italy Institute for Systems Analysis and Computer Science Italian National Research Council Roma00185 Italy Department of Computational Intelligence Czestochowa University of Technology Czestochowa42-201 Poland

Modern neural networks models for computer vision are trained on millions of images. The idea is that models are able to increase generalization when the dataset contains well diversified images, e.g. with varied illumination and environmental conditions of the same objects. Generalization is particularly relevant in object detection, especially for what concerns the cross-depiction problem. In this work we explore the use of Neural Style Transfer as a novel technique to morph the original data, with the aim to enhance model generalization. To verify the effect on performances for object detection models, we selected the Faster R-CNN model to be applied on the Pascal VOC 2012 dataset. A number of tests were performed through style variations on images and by tuning Neural Style Transfer parameters to maintain the content of the original images. The experiments showed promising results, which effectively provide a foundation for future studies on cross-depiction via Neural Style Transfer. © 2023 Copyright for this paper by its authors.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Rapid Finger Vein Recognition Approach Based on UNet++ 1

引用

39th CCF National Conference on computer Applications, CCF NCCA 2024

作者： Liu, Peng Jia, Yujiao Cao, Xiaofan Wang, Changjie Fan, Shanshan Institute of Energy and Electrical Engineering Changchun University of Science and Technology Changchun China School of Control and Computer Engineering North China Electric Power University Beijing China Yangzhong Intelligent Electric Research Center North China Electric Power University Beijing China

ISBN: (数字)9789819796748

ISBN: (纸本)9789819796731

With the advancement of biometric technologies, finger vein recognition has garnered widespread attention within the academic community. This paper proposes a method based on the UNet++ model, wherein parameter adjustments are made to the UNet++ architecture to ensure precise pixelwise segmentation of finger vein images. Following the parameter optimization, model compression is applied through structural reparameterization to further increase the recognition speed of the trained model. The approach achieves recognition accuracies of 93.1% on two publicly available finger vein datasets, and it features a feature extraction time of 0.0131 s for a single finger vein image. The recognition time for a single fingerprint vein image is 0.0294 s. The results indicate that the use of the UNet++ model as a framework for finger vein feature extraction and subsequent model compression render it suitable for finger vein recognition tasks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Self-Timed Pipeline with Variable Stage Number*

Self-Timed Pipeline with Variable Stage Number*

引用

Networks, Circuits and Systems (NCS), Seminar on

作者： Igor A. Sokolov Yuri V. Rogdestvenski Yuri A. Stepchenkov Denis Y. Diachenko Yuri G. Diachenko Leonid P. Plekhanov Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Moscow Russia Institute of Informatics Problems Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Moscow Russia

The paper analyzes the problem of improving the self-timed pipeline’s performance. The paper considers possible options for reducing the pipeline latency by decreasing the number of actively operating stages when certain conditions occur, determined by the processed data value or an external signal. One stage bypassing becomes appropriate if it occurs in at least 64% of data processing operations, while two stage bypassing decreases the average pipeline latency if it occurs in 50% of operations.

关键词：

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：