检索结果-内蒙古大学图书馆

Electromagnetic Scattering from a Three-dimensional Object using Physics-informed Neural Network

Applied Computational Electromagnetics Society Journal 2025年第2期40卷 103-111页

作者： Zhang, Yuan Li, Renxian Tang, Huan Shi, Zhuoyuan Wei, Bing Gong, Shuhong Yang, Lixia Yan, Bing School of Physics Xidian University Xi’an710071 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University China School of Information and Communication Engineering North University of China 030051 China Shanxi Key Laboratory of Signal Capturing and Processing North University of China Shanxi Taiyuan030051 China

– Prediction of electromagnetic fields scattered from objects is of great significance in various fields. Traditional computational electromagnetic solvers, which are mesh-based, are expensive and time-consuming. The deep learning technique becomes an alternative method of the prediction of scattered fields with high efficiency. However, the data-driven deep learning method requires a large data set and lacks robustness. For complicated scattering problems, the construction of a large training data set is a hard task. By considering physics-constraints, physics-informed neural networks (PINNs) can solve the partial differential equation (PDE) problem with a small data set and also provide a physical explanation. In this paper, the PINNs are employed to solve the scattering of a plane wave by a three-dimensional object with Maxwell’s equations being physical constraints. In the calculation, a sphere and an ellipsoid are taken as examples, and the effects of the network parameters (including the number of hidden layers, and the number of data sets) are mainly discussed. The results have practical applications in many fields such as radar detection, biomedical imaging, and satellite navigation. © ACES.

关键词： Maxwell equations

来源：评论

学校读者我要写书评

暂无评论

Multiband Kick Drum Separation with Genre-Guided Optimization 10th

Multiband Kick Drum Separation with Genre-Guided Optimizati...

引用

10th Conference on Sound and Music technology, CSMT 2023

作者： Li, Si Jiang, Yuanfeng Wang, Zhaowen Qian, Jiale Li, Wei School of Computer Science and Technology Fudan University Shanghai200438 China Department of Music AI and Information Technology Central Conservatory of Music Beijing100091 China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China

ISBN: (纸本)9789819779611

Kick drum plays an important role in electronic music. When hearing an excellent kick drum sound from a reference music track, music production beginners always feel confused about how it will sound if we solo the kick track and why it sounds perfect in a specific song. Reproducing the kick of a music track is not easy even for professional producers and arrangers. To investigate the ability of artificial intelligence in separating kick-drum sounds, in this paper we propose an end-to-end system which is capable of separating multi-genre high-quality electronic kick drum clips from mixed song tracks. Unlike most of the previous music source separation tasks, we only focus on the electronic kick drum rather than the whole percussion track. First, we design a multiband data representation approach for non-pitched percussions such as kick drums, then adopt a multi-discriminator module trained on a multi-genre kick drum corpus to further optimize the separated kick sound. To the authors’ knowledge, this study marks the first attempt at kick drum separation with stylistic optimization. Objective and subjective evaluations demonstrate that joint multiband representation and genre-guided optimisation can form a high-performance framework, showing a promising solution to the kick drum separation task. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Source separation

来源：评论

学校读者我要写书评

暂无评论

Cross-Task Knowledge Transfer for Semi-supervised Joint 3D Grounding and Captioning 24

Cross-Task Knowledge Transfer for Semi-supervised Joint 3D G...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Liu, Yang Liu, Daizong Guo, Zongming Hu, Wei Wangxuan Institute of Computer Technology State Key Laboratory of Multimedia Information Processing Peking University Beijing China

ISBN: (纸本)9798400706868

3D visual grounding is a fundamental yet important task in multimedia understanding, which aims to locate a specific object in a complicated 3D scene semantically according to a text description. However, this task requires a large number of annotations of labeled text-object pairs for training, so the scarcity of annotated data has been a key obstacle in this task. To this end, this paper makes the first attempt to introduce and address a new semi-supervised setting, where only a few text-object labels are provided during training. Considering most scene data has no annotation, we explore a new solution for unlabeled 3D grounding by additionally training and transferring knowledge from a correlated task, i.e., 3D captioning. Our main insight is that 3D grounding and captioning are complementary and can be iteratively trained with unlabeled data to provide object and text contexts for each other with pseudo-label learning. Specifically, we propose a novel 3D Cross-Task Teacher-Student Framework (3D-CTTSF) for joint 3D grounding and captioning in the semi-supervised setting, where each branch contains parallel grounding and captioning modules. We first pre-train the two modules of the teacher branch with limited labeled data for warm-up. Then, we train the student branch to mimic the ability of the teacher model and iteratively update both branches with the unlabeled data. In particular, we transfer the learned knowledge between the grounding and captioning modules across two branches to generate and refine the pseudo-labels of unlabeled data for providing reliable supervision. To further improve the quality of the pseudo-labels, we design a cross-task pseudo-label generation scheme, filtering low-quality pseudo-labels at the detection, captioning, and grounding levels, respectively. Experimental results on various datasets show competitive performances in both tasks compared to previous fully- and weakly-supervised methods, demonstrating the proposed 3D-CTTSF can se

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Electroencephalogram Channel Selection Method for Lower Limb Motor Imagery Based on ReliefF-Spearman 25

Electroencephalogram Channel Selection Method for Lower Limb...

引用

25th IEEE China Conference on System Simulation technology and its Application, CCSSTA 2024

作者： Chen, Wenjin Yang, Ying Ren, Hui Han, Chunxiao Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing & Intelligent Control Tianjin China

ISBN: (纸本)9798350366600

Research on lower limb motor imagery using electroencephalography (EEG) signals has significant applications in lower limb rehabilitation and neural repair. However, practical applications often face challenges due to the inconvenience of using numerous EEG channels. Efficient EEG channel selection methods are therefore crucial. This paper introduces a novel algorithm based on ReliefF-Spearman for EEG signal classification in lower limb motor imagery. The algorithm selects EEG channels by considering individual differences and band signal characteristics, integrating ReliefF's weighting concept with Spearman's correlation principle. Results demonstrate that it reduces the required number of channels significantly compared to traditional algorithms based on ReliefF while maintaining classification accuracy. Furthermore, the channel selection outcomes are independent of user experience. Spatial distribution analysis shows that selected channels align with established neurophysiological motor imagery locations, validating the approach's scientific reliability. This algorithm provides new insights into EEG channel selection for motor imagery research. © 2024 IEEE.

关键词： Neuromuscular rehabilitation

来源：评论

学校读者我要写书评

暂无评论

Research on the navigation method of large-scale differential tail-control improvised guided munitions based on rotational speed constraints

引用

Defence technology（防务技术） 2024年第8期38卷 155-170页

作者： Ning Liu Wenjiang Zhao Yao Wang Kai Shen Zhong Su Wenhao Qi Yuedong Xie Beijing Key Laboratory of High Dynamic Navigation Technology Beijing Information Science and Technology UniversityBeijing100192China Hua an Industry Group Co. Ltd.Qiqihar161006China Integrated Navigation and Intelligent Navigation Laboratory Beijing Institute of TechnologyBeijing100081China Beijing Institute of Technology Beijing100081China

In the process of launching guided projectile under the conventional system, it is difficult to effectively obtain the precise navigation parameters of the projectile in the high dynamic environment. Aiming at this problem, this paper describes a new system of guided ammunition based on tail spin reduction. After analyzing the mechanism of the ammunition's tail spin reduction, a navigation method of large scale difference tail control simple guided ammunition based on speed constraint is proposed. In this method,the corresponding navigation constraints can be carried out by combining the rotation speed state of the ammunition itself, and the optimal solution of navigation parameters during the flight of the missile can be obtained by Extended Kalman Filter(EKF). Finally, the performance of the proposed method was verified by the simulation environment, and the hardware-in-the-loop simulation test and flight test were carried out to verify the performance of the method in the real environment. The experimental results show that the proposed method can achieve the optimal estimation of navigation parameters for simple guided ammunition with large-scale difference tail control. Under the conditions of simulation test and hardware-in-loop simulation test, the position and velocity errors calculated by the method in this paper converged. Under the condition of flight test, the spatial average error calculated by the method described in this paper is 6.17 m, and the spatial error of the final landing point is 3.50 *** this method, the accurate acquisition of navigation parameters in the process of projectile launching is effectively realized.

关键词： Guided projectiles Tail spin reduction RPM constraints Combined navigation Extended Kalman filter(EKF)

来源：评论

学校读者我要写书评

暂无评论

Hyper-Tuned Convolutional Neural Networks for Authorship Verification in Digital Forensic Investigations

引用

Computers, Materials & Continua 2023年第8期76卷 1947-1976页

作者： Asif Rahim Yanru Zhong Tariq Ahmad Sadique Ahmad Mohammed A.ElAffendi School of Computer and Information Security Guilin University of Electronic TechnologyGuilin541004China Guangxi Key Laboratory of Intelligent Processing of Computer Images and Graphics Guilin University of Electronic TechnologyGuilin541004China School of Information and Communication Guilin University of Electronic TechnologyGuilin541004China EIAS:Data Science and Blockchain Laboratory College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia

Authorship verification is a crucial task in digital forensic investigations,where it is often necessary to determine whether a specific individual wrote a particular piece of *** Neural Networks(CNNs)have shown promise in solving this problem,but their performance highly depends on the choice of *** this paper,we explore the effectiveness of hyperparameter tuning in improving the performance of CNNs for authorship *** conduct experiments using a Hyper Tuned CNN model with three popular optimization algorithms:Adaptive Moment Estimation(ADAM),StochasticGradientDescent(SGD),andRoot Mean Squared Propagation(RMSPROP).The model is trained and tested on a dataset of text samples collected from various authors,and the performance is evaluated using accuracy,precision,recall,and F1 *** compare the performance of the three optimization algorithms and demonstrate the effectiveness of hyperparameter tuning in improving the accuracy of the CNN *** results show that the Hyper Tuned CNN model with ADAM Optimizer achieves the highest accuracy of up to 90%.Furthermore,we demonstrate that hyperparameter tuning can help achieve significant performance improvements,even using a relatively simple model architecture like *** findings suggest that the choice of the optimization algorithm is a crucial factor in the performance of CNNs for authorship verification and that hyperparameter tuning can be an effective way to optimize this ***,this paper demonstrates the effectiveness of hyperparameter tuning in improving the performance of CNNs for authorship verification in digital forensic *** findings have important implications for developing accurate and reliable authorship verification systems,which are crucial for various applications in digital forensics,such as identifying the author of anonymous threatening messages or detecting cases of plagiarism.

关键词： Convolutional Neural Network(CNN) hyper-tuning authorship verification digital forensics

来源：评论

学校读者我要写书评

暂无评论

Scattering Characteristics-guided Self-supervised Learning for Target Classification in SAR Images 24

Scattering Characteristics-guided Self-supervised Learning f...

引用

7th International Conference on Image and Graphics processing, ICIGP 2024

作者： Zhong, Honghu Li, Jianhao Shi, Hao Fang, Zhonghao Chen, Liang Institute of Radar Technology Beijing Institute of Technology Beijing China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing China Innovation Center of Beijing Institute of Technology Chongqing Chongqing401120 China

ISBN: (纸本)9798400716720

With the advancement of science and technology, the spatial resolution of spaceborne Synthetic Aperture Radar (SAR) images has achieved sub-meter precision, enabling the classification and identification of targets. Notably, the rapid and accurate classification of aircraft targets using SAR images has become a significant application requirement. Nevertheless, challenges persist in the classification of targets within aircraft remote sensing images. This paper introduces a novel method aimed at enhancing the scattering characteristics in SAR images to address issues associated with discrete imaging pixels, strong scattering characteristics, and the consequent difficulty in distinguishing aircraft features. The proposed method systematically correlates the discrete SAR image scattering characteristics, thereby facilitating the extraction of characteristic information pertaining to the edge contours of aircraft targets. Recognizing the limitations of traditional supervised classification methods, which often demand substantial manually labeled information, this study integrates self-supervised contrastive learning to mitigate labeling costs. Additionally, acknowledging the imbalanced distribution of samples across different categories and the prevalent "long tail"effect, a weighted loss function is introduced to rectify the imbalance and enhance the network's focus on the learning of underrepresented samples. The efficacy of the proposed method is evaluated using a self-established dataset. The results demonstrate a 1.48% increase in accuracy compared to the original self-supervised method, indicating an improvement in the classification performance for categories characterized by an imbalanced sample distribution. © 2024 ACM.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Performance of a four deep neural network structure in moiré fringe intelligent analysis

引用

Applied Optics 2025年第9期64卷 2208-2216页

作者： Zeng, Xinyu Chen, Yunyun Cheng, Weihao Xie, Wenzhuo Yang, Cuihong State Key Laboratory Cultivation Base of Atmospheric Optoelectronic Detection and Information Fusion Nanjing University of Information Science & Technology Nanjing210044 China Jiangsu Engineering Research Center for Intelligent Optoelectronic Sensing Technology of Atmosphere Nanjing University of Information Science & Technology Nanjing210044 China Jiangsu International Joint Laboratory on Meteorological Photonics and Optoelectronic Detection Nanjing University of Information Science & Technology Nanjing210044 China Nanjing University of Information Science & Technology Nanjing210044 China

Moiré fringe analysis holds significant importance in the assessment of flow fields, while deep learning is advancing rapidly and is frequently employed to handle complex computational challenges. In this paper, the performance of U-net, Unet++, Unet 3+, and ResUnet in moiré fringe analysis is compared and analyzed. The results indicate significant differences among the four neural networks in terms of the training time, prediction speed, prediction accuracy, and generalization capability regarding positional variations. Among the four neural networks, ResUnet exhibits the shortest training times, highest accuracy, and fastest prediction speeds while also exhibiting good generalization capability. Consequently, in practical applications, using ResUnet for moiré fringe analysis is an excellent choice. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale and Improved Skip Connections Network for Skin Lesion Segmentation 9

Multi-Scale and Improved Skip Connections Network for Skin L...

引用

9th International Conference on intelligent Computing and Signal processing, ICSP 2024

作者： Zhang, Botao Chen, Jun College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China

ISBN: (纸本)9798350376548

To solve the problem that the current skin lesion segmentation networks have a poor segmentation accuracy when lesion areas are of different shapes and sizes and low contrast at the edge areas, based on U-Net, we present a skin lesion segmentation network based on multi-scale and improved skip connections. Firstly, a multi-scale feature enhancement module is designed to replace the U-Net's 3× 3 convolution blocks, which can improve the feature extraction ability of the network about lesion areas of different shapes and sizes. Secondly, a lesion attention module is introduced into the skip connection to improve the semantic expression of low-level features and the location attention of high-level features, which can improve the fine-grained information transmission efficiency at the skip connection. Finally, a new hybrid loss function is designed to calculate the label and the edge loss of lesion areas, which improves the ability of the network to segment lesion areas and edges. Experiments are conducted on the ISIC2017 and ISIC2018 datasets, and the results prove that our method have a higher segmentation accuracy in skin lesion segmentation. © 2024 IEEE.

关键词： Problem solving

来源：评论

学校读者我要写书评

暂无评论

Energy management of solid oxide fuel cell/lithium battery hybrid system

引用

CSEE Journal of Power and Energy Systems 2022年 1-14页

作者： Li, Dong Zhong, Xiao Bo Xu, Yuan Wu Wei, Chong Yang Zhao, Song Jiang, Jianhua Deng, Zhonghua Fu, Xiaowei Li, Xi School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry Huazhong University of Science and Technology Hubei Wuhan430074 China College of Computer Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan430081 China

The research of fuel cell and lithium battery hybrid system has attracted more and more researchers because of its advantages of low emission. However, the lower efficiency of energy management has been a critical factor that obstruct the commercialization of hybrid system. In this work, based on finite element ideas, a solid oxide full cell node model is developed to accurately estimate the operating status of the fuel cell. As for lithium battery, previous energy management studies generally only focused on state of charge, however, state of health is also a key parameter for lithium battery. In this paper, considering the strong coupling between variables we use particle filter algorithm to jointly estimate the state of charge and state of health. To reasonably distribute and manage the energy in the hybrid system, a T-S fuzzy controller for the hybrid system is designed by controlling the state variables in the SOFC model and the state of lithium battery. Finally, our algorithm is verified by DSPACE simulation platform. The result shows that the hybrid system with the energy management strategy not only meets the real-time sharply changing demand but also ensures the hybrid system working efficiently and safely. © 2022 China Electric Power Research Institute. All rights reserved.

关键词： Hybrid systems

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：