检索结果-内蒙古大学图书馆

33rd IEEE Intelligent Vehicles Symposium (IEEE IV)

作者： Feriol, Florent Watanabe, Yoko Vivet, Damien Univ Toulouse ISAE SUPAERO Toulouse France ONERA DTIS Toulouse France

ISBN: (纸本)9781665488211

Environmental context detection is a topic of interest for the navigation community since it enables to build a context-adaptive solution. Indeed if the type of environment is known it is then possible to choose the proper data processing algorithm or to select the sensors to be used to dynamically adapt the navigation solution design itself. This paper proposes to build a supervised machine learning model which can robustly classify multiple contexts such as urban canyons, urban, trees and open-sky areas using GNSS data only. A training and test database have been built with four datasets acquired at different times in order to prove the relevance of the solution. These datasets are made available to the community for research purpose. The choices of features and classifier are also discussed and compared to others papers. Our solution achieved an average 82.40% of classification accuracy.

关键词： Training Global navigation satellite system Visualization Solution design Satellites Navigation signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Generating Targeted Adversarial Attacks and Assessing their Effectiveness in Fooling Deep Neural Networks 14

Generating Targeted Adversarial Attacks and Assessing their ...

引用

14th IEEE International Conference on signal processing and Communications (SPCOM)

作者： Gajjar, Shivangi Hati, Avik Bhilare, Shruti Mandal, Srimanta Dhirubhai Ambani Inst Informat & Commun Technol Gandhinagar India

ISBN: (数字)9781665482509

ISBN: (纸本)9781665482509

Deep neural network (DNN) models have gained popularity for most image classification problems. However, DNNs also have numerous vulnerable areas. These vulnerabilities can be exploited by an adversary to execute a successful adversarial attack, which is an algorithm to generate perturbed inputs that can fool a well-trained DNN. Among various existing adversarial attacks, DeepFool, a white-box untargeted attack is considered as one of the most reliable algorithms to compute adversarial perturbations. However, in some scenarios such as person recognition, adversary might want to carry out a targeted attack such that the input gets misclassified in a specific target class. Moreover, studies show that defense against a targeted attack is tougher than an untargeted one. Hence, generating a targeted adversarial example is desirable from an attacker's perspective. In this paper, we propose 'Targeted DeepFool', which is based on computing a minimal amount of perturbation required to reach the target hyperplane. The proposed algorithm produces minimal amount of distortion for conventional image datasets: MNIST and CIFAR10. Further, Targeted DeepFool shows excellent performance in terms of adversarial success rate.

关键词： Deep learning Perturbation methods Neural networks signal processing algorithms Rate distortion theory Distortion Reliability

来源：评论

学校读者我要写书评

暂无评论

Intelligent Omni-Surfaces (IOSs) for the MIMO Broadcast Channel 23

Intelligent Omni-Surfaces (IOSs) for the MIMO Broadcast Chan...

引用

23rd International Workshop on signal processing Advances in Wireless Communication (SPAWC)

作者： Mohamed, Abdelhamed Perovic, Nemanja Stefan Di Renzo, Marco Univ Paris Saclay Cent Supelec CNRS Lab Signaux & Syst 3 Rue Joliot Curie F-91192 Gif Sur Yvette France

ISBN: (纸本)9781665494557

In this paper, we consider intelligent omni-surfaces (IOSs), which are capable of simultaneously reflecting and refracting electromagnetic waves. We focus our attention on the multiple-input multiple-output (MIMO) broadcast channel, and we introduce an algorithm for jointly optimizing the covariance matrix at the base station, the matrix of reflection and transmission coefficients at the IOS, and the amount of power that is reflected and refracted from the IOS. The distinguishable feature of this work lies in taking into account that the reflection and transmission coefficients of an IOS are tightly coupled. Simulation results are illustrated to show the convergence of the proposed algorithm and the benefits of using surfaces with simultaneous reflection and refraction capabilities.

关键词： Wireless communication Transmitters Simulation signal processing algorithms signal processing Reflection Covariance matrices

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimization of Heterogeneous Linear Multi-Agent Systems With Unknown Disturbances and Optimal Gain Tuning

引用

IEEE Transactions on signal and Information processing over Networks 2025年 11卷 563-576页

作者： Mengmeng Duan Shanying Zhu Ziwen Yang Cailian Chen Xinping Guan State Key Laboratory of Submarine Geoscience Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Key Laboratory for Perception and Control in Industrial Network Systems Shanghai China

In this paper, we investigate the distributed optimization problem for heterogeneous linear multi-agent systems with unknown disturbances. To solve this problem, we propose a distributed controller design framework, which reduces the controller design for heterogeneous linear multi-agent systems to the stabilizer design for first-order multi-agent systems. By this framework, we propose two kinds of dynamic controllers under the strong convexity of the objective function and the restricted secant inequality condition, respectively. Based on the optimal condition and singular perturbation analysis technique, we prove that the system converges to the optimal state if the disturbances tend to be constant or vary slowly. To further optimize the performance criterion under system stability and input constraint, we provide an optimal gain tuning algorithm such that the system stability, optimality and feasibility are simultaneously achieved. Numerical examples are provided to illustrate the effectiveness of the theoretical results.

关键词： Optimization Multi-agent systems Linear programming Tuning Heuristic algorithms Real-time systems Stability criteria signal processing algorithms Symmetric matrices Convergence

来源：评论

学校读者我要写书评

暂无评论

RATE CONTROL FOR LEARNED VIDEO COMPRESSION 47

RATE CONTROL FOR LEARNED VIDEO COMPRESSION

引用

47th IEEE International Conference on Acoustics, Speech and signal processing (ICASSP)

作者： Li, Yanghao Chen, Xinyao Li, Jisheng Wen, Jiangtao Han, Yuxing Liu, Shan Xu, Xiaozhong Tsinghua Univ Beijing Peoples R China Tsinghua Univ Shenzhen Res Inst Shenzhen Peoples R China Tencent Media Lab Beijing Peoples R China

ISBN: (纸本)9781665405409

Rate control is a critical part for video compression, especially in bandwidth-limited tasks such as live and broadcast. The newly-rising learned video compression has shown advantageous rate-distortion (RD) performance in previous research, but lack of rate control heavily limits its usage in real coding scenarios. In this work, we present the first rate control scheme tailored for learned video compression. Specifically, we explore the inter-frame dependency of learned video compression and propose a novel R-D-lambda model accordingly for efficient rate allocation. Additionally, a staged update algorithm is developed for robust parameter estimation. Experiments on public datasets show that, the proposed rate control scheme achieves low rate error while maintaining equal or even higher RD performance, without introducing coding time overhead.

关键词： Parameter estimation Conferences signal processing algorithms Rate-distortion Video compression signal processing Encoding

来源：评论

学校读者我要写书评

暂无评论

Spatially Variant Filtering Network Based on Generalized Optimal Constraints for Sidelobe Suppression in SAR Images

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷

作者： Suo, Yuxi Fu, Kun Wu, Youming Meng, Qingbiao Miao, Tian Diao, Wenhui Sun, Xian Chinese Acad Sci Aerosp Informat Res Inst Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Network Informat Syst Technol NIST Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100190 Peoples R China

Sidelobes commonly disturb synthetic aperture radar (SAR) image understanding and interpretation. Traditional spatially variant filtering algorithms achieve a superior tradeoff between sidelobe suppression and resolution preservation by means of adaptively calculating filtering parameters under some specific restrictions, such as filter design restriction and minimum amplitude constraint (MAC). These restriction aims to obtain an efficient analytical solution for filters, which is easy to calculate under unsupervised conditions. However, the restriction scope is so narrow that the suppression performance achieved by these filters is limited. Also, since the unsupervised optimization based on MAC indiscriminately minimizes amplitude, the main-lobe loss is unavoidable. To further improve the performance, a spatially variant convolution neural network (SVNN) is proposed, which consists of two core modules. One is the spatially variant filter generation (SVFG) module, adaptively generating superior spatially variant filters under more relaxed restrictions. The other is a paralleled shifted convolution (PSC) module, converting the signal format to achieve a fast and parallel spatially variant filtering process. Benefiting from more relaxed filter restrictions, the novel network successfully achieves better performance on sidelobe suppression. In addition, with supervised optimization based on another more accurate restriction, namely, minimum error constraint (MEC), the proposed algorithm also achieves superior main-lobe maintenance. All of them are validated by comparative experiments based on satellite data from GaoFen-3 and TerraSAR-X, and our proposed method achieves state-of-the-art performance. The entire project is available at https://***/suoyuxi/SVNN.

关键词： Optimization signal processing algorithms Radar polarimetry Maintenance Synthetic aperture radar signal resolution Convolutional neural networks Computer aided software engineering Spatial resolution Solids Deep learning sidelobe suppression spatially variant filtering synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Development of a Sound Directional Device Based on Ultrasound Modulation and Transducer Array Optimization

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Ma, Zhexuan Zhao, Heng Long, Zhili Ju, Jianzhong Liu, Xicheng Harbin Inst Technol Shenzhen Sch Mech Engn & Automat Shenzhen 518071 Peoples R China

The sound directional system utilizes the directional transmitting of ultrasonic wave to realize the directivity of sound, which has a wide application in civil and military fields. An optimized sound directional device is developed in this article. The signal modulation algorithms with single-frequency and broadband frequency input are theoretically analyzed. The modulation coefficients on sound distortion are evaluated. The sound fields are simulated and show that the sound emitting areas are 0.09 pi and 0.16 pi for the 16- and 10-mm-diameter transducers in 40 kHz, indicating that the 16-mm transducer has better sound directivity. The hardware of sound directional device is established, and the signal modulation is realized by DSP programming. Sound directivity and distortion evaluation principle is proposed, which provides a guidance of ultrasound modulation determination and transducer array optimization. Sound distortion measurement is conducted, and the second-order approximate square root (SASR) is adopted in the proposed hardware. Finally, the sound directional system is compared with the current sound directional array. Experiments show that the total harmonic distortion (THD) is 15.44% of 7x7 array. The sidelobe amplitude intensity of 7x7 array is 71.4 dB and lower than 87.9 dB of the commercial array, demonstrating that the sound emitting of 7x7 array in sidelobe is in high suppression. The sound main beam emitting angle of 7x7 array is 117 degrees, which is significantly lower than 175 degrees of the Audfly array. Therefore, the 7x7 array shows a better sound directivity.

关键词： Distortion Acoustics Amplitude modulation Acoustic distortion signal processing algorithms Frequency modulation Harmonic distortion Harmonic analysis Optimization Array signal processing signal modulation sound directional system sound directivity sound distortion ultrasonic array

来源：评论

学校读者我要写书评

暂无评论

Sparsity and Periodicity-Induced Symplectic Geometry Decomposition for Incipient Fault Diagnosis of Wind Turbine Gearbox

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Zhang, Bo Teng, Wei Bai, Honghua Huang, Weiling Peng, Dikang Liu, Yibing North China Elect Power Univ Minist Educ Key Lab Power Stn Energy Transfer Convers & Syst Beijing 102206 Peoples R China Zhejiang Zhenxing Axiang Grp Co Ltd Huzhou 313008 Zhejiang Peoples R China

When incipient faults of gears or bearings occur in the wind turbine gearbox, their fault information will be readily masked by intensive background noise, which may postpone the fault detection and maintenance schedule. Specifically, the phenomenon manifested in the time domain is that the fault impulse is not obvious, while in the frequency domain, it is manifested that the fault frequency is prone to submerge in other interference frequency components. However, conventional signal processing methods and matrix factorization algorithms make it difficult to intuitively characterize fault features. Complex algorithms often require some manually adjusted parameters, which is difficult to be applied in engineering practice. To balance the performance and complexity of algorithms, a sparsity and periodicity-induced symplectic geometry decomposition (SPSGD) method is proposed. The initial components are obtained by the symplectic geometry mode decomposition method. Stem from the periodicity of gear faults in the time domain and the sparsity in the frequency domain, a periodicity-induced Bayesian clustering method is proposed as a novel iteration termination condition to pursue the fault-related components in the time domain. Then, a sparsity and periodicity-induced inverse filter is designed by the Laplace operator to weigh the faulty components to reduce the noise influence. The proposed SPSGD is validated by three cases, which indicate that the noise can be reduced adaptively as well as enhance the useful fault components effectively.

关键词： Noise reduction Noise Geometry Feature extraction Time-domain analysis signal processing algorithms Gears Vectors Bayes methods Wind turbines Fault diagnosis noise reduction sparsity and periodicity wind turbine

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Action Anticipation Through Action Cluster Prediction

IEEE Open Journal of Signal Processing

引用

IEEE Open Journal of signal processing 2025年 6卷 641-650页

作者： Jiuxu Chen Nupur Thakur Sachin Chhabra Baoxin Li School of Computing and Augmented Intelligence Arizona State University Tempe AZ USA

Predicting near-future human actions in videos has become a focal point of research, driven by applications such as human-helping robotics, collaborative AI services, and surveillance video analysis. However, the inherent challenge lies in deciphering the complex spatial-temporal dynamics inherent in typical video feeds. While existing works excel in constrained settings with fine-grained action ground-truth labels, the general unavailability of such labeling at the frame level poses a significant hurdle. In this paper, we present an innovative solution to anticipate future human actions without relying on any form of supervision. Our approach involves generating pseudo-labels for video frames through the clustering of frame-wise visual features. These pseudo-labels are then input into a temporal sequence modeling module that learns to predict future actions in terms of pseudo-labels. Apart from the action anticipation method, we propose an innovative evaluation scheme GreedyMapper, a unique many-to-one mapping scheme that provides a practical solution to the many-to-one mapping challenge, a task that existing mapping algorithms struggle to address. Through comprehensive experimentation conducted on demanding real-world cooking datasets, our unsupervised method demonstrates superior performance compared to weakly-supervised approaches by a significant margin on the 50Salads dataset. When applied to the Breakfast dataset, our approach yields strong performance compared to the baselines in an unsupervised setting and delivers competitive results to (weakly) supervised methods under a similar setting.

关键词： Videos Feature extraction Training Semantics Predictive models Annotations Transformers Visualization signal processing algorithms signal processing

来源：评论

学校读者我要写书评

暂无评论

Statistical Analysis of the 2^mth-Order Chirp Cyclostationary Processes

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Miao, Hongxia Zhang, Feng Beijing Univ Posts & Telecommun Sch Informat & Commun Engn Beijing 100876 Peoples R China Beijing Inst Technol Sch Informat & Elect Beijing Key Lab Fract Signals & Syst Beijing 100081 Peoples R China

Cyclostationary signals are usually encountered in practical applications, which are properly characterized by cyclic statistics. The chirp cyclostationary (CCS) model, which has recently been proposed as a generalization of the cyclostationary model, is demonstrated to be a more appropriate model for communications and radar systems. However, the cyclic statistics of CCS signals are limited in practical applications because they are zero-value or band-unlimited. The main reason for this is that they are not compatible with the bases of a Fourier transform. In this study, affine cyclic statistics of CCS processes are defined as associated with the affine Fourier transform (AFT). Specifically, the cross time and lags in the 2(m)nd-order moment/cumulant without conjugate term are proven to be separable, based on which a framework for affine cyclic statistics is proposed. As special cases, three types of affine cyclic statistics are discussed in detail. Especially, the affine cyclic moment spectrum is proven to be the moment of the AFT spectrum of CCS processes, which is useful in designing estimators;application of the affine cyclic cumulant in the direction of arrival estimation of CCS sources is introduced;applications of the affine cyclic moment in parameter estimation and electrocardiogram feature extraction are simulated.

关键词： signal processing algorithms Mathematical models Chirp Fourier transforms Estimation Direction-of-arrival estimation Feature extraction Affine Fourier transform (AFT) cyclostationary processes direction of arrival (DOA) electrocardiogram (ECG) higher order statistics

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：