检索结果-内蒙古大学图书馆

A Module to Enhance the Generalization Ability of End-to-End Deep Learning Systems in Optical Fiber Communications

JOURNAL OF LIGHTWAVE TECHNOLOGY 2025年第2期43卷 596-601页

作者： Liu, Zheng Liu, Tiegen Zhao, Jian Uduagbomen, Joshua Wang, Yulin Popov, Sergei Xu, Tianhua Tianjin Univ Sch Precis Instruments & Optoelect Engn Tianjin 300072 Peoples R China Univ Warwick Sch Engn Coventry CV4 7AL England KTH Royal Inst Technol S-16440 Stockholm Sweden Tianjin Univ Tianjin 300072 Peoples R China UCL Dept Elect & Elect Engn London WC1E 7JE England

AnAdapter module is developed to increase the generalization capability of the end-to-end learning system for optical fiber communication systems. The Adapter has an interpretable structure and can be inserted and used without changing the original signal processing structure. The Adapter module can improve the system generalization capability and achieve the correct demapping within the transmission distance fluctuation range of $\pm$100 km and the power fluctuation range of $\pm$0.5 dBm. In addition, using an Adapter can improve the performance of optical communication by modifying the equalization algorithm without altering the structure of the existing transmission system.

关键词： Vectors Deep learning Optical fiber dispersion signal processing algorithms Optical fiber networks Constellation diagram Transceivers End-to-end deep learning fiber nonlinearity generalization geometric shaping optical communication

来源：评论

学校读者我要写书评

暂无评论

Greedy Selection for Heterogeneous Sensors

引用

IEEE TRANSACTIONS ON signal processing 2025年 73卷 1394-1409页

作者： Majumder, Kaushani Pillai, Sibi Raj B. Mulleti, Satish Indian Inst Technol Dept Elect Engn Mumbai 400076 India

Simultaneous operation of all sensors in a large-scale sensor network is power-consuming and computationally expensive. Hence, it is desirable to select fewer sensors. A greedy algorithm is widely used for sensor selection in homogeneous networks with a theoretical worst-case performance of ( 1-1/e) approximate to 63% of the optimal performance when optimizing submodular metrics. For heterogeneous sensor networks (HSNs) comprising multiple sets of sensors, most of the existing sensor selection methods optimize the performance constrained by a budget on the total value of the selected sensors. However, in many applications, the number of sensors to select from each set is known apriori and solutions are not well-explored. For this problem, we propose a joint greedy heterogeneous sensor selection algorithm. Theoretically, we show that the worst-case performance of the proposed algorithm is bounded to 50$% of the optimum for submodular cost metrics. In the special case of HSNs with two sensor networks, the performance guarantee can be improved to 63% when the number of sensors to select from one set is much smaller than the other. To validate our results experimentally, we propose a submodular metric based on the frame potential measure that considers both the correlation among the sensor measurements and their heterogeneity. We prove theoretical bounds for the mean squared error of the solution when this performance metric is used. We validate our results through simulation experiments considering both linear and non-linear measurement models corrupted by additive noise and quantization errors. Our experiments show that the proposed algorithm results in 4- 10 dB lower error than existing methods.

关键词： Sensors Sensor phenomena and characterization Costs Measurement Vectors signal processing algorithms Noise measurement Intelligent sensors Greedy algorithms Accuracy Sensor selection heterogeneous sensor networks submodular maximization greedy algorithm frame potential

来源：评论

学校读者我要写书评

暂无评论

Distributed Adaptive Spatial Filtering With Inexact Local Solvers

引用

IEEE TRANSACTIONS ON signal processing 2025年 73卷 1262-1277页

作者： Hovine, Charles Bertrand, Alexander STADIUS Ctr Dynam Syst Signal Proc & Data Analyt B-3001 Leuven Belgium Katholieke Univ Leuven Leuven AI Inst Artificial Intelligence B-3001 Leuven Belgium

The Distributed Adaptive signal Fusion (DASF) framework is a meta-algorithm for computing data-driven spatial filters in a distributed sensing platform with limited bandwidth and computational resources, such as a wireless sensor network. The convergence and optimality of the DASF algorithm has been extensively studied under the assumption that an exact, but possibly impractical solver for the local optimization problem at each updating node is available. In this work, we provide convergence and optimality results for the DASF framework when used with an inexact, finite-time solver such as (proximal) gradient descent or Newton's method. We provide sufficient conditions that the solver should satisfy in order to guarantee convergence of the resulting algorithm as well as numerical simulations to validate these theoretical results.

关键词： signal processing algorithms Convergence Wireless sensor networks Optimization Distributed databases Principal component analysis Europe Artificial intelligence Adaptive systems Spatial filters Distributed signal processing wireless sensor networks adaptive spatial filtering optimization

来源：评论

学校读者我要写书评

暂无评论

Joint Inter-Symbol Interference and I/Q Imbalance Cancellation in FTN Systems

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2025年第4期24卷 2680-2692页

作者： Tong, Mingfei Huang, Xiaojing Zhang, J. Andrew Univ Technol Sydney Global Big Data Technol Ctr Ultimo NSW 2007 Australia

Current research on faster-than-Nyquist (FTN) systems mainly focuses on baseband digital signal processing without considering the impact of I/Q imbalance (IQI) caused by hardware impairments in the signal chain. To address this problem, this paper considers frequency-dependent IQI and applies the frame-based decision-directed successive interference cancellation (DDSIC) algorithm after minimum mean square error (MMSE) equalization to jointly mitigate inter-symbol interference (ISI) and IQI. We introduce extended-dimension signal models, which use both original and image signals to describe the impact of IQI. Based on the models, a two-stage iterative DDSIC algorithm is then proposed, achieving effective interference cancellation. Furthermore, the theoretical bit error rate (BER) for each iteration of DDSIC and the BER lower bound of the proposed system are derived. Simulation results demonstrate the superiority of DDSIC over some existing algorithms under both additive white Gaussian noise (AWGN) and multipath fading channels. These results also validate the derived theoretical BER expressions and the robustness of our scheme under various ISI and IQI scenarios, respectively.

关键词： Symbols Wireless communication Bit error rate signal processing algorithms Receivers Accuracy OFDM Iterative algorithms System performance Prevention and mitigation FTN signaling I/Q imbalance MMSE equalization ISI cancellation IQI cancellation

来源：评论

学校读者我要写书评

暂无评论

Joint HW/SW signal Co-Conditioning Strategy for Unobtrusive Single-Arm Cardiac Surveillance

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Huang, Linfei Chen, Jiarong Zhang, Xianbin Li, Zhen Xu, Lin Millham, Richard Bian, Gui-Bin Wu, Wanqing Sun Yat Sen Univ Sch Biomed Engn Shenzhen 518107 Peoples R China Shanghai Jiao Tong Univ Dept Micro Nano Elect Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ MoE Key Lab Artificial Intelligence Shanghai 200240 Peoples R China Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China Guangdong Pharmaceut Univ Clin Med Sch 1 Guangzhou 510006 Peoples R China Durban Univ Technol Dept Informat Technol ZA-4001 Durban Kwazulu Natal South Africa Sun Yat Sen Univ Sch Biomed Engn Guangdong Prov Key Lab Sensor Technol & Biomed Ins Guangzhou 510275 Guangdong Peoples R China

The electrocardiogram (ECG) is a crucial tool for cardiac health monitoring, but existing ECG monitoring systems often lack effective signal conditioning coordination between hardware (HW) and software (SW), resulting in poor signal quality and monitoring effectiveness. To address this issue, this study presents a novel single-arm ECG monitoring system based on the Internet of Things (IoT) that comprehensively considers both hardware and software aspects. The system mainly consists of an ECG measurement device and a signal reconstruction algorithm. For the device, impedance matching circuits and preamplifier circuits were specially designed to measure the weak single-arm ECG signal. Additionally, to improve wearing comfort, a metal dry electrode and an armband were developed. On the software side, an ECG signal reconstruction algorithm based on a diffusion model is proposed, and the reverse process of the diffusion model and the noise prediction model are improved according to the characteristics of the ECG signal. The feasibility of the system was verified through monitoring experiments conducted in real environments on healthy subjects and heart disease patients. The experimental results show that the proposed measurement device is capable of long-term ECG monitoring and that the signal reconstruction algorithm effectively removes various real-world noises. The R-wave detection precision, sensitivity, and F1-score of the reconstructed signal improved from 75.90% to 85.87%, 69.16% to 83.40%, and 72.37% to 84.62%, respectively. This demonstrates that the system provides a new solution for efficient cardiac monitoring in daily life. The open-source code is available at https://***/CHENJIAR3/ECG_Denoising/tree/Linfei.

关键词： Electrocardiography Monitoring Noise Biomedical monitoring Electrodes Noise reduction Diffusion models Accuracy signal reconstruction signal processing algorithms Cardiac surveillance diffusion model signal conditioning signal reconstruction single-arm electrocardiogram (ECG)

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Maximum Connected-Component Learning Algorithm for Small Target Detection in Maritime Radars

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2025年第1期61卷 250-265页

作者： Bai, Xiaohui Xu, Shuwen Guo, Zixun Shui, Penglang Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China Northwestern Polytech Univ Sch Elect & Informat Xian 710072 Peoples R China

Anomaly detection needs to learn one-class classifiers from normal instances in observation or feature spaces. In the Neyman-Pearson criterion, the design of one-class classifiers boils down to finding the minimal-volume decision region subject to the error probability of normal instances no larger than a desired false alarm rate. The theoretical solution to this design problem is the probability density function (pdf) level set of normal instances. In low-dimensional feature spaces, by combining training samples with the convexity regularity on decision regions, the convexhull learning algorithm is a technique for designing one-class classifiers. In order to overcome its dimension limitation and the mismatch of convexity to the level sets of a multimodal pdf, this article considers the approach to replace the convexity by the connectivity to regularize decision regions. A fast graph-based maximum connected-component learning algorithm is proposed to design one-class classifiers in high-dimensional feature spaces, which exploits the fast maximum connected-component search algorithm in a large-scale undirected graph. Moreover, for the application of sea-surface small target detection, the proposed algorithm combines ten-dimensional features to design feature-based detectors. Experimental results on the recognized radar database indicate the effectiveness of the proposed algorithm.

关键词： Training Detectors Level set Feature extraction Classification algorithms signal processing algorithms Radar Anomaly detection convexhull learning algorithm feature-based detection graph-based maximum connected-component (GMCC) learning algorithm sea-surface small target detection

来源：评论

学校读者我要写书评

暂无评论

The Effectiveness of Local Updates for Decentralized Learning Under Data Heterogeneity

引用

IEEE TRANSACTIONS ON signal processing 2025年 73卷 751-765页

作者： Wu, Tongle Li, Zhize Sun, Ying Penn State Univ Sch Elect Engn & Comp Sci State Coll PA 16801 USA Singapore Management Univ Sch Comp & Informat Syst Singapore 178902 Singapore

We revisit two fundamental decentralized optimiza-tion methods, Decentralized Gradient Tracking (DGT) and De-centralized Gradient Descent (DGD), with multiple local *** consider two settings and demonstrate that incorporat-ing local update steps can reduce communication ***, for mu-strongly convex andL-smooth loss functions,we proved that local DGT achieves communication complexity O(L/mu(K+1) + delta+mu/mu(1-rho) + rho(1-rho)(2)L+delta/mu), where K is the numberof additional local update,rho measures the network connectivityand delta measures the second-order heterogeneity of the locallosses. Our results reveal the tradeoff between communicationand computation and show increasingKcan effectively reducecommunication costs when the data heterogeneity is low andthe network is well-connected. We then consider the over-parameterization regime where the local losses share the sameminimums. We proved that employing local updates in DGD, evenwithout gradient correction, achieves exact linear convergenceunder the Polyak-& Lstrok;ojasiewicz (PL) condition, which can yielda similar effect as DGT in reducing communication *** of the result to linear models is further provided,with improved rate expression. Numerical experiments validateour theoretical results.

关键词： signal processing algorithms Convergence Complexity theory Optimization Stochastic processes Standards Transient analysis Mesh networks Costs Sun Decentralized optimization data heterogeneity communication efficiency local update

来源：评论

学校读者我要写书评

暂无评论

Physics-Informed Scattering Transform Network for Modulation Recognition in 5G Industrial Cognitive Communications Considering Nonlinear Impairments in Active Phased Arrays

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2025年第1期21卷 425-434页

作者： An, Zeliang Xu, Yuqing Tahir, Abdullah Wang, Jun Ma, Baoze Pedersen, Gert Frolund Shen, Ming Anhui Polytech Univ Sch Comp & Informat Wuhu 241000 Peoples R China Aalborg Univ Dept Elect Syst DK-9220 Aalborg Denmark Univ Engn & Technol Dept Mechatron Engn Faisalabad Campus Lahore 38000 Pakistan Chongqing Univ Posts & Telecommun Sch Optoelect Engn Chongqing 400065 Peoples R China

Modulation recognition (MR) plays a pivotal role due to its application in the spectrum sensing of 5G industrial cognitive communications and radio interference detection at the physical layer of the Internet of Things (IoT). Previous works have mainly focused on simulated fourth-generation (4G) multicarrier systems and ideal radio frequency (RF) scenarios. To bridge the gap between practice and theory, we propose a viable MR algorithm on all-physical testbeds, with nonlinear impairments of 28 GHz active phased arrays (APA). Specifically, our testbed is built on the Rohde&Schwarz (R&S) vector signal generation R&S-SMBV100B and spectrum analyzer R&S-FSW 67 GHz. To extract salient modulation patterns, we develop a physical-informed scattering transform (SCT) MR network (SCTMR-Net). With SCT modules, SCTMR-Net produces the translation-invariant and deformation-stable representations of 5-G signals by wavelet convolution, nonlinear modulus and low-pass filters. Extensive experiments on real-world measurement verify the viability of SCTMR-Net for high robustness to APA impairments.

关键词： OFDM Convolution Radio frequency Internet of Things Feature extraction Wavelet transforms signal processing algorithms 5-G new radio (NR) industrial cognitive communications deep learning (DL) modulation recognition nonlinear active phased arrays (APA) impairments scattering transform modulation recognition-network (SCTMR-Net)

来源：评论

学校读者我要写书评

暂无评论

Scalable Multisubject Vital Sign Monitoring With mmWave FMCW Radar and FPGA Prototyping

引用

IEEE SENSORS JOURNAL 2025年第2期25卷 3571-3583页

作者： Benny, Jewel Moudhgalya, Narahari N. Khan, Mujeev Meena, Hemant Kumar Wajid, Mohd Srivastava, Abhishek IIIT Hyderabad Ctr VLSI & Embedded Syst Technol CVEST Hyderabad 500032 India Aligarh Muslim Univ Dept Elect Engn Aligarh 202001 Uttar Pradesh India Malaviya Natl Inst Technol MNIT Jaipur Dept Elect Engn Jaipur 302017 Rajasthan India

In this work, we introduce an innovative approach to estimate the vital signs of multiple human subjects simultaneously in a noncontact way using a frequency-modulated continuous-wave (FMCW) radar-based system. Traditional vital sign monitoring methods often face significant limitations, including subject discomfort with wearable devices, challenges in calibration, and the risk of infection transmission through contact measurement devices. To address these issues, this research is motivated by the need for versatile, noncontact vital monitoring solutions applicable in various critical scenarios. This work also explores the challenges of extending this capability to an arbitrary number of subjects, including hardware and theoretical limitations. Supported by rigorous experimental results and discussions, the article illustrates the system's potential to redefine vital sign monitoring. A field-programmable gate array (FPGA)-based implementation is also presented as proof of concept for a hardware-based and portable solution, improving upon previous works by offering 2.7x faster execution and 18.4% less look-up table (LUT) utilization, as well as providing over 7400x acceleration compared to its software counterpart.

关键词： Azimuth Ultra wideband radar Frequency measurement Doppler radar signal processing algorithms Monitoring Biomedical measurement Accuracy Sensors Radar measurements 77 GHz breath-rate estimation field-programmable gate array (FPGA) frequency-modulated continuous wave (FMCW) healthcare heart-rate estimation mmWave radar multisubject noncontact

来源：评论

学校读者我要写书评

暂无评论

Clutter Suppression for STAP-Based Radar Using Synthesized Subarray Beampattern

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2025年第2期61卷 4507-4525页

作者： Wan, Fuhai Xu, Jingwei Xu, Yanhong Lan, Lan Wang, Weiwei Liao, Guisheng Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China Xian Univ Sci & Technol Sch Commun & Informat Engn Xian 710054 Peoples R China China Acad Space Technol Xian 710100 Peoples R China

The space-time-coupled grating lobe clutter (GLC) usually exists and is difficult to handle for subarray-based phased array airborne radar, which would cause serious performance degradation in clutter suppression. To alleviate this problem, this article presents a data-independent subarray beampattern synthesis approach for the space-time adaptive processing (STAP) based radar. In particular, the GLC spectrum is first analyzed in detail, based on which the receive overlapped subarray beampattern is designed with certain nulls located at the grating lobe regions to prefilter of GLC. During the GLC suppression, the subarray beampattern synthesis algorithm is devised based on the criterion of maximizing array gain, where phase ambiguity is incorporated into the optimization model to precisely adjust the power responses of the receive subarray beampattern. In this way, the GLC can be prefiltered in subarray and its coupling diffusion characteristic in the space-time domain can be prevented, thus improving the clutter suppression and moving target detection capabilities. In what follows, the subarray-level STAP filter is implemented for the residual space-time coupling mainlobe and sidelobe clutter suppression. Numerical results demonstrate that the proposed subarray beampattern synthesis method can remarkably enhance the output signal-to-clutter-plus-noise ratio loss performance in GLC regions.

关键词： Clutter Gratings Vectors Doppler effect Radar clutter Spaceborne radar Optimization signal processing algorithms Doppler radar Covariance matrices Grating lobe clutter (GLC) suppression overlapped subarray prefiltering space-time adaptive processing (STAP) subarray beampattern synthesis

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：