检索结果-内蒙古大学图书馆

A Novel Current Estimation and Cooperative Localization Method Under Unknown Current and Non-Gaussian Noise

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Fei, Yalin Xu, Bo Wang, Xiaoyu Guo, Yu Harbin Engn Univ Dept Intelligent Syst Sci & Engn Harbin 150001 Peoples R China Harbin Engn Univ Engn Res Ctr Nav Instruments Harbin 150001 Peoples R China

In this article, we uniquely investigate a multi-autonomous underwater vehicles (AUVs) cooperative localization (CL) method that simultaneously tackles ocean current velocity interference and complex non-Gaussian noise, which can better cope with practical engineering problems. First, aiming at the situation that the underwater Doppler velocity log (DVL) cannot track the bottom and the measurement noise is interfered with by outliers, this article constructs a new CL framework that takes into account the interference of ocean currents and the measurement outliers. Second, considering that the existing entropy-based filtering usually adopts a fixed-center Gaussian kernel function, which is difficult to cope with the complicated and changeable ocean environment, and based on the fact that the l(1) -norm measure is more robust to outliers than the l(2) -norm, we propose an improved variable-center maximum entropy filtering with the Laplacian as the kernel function. Finally, since the kernel width is a key parameter affecting the performance of the algorithm, we adopt an improved iterative method to compute the free parameters, which improves the flexibility of the algorithm. The effectiveness and superiority of the proposed method were verified by a multigroup comparison test.

关键词： Oceans Location awareness Noise Kernel Sea measurements Navigation filtering algorithms Robustness Laplace equations Velocity measurement Cooperative localization (CL) current estimation non-gaussian noise

来源：评论

学校读者我要写书评

暂无评论

Alpine Wetlands Information Extraction Using Optimized Multifeatures and Random Forest Algorithm

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 7347-7363页

作者： Wang, Dongchuan Yang, Fei Jia, Shijie Wang, Zhiheng Dong, Chunhua Lang, Mingwei Ye, Kai Liu, Haotian Li, Tingrong Tianjin Chengjian Univ Sch Geol & Geomat Tianjin 300384 Peoples R China

Alpine wetlands are a special ecosystem that is extremely sensitive to global climate change. The unique geographical location and climatic conditions of the Yellow-River-Source National Park give rise to diverse wetland types at the land-water interface, which exhibit phenomena such as "same object with different spectra" and "different objects with the same spectrum." These complexities pose significant challenges in accurately extracting information from alpine wetlands in the study area. To address these challenges, this study proposes a novel integrated multialgorithm feature optimization model that combines three filtering algorithms with a random forest (RF) algorithm for classifying alpine wetland information. First, the rich feature information in the image is initially filtered using a fusion of the three algorithms. Then, the RF algorithm is applied to optimize the filtered features. Finally, the RF classification model is used to refine wetland extraction based on this optimized feature set. The results show that 1) the fused filtering algorithm demonstrates higher stability than each individual algorithm and takes into consideration the strengths and weaknesses of each individual algorithm;2) the classification accuracy of the RF algorithm reaches its highest value when the number of feature variables is 21;3) the optimal classification of alpine wetlands is achieved using the RF classification model based on the best set of feature variables, resulting in an overall accuracy of 93.32% and a Kappa coefficient of 91.65% . Compared to existing land cover datasets, the proposed method provides a more detailed classification of alpine wetlands.

关键词： Climate change Random forests Wetlands Ecosystems Classification algorithms Radio frequency filtering algorithms Information filters Stability analysis Optimization models Land surface Alpine wetlands feature selection filter algorithms random forest (RF)

来源：评论

学校读者我要写书评

暂无评论

USSD: Unsupervised Sleep Spindle Detector

引用

IEEE ACCESS 2025年 13卷 18644-18659页

作者： Ramirez, Edgardo Estevez, Pablo A. Adams, Martin D. Perez, Claudio A. Garrido Gonzalez, Marcelo Peirano, Patricio Univ Chile Dept Elect Engn Santiago 8330015 Chile Millennium Inst Intelligent Healthcare Engn Santiago 1025000 Chile Ctr Intervent Med Precis & Adv Cellular Therapy IMPACT Santiago 1025000 Chile Univ Chile Inst Nutr & Food Technol Sleep Lab Santiago 8330015 Chile Univ Diego Portales UDP Fac Educ Santiago 8370109 Chile

Sleep spindles (SSs) appear in electroencephalogram (EEG) recordings during sleep stage N2, and they are usually detected through visual inspection by an expert. Labeling SSs in large datasets is time-consuming and depends on the expert criteria. In this work, we propose an unsupervised SS detector based on dictionary learning called the Unsupervised Sleep Spindle Detector (USSD). The proposed detector learns prototype SSs of different lengths (called atoms). An unsupervised adaptive threshold method based on the distribution of the automatically detected SS lengths is developed, which allows the adaptation of the USSD algorithm to different datasets in an unsupervised way. For each detection, the USSD estimates the probability of being an SS. The USSD performances on the labeled MASS-SS2 and INTA-UCH datasets yield F1-scores of $0.72 \pm 0.02$ and $0.72 \pm 0.04$ , respectively. The USSD outperforms the A7 and LUNA detectors, which are traditional unsupervised models. Next, we fine-tune the resulting USSD model with 20% of the labeled MASS-SS2 and INTA-UCH datasets, achieving F1 scores of $0.78 \pm 0.06$ and $0.75 \pm 0.05$ , respectively. In addition, the SSs detected by USSD on the unlabeled CAP dataset are used to pre-train a supervised deep learning method, which after fine-tuning with 20% of the MODA dataset, reaches an F1-score of $0.81 \pm 0.02$ .

关键词： Sleep Electroencephalography Signal processing algorithms Brain modeling Detectors Dictionaries Matching pursuit algorithms Machine learning Recording filtering algorithms EEG sleep spindle unsupervised learning dictionary learning

来源：评论

学校读者我要写书评

暂无评论

An Information Flow Switching-Based Despeckling Network Under Real Dual-Polarization SAR Conditions

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Lin, Liupeng Shen, Huanfeng Li, Jie Wu, Jingan Shi, Shaowei Yuan, Qiangqiang Wuhan Univ Sch Resource & Environm Sci Wuhan 430079 Peoples R China Wuhan Univ Sch Geodesy & Geomat Wuhan 430079 Peoples R China Sun Yat Sen Univ Sch Geospatial Engn & Sci Zhuhai 519082 Peoples R China

Polarimetric synthetic aperture radar (SAR) can capture rich polarization information of targets, but it is inherently affected by speckle. Learning-based methods have demonstrated superior speckle suppression potential. Most existing methods use optical images to simulate SAR noise for model training. Because of the significant differences in the imaging mechanisms between optical and SAR images, the data characteristics of these two types differ significantly, resulting in poor generalization performance. To this end, an Information Flow Switching-based Despeckling Network (IFSDN) is proposed for dual-polarization SAR image. By using the long time series data, the first dual-polarization SAR real dataset is constructed. The hybrid feature extraction module (HFEM) is constructed to independently extract and integrate features from both the diagonal and nondiagonal elements of the covariance matrix. Additionally, the multihierarchical residual attention despeckling (MRAD) module performs despeckling on feature maps from low to high levels. On this basis, the information flow switching mechanism facilitates the interaction of dominant features before and after despeckling, injecting spatial details into the despeckled results, reducing speckle noise, and preserving polarization information. By considering temporal changes, an adaptive joint loss function is, furthermore, constructed to guide the network training process, achieving high-fidelity despeckling while maintaining spatial-polarization information. Experiments show that IFSDN outperforms existing state-of-the-art methods in the speckle removal task for real dual-polarization SAR images, which can effectively preserve spatial and polarization information while suppressing speckles. Besides, generalization experiments demonstrate that the proposed model can be effectively applied to diverse datasets across various climate zones, showcasing its strong robustness.

关键词： Radar polarimetry Covariance matrices Speckle Feature extraction Training Optical filters Noise reduction Noise measurement filtering algorithms Microwave filters Deep learning dual-polarization SAR (Dual-SAR) image despeckling information flow switching mechanism real synthetic aperture radar (SAR) data remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Robust Unified Strategy for Maximum Torque per Ampere and Field Weakening in Permanent Magnet Synchronous Motor

引用

IEEE TRANSACTIONS ON POWER ELECTRONICS 2024年第5期39卷 5286-5297页

作者： Zuo, Kunkun Wang, Fengxiang Li, Zheng Ke, Dongliang Kennel, Ralph Heldwein, Marcelo Lobo Tech Univ Munich Chair High power Converter Syst TUM Sch Engn Design D-80333 Munich Germany Fujian Sci & Technol Innovat Lab Optoelect Informa Fuzhou 350108 Peoples R China Chinese Acad Sci Quanzhou Inst Equipment Mfg Haixi Inst Quanzhou 362200 Peoples R China

The intricate control structure and demanding preparations undeniably make the high precision and performance realization of maximum torque per ampere (MTPA) and field-weakening (FW) strategies challenging in the permanent magnet synchronous motor (PMSM). This article proposes a straightforward yet potent strategy to surmount this challenge. By redefining the whole control process as a convex optimization and employing the indicator function to approximate constraints, the MTPA-FW control is seamlessly realized through the calculation of a single equation online, obviating the requirement for any supplementary operation. Meanwhile, a model correction method based on the moving horizon estimator (MHE) is designed to mitigate the impact of parameter variation and enhance the calculation accuracy. The experimental results have proved the superiority of the proposed strategy.

关键词： Torque Mathematical models Table lookup Stators Flowcharts filtering algorithms Electromagnetics Field weakening (FW) maximum torque per ampere (MTPA) permanent magnet synchronous motor (PMSM)

来源：评论

学校读者我要写书评

暂无评论

Distributionally Robust State Estimation for Highly Maneuvering Target Tracking With Model Uncertainty and Impulsive Measurement Outliers

引用

IEEE SENSORS JOURNAL 2025年第6期25卷 9876-9886页

作者： Zhang, Wenbo Song, Shenmin Harbin Inst Technol Ctr Control Theory & Guidance Technol Harbin 150001 Peoples R China

Due to the high maneuverability of the non-cooperative target and the complexity of the confrontation environment, the uncertainty of the tracking model and impulsive outliers in measurements degrade tracking accuracy and may even lead to complete loss of tracking. Existing research can hardly address these challenges. To ensure accurate tracking in the presence of uncertainty and impulsive measurement outliers (IMOs), we propose a distributionally robust state estimation (DRSE) method based on moment-based ambiguity sets. First, virtual maneuvering noise and a first-order Markov process are utilized to describe the maneuvering acceleration, while a set of independent and identically distributed random variables is used to characterize the interval length of IMO, thus constructing the process and measurement models, respectively. Then, the uncertainty of model is represented by moment-based ambiguity sets, and the state is estimated under the worst case conditional prior distribution. Furthermore, we employ an adaptive saturation mechanism to mitigate the impact of IMO, thereby ensuring robust-bounded-error state estimation in the presence of outliers. Finally, a glide trajectory of a typical hypersonic vehicle is established in this study. The numerical experiment results demonstrate the algorithm's effective handling of tracking model uncertainty and IMO.

关键词： Radar tracking Uncertainty Adaptive filters Noise filtering algorithms Accuracy Pollution measurement Mathematical models Adaptation models Distributionally robust impulsive measurement outliers (IMOs) model uncertainty moment-based ambiguity sets target tracking target tracking

来源：评论

学校读者我要写书评

暂无评论

Adaptive Filter Pruning via Sensitivity Feedback

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第8期35卷 10996-11008页

作者： Zhang, Yuyao Freris, Nikolaos M. Univ Sci & Technol China Inst Adv Technol Hefei 230000 Peoples R China Univ Sci & Technol China Sch Comp Sci & Technol Hefei 230000 Peoples R China

Filter pruning is advocated for accelerating deep neural networks without dedicated hardware or libraries, while maintaining high prediction accuracy. Several works have cast pruning as a variant of l(1)-regularized training, which entails two challenges: 1) the l(1)-norm is not scaling-invariant (i.e., the regularization penalty depends on weight values) and 2) there is no rule for selecting the penalty coefficient to trade off high pruning ratio for low accuracy drop. To address these issues, we propose a lightweight pruning method termed adaptive sensitivity-based pruning (ASTER) which: 1) achieves scaling-invariance by refraining from modifying unpruned filter weights and 2) dynamically adjusts the pruning threshold concurrently with the training process. ASTER computes the sensitivity of the loss to the threshold on the fly (without retraining);this is carried efficiently by an application of L-BFGS solely on the batch normalization (BN) layers. It then proceeds to adapt the threshold so as to maintain a fine balance between pruning ratio and model capacity. We have conducted extensive experiments on a number of state-of-the-art CNN models on benchmark datasets to illustrate the merits of our approach in terms of both FLOPs reduction and accuracy. For example, on ILSVRC-2012 our method reduces more than 76% FLOPs for ResNet-50 with only 2.0% Top-1 accuracy degradation, while for the MobileNet v2 model it achieves 46.6% FLOPs Drop with a Top-1 Acc. Drop of only 2.77%. Even for a very lightweight classification model like MobileNet v3-small, ASTER saves 16.1% FLOPs with a negligible Top-1 accuracy drop of 0.03%.

关键词： Training Adaptation models Sensitivity Computational modeling Adaptive filters Libraries filtering algorithms Adaptive pruning deep neural networks model compression structured model pruning

来源：评论

学校读者我要写书评

暂无评论

A Control to Address Issues of Synchronization and Voltage Rise in Grid Integrated Solar Photovoltaic-Battery Storage System

引用

IEEE TRANSACTIONS ON POWER ELECTRONICS 2025年第1期40卷 2385-2396页

作者： Modi, Gaurav Singh, Bhim Indian Inst Technol Delhi Dept Elect Engn New Delhi 110016 India

This work presents a second-order generalized integrator (SOGI)-adaptive complex filter (ACF) based control with variable power mode to address synchronization and voltage rise issues in a grid integrated solar photovoltaic battery storage system. SOGI-ACF method is a fourth-order filter that resolves synchronization and power quality (PQ) issues by obtaining positive sequence components (PSCs) of unbalanced/distorted grid voltages. It has an excellent dynamic response with inherent dc offset, negative sequence rejection capabilities, and better harmonic rejection than other fourth-order generalized integrator-based filters. This algorithm is also used to acquire the load current's PSCs, incorporating multifunctional capability into system. In addition, the system provides grid support by restraining voltage rise at the point of common coupling during high solar photovoltaic array penetration into ac grid, according to the IEEE std 1547 limit. To provide grid support, the control strategy operates the system in variable power operating modes, depending upon system constraints, and accordingly regulates active and reactive powers of ac grid. Experimental results reveal restrain in voltage rise during peak generation and PQ improvement under unbalanced/ distorted grid voltage and load current conditions.

关键词： Power harmonic filters Harmonic analysis Voltage control Reactive power Band-pass filters filtering algorithms Photovoltaic systems Distorted-unbalanced voltage overvoltage solar photovoltaic system (SPV) synchronization weak grid

来源：评论

学校读者我要写书评

暂无评论

One New Designed Wiener Filter Method for SQUID Magnetogastrogram Detection

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Li, Hua Zhang, Mingyue Chinese Acad Sci Shanghai Inst Microsyst & Informat Technol Natl Key Lab Mat Integrated Circuits Shanghai 200050 Peoples R China

Superconducting quantum interference device (SQUID) magnetogastrogram (MGG) is a medical functional imaging method with great clinical potential for noninvasive diagnosis of gastric diseases. MGG signal frequency is about 0.05 Hz, and the low-frequency environmental noise interference is serious, can be several times stronger in magnitude than the signals of interest, and may severely impede the extraction of relevant information. Wiener filter is one classic denoising solution for biomagnetic applications. In this article, a new high-pass Wiener filter and signal processing framework for MGG measurement is proposed, which can filter low-frequency noises not only specific artifacts. The filter was successfully applied to MGG signal denoising. Using this general Wiener filter frame, the filter signal-to-noise ratio (SNR) is 11.3 dB better than the classical Wiener filter and it also has 16.7 dB of SNR better than without signal noise separation step. Based on our methods, 36-point array MGG signals were detected successfully and the results were consistent with the main gastric slow wave activity.

关键词： Wiener filters Signal to noise ratio Magnetic separation Superconducting filters Adaptive filters Fitting filtering theory filtering algorithms SQUIDs Nonlinear filters Denoising solutions magnetogastrogram (MGG) superconducting quantum interference device (SQUID) applications SQUID biomagnetism Wiener filter

来源：评论

学校读者我要写书评

暂无评论

Tracking Analysis of Maximum Versoria Criterion Based Adaptive Filter

引用

IEEE ACCESS 2024年 12卷 30747-30753页

作者： Khalili, Azam Rastegarnia, Amir Farzamnia, Ali Sanei, Saeid Alghamdi, Thamer A. H. Malayer Univ Dept Elect Engn Malayer *** Iran Univ Malaysia Sabah Fac Engn Kota Kinabalu 88400 Malaysia Imperial Coll London Dept Elect & Elect Engn London SW7 2AZ England Al Baha Univ Fac Engn Comp Engn Dept Al Bahah 65779 Saudi Arabia Cardiff Univ Wolfson Ctr Magnet Sch Engn Cardiff CF24 3AA England

Recently, maximum Versoria criterion-based adaptive algorithms have been introduced as a new solution for robust adaptive filtering. This paper studies the steady-state tracking analysis of an adaptive filter with maximum Versoria criterion (MVC) in a non-stationary (Markov time-varying) system. Our analysis relies on the energy conservation method. Both Gaussian and general non-Gaussian noise are considered, and for both cases, the closed-form expression for steady-state excess mean square error (EMSE) is derived. Regardless of noise type, unlike the stationary environment, the EMSE curves are not increasing functions of step-size parameter. The validity of the theoretical results is justified via simulation.

关键词： Adaptive filters Steady-state filtering algorithms Cost function Information filters Symbols Gaussian noise Robustness Performance analysis Tracking Adaptive filter non-stationary performance analysis tracking Versoria

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：