Recently, methods based on convolutional neural networks (CNNs) achieve superior performance in polarimetric synthetic aperture radar (PolSAR) image classification. However, the current CNN-based classifiers follow patch-based frameworks, which need input images to be divided into overlapping patches. Consequently, these classification approaches have the drawback of requiring repeated calculations and only relying on local information. In addition, the receptive field size in conventional CNN-based methods is fixed, which limits the potential to extract features. In this paper, a hybrid attention-based encoder–decoder fully convolutional network (HA-EDNet) is presented for PolSAR classification. Unlike traditional CNN-based approaches, the encoder–decoder fully convolutional network (EDNet) can use an arbitrary-size image as input without dividing. Then, the output is the whole image classification result. Meanwhile, the self-attention module is used to establish global spatial dependence and extract context characteristics, which can improve the performance of classification. Moreover, an attention-based selective kernel module (SK module) is included in the network. In the module, softmax attention is employed to fuse several branches with different receptive field sizes. Consequently, the module can capture features with different scales and further boost classification accuracy. The experiment results demonstrate that the HA-EDNet achieves superior performance compared to CNN-based and traditional fully convolutional network methods.
High-resolution synthetic aperture radar (SAR) images are mostly used in the current field of ship classification, but in practical applications, moderate-resolution SAR images that can offer wider swath are more suitable for maritime surveillance. The ship targets in moderate-resolution SAR images occupy only a few pixels, and some of them show the shape of bright spots, which brings great difficulty for ship classification. To fully explore the deep-level feature representations of moderate-resolution SAR images and avoid the “dimension disaster”, we innovatively proposed a feature fusion framework based on the classification ability of individual features and the efficiency of overall information representation, called maximum-information-minimum-redundancy (MIMR). First, we applied the Filter method and Kernel Principal Component Analysis (KPCA) method to form two feature subsets representing the best classification ability and the highest information representation efficiency in linear space and nonlinear space. Second, the MIMR feature fusion method is adopted to assign different weights to feature vectors with different physical properties and discriminability. Comprehensive experiments on the open dataset OpenSARShip show that compared with traditional and emerging deep learning methods, the proposed method can effectively fuse non-redundant complementary feature subsets to improve the performance of ship classification in moderate-resolution SAR images.
Wheeled mobile robots are widely implemented in the field environment where slipping and skidding may often occur. This paper presents a self-adaptive path tracking control framework based on a radial basis function (RBF) neural network to overcome slippage disturbances. Both kinematic and dynamic models of a wheeled robot with skid-steer characteristics are established with position, orientation, and equivalent tracking error definitions. A dual-loop control framework is proposed, and kinematic and dynamic models are integrated in the inner and outer loops, respectively. An RBF neutral network is employed for yaw rate control to realize adaptability to longitudinal slippage. Simulations employing the proposed control framework are performed to track snaking and a DLC reference path with slip ratio variations. The results suggest that the proposed control framework yields much lower position and orientation errors compared with those of a PID and a single neuron network (SNN) controller. It also exhibits prior anti-disturbance performance and adaptability to longitudinal slippage. The proposed control framework could thus be employed for autonomous mobile robots working on complex terrain.
Abstract. The aerosol mixing state is a crucial physical-chemical property that affects their optical properties and cloud condensation nuclei (CCN) activity. Multiple techniques are commonly employed to determine aerosol mixing states for various applications, and comparisons between these techniques provide insights of the variations in aerosol chemical and physical properties. These techniques include size-resolved CCN activity measurements using a system with CCN counter (CCNC) coupled with a differential mobility analyzer (DMA), a Humidified/Volatility Tandem differential mobility analyzer (H/V-TDMA) which measures aerosol hygroscopicity/volatility distributions, and a single particle soot photometer (SP2) which directly quantifies black carbon (BC) mixing states. This study provides a first time intercomparisons of aerosol mixing state parameters obtained through simultaneous measurements of a DMA-CCNC, a H/VTDMA and a DMA-SP2. The impact of primary aerosols emissions and secondary aerosol formations on the aerosol mixing states and intercomparison results were analyzed. The results showed that differences in mixing state parameters measured by different techniques varied greatly under different conditions. The V-TDMA and DMA-SP2 measurements showed that the non-volatile population identified by the V-TDMA was mainly contributed by BC-containing aerosols. The HTDMA and DMA-SP2 measurements indicated that a substantial proportion of nearly hydrophobic aerosols were not contributed from BC-containing aerosols, but likely originated from fossil fuel combustion and biomass burning emissions. Synthesized comparison results between DMA-CCNC, HTDMA and DMA-SP2 measurements revealed that some of the nearly hydrophobic BC-free particles were CCN-inactive under supersaturated conditions, likely from fossil combustion emissions, while others were CCN-active under supersaturated conditions linked to biomass burning emissions. Fossil fuel combustion-emitted BC-containing aerosols tended to be more externally mixed with other aerosol compositions compared to those emitted from biomass burning activities. These results highlight significant disparities in the mixing states as well as physiochemical properties between aerosol originated from fossil fuel combustion and biomass burning. The formation of secondary nitrate and organic aerosols exerted significant impacts on variations in aerosol mixing states, generally enhancing aerosol hygroscopicity and volatility, while reducing differences in mixing state parameters derived from different techniques, resulting in a reduction in aerosol heterogeneity. The variations in BC-free particle number fractions showed that secondary aerosols tended to form more quickly on BC-free particles than on BC-containing particles. Further comparison of mixing state parameters revealed that the two resolved SOA factors in this study exhibited remarkably different physical properties, indicating that they were likely formed through different pathways. These findings suggest that intercomparisons among aerosol mixing states derived from different techniques can provide deeper insight into aerosol physical properties and how they are impacted by secondary aerosol formation, aiding the investigation of secondary aerosol formation pathways.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.