For the polarimetric synthetic aperture radar interferometry (PoIInSAR) processing, it is necessary to coregister all the images, including the coregistration of polarimetric SAR images and the coregistration of inter...
详细信息
For the polarimetric synthetic aperture radar interferometry (PoIInSAR) processing, it is necessary to coregister all the images, including the coregistration of polarimetric SAR images and the coregistration of interferometric SAR images. Otherwise, the performance of the estimated optimal interferograms will be deteriorated. A generalized scattering vector (GSV) model is proposed to execute the PoIInSAR optimal interferograms estimation. The generalized scattering vector is constructed by the Pauli scattering vectors of the processing pixel and the surrounding pixels. Even though there are coregistration errors, all the polarimetric information of the current processing pixel is entirely included in the generalized scattering vector. Therefore, the GSV-based method can automatically recover the optimal scattering mechanisms of the processing pixel with coregistration errors either in interferoemetric channels or polarimetric channels. Theoretical analysis and processing results of simulated PoISARPro data and real PALSAR data validate the effectiveness and correctness of the proposed method.
To solve the problem of low performance of network intrusion detection,a deep learning intrusion detection model based on space-time fusion features and attention mechanism—CLT-net is *** this model,space-time fusion...
详细信息
ISBN:
(纸本)9781665431293
To solve the problem of low performance of network intrusion detection,a deep learning intrusion detection model based on space-time fusion features and attention mechanism—CLT-net is *** this model,space-time fusion features are obtained by integrating convolutional neural network and long short-time memory network,and attention module is added to calculate the importance of the input features,and softmax function is used for *** a large number of simulation experiments on NSL-KDD data sets,CLT-net has significantly improved the convergence of the training set and the accuracy of the test *** with the traditional CNN model with similar structure and the space-time fusion CLSTM the accuracy of the model increased by 11.8% and 10.9%*** shows that this model has great potential in the application field of network intrusion detection.
We propose a new framework combining weak measurement and second-order correlated technique. The theoretical analysis shows that weak value amplification （WVA） experiment can also be implemented by a second-order co...
详细信息
We propose a new framework combining weak measurement and second-order correlated technique. The theoretical analysis shows that weak value amplification （WVA） experiment can also be implemented by a second-order correlated system. We then build two-dimensional second-order correlated function patterns for achieving higher amplification factor and discuss the signal-to-noise ratio influence. Several advantages can be obtained by our proposal. For instance, detectors with high resolution are not necessary. Moreover, detectors with low saturation intensity are available in WVA setup. Finally, type-one technical noise can be effectively suppressed.
Indoor localization is a popular topic because of the poor performance of GPS in the indoor environment. This paper has provided a new method to achieve the goal of indoor localization. Combining the usage of posture ...
详细信息
To enhance the reliability of launch vehicle attitude control systems and prevent the control invalidation caused by swing engine deadlock, a control reconfiguration of fault-tolerant control is proposed. Firstly, the...
详细信息
ISBN:
(纸本)9780955529337
To enhance the reliability of launch vehicle attitude control systems and prevent the control invalidation caused by swing engine deadlock, a control reconfiguration of fault-tolerant control is proposed. Firstly, the coupling identity between the channels is discussed based on the dynamic model of the vehicle. Then, under the assumption of no rolling motion, we study the swing angles reconfiguration method based on the moment balance principle, and then deduce the relationship between the swing angle of the deadlocked engines and the engines still operate well. From the rationality analysis, the safe bound of the deadlocked engine and reconfiguration conditions are proposed under several assumptions. Finally, the numerical simulation of rocket attitude control based on the discussed reconfiguration strategy is given to demonstrate that the variance of the control affect by the deadlocked engine could be rectified by other booster-engines effectively.
作者：
ZHANG YunLU RunyanCAI YunzeDepartment of Automation
Key Laboratory of System Control and Information Processing of Ministry of EducationKey Laboratory of Marine Intelligent Equipment and System of Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China
In situation assessment(SA)of missile versus target fighter,the traditional SA models generally have the characteristics of strong subjectivity and poor dynamic *** paper considers SA as an expectation of future retur...
详细信息
In situation assessment(SA)of missile versus target fighter,the traditional SA models generally have the characteristics of strong subjectivity and poor dynamic *** paper considers SA as an expectation of future returns and establishes a missile-target simulation battle *** actor-critic(AC)algorithm in reinforcement learning(RL)is used to train the evaluation network,and a missile-target SA model is established in simulation battle *** and comparative experiments show that the model can effectively estimate the expected effect of missile attack under the current situation,and it provides an effective basis for missile attack decision.
作者：
Wang X.Su H.Cai Y.Department of Automation
Shanghai Jiaotong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China School of Automation
Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Luoyu Road 1037 Wuhan 430074 China
This paper focuses on the robust semi-global coordinated tracking of general linear systems subject to input saturation together with input additive disturbance and dead zone. A fully distributed algorithm which relat...
详细信息
In this paper, we propose an improved particle filter algorithm for real-time tracking a randomly moving target in dynamic environment with a moving monocular camera. For making the tracking task robustly and effectiv...
详细信息
ISBN:
(纸本)9780819469502
In this paper, we propose an improved particle filter algorithm for real-time tracking a randomly moving target in dynamic environment with a moving monocular camera. For making the tracking task robustly and effectively, color histogram based target model is integrated into particle filter algorithm. Bhattacharyya distance is used to weight samples by calculating each sample's histogram with a specified target model and it makes the measurement matching and samples' weight updating more reasonable. In order to reduce sample depletion, the improved algorithm will be able to take the latest observation into account. The experimental results confirm that the method is effective even when the monocular camera is moving and the target object is partially occluded in a clutter background.
A nuclear export signal (NES) is a sequence of amino acids, which is a protein localization signal, and contributes to regulate localization of cellular proteins. In recent peering works, activity of NESs were introdu...
详细信息
Generative adversarial network(GAN)has achieved great success in many fields such as computer vision,speech processing,and natural language processing,because of its powerful capabilities for generating realistic *** ...
详细信息
Generative adversarial network(GAN)has achieved great success in many fields such as computer vision,speech processing,and natural language processing,because of its powerful capabilities for generating realistic *** this paper,we introduce GAN into the field of electromagnetic signal classification(ESC).ESC plays an important role in both military and civilian ***,in many specific scenarios,we can’t obtain enough labeled data,which cause failure of deep learning methods because they are easy to fall into ***,semi-supervised learning(SSL)can leverage the large amount of unlabeled data to enhance the classification performance of classifiers,especially in scenarios with limited amount of labeled *** present an SSL framework by incorporating GAN,which can directly process the raw in-phase and quadrature(IQ)signal *** to the characteristics of the electromagnetic signal,we propose a weighted loss function,leading to an effective classifier to realize the end-to-end classification of the electromagnetic *** validate the proposed method on both public RML2016.04c dataset and real-world Aircraft Communications Addressing and Reporting System(ACARS)signal *** experimental results show that the proposed framework obtains a significant increase in classification accuracy compared with the state-of-the-art studies.
暂无评论