Intelligent Passive Detection of Aerial Target in Space-Air-Ground Integrated Networks

Passive detection of moving target is an important part of intelligent surveillance. Satellite has the potential to play a key role in many applications of space-air-ground integrated networks(SAGIN). In this paper, we propose a novel intelligent passive detection method for aerial target based on reservoir computing networks. Specifically, delayed feedback networks are utilized to refine the direct signals from the satellite in the reference channels. In addition, the satellite direct wave interference in the monitoring channels adopts adaptive interference suppression using the minimum mean square error filter. Furthermore, we employ decoupling echo state networks to predict the clutter interference in the monitoring channels and construct the detection statistics accordingly. Finally, a multilayer perceptron is adopted to detect the echo signal after interference suppression. Extensive simulations is conducted to evaluate the performance of our proposed method. Results show that the detection probability is almost 100% when the signal-to-interference ratio of echo signal is-36 dB, which demonstrates that our proposed method achieves efficient passive detection for aerial targets in typical SAGIN scenarios.

Feedback LSTM Network Based on Attention for Image Description Generator

Images are complex multimedia data which contain rich semantic information.Most of current image description generator algorithms only generate plain description,with the lack of distinction between primary and secondary object,leading to insufficient high-level semantic and accuracy under public evaluation criteria.The major issue is the lack of effective network on high-level semantic sentences generation,which contains detailed description for motion and state of the principal object.To address the issue,this paper proposes the Attention-based Feedback Long Short-Term Memory Network(AFLN).Based on existing codec framework,there are two independent sub tasks in our method:attention-based feedback LSTM network during decoding and the Convolutional Block Attention Module(CBAM)in the coding phase.First,we propose an attentionbased network to feedback the features corresponding to the generated word from the previous LSTM decoding unit.We implement feedback guidance through the related field mapping algorithm,which quantifies the correlation between previous word and latter word,so that the main object can be tracked with highlighted detailed description.Second,we exploit the attention idea and apply a lightweight and general module called CBAM after the last layer of VGG 16 pretraining network,which can enhance the expression of image coding features by combining channel and spatial dimension attention maps with negligible overheads.Extensive experiments on COCO dataset validate the superiority of our network over the state-of-the-art algorithms.Both scores and actual effects are proved.The BLEU 4 score increases from 0.291 to 0.301 while the CIDEr score rising from 0.912 to 0.952.

Research on Narrowband Line Spectrum Noise Control Method Based on Nearest Neighbor Filter and BP Neural Network Feedback Mechanism

Thefilter-x least mean square(FxLMS)algorithm is widely used in active noise control(ANC)systems.However,because the algorithm is a feedback control algorithm based on the minimization of the error signal variance to update thefilter coefficients,it has a certain delay,usually has a slow convergence speed,and the system response time is long and easily affected by the learning rate leading to the lack of system stability,which often fails to achieve the desired control effect in practice.In this paper,we propose an active control algorithm with near-est-neighbor trap structure and neural network feedback mechanism to reduce the coefficient update time of the FxLMS algorithm and use the neural network feedback mechanism to realize the parameter update,which is called NNR-BPFxLMS algorithm.In the paper,the schematic diagram of the feedback control is given,and the performance of the algorithm is analyzed.Under various noise conditions,it is shown by simulation and experiment that the NNR-BPFxLMS algorithm has the following three advantages:in terms of performance,it has higher noise reduction under the same number of sampling points,i.e.,it has faster convergence speed,and by computer simulation and sound pipe experiment,for simple ideal line spectrum noise,compared with the convergence speed of NNR-BPFxLMS is improved by more than 95%compared with FxLMS algorithm,and the convergence speed of real noise is also improved by more than 70%.In terms of stability,NNR-BPFxLMS is insensitive to step size changes.In terms of tracking performance,its algorithm responds quickly to sudden changes in the noise spectrum and can cope with the complex control requirements of sudden changes in the noise spectrum.

Adaptive functional link network control of near-space vehicles with dynamical uncertainties

The control law design for a near-space hypersonic vehicle（NHV） is highly challenging due to its inherent nonlinearity,plant uncertainties and sensitivity to disturbances.This paper presents a novel functional link network（FLN） control method for an NHV with dynamical thrust and parameter uncertainties.The approach devises a new partially-feedback-functional-link-network（PFFLN） adaptive law and combines it with the nonlinear generalized predictive control（NGPC） algorithm.The PFFLN is employed for approximating uncertainties in flight.Its weights are online tuned based on Lyapunov stability theorem for the first time.The learning process does not need any offline training phase.Additionally,a robust controller with an adaptive gain is designed to offset the approximation error.Finally,simulation results show a satisfactory performance for the NHV attitude tracking,and also illustrate the controller＇s robustness.

Subgradient-based feedback neural networks for non-differentiable convex optimization problems

This paper developed the dynamic feedback neural network model to solve the convex nonlinear programming problem proposed by Leung et al. and introduced subgradient-based dynamic feedback neural networks to solve non-differentiable convex optimization problems. For unconstrained non-differentiable convex optimization problem, on the assumption that the objective function is convex coercive, we proved that with arbitrarily given initial value, the trajectory of the feedback neural network constructed by a projection subgradient converges to an asymptotically stable equilibrium point which is also an optimal solution of the primal unconstrained problem. For constrained non-differentiable convex optimization problem, on the assumption that the objective function is convex coercive and the constraint functions are convex also, the energy functions sequence and corresponding dynamic feedback subneural network models based on a projection subgradient are successively constructed respectively, the convergence theorem is then obtained and the stopping condition is given. Furthermore, the effective algorithms are designed and some simulation experiments are illustrated.

Real-Time Fault Diagnosis for Gas Turbine Blade Based on Output-Hidden Feedback Elman Neural Network

In order to remotely monitor and maintain large-scale complex equipment in real time, China Telecom plans to create a total solution that integrates remote data collection, transmission, storage, analysis and prediction. This solution can provide manufacturers with proactive, systematic, integrated operation and maintenance service, and the data analysis and health forecasting are the most important part. This paper conducts health management for the turbine blades. Elman neural network, and improved Elman neural network, i.e., outputhidden feedback(OHF) Elman neural network are studied as the main research methods. The results verify the applicability of OHF Elman neural network.

COOPERATIVE DYNAMICS OF LOYAL CUSTOMERS IN QUEUEING NETWORKS

We consider queueing networks （QN＇s） with feedback loops roamed by ＂intelligent＂ agents, able to select their routing on the basis of their measured waiting times at the QN nodes. This is an idealized model to discuss the dynamics of customers who stay loyal to a service supplier, provided their service time remains below a critical threshold. For these QN＇s, we show that the traffic flows may exhibit collective patterns typically encountered in multi-agent systems. In simple network topologies, the emergent cooperative behaviors manifest themselves via stable macroscopic temporal oscillations, synchronization of the queue contents and stabilization by noise phenomena. For a wide range of control parameters, the underlying presence of the law of large numbers enables us to use deterministic evolution laws to analytically characterize the cooperative evolution of our multi-agent systems. In particular, we study the case where the servers are sporadically subject, to failures altering their ordinary behavior.

Towards a Unified Recurrent Neural Network Theory： The Uniformly Pseudo-Projection-Anti-Monotone Net

In the past decades, various neural network models have been developed for modeling the behavior of human brain or performing problem-solving through simulating the behavior of human brain. The recurrent neural networks are the type of neural networks to model or simulate associative memory behavior of human being. A recurrent neural network （RNN） can be generally formalized as a dynamic system associated with two fundamental operators： one is the nonlinear activation operator deduced from the input-output properties of the involved neurons, and the other is the synaptic connections （a matrix） among the neurons. Through carefully examining properties of various activation functions used, we introduce a novel type of monotone operators, the uniformly pseudo-projectionanti-monotone （UPPAM） operators, to unify the various RNN models appeared in the literature. We develop a unified encoding and stability theory for the UPPAM network model when the time is discrete. The established model and theory not only unify but also jointly generalize the most known results of RNNs. The approach has lunched a visible step towards establishment of a unified mathematical theory of recurrent neural networks.