Search

It is crucial to develop an effective controller for the multi-UAV system to contribute to the frontier fields, such as the electronic warfare. To address the dilemma of the cooperative formation with the high dimensional data, a deep neural network(NN) controller is developed in this paper. Firstly, a deep NN model is used to tune parameters of PID controller online. Secondly, this paper introduces an improved deep NN model integrating the momentum to improve the performance of the classical NN model and satisfy the condition for the real time cooperative formation. Lastly, the cooperative formation task is achieved by extending the proposed cooperative controller with an improved NN to the complex multi-UAV system. The simulation result of multi-UAV formation demonstrates the effectiveness of the proposed method, which achieves a faster formation than competitors.

Discretization of multidimensional attributes can improve the training speed and accuracy of machine learning algorithm. At present, the discretization algorithms perform at a lower level, and most of them are single attribute discretization algorithm, ignoring the potential association between attributes. Based on this, we proposed a discretization algorithm based on forest optimization and rough set (FORDA) in this paper. To solve the problem of discretization of multi-dimensional attributes, the algorithm designs the appropriate value function according to the variable precision rough set theory, and then constructs the forest optimization network and iteratively searches for the optimal subset of breakpoints. The experimental results on the UCI datasets show that:compared with the current mainstream discretization algorithms, the algorithm can avoid local optimization, significantly improve the classification accuracy of the SVM classifier, and its discretization performance is better, which verifies the effectiveness of the algorithm.

In order to resolve the problem of joint direction of departure (DOD) and direction of arrival (DOA) estimation in bistatic MIMO array, a dimensional reduced-Capon method based on Taylor series expansion and signal subspace is proposed in this paper. Firstly, the Taylor series expansion of the steering vector is used to reduce the two-dimensional (2D) spectrum peak searching of Capon method to one-dimensional searching. Then, the DOD estimator can be achieved via Lagrange multiplier by one-dimension search. Finally, the steering vector of DOA corresponding to the DOD estimator is achieved and the DOA can be estimated. Hence, the estimated DOD and DOA are obtained automatically paired. And also, the proposed method can avoid the high computational complexity of MIMO Capon method. Simulation results are presented to illustrate the effectiveness of the proposed method.

In order to guarantee the QoS requirements of multiple services in airborne all-domain heterogeneous and flexible networks, we propose a novel multi-priority and multi-path based QoS routing (MP2R) protocol in this paper. In the protocol, in terms of the route effectiveness and reliability, the route cost penalty function is constructed based on the multi-priority M/M/1 queueingqueuing system with the preemptive-resume policy. The minimum value of the function is derived through the optimization theory, and the optimum routing solution is acquired. The simulation results show that the MP2R protocol not only has the capabilities of differentiation services for different kinds of traffic and QoS provision, but also can utilize the network resource rationally, avoid congestion, achieve the load balancing, and meet the requirements of airborne all-domain heterogeneous and flexible networks effectively.

Distributed sources can be regarded as an assembly of point sources within a spatial distribution. In this paper, we explore the estimation of the two-dimensional incoherently distributed sources using double L-shape arrays. The rotational invariance properties of the nominal elevation and nominal elevation are firstly obtained by taking first-order Taylor series expansions with regard to the generalized steering vectors of two pairs of parallel subarrays. The rotation operators can be solved based on signal subspace. Then the nominal elevation and nominal elevation can be obtained from parameters matching method. Estimation of direction of arrival can be used in multi-source scenario and needn't peak-finding search. Lastly the angular spreads can be solved through two-dimensional Capon search based on nominal angles. The simulation experiments show that the proposed method has good performance on the estimation of two-dimensional incoherently distributed sources. Investigating different experimental conditions, sources with different angular spreads, simulations are conducted to validate better estimation accuracy of the proposed method.

In underwater acoustic target recognition, the target signal is usually complex and the samples which are difficult to obtain also have some uncertain information. In order to effectively solve these problems, the evidence clustering recognition algorithm (TECRA) is presented. In this new method, the k-nearest neighbor are first determined by using the feature distance between the object and its neighbors in each class of the training set, and a reasonable initial basic belief assignments (bba's) for each target data are constructed by the improved k-nearest neighbor classification algorithm. Then the final global bba's of the target is obtained by optimizing the objective function of the algorithm. Finally the object can be recognized by the fusion result and the classification rule presented in the paper. Several experiments based on real underwater acoustic data sets are made to test the effectiveness of TECRA in comparison with some other methods. The results indicate that TECRA can effectively improve the recognition accuracy.