No abstract

No abstract

This paper proposes a wireless network traffic prediction model based on Bayesian Gaussian tensor decomposition and recurrent neural network with rectified linear unit (BGCP-RNN-ReLU model), which can effectively predict the changes in the upstream and downstream network traffic in a short period of time in the future. The research is divided into two parts: (i) The missing observations are imputed by an algorithm based on Bayesian Gaussian tensor decomposition. (ii) The recurrent neural network is used to forecast the true observations only rather than both true and estimated observations. The results show that, compared with other combined models of missing data imputation and neural networks, the BGCP-RNN-ReLU model proposed in this paper has the smallest prediction error for both the upstream and downstream traffic. The new model achieves better forecasting precision, and thus can help to regulate the load of communication station to reduce resource consumption. Highlights The problem of forecasting wireless network traffic with missing values is divided in two stages to handle. A newly propose d method can more efficiently impute missing values in wireless network traffic data. Simple recurrent neural network obtains better prediction performance than other complex networks.

To improve penetration performance of the classical conical shaped charge, a bore-center annular shaped charge (BCASC) was designed and effects of key parameters on its formation and penetration into concrete targets were investigated numerically and experimentally. As a result, suitable parameters of the BCASC, which comprehensive consideration of penetration hole diameter and depth into concrete targets, were provided. Subsequently, tests of the optimized BCASC penetration into single-layer and doublelayer concrete targets were performed. The results indicate that, for all the cases, the diameters of the rear crater are larger than that of the front ones. The influence of factors h (standoff distance) and f (the radial distance between the center of the inner and outer liner wall) on the diameters of the front crater, the penetrating tunnel, and the rear crater are greater than that of other factors. The diameters of the front crater and the penetrating tunnel decrease with the increase of factors h and f. The penetration depth of optimized BCASC into concrete exceeds 3.0 times of the charge diameter (D). Hole diameters of penetrating tunnels are larger than the charge diameter. For the single-layer concrete target, the hole diameter of the penetrating tunnel is 2.26D. And, for the double-layer concrete target, the hole diameters of the first and second layers are 1.41D and 1.33D, respectively.

It has discussed the approach to establish the models of terrain, threat and the evaluation of route cost in the route planning for UAV in low-altitude penetration. An Ant Algorithm is introduced into UAV route planning, since stagnation may appear during searching in use of traditional ant colonies algorithm,this paper introduces yaw angle to improve heuristic information, establishes the prior search set, makes ant colony algorithm the more rapid and effective search to the best route, simulation results prove the efficiency of the planning method.