Learning Embedding Features Based on Multisense-Scaled Attention Architecture to Improve the Predictive Performance of Air Combat Intention Recognition

Abstract

In modern air combat, acquiring the opponent's air combat intention is one of essential prerequisites to evaluate the air combat situation effectively and master the battlefield initiative. On account of multi-dimensional and temporal characteristics of the target state, a recognition model is proposed to identify tactical intention of aerial target based on a multi-sense-scaled attention architecture. First of all, the multi-dimensional feature information, including target state attributes, battlefield environment, target attributes and so on, is constructed as target feature. Secondly, the non-numerical information, such as battlefield environment characteristics, enemy and friend attributes of targets, radar status, maneuver type, etc, is transformed into numerical data. For the purpose of subsequent data processing, the flight speed, altitude, RCS, etc, in the target status information are normalized into the same dimension. Furthermore, a target intention recognition model with multiple sense-scaled attention mechanism is designed to depict the target state, attributes and the information of the battlefield environment from multiple dimensions, which is convenient to be close to the actual combat. The BiLSTM neural network is used to learn the deep-seated information in the air combat intention feature vector, and the attention mechanism is used to adaptively allocate the network weights. The air combat feature information with different weights is introduced into the softmax function layer for intention recognition. Compared with the traditional air tactical target intention recognition model, the proposed model effectively improves the efficiency of air target tactical intention recognition as well as affords important theoretical significance and reference value for the auxiliary combat system.

Robust Air Target Intention Recognition Based on Weight Self-Learning Parallel Time-Channel Transformer Encoder

“…The highest recall, precision, and F1 score are obtained for attack intention because the maneuvers and tactical actions of attack intention are apparent, and the model can learn its characters better. The method used are XGboost [40], SVM [37], Random Forrest (RF) [38], FCN [43], CNN [43], LSTM [43], BiGRU-ATTENTION [52], CNN-BiLSTM-ATTENTION [53]. Under the same sliding window length, intention feature and space, the methods are trained, and the final recognition performance are obtained.…”

“…Finally, it is worth noting that more complex network structures do not necessarily lead to performance gains, e.g., the recognition accuracy of CNN-BiLSTM-ATTENTION is 91.17%, which is lower than the recognition accuracy of LSTM and BiGRU-ATTENTION. XGboost [40] 92.33 0.9206 SVM [37] 80.20 0.7901 RF [38] 81.75 0.7912 FCN [43] 85.25 0.8319 CNN [43] 89.84 0.8934 LSTM [43] 92.67 0.9205 BiGRU-ATTENTION [52] 95.11 0.9491 CNN-BiLSTM-ATTENTION [53] 91.17 0.9058 WSPTCTE-IR 96.90 0.9676…”