Aerial target threat assessment based on gated recurrent unit and self-attention mechanism

doi:10.23919/JSEE.2023.000116

Abstract

Abstract:

Aerial threat assessment is a crucial link in modern air combat, whose result counts a great deal for commanders to make decisions. With the consideration that the existing threat assessment methods have difficulties in dealing with high dimensional time series target data, a threat assessment method based on self-attention mechanism and gated recurrent unit (SA-GRU) is proposed. Firstly, a threat feature system including air combat situations and capability features is established. Moreover, a data augmentation process based on fractional Fourier transform (FRFT) is applied to extract more valuable information from time series situation features. Furthermore, aiming to capture key characteristics of battlefield evolution, a bidirectional GRU and SA mechanisms are designed for enhanced features. Subsequently, after the concatenation of the processed air combat situation and capability features, the target threat level will be predicted by fully connected neural layers and the softmax classifier. Finally, in order to validate this model, an air combat dataset generated by a combat simulation system is introduced for model training and testing. The comparison experiments show the proposed model has structural rationality and can perform threat assessment faster and more accurately than the other existing models based on deep learning.

Key words: target threat assessment, gated recurrent unit (GRU), self-attention (SA), fractional Fourier transform (FRFT)

Chen CHEN, Wei QUAN, Zhuang SHAO. Aerial target threat assessment based on gated recurrent unit and self-attention mechanism[J]. Journal of Systems Engineering and Electronics, 2024, 35(2): 361-373.

Figures/Tables 17

Fig 1

Fig 2

Fig 3

Fig 4

Fig 5

Fig 6

Fig 7

Fig 8

Table 1

Fig 9

Table 2

Fig 10

Table 3

Fig 11

Table 4

Table 5

Table 6

References 33

1	ZHANG K, KONG W, LIU P P, et al Assessment and sequencing of air target threat based on intuitionistic fuzzy entropy and dynamic VIKOR. Journal of Systems Engineering and Electronics, 2018, 29 (2): 305- 310. doi: 10.21629/JSEE.2018.02.11
2	XI Z F, XU A, KOU Y X, et al Target maneuver trajectory prediction based on RBF neural network optimized by hybrid algorithm. Journal of Systems Engineering and Electronics, 2021, 32 (2): 498- 516. doi: 10.23919/JSEE.2021.000042
3	ZHANG J D, YANG Q M, SHI G Q, et al UAV cooperative air combat maneuver decision based on multi-agent reinforcement learning. Journal of Systems Engineering and Electronics, 2021, 32 (6): 1421- 1438. doi: 10.23919/JSEE.2021.000121
4	KONG D P, CHANG T Q, WANG Q D, et al. A threat assessment method of group targets based on interval-valued intuitionistic fuzzy multi-attribute group decision-making. Applied Soft Computing, 2018, 67: 350–369.
5	SUN H W, XIE X F Threat evaluation method of warships formation air defense based on AR(p)-DITOPSIS. Journal of Systems Engineering and Electronics, 2019, 30 (2): 297- 307. doi: 10.21629/JSEE.2019.02.09
6	ZHEN H F, BEN H S, JIN Y C, et al. A novel dynamic Bayesian network based threat assessment algorithm. Proc. of the 4th International Conference on Systems and Informatics, 2017: 611–615.
7	ZHAO R J, YANG F B, JI L N, et al Dynamic air target threat assessment based on interval-valued intuitionistic fuzzy sets, game theory, and evidential reasoning methodology. Mathematical Problems in Engineering, 2021, 2021, 6652706.
8	GAO Y, LI D S, ZHONG H A novel target threat assessment method based on three-way decisions under intuitionistic fuzzy multi-attribute decision making environment. Engineering Applications of Artificial Intelligence, 2020, 87, 103276. doi: 10.1016/j.engappai.2019.103276
9	XU Y J, WANG Y C, MIU X D Multi-attribute decision making method for air target threat evaluation based on intuitionistic fuzzy sets. Journal of Systems Engineering and Electronics, 2012, 23 (6): 891- 897. doi: 10.1109/JSEE.2012.00109
10	CHEN J, SUN J, WANG G From unmanned systems to autonomous intelligent systems. Engineering, 2022, 12 (5): 16- 19.
11	YANG C, XIA X C, LI T B, et al Analysis of rationality of K-means cluster analysis in target threat assessment. Ship Electronic Engineering, 2017, 37 (11): 21- 23, 86.
12	WANG F, WU Z Q, SHI H Q Research on anti-air threat assessment based on SVM. Fire Control & Command Control, 2018, 40 (8): 1760- 1768.
13	CHEN X, LIU Z L, LIANG H L Assessment of aerial target threat based on genetic algorithm optimizing fuzzy recurrent wavelet neural network. Journal of Northwestern Polytechnical University, 2019, 37 (2): 424- 432. doi: 10.1051/jnwpu/20193720424
14	ZHAI X Y, YANG F B, JI L N, et al Air combat targets threat assessment based on standardized fully connected network and residual network. Fire Control & Command Control, 2018, 43 (8): 66- 69.
15	YUE L F, YANG R N, ZUO J L, et al Air target threat assessment based on improved moth flame optimization-gray neural network model. Mathematical Problems in Engineering, 2019, 2019, 4203538.
16	YUAN C, KOU Y X, AN X, et al Target threat assessment in air combat based on improved glowworm swarm optimization and ELM neural network. International Journal of Aerospace Engineering, 2021, 2021, 4687167.
17	XI Z F, XU A, KOU Y X, et al Target threat assessment in air combat based on PCA-MPSO-ELM algorithm. Acta Aeronautica et Astronautica Sinica, 2020, 41 (9): 211- 226.
18	XU J Q, BI Y M, LIANG W, et al Airport threaten degree evaluation based on maximal deviations. Systems Engineering and Electronics, 2011, 33 (8): 1816- 1819.
19	LI S Y, CHEN M, WU Q X, et al Threat sequencing of multiple UCAVs with incomplete information based on game theory. Journal of Systems Engineering and Electronics, 2022, 33 (4): 986- 996. doi: 10.23919/JSEE.2022.000095
20	XU X M, YANG R N, YU Y. Threat assessment in air combat based on ELM neural network. Proc. of the IEEE International Conference on Artificial Intelligence and Computer Applications, 2019: 114–120.
21	LI S Y, WU Q X, CHEN M, et al. Air combat situation assessment of multiple UCAVs with incomplete information. Proc. of the Chinese Intelligent Systems Conference, 2021: 18–26.
22	LI G Q, SONG Z Y, FU Q A convolutional neural network based approach to sea clutter suppression for small boat detection. Frontiers of Information Technology & Electronic Engineering, 2020, 21 (10): 1504- 1520.
23	GAO W B, LI B Z Convolution theorem involving n-dimensional windowed fractional Fourier transform. Science China (Information Sciences), 2021, 64 (6): 244- 246.
24	OZAKTAS H M, ARIKAN O, KUTAY M A, et a1 Digital computation of the fractional Fourier transform. IEEE Trans. on Signal Processing, 1996, 44 (9): 2141- 2150. doi: 10.1109/78.536672
25	WU X, TAO R, HONG D F, et al The FrFT convolutional face: toward robust face recognition using the fractional Fourier transform and convolutional neural networks. Science China (Information Sciences), 2020, 63 (1): 235- 237.
26	ZHANG X C, QIU X P, PANG J M, et al Dual-axial self-attention network for text classification. Science China (Information Sciences), 2021, 64 (12): 80- 90.
27	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need. Proc. of the 31st International Conference on Neural Information Processing Systems, 2017: 6000–6010.
28	SHAO Z, CHEN C. Aerial battlefield targets grouping based on DTW-DBSCAN algorithm. Proc. of the 40th Chinese Control Conference, 2021: 3397–9402.
29	HAN H, XIE T Lane change trajectory prediction of vehicles in highway interweaving area using Seq2Seq-attention network. China Journal of Highway and Transport, 2020, 33 (6): 106- 118.
30	SU J Y, COOMBES M, LIU C J, et al. Machine learning-based crop drought mapping system by UAV remote sensing RGB imagery. Unmanned Systems, 2020, 8(1): 71–83.
31	SABOR N, LI Y F, ZHANG Z, et al Detection of the interictal epileptic discharges based on wavelet bispectrum interaction and recurrent neural network. Science China (Information Sciences), 2021, 64 (6): 203- 221.
32	XIANG Z R, YAN J, DEMIR I A rainfall-runoff model with LSTM-based sequence-to-sequence learning. Water Resources Research, 2020, 56 (1): 165- 181.
33	GRAF R, ZHU S, SIVAKUMAR B. Forecasting river water temperature time series using a wavelet-neural network hybrid modelling approach. Journal of Hydrology, 2019, 578: 124115.

Threat level	Samples number	Ratio/%
1	7 124	9.40
2	6 412	8.46
3	11 809	15.59
4	10 346	13.66
5	6 689	8.83
6	5 420	7.16
7	6 085	8.03
8	7 665	10.12
9	8 891	11.74
10	3 310	4.37
11	2 000	2.64

Threat level	Precision	Recall	F1-score
1	92.5	92.0	92.3
2	93.2	91.3	92.2
3	90.6	82.5	86.4
4	89.7	92.7	91.1
5	95.7	93.9	94.8
6	81.9	99.0	89.6
7	84.0	56.8	67.7
8	79.8	77.0	78.0
9	82.5	87.1	84.7
10	93.4	90.7	92.0
11	93.5	91.8	92.6

Model	Accuracy	Precision	Recall	F1
SA-GRU	90.4	90.4	90.5	90.3
GA-SL FRWNN	64.2	64.2	64.1	63.4
IGSO-ELM	55.6	55.6	56.0	55.3
ResNet	41.9	41.9	43.5	36.0
LSTM-LSTM	76.7	79.3	77.4	77.4

Augmentation	Accuracy	Precision	Recall	F1
No	60.3	69.7	60.3	57.0
Yes	90.4	90.4	90.5	90.3

Model	seq2seq	SA	Residual
ResNet	0	0	1
seq2seq	1	0	0
Res-seq2seq	1	0	1
SA-seq2seq	1	1	0
SA-GRU	1	1	1