Improved spatio-temporal evidence fusion for radar aerial target tactical intention recognition

doi:10.23919/JSEE.2025.000041

Journal of Systems Engineering and Electronics ›› 2026, Vol. 37 ›› Issue (1): 148-156.doi: 10.23919/JSEE.2025.000041

• DEFENCE ELECTRONICS TECHNOLOGY • Previous Articles Next Articles

Improved spatio-temporal evidence fusion for radar aerial target tactical intention recognition

Liangliang HUAI¹^,²(), Xinyu ZHANG¹(), Shuying WU¹(), Peng YUN²(), Bo LI¹^,*()

¹School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710129, China
²AVIC Leihua Electronic Technology Research Institute, Wuxi 214063, China

Received:2024-05-10 Accepted:2025-03-10 Online:2026-02-18 Published:2026-03-09
Contact: Bo LI E-mail:leonhuai@mail.nwpu.edu.cn;chengx0919@gmail.com;shuying.wu@mail.nwpu.edu.cn;yunp009@avic.com;libo803@nwpu.edu.cn
About author:
HUAI Liangliang was born in 1980. He received his M.E. degree in signal and information processing from Nanjing University of Science and Technology, Nanjing, China, in 2005, and M.E. degree in embedded system from ISAE-SUPAERO, Toulouse, France, in 2011, respectively. He is currently a senior engineer with AVIC Leihua Electronic Technology Research Institute. His current research interests include target tracking, intention recognition and signal processing. E-mail: leonhuai@mail.nwpu.edu.cn

ZHANG Xinyu was born in 2001. She received her B.E. degree in detection guidance and control technology from Northwestern Polytechnical University in Xi’an, China in 2023, where she is currently pursuing her M.S. degree in control science and engineering. Her current research interests include intelligent decision and control and intention recognition. E-mail: chengx0919@gmail.com

WU Shuying was born in 2001. She received her B.E. degree in detection guidance and control technology from Northwestern Polytechnical University in Xi’an, China in 2023, where she is currently pursuing her Ph.D. degree in electronic science and technology. Her current research interests include machine learning and intelligent decision and control. E-mail: shuying.wu@mail.nwpu.edu.cn

YUN Peng was born in 1994. He received his Ph.D. degree in control science and engineering from Nanjing University of Science and Technology, Nanjing, China, in 2022. He is currently an engineer with AVIC Leihua Electronic Technology Research Institute. His current research interests include deep learning, target tracking, and data processing. E-mail: yunp009@avic.com

LI Bo was born in 1978. He received his B.E. degree in electronic information technology and M.E. and Ph.D. degrees in systems engineering from Northwestern Polytechnical University, Xi’an, China, in 2000, 2002, and 2008, respectively. From 2014 to 2015, he was a visiting scholar with London South Bank University, London, U.K. He is currently a professor with the School of Electronics and Information, Northwestern Polytechnical University. His current research interests include intelligent decision and control, deep reinforcement learning, and uncertain information processing. E-mail: libo803@nwpu.edu.cn
Supported by:
This work was supported by the Key Research and Development Program of Shaanxi Province (2023-GHZD-33), the Open Project of the State Key Laboratory of Intelligent Game (ZBKF-23-05), and the National Nature Science Foundation of China (62003267).

Abstract

Abstract:

To address the issue of incorrect fusion results caused by conflicting evidence due to inaccurate evidence and incomplete recognition frameworks in radar airborne target tactical intention recognition, a spatiotemporal evidence fusion algorithm is proposed. To resolve the conflict evidence fusion problem caused by inaccurate evidence, the algorithm performs discounting of evidence from both spatial and temporal dimensions. Spatial discounting is influenced by both inter-evidence inconsistency and intra-evidence inconsistency, while temporal discounting is determined by time intervals and information entropy. For the problem of conflicting evidence fusion due to an incomplete recognition framework, an open recognition architecture based on dynamic composite focal elements is proposed. This approach allocates some conflicting information to temporary composite focal elements, avoiding excessive basic probability assignment (BPA) of the empty set after fusion, which can lead to deviations from the actual fusion results. Simulation experiments comparing various methods indicate that the proposed method can effectively improve target intention recognition accuracy and demonstrates good stability.

Key words: evidence fusion, tactical intention recognition, evidence discount, open frame of discernment

Liangliang HUAI, Xinyu ZHANG, Shuying WU, Peng YUN, Bo LI. Improved spatio-temporal evidence fusion for radar aerial target tactical intention recognition[J]. Journal of Systems Engineering and Electronics, 2026, 37(1): 148-156.

Figures/Tables 9

Fig 1

Fig 2

Table 1

Fig 3

Table 2

Fig 4

Table 3

Fig 5

Table 4

References 26

1	QUOST B, MASSON M H, DENOEUX T Classifier fusion in the Dempster-Shafer framework using optimized t-norm based combination rules. International Journal of Approximate Reasoning, 2011, 57 (3): 353- 374.
2	LI N P, GEBRAEEL N, LEI Y G, et al Remaining useful life prediction based on a multi-sensor data fusion model. Reliability Engineering & System Safety, 2021, 208, 107249.
3	HUA Z, JING X C An improved belief Hellinger divergence for Dempster-Shafer theory and its application in multi-source information fusion. Applied Intelligence, 2023, 53 (14): 17965- 17984. doi: 10.1007/s10489-022-04428-w
4	DUAN X B, FAN Q C, BI W H, et al Belief exponential divergence for DS evidence theory and its application in multi-source information fusion. Journal of Systems Engineering and Electronics, 2024, 35 (6): 1454- 1468.
5	ZHOU K Y, LU N Y, JIANG B, et al Review on uncertainty analysis and information fusion diagnosis of aircraft control system. Journal of Systems Engineering and Electronics, 2024, 35 (5): 1245- 1263.
6	LIU Z G, LIU Y, DEZERT J, et al Evidence combination based on credal belief redistribution for pattern classification. IEEE Trans. on Fuzzy Systems, 2019, 28 (4): 618- 631.
7	DUAN Z X, BI H Y, ZHANG Z W A D-S evidence reasoning based hybrid classification algorithm for incomplete data. Information and Control, 2020, 49 (4): 455- 463,471. doi: 10.5755/j01.itc.49.4.25367
8	TIAN H P, WANG X L, TAN Y G. Incomplete data evidential classification with inconsistent distribution. Information Sciences, 2024, 676: 120824.
9	TANG Y C, ZHANG X, ZHOU Y, et al A new correlation belief function in Dempster-Shafer evidence theory and its application in classification. Scientific Reports, 2023, 13 (1): 7609. doi: 10.1038/s41598-023-34577-y
10	LIU Z G, LIU Y, DEZERT J, et al Credal c-means clustering method based on belief functions. Knowledge-Based Systems, 2015, 74, 119- 132. doi: 10.1016/j.knosys.2014.11.013
11	HUANG W B, WANG C Y, JIA H B, et al Pilot operation intention analysis and tactile feedback technology based on multi-channel data fusion. Journal of Xi’an Technological University, 2022, 42 (2): 178- 187.
12	LIU Q, LIU Q M, WANG M Sustainable decision-making enhancement: trust and linguistic-enhanced conflict measurement in evidence theory. Sustainability, 2024, 16 (6): 2288. doi: 10.3390/su16062288
13	KAVYA R, CHRISTOPHER J Interpretable systems based on evidential prospect theory for decision-making. Applied Intelligence, 2023, 53 (2): 1640- 1665. doi: 10.1007/s10489-022-03276-y
14	AHMAD J, MUHAMMAD K, KWON S, et al. Dempster-Shafer fusion based gender recognition for speech analysis applications. Proc. of the International Conference on Platform Technology and Service, 2016. DOI: 10.1109/PlatCon.2016.7456788.
15	BOSCARO A, JACQUIR S, SANCHEZ K, et al. Automatic defect localization in VLSI circuits: a fusionapproach based on the Dempster-Shafer theory. Proc. of the 20th International Conference on Information Fusion, 2017. DOI: 10.23919/ICIF.2017.8009813.
16	ZHOU L. Research on data fusion methods in airborne multi-sensors for target identification. Chengdu: University of Electronic Science and Technology of China, 2018. (in Chinese)
17	ZHANG Z, WANG H F, GENG J, et al An information fusion method based on deep learning and fuzzy discount-weighting for target intention recognition. Engineering Applications of Artificial Intelligence, 2022, 109, 104610. doi: 10.1016/j.engappai.2021.104610
18	LIU Z An evidential sine similarity measure for multisensor data fusion with its applications. Granular Computing, 2024, 9 (1): 4. doi: 10.1007/s41066-023-00426-6
19	HE Y. Multi-sensor information fusion. Beijing: Electronic Industry Press, 2000. (in Chinese)
20	LIU Y F. Research of information fusion algorithm based on evidence theory in open frame of discernment. Changsha: Hunan University, 2017. (in Chinese)
21	HE Y, WANG G H. Multi-sensor data fusion and application. Beijing: Electronic Industry Press, 2007. (in Chinese)
22	LIU Z G, CHENG Y M, PAN Q, et al Weight evidence combination for multi-sensor conflict information. Sensors and Actuators, 2009, 22 (3): 366- 370.
23	LIU Z G, PAN Q, et al. Uncertain data trust classification and fusion. Beijing: Science Press, 2016. (in Chinese)
24	DANIEL M. Conflicts within and between belief functions. Proc. of the International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, 2010: 696−705.
25	ZHANG Y. Research on perceived target classification based on decision fusion in wireless sensor networks. Beijing: Beijing Jiaotong University, 2019. (in Chinese)
26	XIAO J Y, TONG M M, ZHU C J, et al Improved combination rule of evidence based on pignistic probability distance. Journal of Shanghai Jiao Tong University, 2012, 46 (4): 636- 641, 645.

Type	Distance/km	Speed/(m·s⁻¹)	Altitude/km	Heading/(°)
Attack	10−20	400−700	3−10	300−60
Penetration	20−30	300−800	1−3	55−125
Reconnaissance	30−50	200−300	2−8	300−60
Withdrawal	10−50	500−800	1−5	150−210

Algorithm	Inconsistency among the evidence	Inconsistency within the evidence	Time	Information entropy
Fusion algorithm 1	−	−	−	−
Fusion algorithm 2	√	−	−	−
Fusion algorithm 3	−	−	√	−
Fusion algorithm 4	√	−	√	−
Fusion algorithm 5	√	√	√	−
Fusion algorithm 6	√	−	√	√
The proposed algorithm	√	√	√	√

Algorithm	Mean accuracy	Maximum accuracy
Fusion algorithm 1	74.214	76.125
Fusion algorithm 2	74.333	76.125
Fusion algorithm 3	73.349	75.000
Fusion algorithm 4	74.776	76.125
Fusion algorithm 5	74.750	76.250
Fusion algorithm 6	75.859	77.125
Fusion algorithm 7	74.055	75.875
The proposed algorithm	76.224	78.375

Algorithm	Mean accuracy	Maximum accuracy
Fusion algorithm 1	74.214	76.125
Fusion algorithm 2	76.297	78.250
Fusion algorithm 3	76.396	77.125
Fusion algorithm 4	77.016	78.000
Fusion algorithm 5	77.349	78.375
Fusion algorithm 6	77.229	78.250
Fusion algorithm 7	75.936	77.875
The proposed algorithm	77.724	79.125

[1]	Chengkun LUO, Yunxiang CHEN, Huachun XIANG, Weijia WANG, Zezhou WANG. Evidence combination method in time domain based on reliability and importance [J]. Journal of Systems Engineering and Electronics, 2018, 29(6): 1308-1316.
[2]	Hongfei Li, Hongbin Jin, and Kangsheng Tian. Evidence fusion procedure based on hybrid DSm model [J]. Journal of Systems Engineering and Electronics, 2014, 25(6): 959-967.

Improved spatio-temporal evidence fusion for radar aerial target tactical intention recognition

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 9

References 26

Related Articles 2

Recommended Articles

Metrics

Comments