UAV data link anti-interference via SLHS-SVM-AdaBoost algorithm: Classification prediction and route planning

Abstract

The ability to predict the anti-interference communications performance of unmanned aerial vehicle (UAV) data links is critical for intelligent route planning of UAVs in real combat scenarios. Previous research in this area has encountered several limitations: Classifiers exhibit low training efficiency, their precision is notably reduced when dealing with imbalanced samples, and they cannot be applied to the condition where the UAV’s flight altitude and the antenna bearing vary. This paper proposes the sequential Latin hypercube sampling (SLHS)-support vector machine (SVM)-AdaBoost algorithm, which enhances the training efficiency of the base classifier and circumvents local optima during the search process through SLHS optimization. Additionally, it mitigates the bottleneck of sample imbalance by adjusting the sample weight distribution using the AdaBoost algorithm. Through comparison, the modeling efficiency, prediction accuracy on the test set, and macro-averaged values of Precision, Recall, and F1-score for SLHS-SVM-AdaBoost are improved by 22.7%, 5.7%, 36.0%, 25.0%, and 34.2%, respectively, compared with Grid-SVM. Additionally, these values are improved by 22.2%, 2.1%, 11.3%, 2.8%, and 7.4%, respectively, compared with particle swarm optimization (PSO)-SVM-AdaBoost. Combining Latin hypercube sampling with the SLHS-SVM-AdaBoost algorithm, the classification prediction model of anti-interference performance of UAV data links, which took factors like three-dimensional space position of UAV and antenna bearing into consideration, is established and used to assess the safety of the classical flying path and optimize the flying route. It was found that the risk of loss of communications could not be completely avoided by adjusting the flying altitude based on the classical path, and that intelligent path planning based on the classification prediction model of anti-interference performance can realize complete avoidance of being interfered while reducing the route length by at least 2.3%, thus benefiting both safety and operation efficiency.

Keywords

AdaBoost / Anti-interference performance / Classification prediction / Data link / Route planning / Sequential Latin hypercube sampling / Unmanned aerial vehicle (UAV)

Declaration of competing interest

No potential conflict of interest was reported by the authors.

References

[1] X.-Y. Wang, M.C. Gursoy, Resilient path planning for UAVs in data collection under adversarial attacks, IEEE T. Inf. Foren. Sec. 18 (Apr. 2023) 2766-2779.

[2] L.-Y. Zhou, X.-T. Zhao, X. Guan, E.-B. Song, X. Zeng, Q.-J. Shi, Robust trajectory planning for UAV communication systems in the presence of jammers, Chinese J. Aeronaut. 35 (10) (Oct. 2022) 265-274.

[3] G.C. Batista, J. Öberg, O. Saotome, H.F. de Campos Velho, E.H. Shiguemori, I. Söderquist, Machine learning algorithm partially reconfigured on FPGA for an image edge detection system, Journal of Electronic Science and Technology 22 (2) (Jun. 2024) 100248:1-21.

[4] Y.-Y. Su, N. Qi, Z.-Q. Huang, R.-G. Yao, L.-L. Jia, Cooperative anti-jamming and interference mitigation for UAV networks: A local altruistic game approach, China Commun. 21 (2) (Feb. 2024) 183-196.

[5] H.-C. Wang, G.-R. Ding, J. Chen, Y.-L. Zou, F.-F. Gao, UAV anti-jamming communications with power and mobility control, IEEE T. Wirel. Commun. 22 (7) (Jul. 2023) 4729-4744.

[6] B.-Q. Duan, D. Yin, Y.-R. Cong, H. Zhou, X.-J. Xiang, L.-C. Shen, Anti-jamming path planning for unmanned aerial vehicles with imperfect jammer information, in: Proc. of the IEEE Intl. Conf. on Robotics and Biomimetics, Kuala Lumpur, Malaysia, (2018), pp. 729-735.

[7] Digital Engineering Strategy, Department of Defense Office of the Deputy Assistant Secretary of Defense for Systems Engineering, Washington, DC (2018)

[8] A.F. Mendi, T. Erol, D. Doğan, Digital twin in the military field, IEEE Internet Comput. 26 (5) (Sept.-Oct. 2022) 33-40.

[9] W.-W. Zhang, W.-R. Ding, C.-H. Liu, Prediction of interference effect on UAV data link in complex environment, Syst. Eng. Electron. 38 (4) (Apr. 2016) 760-766.

[10] Calculation of Free-Space Attenuation, Recommendation P.525–4, International Telecommunication Union, Geneva, (2019), p. 3.

[11] D.L. Adamy, EW 103: Tactical Battlefield Communications Electronic Warfare, Artech House, Boston, (2008).

[12] Y. Albagory, F. Alraddady, An efficient recursive multibeam pattern subtraction (MPS) beamformer for planar antenna arrays optimization, Electronics 11 (7) (Mar. 2022) 1015:1-16.

[13] J.-Z. Zhuang, X.-J. Zhang, Z.-S. He, Synthesis of sparse planar arrays with multiple patterns: an automatic coordinate pairing approach, Signal Process. 212 (Nov. 2023) 109161:1-16.

[14] P.-F. Wei, X. Zhang, M. Beer, Adaptive experiment design for probabilistic integration, Comput. Methods Appl. M. 365 (Jun. 2020) 113035:1-17.

[15] H. Li, L.-Q. Yang, M.-Q. Liu, Construction of space-filling orthogonal Latin hypercube designs, Stat. Probabil. Lett. 180 (Jan. 2022) 109245:1-8.

[16] Z. Mehmood, S. Asghar, Customizing SVM as a base learner with AdaBoost ensemble to learn from multi-class problems: A hybrid approach AdaBoost-MSVM, Knowl.-Based Syst. 217 (Apr. 2021) 106845:1-13.

[17] S.-K. Wan, X.-H. Li, Y.-J. Yin, J. Hong, Milling chatter detection by multi-feature fusion and AdaBoost-SVM, Mech. Syst. Signal Pr. 156 (Jul. 2021) 107671:1-15.

[18] R. Li, W.-R. Li, H.-N. Zhang, State of health and charge estimation based on adaptive boosting integrated with particle swarm optimization/support vector machine (AdaBoost-PSO-SVM) model for lithium-ion batteries, Int. J. Electrochem. Sc. 17 (2) (Feb. 2022) 220212:1-17.

[19] W.-C. Huang, H.-Y. Liu, Y. Zhang, et al., Railway dangerous goods transportation system risk identification: Comparisons among SVM, PSO-SVM, GA-SVM and GS-SVM, Appl. Soft Comput. 109 (Sept. 2021) 107541:1-16.

[20] B. Al-Salemi, M. Ayob, G. Kendall, S.A.M. Noah, Multi-label Arabic text categorization: A benchmark and baseline comparison of multi-label learning algorithms, Inform. Process. Manag. 56 (1) (Jan. 2019) 212-227.

[21] R.S. Queiroz, J.P.B. Silva, E.C. das Neves, L.C. da Silva, R.S. Coelho, H.A. Lepikson, Development and fusion of NDT classifiers for defect detection on underwater structures, NDT&E Int. 144 (Jun. 2024) 103098:1-17.

[22] A Practical Guide to Support Vector Classification, Department of Computer Science, National Taiwan University, Taipei, China, (2003).

[23] M.D. Phung, Q.P. Ha, Safety-enhanced UAV path planning with spherical vector-based particle swarm optimization, Appl. Soft Comput. 107 (Aug. 2021) 107376:1-15.

[24] Y. Liu, X.-M. Zhu, X.-Y. Zhang, J.-N. Xiao, X.-H. Yu, RGG-PSO+: random geometric graphs based particle swarm optimization method for UAV path planning, Int. J. Comput. Int. Sys. 17 (1) (May 2024) 127:1-13.

[25] H.-H. Zhang, X.-S. Gan, S.-F. Li, Z.-Y. Chen, UAV safe route planning based on PSO-BAS algorithm, J. Syst. Eng. Electron. 33 (5) (Oct. 2022) 1151-1160.