Task-Incremental Learning for Drone Pilot Identification Scheme
Abstract
:1. Introduction
- We propose a novel incremental learning-based drone pilot identification scheme for protecting drones from impersonation attacks.
- For obtaining high-quality drone flight data, we design a background service to collect the subscribed topics from uORB message bus without altering the hardware and software architecture.
- To adopt dynamic pilot membership management, we construct an extensible framework and propose an updating mechanism for adopting newly joined pilots into the well-established identification scheme.
- Numerous experiments have demonstrated that the proposed scheme can maintain high identification accuracy for newly and previously registered pilots with minimal system overhead.
2. Materials and Methods
2.1. UAV Inner Communication Mechanism
2.2. UAV Pilot Impersonation Attack
2.3. Incremental Learning
2.4. Problem Definition
2.5. Pilot Identification Based on UAV Flight Data
2.5.1. Data Collection and Preprocessing
2.5.2. Drone Pilot Identification
2.5.3. Drone Pilot Identification Updating Mechanism
Algorithm 1: Drone Pilot Identification Updating Algorithm |
1: Start: feature extraction parameters identification parameters for the previous registered pilots added parameters for newly registered pilots newly registered pilot’s drone flight data and their identity 2: Initialize: Pilot Identification RANDINT 3: Train: Define = Pilot Identification() ▹ previous registered pilot identity estimation Define = Pilot Identification() ▹ newly registered pilot identity estimation , , ← () |
3. Results
3.1. Environmental Setting
3.2. The Hardware and Software Architecture
3.3. Drone Pilot Identification Based on P450
3.4. Drone Pilot Identification Based on S500
3.5. Performance Comparison
3.5.1. Comparison with the Related Works
3.5.2. Comparison with the Algorithms Mentioned in Related Works
3.5.3. Comparison with the SOTA Incremental Learning Algorithms
3.6. Time and Space Complexity
4. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
UAV | Unmanned Aerial Vehicle |
GPS | Global Positioning System |
GCS | Ground Control Station |
MEMS | Micro-Electro-Mechanical Systems |
LD | Linear dichroism |
QD | quadratic discriminant |
SVM | Support vector machine |
kNN | K-nearest neighbors |
RF | Random forest |
DT | Decision tree |
LSTM | Long short-term memory |
SGD | Stochastic gradient descent |
ESC | Electronic Speed Controller |
NED | North East Down |
ReLU | Rectification Linear function |
lwf | learning without forget |
ewc | elastic weight consolidation |
mas | memory aware synapses |
SOTA | state-of-the-art work |
References
- Shakeri, R.; Al-Garadi, M.A.; Badawy, A.; Mohamed, A.; Khattab, T.; Al-Ali, A.K.; Harras, K.A.; Guizani, M. Design challenges of multi-UAV systems in cyber-physical applications: A comprehensive survey and future directions. IEEE Commun. Surv. Tutorials 2019, 21, 3340–3385. [Google Scholar] [CrossRef] [Green Version]
- Hassija, V.; Chamola, V.; Agrawal, A.; Goyal, A.; Luong, N.C.; Niyato, D.; Yu, F.R.; Guizani, M. Fast, reliable, and secure drone communication: A comprehensive survey. IEEE Commun. Surv. Tutorials 2021, 23, 2802–2832. [Google Scholar] [CrossRef]
- Eldosouky, A.; Ferdowsi, A.; Saad, W. Drones in distress: A game-theoretic countermeasure for protecting uavs against gps spoofing. IEEE Internet Things J. 2019, 7, 2840–2854. [Google Scholar] [CrossRef] [Green Version]
- Son, Y.; Shin, H.; Kim, D.; Park, Y.; Noh, J.; Choi, K.; Choi, J.; Kim, Y. Rocking drones with intentional sound noise on gyroscopic sensors. In Proceedings of the 24th {USENIX} Security Symposium ({USENIX} Security 15), Washington, DC, USA, 12–14 August 2015; pp. 881–896. [Google Scholar]
- Alladi, T.; Chamola, V.; Zeadally, S. Industrial control systems: Cyberattack trends and countermeasures. Comput. Commun. 2020, 155, 1–8. [Google Scholar] [CrossRef]
- Choudhary, G.; Sharma, V.; Gupta, T.; Kim, J.; You, I. Internet of drones (iod): Threats, vulnerability, and security perspectives. arXiv 2018, arXiv:1808.00203. [Google Scholar]
- Zhang, Y.; He, D.; Li, L.; Chen, B. A lightweight authentication and key agreement scheme for Internet of Drones. Comput. Commun. 2020, 154, 455–464. [Google Scholar] [CrossRef]
- Alladi, T.; Naren; Bansal, G.; Chamola, V.; Guizani, M. SecAuthUAV: A Novel Authentication Scheme for UAV-Ground Station and UAV-UAV Communication. IEEE Trans. Veh. Technol. 2020, 69, 15068–15077. [Google Scholar] [CrossRef]
- Wazid, M.; Das, A.K.; Kumar, N.; Vasilakos, A.V.; Rodrigues, J.J. Design and analysis of secure lightweight remote user authentication and key agreement scheme in internet of drones deployment. IEEE Internet Things J. 2018, 6, 3572–3584. [Google Scholar] [CrossRef]
- Srinivas, J.; Das, A.K.; Kumar, N.; Rodrigues, J.J. TCALAS: Temporal credential-based anonymous lightweight authentication scheme for Internet of drones environment. IEEE Trans. Veh. Technol. 2019, 68, 6903–6916. [Google Scholar] [CrossRef]
- Shoufan, A. Continuous authentication of uav flight command data using behaviometrics. In Proceedings of the 2017 IFIP/IEEE International Conference on Very Large Scale Integration (VLSI-SoC), Abu Dhabi, Saudi Arabia, 23–25 October 2017; pp. 1–6. [Google Scholar]
- Shoufan, A.; Al-Angari, H.M.; Sheikh, M.F.A.; Damiani, E. Drone pilot identification by classifying radio-control signals. IEEE Trans. Inf. Forensics Secur. 2018, 13, 2439–2447. [Google Scholar] [CrossRef]
- Alkadi, R.; Al-Ameri, S.; Shoufan, A.; Damiani, E. Identifying drone operator by deep learning and ensemble learning of imu and control data. IEEE Trans. Hum. Mach. Syst. 2021, 51, 451–462. [Google Scholar] [CrossRef]
- Balakrishnama, S.; Ganapathiraju, A. Linear discriminant analysis-a brief tutorial. Inst. Signal Inf. Process. 1998, 18, 1–8. [Google Scholar]
- Tharwat, A. Linear vs. quadratic discriminant analysis classifier: A tutorial. Int. J. Appl. Pattern Recognit. 2016, 3, 145–180. [Google Scholar] [CrossRef]
- Suthaharan, S.; Suthaharan, S. Support vector machine. In Machine Learning Models and Algorithms for Big Data Classification: Thinking With Examples for Effective Learning; Springer: Berlin/Heidelberg, Germany, 2016; pp. 207–235. [Google Scholar]
- Tan, S. Neighbor-weighted k-nearest neighbor for unbalanced text corpus. Expert Syst. Appl. 2005, 28, 667–671. [Google Scholar] [CrossRef] [Green Version]
- Belgiu, M.; Drăguţ, L. Random forest in remote sensing: A review of applications and future directions. ISPRS J. Photogramm. Remote. Sens. 2016, 114, 24–31. [Google Scholar] [CrossRef]
- Hochreiter, S.; Schmidhuber, J. Long short-term memory. Neural Comput. 1997, 9, 1735–1780. [Google Scholar] [CrossRef]
- Nanopoulos, A.; Alcock, R.; Manolopoulos, Y. Feature-based classification of time-series data. Int. J. Comput. Res. 2001, 10, 49–61. [Google Scholar]
- Gopinath, B.; Gupt, B. Majority voting based classification of thyroid carcinoma. Procedia Comput. Sci. 2010, 2, 265–271. [Google Scholar] [CrossRef] [Green Version]
- Chen, T.; Guestrin, C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; pp. 785–794. [Google Scholar]
- Kwak, B.I.; Han, M.L.; Kim, H.K. Driver identification based on wavelet transform using driving patterns. IEEE Trans. Ind. Inform. 2020, 17, 2400–2410. [Google Scholar] [CrossRef]
- Hallac, D.; Sharang, A.; Stahlmann, R.; Lamprecht, A.; Huber, M.; Roehder, M.; Leskovec, J.; Sosic, R. Driver identification using automobile sensor data from a single turn. In Proceedings of the 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), Rio de Janeiro Brazil, 1–4 November 2016; pp. 953–958. [Google Scholar]
- Meier, L.; Honegger, D.; Pollefeys, M. PX4: A node-based multithreaded open source robotics framework for deeply embedded platforms. In Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA), Seattle, WA, USA, 26–30 May 2015; pp. 6235–6240. [Google Scholar]
- Wei, H.; Shao, Z.; Huang, Z.; Chen, R.; Guan, Y.; Tan, J.; Shao, Z. RT-ROS: A real-time ROS architecture on multi-core processors. Future Gener. Comput. Syst. 2016, 56, 171–178. [Google Scholar] [CrossRef]
- Willner, D.; Chang, C.; Dunn, K. Kalman filter algorithms for a multi-sensor system. In Proceedings of the 1976 IEEE Conference on Decision and Control Including the 15th Symposium on Adaptive Processes, Clearwater, FL, USA, 1–3 December 1976; pp. 570–574. [Google Scholar]
- Schlimmer, J.C.; Fisher, D. A case study of incremental concept induction. Proc. AAAI 1986, 86, 496–501. [Google Scholar]
- Kirkpatrick, J.; Pascanu, R.; Rabinowitz, N.; Veness, J.; Desjardins, G.; Rusu, A.A.; Milan, K.; Quan, J.; Ramalho, T.; Grabska-Barwinska, A.; et al. Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. USA 2017, 114, 3521–3526. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Aljundi, R.; Babiloni, F.; Elhoseiny, M.; Rohrbach, M.; Tuytelaars, T. Memory aware synapses: Learning what (not) to forget. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 139–154. [Google Scholar]
- Wolf, T.; Debut, L.; Sanh, V.; Chaumond, J.; Delangue, C.; Moi, A.; Cistac, P.; Rault, T.; Louf, R.; Funtowicz, M.; et al. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Online, 16–20 November 2020; pp. 38–45. [Google Scholar]
- Li, Z.; Hoiem, D. Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 40, 2935–2947. [Google Scholar] [CrossRef] [Green Version]
- Rebuffi, S.A.; Kolesnikov, A.; Sperl, G.; Lampert, C.H. icarl: Incremental classifier and representation learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 2001–2010. [Google Scholar]
- Wu, Y.; Chen, Y.; Wang, L.; Ye, Y.; Liu, Z.; Guo, Y.; Fu, Y. Large scale incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 374–382. [Google Scholar]
- Chandrashekar, G.; Sahin, F. A survey on feature selection methods. Comput. Electr. Eng. 2014, 40, 16–28. [Google Scholar] [CrossRef]
- Xun, Y.; Liu, J.; Kato, N.; Fang, Y.; Zhang, Y. Automobile driver fingerprinting: A new machine learning based authentication scheme. IEEE Trans. Ind. Inform. 2019, 16, 1417–1426. [Google Scholar] [CrossRef]
- LeCun, Y.; Bottou, L.; Bengio, Y.; Haffner, P. Gradient-based learning applied to document recognition. Proc. IEEE 1998, 86, 2278–2324. [Google Scholar] [CrossRef] [Green Version]
- Li, Y.; Yuan, Y. Convergence analysis of two-layer neural networks with relu activation. Adv. Neural Inf. Process. Syst. 2017, 30. [Google Scholar]
- Bottou, L. Stochastic gradient descent tricks. In Neural Networks: Tricks of the Trade: Second Edition; Springer: Berlin/Heidelberg, Germany, 2012; pp. 421–436. [Google Scholar]
- Hinton, G.; Vinyals, O.; Dean, J. Distilling the knowledge in a neural network. arXiv 2015, arXiv:1503.02531. [Google Scholar]
- Syarif, I.; Prugel-Bennett, A.; Wills, G. SVM parameter optimization using grid search and genetic algorithm to improve classification performance. TELKOMNIKA (Telecommun. Comput. Electron. Control) 2016, 14, 1502–1509. [Google Scholar] [CrossRef]
- Donahue, J.; Jia, Y.; Vinyals, O.; Hoffman, J.; Zhang, N.; Tzeng, E.; Darrell, T. Decaf: A deep convolutional activation feature for generic visual recognition. In Proceedings of the International Conference on Machine Learning, PMLR, Beijing, China, 21–26 June 2014; pp. 647–655. [Google Scholar]
- Girshick, R.; Donahue, J.; Darrell, T.; Malik, J. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 23–28 June 2014; pp. 580–587. [Google Scholar]
- Liu, M.; Wang, J.; Zhao, N.; Chen, Y.; Song, H.; Yu, F.R. Radio frequency fingerprint collaborative intelligent identification using incremental learning. IEEE Trans. Netw. Sci. Eng. 2021, 9, 3222–3233. [Google Scholar] [CrossRef]
- Liu, Y.; Wang, J.; Li, J.; Niu, S.; Song, H. Class-incremental learning for wireless device identification in IoT. IEEE Internet Things J. 2021, 8, 17227–17235. [Google Scholar] [CrossRef]
- Chua, L.O. CNN: A vision of complexity. Int. J. Bifurc. Chaos 1997, 7, 2219–2425. [Google Scholar] [CrossRef]
Topic | Attribute | Minimize | Maximize | Frequency | Description |
---|---|---|---|---|---|
received instructions | values[0:4] | 1200 | 1800 | 2 Hz | pilot |
instructions | |||||
executor control | controls[0:4] | 0.5 | 1.5 | 20 Hz | flight controller |
instructions | |||||
actuator output | output[0:4] | 900 | 2100 | 10 Hz | instructions for |
ESC | |||||
accelerator | x, y, z | −30 | 30 | 1 Hz | acceleration in |
body frame | |||||
gyroscope | x, y, z | −5 | 5 | 1 Hz | angular velocity |
in body frame | |||||
magnetometer | x, y, z | −2 | 2 | 1 Hz | magnet in |
NED | |||||
angular velocity | xyz[0:3] | −5 | 5 | 100 Hz | angular velocity |
in NED | |||||
local attitude | q[0:4] | −1 | 1 | 10 Hz | flight attitude |
in quaternions |
UAV | Environment | Participates | Routines | Samples | |
---|---|---|---|---|---|
1 | P450 | Nature | 15 | 150 | 65,337 |
Constrained | 61,370 | ||||
2 | S500 | Nature | 15 | 150 | 62,118 |
Constrained | 58,921 |
T1 | T2 | T3 | T4 | T5 | T6 | T7 | T8 | T9 | T10 | T11 | T12 | T13 | T14 | T15 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
P1 | 100.0 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. |
97.73 | 0. | 0. | 0.81 | 0. | 0.28 | 0. | 1.11 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | |
P2 | 0. | 99.12 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0.81 | 0. | 0. | 0. | 0. |
0. | 99.43 | 0. | 0. | 0. | 0.56 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | |
P3 | 0. | 0. | 88.78 | 0. | 0. | 0. | 0. | 0. | 11.23 | 0. | 0. | 0. | 0. | 0. | 0. |
0. | 0. | 98.91 | 1.12 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | |
P4 | 0. | 0. | 0. | 95.54 | 0. | 0. | 0. | 0. | 0. | 0. | 3.98 | 0.54 | 0. | 0. | 0. |
0. | 0.21 | 0.59 | 99.22 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | |
P5 | 0. | 0. | 0.84 | 0. | 85.12 | 9.71 | 0. | 0. | 0. | 0. | 0. | 1.22 | 0. | 0. | 3.01 |
0. | 0. | 0. | 0. | 97.36 | 0. | 2.67 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | |
P6 | 0. | 0. | 0. | 0. | 0. | 99.24 | 0.76 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. |
0. | 0. | 2.56 | 0. | 0. | 96.23 | 0. | 0. | 1.23 | 0. | 0. | 0. | 0. | 0. | 0. | |
P7 | 0. | 0. | 0. | 0. | 0. | 8.7 | 91.22 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. |
0. | 0. | 0. | 0. | 0. | 0. | 98.22 | 0. | 0. | 1.75 | 0. | 0. | 0. | 0. | 0. | |
P8 | 0. | 0.74 | 0. | 0. | 0. | 0. | 0. | 99.2 | 0. | 0. | 0. | 0. | 0. | 0. | 0. |
0. | 0. | 0. | 0. | 0. | 0. | 0. | 100. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | |
P9 | 0. | 0. | 3.92 | 0. | 0. | 2.09 | 0. | 0. | 89.72 | 0. | 0. | 0. | 0. | 0. | 4.13 |
0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 100. | 0. | 0. | 0. | 0. | 0. | 0. | |
P10 | 0. | 0. | 0. | 21.72 | 0. | 0. | 0. | 0. | 0. | 73.54 | 3.54 | 0. | 0. | 1.08 | 0. |
0. | 0. | 0. | 0. | 0.46 | 0. | 0. | 0. | 0. | 98.32 | 0. | 0. | 1.22 | 0. | 0. | |
P11 | 0. | 0. | 0. | 0.65 | 0. | 0. | 0. | 0. | 0. | 1.08 | 87.82 | 9.78 | 0. | 0. | 0.65 |
0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 3.09 | 0.71 | 96.22 | 0. | 0. | 0. | 0. | |
P12 | 0. | 0. | 0. | 3.78 | 0. | 0. | 0. | 0. | 0. | 0. | 7.14 | 89.12 | 0. | 0. | 0. |
0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 100. | 0. | 0. | 0. | |
P13 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 100. | 0. | 0. |
0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 100. | 0. | 0. | |
P14 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 100. | 0. |
0.13 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0.14 | 0. | 99.36 | 0.43 | |
P15 | 0. | 0. | 0. | 0. | 0. | 2.26 | 0. | 0. | 0. | 0. | 0. | 2.95 | 0. | 0. | 94.72 |
0. | 0. | 0. | 0. | 0. | 1.45 | 0. | 0. | 0. | 0. | 0. | 0.62 | 0. | 0. | 97.92 |
T1 | T2 | T3 | T4 | T5 | T6 | T7 | T8 | T9 | T10 | T11 | T12 | T13 | T14 | T15 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
P1 | 100.0 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. |
94.56 | 0. | 0. | 0. | 0. | 5.44 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | |
P2 | 0. | 91.54 | 0. | 0. | 0. | 0.12 | 0. | 0. | 0. | 0.24 | 0. | 6.67 | 0. | 0. | 1.43 |
0. | 96.07 | 0.95 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 2.26 | 0. | 0. | 0.72 | |
P3 | 0. | 10.01 | 88.49 | 0. | 0. | 0. | 0. | 0. | 0. | 0.15 | 0. | 0. | 0. | 0. | 1.35 |
0. | 7.74 | 91.48 | 0. | 0. | 0. | 0. | 0. | 0. | 1.05 | 0. | 0. | 0. | 0. | 0. | |
P4 | 0. | 0. | 0. | 100. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. |
0. | 0. | 0. | 100. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | |
P5 | 0.42 | 0. | 0. | 0. | 91.98 | 0. | 0.42 | 0. | 0. | 0. | 0. | 0. | 0. | 7.17 | 0. |
0. | 0. | 0. | 0. | 97.47 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 2.53 | 0. | |
P6 | 0. | 0. | 0. | 0. | 0. | 98.52 | 0.59 | 0. | 0. | 0. | 0. | 0.89 | 0. | 0. | 0. |
0.15 | 0. | 0. | 0. | 0. | 95.72 | 0. | 0. | 0. | 0. | 0. | 3.69 | 0. | 0.44 | 0. | |
P7 | 0. | 0. | 0. | 0.2 | 0. | 0. | 99.8 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. |
0. | 0. | 0. | 4.88 | 0. | 0. | 93.09 | 0. | 0. | 0. | 0. | 2.03 | 0. | 0. | 0. | |
P8 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 96.98 | 0. | 0. | 0. | 0. | 3.02 | 0. | 0. |
0. | 0. | 0. | 0. | 0. | 0. | 0. | 92.58 | 0. | 0. | 0. | 0. | 7.42 | 0. | 0. | |
P9 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 91.53 | 0. | 6.88 | 0. | 0. | 1.59 | 0. |
0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 97.62 | 0. | 2.38 | 0. | 0. | 0. | 0. | |
P10 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 100. | 0. | 0. | 0. | 0. | 0. |
0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 100. | 0. | 0. | 0. | 0. | 0. | |
P11 | 0. | 0. | 0. | 0. | 4.3 | 0. | 0.2 | 0. | 0. | 0. | 95.49 | 0. | 0. | 0. | 0. |
0. | 0. | 0. | 0. | 8.81 | 0. | 1.23 | 0. | 0. | 0. | 89.55 | 0. | 0. | 0.2 | 0.2 | |
P12 | 0. | 0.67 | 0. | 0. | 0. | 10.72 | 0. | 0. | 0. | 0. | 0. | 88.47 | 0. | 0. | 0.13 |
0. | 0. | 0. | 0. | 0. | 17.69 | 0. | 0. | 0. | 0. | 0. | 82.17 | 0. | 0. | 0.13 | |
P13 | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 0. | 1.79 | 0. | 98.21 | 0. | 0. |
0. | 0. | 0. | 0. | 0. | 0. | 0. | 0.32 | 0. | 0. | 0. | 0. | 99.68 | 0. | 0. | |
P14 | 4.89 | 0. | 0. | 0. | 3.33 | 0. | 1.11 | 0. | 0. | 0. | 0. | 0. | 0. | 90.22 | 0.44 |
1.56 | 0. | 0. | 0. | 0.44 | 0. | 0. | 0. | 0.22 | 0. | 0. | 0. | 0. | 97.56 | 0.22 | |
P15 | 0.42 | 2.51 | 0.31 | 0. | 0. | 0. | 0. | 2.93 | 0. | 0.1 | 0. | 0.52 | 1.26 | 0. | 91.94 |
0. | 3.56 | 0. | 0. | 0. | 0. | 0.73 | 0. | 0. | 0. | 0. | 1.99 | 0. | 0. | 93.72 |
Environment | Objectiveness | Pilots | Signals | UAV | Extensible | Accuracy | |
---|---|---|---|---|---|---|---|
Soufan (2017) [11] | Robotic lab | Authentication | 5 | Pilot instructions | quadcopter | No | 82% |
Soufan (2018) [12] | Identification | 20 | 89% | ||||
Alkadi (2021) [13] | Authentication | 20 | Pilot instructions motion sensors | Yes | 97% | ||
Ours | Controlled & Natural environment | Identification | 15 | uORB topics | 95.71% |
T1 | T2 | T3 | T4 | T5 | T6 | T7 | T8 | T9 | T10 | T11 | T12 | T13 | T14 | T15 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
QD [12] | 42.14 | 57.09 | 93.72 | 93.99 | 86.74 | 79.36 | 59.63 | 95.48 | 59.07 | 46.11 | 63.52 | 72.81 | 43.66 | 45.84 | 22.72 |
45.32 | 63.98 | 90.47 | 87.71 | 75.43 | 82.11 | 68.55 | 90.53 | 49.67 | 51.92 | 60.34 | 69.17 | 60.22 | 58.11 | 39.73 | |
RF [12] | 29.82 | 85.69 | 49.13 | 93.48 | 71.08 | 51.32 | 45.49 | 92.37 | 89.87 | 68.88 | 79.67 | 53.97 | 79.87 | 72.74 | 58.74 |
35.77 | 74.51 | 45.49 | 90.32 | 59.77 | 59.14 | 52.88 | 82.17 | 80.15 | 69.87 | 62.29 | 55.41 | 78.32 | 63.33 | 51.25 | |
Bagging [12] | 47.12 | 20.05 | 19.58 | 99.82 | 61.18 | 53.17 | 42.27 | 80.61 | 33.86 | 92.08 | 76.02 | 83.19 | 63.89 | 23.16 | 22.26 |
40.11 | 30.79 | 17.98 | 80.34 | 53.27 | 59.16 | 38.65 | 76.44 | 30.78 | 82.17 | 77.29 | 87.44 | 62.63 | 30.35 | 29.87 | |
DT [12] | 18.48 | 66.86 | 97.11 | 90.29 | 81.29 | 36.51 | 71.51 | 27.11 | 27.42 | 23.33 | 47.08 | 15.89 | 76.94 | 48.73 | 31.62 |
23.88 | 60.64 | 84.87 | 75.91 | 71.17 | 45.35 | 82.44 | 34.47 | 31.82 | 38.65 | 45.22 | 19.97 | 49.12 | 59.88 | 19.65 | |
LSTM [13] | 91.73 | 94.41 | 92.89 | 93.32 | 89.35 | 95.52 | 93.22 | 94.44 | 93.37 | 96.53 | 94.16 | 95.12 | 96.16 | 94.47 | 96.61 |
94.42 | 91.99 | 95.25 | 94.17 | 93.89 | 95.11 | 98.22 | 93.77 | 92.29 | 91.88 | 94.37 | 94.41 | 95.33 | 94.48 | 94.37 | |
Feature [13] | 47.21 | 68.45 | 92.73 | 95.41 | 89.98 | 83.67 | 82.81 | 79.49 | 85.62 | 81.66 | 76.27 | 80.35 | 62.51 | 74.88 | 61.67 |
55.32 | 77.45 | 82.62 | 85.68 | 91.98 | 85.33 | 92.41 | 89.55 | 65.77 | 84.32 | 79.31 | 90.41 | 83.15 | 65.97 | 71.72 | |
Voted [13] | 58.95 | 61.26 | 84.31 | 93.82 | 100. | 70.45 | 98.37 | 68.36 | 46.03 | 49.05 | 41.59 | 10.98 | 72.56 | 66.94 | 36.18 |
60.45 | 60.57 | 84.62 | 94.51 | 95.27 | 71.34 | 98.44 | 64.52 | 41.27 | 49.61 | 39.85 | 12.51 | 71.19 | 68.48 | 33.75 | |
SVM [23] | 76.02 | 63.17 | 98.21 | 100. | 90.21 | 79.38 | 90.45 | 99.65 | 89.94 | 100. | 84.24 | 56.25 | 92.93 | 91.52 | 90.24 |
81.41 | 73.52 | 95.35 | 94.24 | 85.45 | 68.97 | 84.33 | 93.12 | 91.47 | 84.71 | 87.24 | 58.12 | 89.93 | 93.71 | 94.14 | |
XGB [23] | 93.72 | 92.75 | 95.25 | 91.88 | 94.55 | 70.18 | 98.32 | 94.51 | 94.84 | 95.57 | 72.13 | 89.33 | 94.71 | 99.72 | 95.21 |
88.95 | 94.17 | 85.93 | 92.08 | 99.55 | 82.18 | 96.11 | 93.42 | 89.88 | 85.99 | 82.13 | 90.16 | 88.35 | 94.32 | 96.17 | |
RF [23] | 94.76 | 99.88 | 96.56 | 91.92 | 95.45 | 80.53 | 95.21 | 91.19 | 92.45 | 98.06 | 95.45 | 50.81 | 63.82 | 94.61 | 95.17 |
97.33 | 92.85 | 93.71 | 90.45 | 93.16 | 84.33 | 93.35 | 93.39 | 94.17 | 95.21 | 94.42 | 63.22 | 73.41 | 91.18 | 94.57 | |
Ours | 100. | 99.12 | 88.78 | 95.54 | 85.12 | 99.24 | 91.22 | 99.24 | 89.72 | 73.54 | 87.82 | 89.12 | 100. | 100. | 94.72 |
97.73 | 99.43 | 98.91 | 99.22 | 97.36 | 96.23 | 98.22 | 100. | 100. | 98.32 | 96.22 | 100. | 100. | 99.36 | 97.92 |
T1 | T2 | T3 | T4 | T5 | T6 | T7 | T8 | T9 | T10 | T11 | T12 | T13 | T14 | T15 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
QD [12] | 22.72 | 56.73 | 63.52 | 93.99 | 63.29 | 45.19 | 35.77 | 92.51 | 79.36 | 93.72 | 59.63 | 20.37 | 67.14 | 86.44 | 35.18 |
35.22 | 53.47 | 60.82 | 88.31 | 55.37 | 42.44 | 38.95 | 88.74 | 81.52 | 91.33 | 50.11 | 19.47 | 55.25 | 83.44 | 39.13 | |
RF [12] | 60.12 | 56.61 | 81.01 | 91.25 | 97.89 | 69.71 | 93.91 | 69.38 | 49.73 | 49.03 | 40.61 | 12.56 | 72.38 | 65.53 | 33.59 |
64.24 | 62.88 | 85.49 | 90.37 | 89.72 | 73.41 | 92.33 | 72.17 | 50.58 | 59.45 | 38.11 | 15.41 | 78.32 | 63.27 | 41.62 | |
Bagging [12] | 34.19 | 52.56 | 93.33 | 99.82 | 86.56 | 32.27 | 77.25 | 24.57 | 58.64 | 41.55 | 27.21 | 61.92 | 57.14 | 34.29 | 48.48 |
46.11 | 48.47 | 87.88 | 90.34 | 83.55 | 29.99 | 68.65 | 26.14 | 49.78 | 52.51 | 28.49 | 57.44 | 62.63 | 30.35 | 59.87 | |
DT [12] | 33.88 | 20.64 | 84.87 | 85.91 | 84.17 | 45.35 | 56.61 | 74.47 | 51.82 | 49.49 | 35.22 | 79.31 | 62.12 | 63.22 | 52.65 |
45.14 | 36.51 | 77.62 | 92.33 | 75.98 | 52.17 | 67.32 | 82.13 | 58.77 | 48.65 | 33.11 | 57.41 | 82.54 | 61.17 | 56.18 | |
LSTM [13] | 87.73 | 92.41 | 88.89 | 89.22 | 93.35 | 94.35 | 91.77 | 88.48 | 93.37 | 95.21 | 91.11 | 89.12 | 89.97 | 93.32 | 91.44 |
89.45 | 93.02 | 85.17 | 91.44 | 97.02 | 91.38 | 88.53 | 91.92 | 94.44 | 93.38 | 85.61 | 77.38 | 88.47 | 95.19 | 92.03 | |
Feature [13] | 55.13 | 58.41 | 72.71 | 95.32 | 89.98 | 82.75 | 77.95 | 89.41 | 85.36 | 91.52 | 76.27 | 87.39 | 91.51 | 86.47 | 82.21 |
49.33 | 59.35 | 63.92 | 95.41 | 84.12 | 73.99 | 62.37 | 85.47 | 76.11 | 93.37 | 85.11 | 82.35 | 83.44 | 84.18 | 81.67 | |
Voted [13] | 34.39 | 92.61 | 49.13 | 96.36 | 68.71 | 47.35 | 43.64 | 98.31 | 97.04 | 88.62 | 83.25 | 63.17 | 80.35 | 74.36 | 57.91 |
29.45 | 89.57 | 51.62 | 94.51 | 75.27 | 51.34 | 44.44 | 84.52 | 91.27 | 89.61 | 79.85 | 62.51 | 85.19 | 68.48 | 53.75 | |
SVM [23] | 90.05 | 85.93 | 85.36 | 91.92 | 92.82 | 80.68 | 88.31 | 98.32 | 89.02 | 89.77 | 98.81 | 94.56 | 64.77 | 78.72 | 74.97 |
86.41 | 83.17 | 75.35 | 94.24 | 90.21 | 79.38 | 90.45 | 93.62 | 89.88 | 94.71 | 84.24 | 86.25 | 61.93 | 73.71 | 80.24 | |
XGB [23] | 93.34 | 92.21 | 91.17 | 92.04 | 89.88 | 98.67 | 68.85 | 96.31 | 65.82 | 96.61 | 94.13 | 92.52 | 60.38 | 93.32 | 93.19 |
93.72 | 92.75 | 95.25 | 91.88 | 94.55 | 70.18 | 98.32 | 94.51 | 94.84 | 95.57 | 72.13 | 89.33 | 94.71 | 99.72 | 95.21 | |
RF [23] | 91.95 | 93.37 | 90.44 | 96.12 | 89.03 | 98.41 | 36.68 | 100. | 75.11 | 96.66 | 96.41 | 88.79 | 99.51 | 100. | 97.38 |
92.37 | 90.48 | 93.71 | 91.92 | 95.45 | 80.53 | 95.21 | 91.19 | 92.45 | 98.06 | 95.45 | 50.81 | 63.82 | 94.61 | 95.17 | |
Ours | 100. | 91.54 | 88.49 | 100. | 91.98 | 98.52 | 99.81 | 96.98 | 91.53 | 100. | 95.49 | 88.47 | 98.21 | 90.22 | 91.94 |
94.56 | 96.07 | 91.48 | 100. | 97.47 | 95.72 | 93.09 | 92.58 | 97.62 | 100. | 89.55 | 82.17 | 99.68 | 97.56 | 93.72 |
7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | |
---|---|---|---|---|---|---|---|---|---|
lwf [32] | 97.58 | 93.44 | 89.26 | 83.12 | 76.45 | 72.22 | 68.27 | 64.66 | 61.25 |
96.41 | - | 89.33 | - | 81.12 | - | 76.19 | - | 64.25 | |
97.33 | - | - | - | 83.39 | - | - | - | 65.58 | |
ewc [29] | 98.22 | 95.36 | 92.41 | 88.99 | 85.68 | 84.44 | 83.39 | 83.22 | 81.08 |
99.18 | - | 93.46 | - | 87.75 | - | 84.44 | - | 82.08 | |
97.32 | - | - | - | 85.59 | - | - | - | 83.14 | |
mas [30] | 98.11 | 95.45 | 88.67 | 85.44 | 82.21 | 74.65 | 69.91 | 65.44 | 60.12 |
97.26 | - | 86.12 | - | 75.34 | - | 67.22 | - | 63.72 | |
97.12 | - | - | - | 79.11 | - | - | - | 64.41 | |
ours | 98.02 | 98.76 | 98.02 | 97.51 | 95.52 | 94.49 | 94.22 | 93.98 | 92.94 |
99.02 | - | 97.33 | - | 94.46 | - | 93.18 | - | 93.18 | |
97.94 | - | - | - | 95.67 | - | - | - | 92.94 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Han, L.; Zhong, X.; Zhang, Y. Task-Incremental Learning for Drone Pilot Identification Scheme. Sensors 2023, 23, 5981. https://doi.org/10.3390/s23135981
Han L, Zhong X, Zhang Y. Task-Incremental Learning for Drone Pilot Identification Scheme. Sensors. 2023; 23(13):5981. https://doi.org/10.3390/s23135981
Chicago/Turabian StyleHan, Liyao, Xiangping Zhong, and Yanning Zhang. 2023. "Task-Incremental Learning for Drone Pilot Identification Scheme" Sensors 23, no. 13: 5981. https://doi.org/10.3390/s23135981
APA StyleHan, L., Zhong, X., & Zhang, Y. (2023). Task-Incremental Learning for Drone Pilot Identification Scheme. Sensors, 23(13), 5981. https://doi.org/10.3390/s23135981