Machine Learning for RF Fingerprinting Extraction . . .
203
6 Conclusion
This paper proposed a classification method by integrating different RF fingerprint features and unique classifiers and carried out extensive experiments to
evaluate the performance. The contribution and novelty are three aspects. First,
six different features in three special fields are adopted and found effective in
classifying four terminals. Second, three classifiers were utilized to adaptively
integrating features with the weights. Finally, a test bed consistsing of low-cost
USRP devices as transceivers were constructed. Compared to the existing work,
much more experiments were carried out to evaluate the performance of RF fingerprint under different channel conditions. In addition to bagged tree, weighted
KNN such good classifiers, we will also design a more robust classifier by taking into account channel influences. Furthermore, the application of machine
learning in signal fingerprinting [11] will be considered in our future work.
Acknowledgements. This work was supported in part by the National Key R&D
Program of China under Grant 2018YFC0807101, in part by the National Natural Science Foundation of China under Grant 61701503/61571082, and in part by the Ministry
of Science and Technology of China (MOST) Program of International S&T Cooperation under Grant 2016YFE0123200. The work of S. Hu was supported in part by
National Natural Science Foundation of China through the Research Fund for International Young Scientists under Grant 61750110527.
References
1. Hariyanto, Sudiro SA, Lukman S (2015) Minutiae matching algorithm using artificial neural network for fingerprint recognition. In: Proceedings of the 2015 3rd international conference on artificial intelligence, modelling and simulation (AIMS),
Kota Kinabalu, Malaysia, Dec 2015
2. Cripps SC (2000) RF power amplifiers for wireless communications. IEEE Microw
Mag 1(1):64–64
3. Eagle N, Pentland A (2006) Reality mining: sensing complex social systems. Pers
Ubiquit Comput 10(4):255–268
4. Kennedy IO, Scanlon P, Mullany FJ, Buddhikot MM, Nolan KE, Rondeau TW
(2008) Radio transmitter fingerprinting: a steady state frequency domain approach.
In: Proceedings of the IEEE 68th vehicular technology conference (VTC), Calgary,
BC, Canada, Sept 2008
5. Uzundurukan E, Ali AM, Kara A (2017) Design of low-cost modular RF front
end for RF fingerprinting of bluetooth signals. In: Proceedings of the 25th signal
processing and communications applications conference (SIU), Antalya, Turkey
6. Bertoncini C, Rudd K, Nousain B, Hinders M (2012) Wavelet fingerprinting of
radio-frequency identification (RFID) tags. IEEE Trans Ind Electron 59(12):4843–
4850
7. Rehman SU, Alam S, Ardekani IT (2014) An overview of radio frequency fingerprinting for low-end devices. In: Proceedings of the IGI Global
8. Wu L, Zhao YQ, Wang Z, Abdalla FYO, Ren GH (2017) Specific emitter identification using fractal features based on box-counting dimension and variance dimension. In: Proceedings of the 2017 IEEE international symposium on signal processing and information technology (ISSPIT), Bilbao, Spain, Dec 2017
203
6 Conclusion
This paper proposed a classification method by integrating different RF fingerprint features and unique classifiers and carried out extensive experiments to
evaluate the performance. The contribution and novelty are three aspects. First,
six different features in three special fields are adopted and found effective in
classifying four terminals. Second, three classifiers were utilized to adaptively
integrating features with the weights. Finally, a test bed consistsing of low-cost
USRP devices as transceivers were constructed. Compared to the existing work,
much more experiments were carried out to evaluate the performance of RF fingerprint under different channel conditions. In addition to bagged tree, weighted
KNN such good classifiers, we will also design a more robust classifier by taking into account channel influences. Furthermore, the application of machine
learning in signal fingerprinting [11] will be considered in our future work.
Acknowledgements. This work was supported in part by the National Key R&D
Program of China under Grant 2018YFC0807101, in part by the National Natural Science Foundation of China under Grant 61701503/61571082, and in part by the Ministry
of Science and Technology of China (MOST) Program of International S&T Cooperation under Grant 2016YFE0123200. The work of S. Hu was supported in part by
National Natural Science Foundation of China through the Research Fund for International Young Scientists under Grant 61750110527.
References
1. Hariyanto, Sudiro SA, Lukman S (2015) Minutiae matching algorithm using artificial neural network for fingerprint recognition. In: Proceedings of the 2015 3rd international conference on artificial intelligence, modelling and simulation (AIMS),
Kota Kinabalu, Malaysia, Dec 2015
2. Cripps SC (2000) RF power amplifiers for wireless communications. IEEE Microw
Mag 1(1):64–64
3. Eagle N, Pentland A (2006) Reality mining: sensing complex social systems. Pers
Ubiquit Comput 10(4):255–268
4. Kennedy IO, Scanlon P, Mullany FJ, Buddhikot MM, Nolan KE, Rondeau TW
(2008) Radio transmitter fingerprinting: a steady state frequency domain approach.
In: Proceedings of the IEEE 68th vehicular technology conference (VTC), Calgary,
BC, Canada, Sept 2008
5. Uzundurukan E, Ali AM, Kara A (2017) Design of low-cost modular RF front
end for RF fingerprinting of bluetooth signals. In: Proceedings of the 25th signal
processing and communications applications conference (SIU), Antalya, Turkey
6. Bertoncini C, Rudd K, Nousain B, Hinders M (2012) Wavelet fingerprinting of
radio-frequency identification (RFID) tags. IEEE Trans Ind Electron 59(12):4843–
4850
7. Rehman SU, Alam S, Ardekani IT (2014) An overview of radio frequency fingerprinting for low-end devices. In: Proceedings of the IGI Global
8. Wu L, Zhao YQ, Wang Z, Abdalla FYO, Ren GH (2017) Specific emitter identification using fractal features based on box-counting dimension and variance dimension. In: Proceedings of the 2017 IEEE international symposium on signal processing and information technology (ISSPIT), Bilbao, Spain, Dec 2017