射頻指紋辨識(RF fingerprinting)是透過學習傳送端的硬體指紋特徵來辨識設備，而這些特徵可以從接收訊號中分析並提取，但訊號在傳播途中會受到無線通道所造成的衰減、延遲影響，進而使得特徵受到干擾並導致辨識率下降。
本文使用15張網卡進行IEEE 802 .11g訊號收發實驗，共接收了12000筆封包。利用實驗所得資料並且透過模擬萊斯衰落通道(Rician fading channel)來分析通道對射頻指紋辨識之影響。本論文估算通道頻率響應，並提出了減少通道影響因素之射頻指紋特徵提取方法。亦在研究結果中比較了訓練、辨識相同通道以及不同通道之辨識率，透過本文提出的方法，在訓練、辨識不同通道下之辨識率平均可提升約27.6%。

Radio frequency fingerprint that is analyzed and extracted from the received signal can be used to identify the device by learning the hardware fingerprint features of the transmitter. Yet the received signal can be affected by the attenuation and delay caused by the wireless channel during the propagation, which results in the RF fingerprint feature disturbances and identification rate degradation.
In this thesis, 15 wireless local area network adapters are used for IEEE 802.11g signal transmission and reception experiments, in which 12,000 packets are received in total. By passing these experimental data through simulated Rician fading channels, the impact of the channel to the radio frequency fingerprint identification is analyzed.
In this work, we estimate the channel frequency response and propose a method for extracting radio frequency fingerprint features with less channel effect. The simulation results compare identification rates of using training and classification data of the same channel and that of different channels. Applying the proposed method, the identification rates with channel variation increases about 27.6% in average.

[1] V. Brik, S. Banerjee, M. Gruteser, and S. Oh, "Wireless device identification with radiometric signatures," in Proceedings of the 14th ACM international conference on Mobile computing and networking, 2008, pp. 116-127.
[2] T. J. O’Shea, J. Corgan, and T. C. Clancy, "Convolutional radio modulation recognition networks," in International conference on engineering applications of neural networks, 2016: Springer, pp. 213-226.
[3] R. Saha, Power Delay Profile and Channel Classification in Cellular Mobile Communications/ A Handbook on Cellular Mobile Communication Laboratory A MATLAB-Based Approach. 2016.
[4] Y. Ren, L. Peng, W. Bai, and J. Yu, "A Practical Study Of Channel Influence On Radio Frequency Fingerprint Features," in 2018 IEEE International Conference on Electronics and Communication Engineering (ICECE), 10-12 Dec. 2018, pp. 1-7, doi: 10.1109/ICECOME.2018.8644931.
[5] W. Wang, Z. Sun, S. Piao, B. Zhu, and K. Ren, "Wireless Physical-Layer Identification: Modeling and Validation," IEEE Transactions on Information Forensics and Security, vol. 11, no. 9, pp. 2091-2106, 2016, doi: 10.1109/TIFS.2016.2552146.
[6] Y. Chapre, A. Ignjatovic, A. Seneviratne, and S. Jha, "Csi-mimo: Indoor wi-fi fingerprinting system," in 39th annual IEEE conference on local computer networks, 2014: IEEE, pp. 202-209.
[7] T. Jian et al., "Deep learning for RF fingerprinting: A massive experimental study," IEEE Internet of Things Magazine, vol. 3, no. 1, pp. 50-57, 2020.
[8] N. Soltani, K. Sankhe, J. Dy, S. Ioannidis, and K. Chowdhury, "More is better: Data augmentation for channel-resilient RF fingerprinting," IEEE Communications Magazine, vol. 58, no. 10, pp. 66-72, 2020.
[9] G. R. Hiertz, D. Denteneer, L. Stibor, Y. Zang, X. P. Costa, and B. Walke, "The IEEE 802.11 universe," IEEE Communications Magazine, vol. 48, no. 1, pp. 62-70, 2010, doi: 10.1109/MCOM.2010.5394032.
[10] J. Sterba and D. Kocur, "Pilot symbol aided channel estimation for OFDM system in frequency selective Rayleigh fading channel," in 2009 19th International Conference Radioelektronika, 22-23 April 2009, pp. 77-80, doi: 10.1109/RADIOELEK.2009.5158729.
[11] MATLAB, Fading Channels. [Online]. Available: https://www.mathworks.com/help/comm/ug/fading-channels.html.
[12] R. Jain, "Channel models: A tutorial," in WiMAX forum AATG, 2007, vol. 10: Washington Univ. St. Louis, Dept. CSE.
[13] 蔣政儒, "MC-CDMA與MC-DS-CDMA在多路徑通道下之系統效能比較," 國立交通大學電信工程研究所, 2004.