射頻指紋特徵被運用在許多領域上面，其中包含真偽卡的辨識，近年來許多有心人士偽造卡片，為了能分辨出真偽卡，可以提取每張卡片獨有的指紋特徵從中分辨，由於每張卡片被製造時都有所不同，這使得指紋特徵難以被仿冒，大幅減少被偽造的可能性
本論文透過結合K近鄰模型(K Nearest Neighbours Model, KNNM)以及支援向量機(Support Vector Machine, SVM)兩種演算法以辨識出真偽卡，進行K近鄰模型前先經由線性判別分析(Linear Discriminant Analysis, LDA)做降維，將資料做好事先的分類，使相同類別的資料盡可能靠近，不同類別資料盡可能遠離，以提升K近鄰模型的準確率，K近鄰模型會將相鄰的同類別的資料視為一個群集，從群集中找出一個代表點並畫出該群集的範圍，只要新資料落在某群集範圍內，該資料便視為某群集的類別，如果沒落在任何一個群集的類別將視為偽卡，過程中可以透過放大群集的範圍以提升真卡落在群集範圍的機率，降低真卡誤辨識成偽卡的機率，但也可能造就真卡被誤辨識成其他真卡的情況，此時可以透過支援向量機提升真卡的準確率，以解決此問題。

Radio frequency fingerprint is used in many fields, including the identification of cards. In recent years, people with bad intentions have forged cards. In order to distinguish the identification of cards, the unique radio frequency fingerprint of each card can be extracted. Due to the difference of manufacturers, it is hard to counterfeit the radio frequency fingerprint. It reduces the chance of being counterfeited.
In this paper, we combine the KNNM with SVM to identify the cards. We use LDA to implement the dimensionality reduction before KNNM. It can make the data of the same class as close as possible to improve the accuracy of KNNM, which will regard adjacent data of the same class as a cluster. Finding a representative point in the cluster and circle the range of the cluster. If the testing data falls in the range of a cluster, the testing data is classified as the cluster. If it does not fall into any cluster, it will be regarded as a fake card. In the process, we can increase the probability of the real card falling into the cluster by enlarging the range of clusters. It can reduce the mistake of the real card being misidentified as a fake card. However, it may also cause the real card to be misidentified as another real card. In this case, the accuracy of the real card can be improved through SVM.

[1] Q. Xu, R. Zheng, W. Saad, and Z. Han, "Device Fingerprinting in Wireless Networks: Challenges and Opportunities," IEEE Communications Surveys & Tutorials, vol. 18, no. 1, pp. 94-104, 2016.
[2] 陳信豪, "ISO 14443 Type A 標籤模擬器研製," 碩士, 電機工程系, 國立臺灣科技大學, 台北市, 2017.
[3] G. Zhang, L. Xia, S. Jia, and Y. Ji, "Physical-layer identification of HF RFID cards based on RF fingerprinting," in International Conference on Information Security Practice and Experience, 2016, pp. 284-299: Springer.
[4] G. Zhang, L. Xia, S. Jia, and Y. Ji, "Identification of cloned HF RFID proximity cards based on RF fingerprinting," in 2016 IEEE Trustcom/BigDataSE/ISPA, 2016, pp. 292-300: IEEE.
[5] J. Shi, G. He, and X. Liu, "Anomaly detection for key performance indicators through machine learning," in 2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC), 2018, pp. 1-5: IEEE.
[6] H. Henderi, T. Wahyuningsih, and E. Rahwanto, "Comparison of Min-Max normalization and Z-Score Normalization in the K-nearest neighbor (kNN) Algorithm to Test the Accuracy of Types of Breast Cancer," International Journal of Informatics and Information Systems, vol. 4, no. 1, pp. 13-20, 2021.
[7] D. B. Williams and V. Madisetti, "Detection: Determining the number of sources," in Wireless, Networking, Radar, Sensor Array Processing and Nonlinear Signal Processing: CRC Press, 2009, pp. 8-1-8-10.
[8] J. Hogenboom, "Principal component analysis and side-channel attacks-master thesis," Principal component analysis and side-channel attacks-master thesis, pp. 536-539, 2010.
[9] C. Li, "Preprocessing methods and pipelines of data mining: An overview," seminar data mining,, 2019.
[10] T. Hastie, R. Tibshirani, and J. H. Friedman, The elements of statistical learning: data mining, inference, and prediction. Springer, pp. 106-119, 2009.
[11] T. Cover and P. Hart, "Nearest neighbor pattern classification," IEEE transactions on information theory, vol. 13, no. 1, pp. 21-27, 1967.
[12] U. Lall and A. Sharma, "A nearest neighbor bootstrap for resampling hydrologic time series," Water resources research, vol. 32, no. 3, pp. 679-693, 1996.
[13] D. Cheng, S. Zhang, Z. Deng, Y. Zhu, and M. Zong, "kNN algorithm with data-driven k value," in International Conference on Advanced Data Mining and Applications, 2014, pp. 499-512: Springer.
[14] S. Zhang, M. Zong, K. Sun, Y. Liu, and D. Cheng, "Efficient kNN algorithm based on graph sparse reconstruction," in International Conference on Advanced Data Mining and Applications," IEEE Trans. Image Process, 2014, pp. 356-369: Springer.
[15] X. Zhu, L. Zhang, and Z. Huang, "A sparse embedding and least variance encoding approach to hashing," IEEE transactions on image processing, vol. 23, no. 9, pp. 3737-3750, 2014.
[16] G. Guo, H. Wang, D. Bell, Y. Bi, and K. Greer, "KNN model-based approach in classification," in OTM Confederated International Conferences" On the Move to Meaningful Internet Systems", 2003, pp. 986-996: Springer.
[17] S. Zhang, D. Cheng, Z. Deng, M. Zong, and X. Deng, "A novel kNN algorithm with data-driven k parameter computation," Pattern Recognition Letters, vol. 109, pp. 44-54, 2018.
[18] V. Vapnik, "The nature of statistical learning theory, " Springer science & business media, 1999.
[19] P. Tao, Z. Sun, and Z. Sun, "An improved intrusion detection algorithm based on GA and SVM," Ieee Access, 6, vol. 6, pp. 13624-13631, 2018.
[20] V. K. Chauhan, K. Dahiya, and A. Sharma, "Problem formulations and solvers in linear SVM: a review," Artificial Intelligence Review, vol. 52, no. 2, pp. 803-855, 2019.
[21] Q.-Q. Tao, S. Zhan, X.-H. Li, and T. Kurihara, "Robust face detection using local CNN and SVM based on kernel combination," Neurocomputing 211, vol. 211, pp. 98-105, 2016.
[22] S. Kumar, S. Singh, and J. Kumar, "Multiple face detection using hybrid features with SVM classifier," in Data and Communication Networks: Springer, 2019, pp. 253-265.
[23] M. Aljanabi, M. H. Qutqut, and M. Hijjawi , "Machine learning classification techniques for heart disease prediction: a review," International Journal of Engineering & Technology, vol. 7, no. 4, pp. 5373-5379, 2018.
[24] N. Caballé-Cervigón, J. L. Castillo-Sequera, J. A. Gómez-Pulido, J. M. Gómez-Pulido, and M. L. Polo-Luque, "Machine learning applied to diagnosis of human diseases: A systematic review," Applied Sciences, vol. 10, no. 15, p. 5135, 2020.
[25] H. Li and F. Systems, "Text recognition and classification of english teaching content based on SVM," Journal of Intelligent & Fuzzy Systems, vol. 39, no. 2, pp. 1757-1767, 2020.
[26] L. M. Francis, N. Sreenath, and I. Sciences, "TEDLESS–Text detection using least-square SVM from natural scene," Journal of King Saud University-Computer and Information Sciences, vol. 32, no. 3, pp. 287-299, 2020.
[27] S. Huang et al., "Applications of support vector machine (SVM) learning in cancer genomics," Cancer genomics & proteomics, vol. 15, no. 1, pp. 41-51, 2018
[28] G. Shen, J. Zhang, A. Marshall, and J. R. Cavallaro, "Towards scalable and channel-robust radio frequency fingerprint identification for LoRa," IEEE Transactions on Information Forensics and Security, vol. 17, pp. 774-787, 202