在通訊領域中有許多應用需要先檢測訊號的調變類型，例如:頻譜監控和電子戰等等，隨著數位調變種類越來越多，複雜性也越來越高，自動調變識別(automatic modulation classification)系統進而變得越來越重要。
自動調變辨識系統的作用在於檢測接收到的未知訊號並辨識其調變類型，即可對此信號進行解調，進而得到訊號中傳輸的內容，此一技術在軍事情報領域中就顯得相當的重要。
自動調變辨識系統常見的有兩種方法，第一種為最大似然法(Maximum Likelihood, ML)，第二種是基於訊號特徵(Feature-based, FB)的方法。而高階累積量(Higher Order Cumulants, HOCs)屬於FB的方法之一，高階累積量的特性為訊號經過可加性高斯白噪聲(AWGN)通道後，仍能辨識出未知調變的訊號種類。
本論文將會比較7篇使用HOCs的不同辨識系統，在能成功辨識出12種調變以及多載波訊號的條件下，提出提升平均正確辨識率系統以及降低複雜度方法之辨識系統，再與7篇原始辨識系統進行效能比較。

For many applications in the field of communication, such as spectrum surveillance and electronic warfare, which requires to detect the modulation type of a given communication signal. With the increasing variety of digital modulation and complexity, the automatic modulation classification system has become more and more important.
The function of the automatic modulation identification system is to detect the received unknown signal and identify its modulation type, and then demodulate the signal to obtain the content transmitted in the signal. This technology is quite important in the field of military intelligence.
There are two common methods for automatic modulation identification systems. First one is Maximum Likelihood (ML), and second one is based on Feature-Based (FB). Higher Order Cumulants (HOCs) is one of the methods using FB. The advantage of HOCs is even the signal pass the additivity white Gaussian noise (AWGN) channel, the unknown modulation signal type can still be identified by HOCs.
In this paper, we compare 7 different identification systems using HOCs. Under the condition that 12 kinds of modulation type and multi-carrier signals can be successfully identified, the best probability correct classification system and the lowest complexity classification system are proposed. Then we compare the classification system we proposed to the original classification system.

[1] A. Hazza, M. Shoaib, S. A. Alshebeili, and A. Fahad, ‘‘An overview of feature-based methods for digital modulation classification,’’ in Proc. ICCSPA , Sharjah, United Arab Emirates, Feb. 2013, pp. 1–6. 2013
[2] O. A. Dobre, A. Abdi, Y. Bar-Ness, and W. Su, “Survey of automatic modulation classification techniques: Classical approaches and new trends,”in IET Comm., vol. 1, 2007 ,pp. 137-156.
[3] A. K. Nandi and E. E. Azzouz, "Algorithms for automatic recognition of communication signals,"in IEEE Trans. Commun.,vol. 46, pp. 431-436, 1998
[4] Mendel, J.M.: “ Tutorial on higher-order-statistics (spectra) in signal processing and system theory: theoretical results and some applications ”,in Proc. IEEE , 1991, 79 , (3), pp. 278 – 305
[5] C. Nikias and J. Mendel. “Signal Processing with Higher- Order Statistics”.in IEEE Signal Processing, July 1993, pp 10 – 38
[6] D. R. Brillinger, Time Series: Data Analysis and Theory. New York: McGraw-Hill, 1981.
[7] S. El-Khamy, H. Elsayed, and M. Rizk, “Classification of multi-user chirp modulation signals using higher order cumulant features and four types of classifiers,” in Radio Science Conference (NRSC), 2011 28th National , april 2011, pp. 1 –10.
[8] A. Swami and B. M. Sadler, “Hierarchical digital modulation classification using cumulants,” IEEE Trans. Commun., vol. 48, no. 3, Mar. 2000 ,pp. 416–429.
[9] M. Shi, Y. Bar-Ness, and W. Su, “Fourth order cumulants in distinguishing single carrier from OFDM signals,” in Proc. IEEE MILCOM , San Diego, CA, Nov. 2008, pp. 1–6.
[10] L. De Vito and S. Rapuano, “Validating a method for classifying digitally modulated signals,”in Measurement, vol. 42 issue 3, April 2009, pp. 427-435.
[11] L. De Vito, S. Rapuano, M. Villanacci: “Prototype of an Automatic Digital Modulation Classifier Embedded in a Real-Time Spectrum Analyzer.”in IEEE Transactions on Instrum. And Meas., vol. 59, No. 10, Oct. 2010, pp. 2639 – 2651.
[12] W. Liu, J. Wang, and S. Li, “Blind detection and estimation of OFDM signals in cognitive radio contexts,” in Proc. 2nd ICSPS , Dalian, China, Jul. 5–7, 2010, pp. 347–351.
[13] Y. Xu, L. Ge, and B. Wang, “Digital Modulation Recognition Method based on Self-Organizing Map Neural Networks,” in Proc. WiCom 08, Dalian, Oct. 2008, pp. 1-4.
[14] M. L. D. Wong and A. K. Nandi, “Automatic digital modulation recognition using artificial neural network and genetic algorithm,”in ELSEVIER, Signal Processing, 2004, pp. 351-365.
[15] K. Hassan, I. Dayoub, W. Hamouda, and M. Berbineau, “Automatic Modulation Recognition Using Wavelet Transform and Neural Networks in Wireless Systems,”in EURASIP JASP, vol. 2010, Article ID 532898, 13 pages, 2010
[16] S. Theodoridis and K. Koutroumbas, “Pattern Recogntition,” 4th ed., Academic Press, 2009.
[17] J.J. Popoola, R. van Olst, “A Novel Modulation-Sensing Method,”in IEEE Vehicular Tech. Mag., vol.6, no.3, Sept. 2011, pp.60-69.
[18] X. Zhou, Y. Wu, B. Yang, “Signal Classification Method Based on Support Vector Machine and High-Order Cumulants,”in Sicintific research, Wireless Sensor Networks, No. 2, Nov. 2009, pp. 48-52.
[19] F.C.B.F Muller, C. Cardoso, A. Klautau, “A Front End for Discriminative Learning in Automatic Modulation Classification,”in IEEE Comm. Lett. , vol.15, no.4, April 2011 ,pp.443-445.
[20] J. Yuan, Z. Zhao-Yang, and Q. Pei-Liang, “Modulation Classification of Communication Signals,” in Proc. MILCOM, Oct. 2004, vol. 3, CA, pp. 1470-1476.
[21] K. Maliatsos, S. Vassaki, Ph. Constantinou, “Interclass and Intraclass modulation recognition using the Wavelet Transformation,” in Proc. PIMRC, Athens, Sept. 2007, pp. 1-5.
[22] L. Youyong, L. Guolong, X. Xiaoka, and L. Xinxin, “The methods of recognition for common used M-ary digital modulations,” in Proc. WiCOM 08, Dalian, Oct. 2008, pp. 1-4.
[23] H. Fu-qing, Z. Zhi-ming, X. Yi-tao, and R. Guo-chun, “Modulation Recognition of Symbol Shaped Digital Signals,” in Proc. ICCCAS, Fujian, May 2008, pp. 328-332.
[24] A. Gorcin, H. Arslan, “An OFDM Signal Identification Method for Wireless Communications Systems”,in IEEE Transactions on Vehicular Technology, 2015, pp.5688-5700.
[25] D. Brillinger and M. Rosenblatt, “Computation and interpretation of kth-order spectra,” in Spectral Analysis of Time Series, B. Harris, Ed. New York, NY, USA: Wiley, 1967, pp. 189–232.
[26] Y. Zhao, Y. t. Xu, H. Jiang, Y. j. Luo and Z. w. Wang, “Recognition of digital modulation signals based on high-order cumulants”, in Wireless Communications & Signal Processing (WCSP), 2015 International Conference on , Nanjing, 2015, pp. 1-5.
[27] Mingzhu, L., Yue, Z., Lin, S. and Jingwei, D., “Research on recognition algorithm of digital modulation by higher order cumulants”. in Instrumentation and Measurement, Computer, Communication and Control (IMCCC), 2014 Fourth International Conference on ,pp. 686-690.
[28] L. Liu and J. Xu, “A novel modulation classification method based on high order cumulants,” in International Conference on Wireless Communications, Networking and Mobile Computing, WiCOM , September 2006, pp. 1–5.
[29] D. Das, P. K. Bora, and R. Bhattacharjee, “Cumulant based automatic modulation classification of QPSK, OQPSK, 8-PSK and 16-PSK,” in 2016 8th International Conference on Communication Systems and Networks (COMSNETS) , Jan 2016, pp. 1–5.
[30] A. Ali, F. Yangyu, “Higher-order statistics based modulation classification using hierarchical approach”, in IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), 2016, pp. 370-374.
[31] M. Flohberger, W. Gappmair and O. Koudelka, “Modulation classifier for signals used in satellite communications,” in 5th Advanced Satellite Multimedia Systems Conference and the 11th Signal Processing for Space Communications Workshop , 2010,pp. 198 - 202.
[32] G. G.H. and V. L. C.F., Matrix Computations (3rd Ed.) , Johns Hopkins University Press, 1996.
[33] Proakis, J.G. and Salehi, M., Digital Communications. 5th Edition, New York: McGraw-Hill, 2008.