臺灣博碩士論文加值系統

在本論文中,我們提出機器學習於感知無線電網之合作式頻譜感測，我們結合了非監督式學習與監習的分類技術於頻譜感測上，在機器學習環境下，分類需要通過訓練階段分成通道可用與通道不可用。我們利用了非監督式K-means 分群演算法劃分訓練特徵向量為$K$群集，其中每個群集對應於主要使用者的狀態，接著分類器判定測試能量向量屬於的群集，將所得到之結果當作監督式高斯過程的輸入值來做分類，接著利用高斯過程來進一步提升它的效能。高斯過程分類是藉由訓練一組輸入與輸出的相關性，當再接受到新的一個輸入值時，能得到輸出的預測機率值，利用此機率值來判定新接收到的資訊為哪一類別。最後我們的模擬將比較我們提出的高斯過程分類、K-means 分群演算法與支持向量機。利用操作特性曲線來比較各方法之性能，也比較各方法之計算複雜度。

This thesis proposes the application of machine learning which combine unsupervised learning and supervised learning classification techniques for cooperative spectrum sensing(CSS) in cognitive radio networks. This method is characterized by using the results of unsupervised K-means clustering algorithm as an input of Gaussian process to determine whether the channel is available or not. The classification need to go through a training phase which K-means clustering algorithm divided the training feature vectors into K clusters, where each cluster corresponds to the state of a primary user, and then the classifier determines test energy vector belongs to. However, due to its poor classification results, we combine Gaussian process to improve its performance. Gaussian process classification is by training a group of relation about input data and output data when receiving a new input data can obtain the prediction probability of output, and use this probability to determine the new data belongs to which class. Simulation results show the operating characteristic curve(ROC) to compare the performance of each technique, and compare the computational complexity.

第一章 緒論 1
1.1 引言 ...........................1
1.2 研究動機與目的 .....................2
1.3 內容章節概述 ......................4
第二章 相關背景回顧 5
2.1 感知無線電 . ......................5
2.2 頻譜感測 . .......................6
2.3 合作式頻譜感測 . ....................9
2.4 機器學習介紹. .....................13
2.4.1 K-means 分群演算法 . .............13
2.4.2 高斯過程 . ...................14
2.5 假設檢測器 . ......................18
2.6 結語. ..........................19
第三章在感知無線電網路下基於高斯過程及假設檢測器之合作式頻譜感測 20
3.1 通道分類基於機器學習 . ................21
3.1.1 K-means 分群演算法 . .............22
3.1.2 高斯過程分類 . .................24
3.2 通道分類基於假設檢測器 . ..............27
3.3 模擬分析與討論 . ....................29
3.4 結語. ..........................36
第四章 結論與未來展望 37
4.1 結論 . ..........................37
4.2 未來展望 . .......................37
參考文獻 39

[1]J. Mitola and G.Q. Maquire Jr., “Cognitive radio: making software radios more personal,” IEEE Pers. Commun., vol. 6, no. 4, pp. 13-18, Aug. 1999.

[2]E. Hossain and V. K. Bhargava, ed. Cognitive Wireless Communication Net-works. Springer, 2007.

[3]T. Weiss and F. K. Jondral, “Spectrum pooling: an innovative strategy for the enhancement of spectrum efficiency,” IEEE Commun. Magazine, vol. 42, no. 3, pp. S8-14, Mar. 2004.

[4]Y.-C. Liang, K.-C. Chen, G.Y. Li and P. Mahonen, “Cognitive radio network-ing and communications: an overview,” IEEE Trans. Vehicular Technology, vol. 60, no. 7, pp. 3386-3407, Sep. 2011.

[5]J. Mitola, “Cognitive radio: An integrated agent architecture for software defined radio,” Doctor of tech. Royal Inst. Technol, 2000.

[6]H. Huang, Z. Zhang, P. Cheng, and P. Qiu, “Opportunistic spectrum access in cognitive radio system employing cooperative spectrum sensing,” in Proc. IEEE Vehicular Technology Conference, vol. 11, no. 11, pp. 1 5, 26-29, Apr. 2009.

[7]C. Li and C. Li, “Opportunistic spectrum access in cognitive radio networks,” IEEE International Joint Conference on Neural Networks, pp. 3412 3415, Jun. 2008.

[8]S. Haykin, D. Thomson and J. Reed, “Spectrum sensing for cognitive radio,” Proc. IEEE, Vol. 97, no. 5, pp. 849-877, 2009.

[9]T. Yucek and H. Arslan, “A survey of spectrum sensing algorithms for cog-nitive radio applications,” IEEE Comm. Survey and Tutorials, vol. 11, no. 1,pp.116-130, Mar. 2009.

[10]H. Urkowitz, “Energy detection of unknown deterministic signals” Proc. IEEE, vol. 55, no. 4, pp. 523-531, Apr. 1967.

[11]E. Alpaydin, Introduction to Machine Learning. MIT Press, 2004.

[12]K. B. Letaief, W. Zhang, “Cooperative communications for cognitive radio networks,” in Proc. IEEE, vol. 97, no. 5, pp. 878 - 893, May 2009.

[13]S. M. Kay, Fundamemtals of Sattistical Signal Processing: Detection Theory. Prentice-Hall, 1998.

[14]X. L. Huang, F. Hu, J. Wu, H. H. Chen, G. Wang, and T. Jiang, “Intelligent cooperative spectrum sensing via hierarchical Dirichlet process in cognitive radio networks,” IEEE Journal on Selected Areas in Commun., vol. 33, no. 5, pp. 771-787, May 2015.

[15]Z. Li, F. Zhou, J. Si, P. Qi, and L. Guan, “Feasibly efficient cooperative spectrum sensing scheme based on Cholesky decomposition of the correlation matrix,” IET Commun., vol. 10, no. 9, pp. 1003 - 1011, Jun. 2016.

[16]H. Zhang, H. C. Wu, and L. Lu, “Analysis and algorithm for robust adaptive cooperative spectrum sensing,” IEEE Trans. Wireless Commun., vol. 13, no. 2, pp. 618 - 629, Feb. 2014.

[17]D. J. Lee, “Adaptive random access for cooperative spectrum sensing in cog-nitive radio networks,” IEEE Trans. Wireless Commun., vol. 14, no. 2, pp. 831 - 840, Feb. 2015.

[18]X. Wu, N. Fu, and F. Labeau, “Relay-based cooperative spectrum sensing framework under imperfect channel estimation,” IEEE Commun. Lett., vol. 19, no. 2, pp. 239 - 242, Feb. 2015.

[19]K. M. Thilina K. W. Choi, N. Saquib, and E. Hossain, “Machine learning tech-niques for cooperative spectrum sensing in cognitive radio networks,” IEEE Journal on Selected Areas in Commun., vol. 31, no. 11, pp. 2209 - 2221, Nov. 2013.

[20]C. E. Rasmussen, “Gaussian processes in machine learning,” Advanced Lec-tures on Machine Learning, Vol. 3176, pp. 63 - 71, 2004.

[21]S. P. Chepuri, G. Leus and R. de Francisco, “Multiple hypothesis testing for compressive wideband sensing,” 2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Comm., pp. 590-594, Jun. 2012.

[22]C. E. Rasmussen, and C. K. I. Williams, Gaussian Processes for Machine Learning. Cambridge, MA, USA: MIT Press, 2006.

[23]M. Steinbach, G. Karypis and V. Kumar, “A comparison of document clus-tering techniques,” Proc. KDD-2000 Workshop TextMining, Aug. 2000.

[24]M. Kuss and C. E. Rasmussen, “Assessing approximate inference for binary gaussian process classification” Journal of Machine Learning Research 6, pp. 1679-1704, 2005.

[25]T. P. Minka, “Expectation propagation for approximate Bayesian inference” Uncertainty in Artificial Intelligence, pp. 362-369, 2001.