一種快速的在線SVM多用戶檢測算法

王子磊; 奚宏生; 趙宇; 盛延敏

一種快速的在線SVM多用戶檢測算法

計量
- 文章訪問數: 2531
- HTML全文瀏覽量: 84
- PDF下載量: 1072
- 被引次數: 0
出版歷程
- 收稿日期: 2004-11-22
- 修回日期: 2005-11-23
- 刊出日期: 2006-08-19

A Fast Online SVM Algorithm for Multi-user Detection

摘要

摘要: 基于傳統支持向量機的多用戶檢測算法運算量大、耗時久，無法滿足實時性要求。該文提出了一種快速的在線支持向量機多用戶檢測算法。該算法利用KKT條件判別實時增加的訓練序列并構造當前訓練樣本集，從而能夠有效地減少訓練樣本大小，加快訓練速度。仿真實驗表明，該算法在不影響分類效果的情況下大大加快了訓練速度，且用于分類的支持向量較少，同時性能與傳統支持向量機算法相當且明顯優(yōu)于MMSE(RLS)多用戶檢測器。
- CDMA;在線支持向量機;多用戶檢測;快速算法
Abstract: The runtime of conventional SVM-MUD is too long to satisfy the requirement of real-time application. A fast algorithm based on online training of SVM (FOSVC) for multiuser detection is proposed in the paper. The algorithm distinguishes new added samples and constructs the current training data set using KKT condition in order to reduce the size of training samples. As a result, the training speed is effectively increased. Simulation results illustrate that the algorithm has a faster training speed and a smaller number of support vectors preserving the same quality of separating hyperplane. The performance of the FOSVC detectors is pretty much the same thing as that of SVM detectors, and much better than that of MMSE detectors.

HTML全文

參考文獻(1)

Verdu S. Multiuser Detection[M]. London: Cambridge UniversityPress, 1998: 154-387.[2]張賢達, 保錚. 通訊信號處理[M]. 北京：國防工業(yè)出版社,2000: 420-482.[3]Madhow U, Honing M. MMSE interference suppression fordirect-sequence spread spectrum CDMA[J]. IEEE Trans. onCommunications, 1998, 46(8): 3178-3188.[4]Host-Madsen A, Kyung-Sean Cho. MMSE/PIC multiuserdetection for DS/CDMA systems with inter-and intra-cellinterference[J].IEEE Trans. on Communications.1999, 47(2):291-299[5]Kechriotis G, Manolakos E S. Hopfield neural network implementtationin the optimal CDMA multiuser detector[J]. IEEETrans. on Neural Networks, 1996, NN-7(1): 131-141.[6]Vapnik V. Statistical Learning Theory[M]. New York: Wiley-Interscience Publication, 1998: 401-491.[7]Nello C, John S T. An Introduction to Support VectorMachines[M]. London: Cambridge University Press, 2000:93-122.[8]Gong X H, Kuh A. Support vector machine for multiuserdetection in CDMA communications[A]. Conference Record ofthe Thirty-Third Asilomar Conference on Signals, Systems, andComputers [C]. Vol.1, 24-27 Oct., 1999: 680-684.[9]周偉達, 張莉, 焦李成. 自適應支撐矢量機多用戶檢測[J]. 電子學報, 2002, 31(1): 92-97.[10]劉楓, 張?zhí)? 孫建成. 基于修改核函數的RLS-SVM 多用戶檢測算法[J].電子與信息學報.2003, 25(8):1130-1134瀏覽[11]楊恒, 張賢達. Rayleigh 信道下的支持向量機多用戶檢測方法[J].電子與信息學報.2002, 24(2):257-260瀏覽[12]Lau K W, Wu Q H. Online training of support vector classifier[J].Patten Recognition.2003, 36(8):1913-1920[13]Osuna E, Freund R, Girosi F. An improved training algorithm forsupport vector machines[A]. Neural Network for SignalProcessing[1997] Ⅶ. Proceedings of the 1997 IEEE Workshop.USA , 24-26 Sept., 1997 [C]: 276-285.[14]Platt J. Fast training of support vector machines using sequentialminimal optimization[A]. In: Sch.lkopf B., Burges C.J.C., andSmola A.J. (Eds.) Advances in Kernel Methods-Support VectorLearning, Cambridge, MA, MIT Press. 1999: 185-208.[15]Chang C C, Hsu C W, Lin C J. The analysis of decompositionmethods for support vector machines[J]. IEEE Trans. on NeuralNetworks, 2000, 11(4): 1003-1008.

施引文獻

資源附件(0)

訪問統計