Adaptive beamforming in antenna arrays aims at adjusting the weighted linear combination of the output signals provided by the antennas so that the power of the received signals at dominant paths is maximized at the same time that the power of interference and noise signals is minimized. The weight vectors, each one associated with one received signal, can be directly obtained if the direction of arrival (DOA) of the corresponding signal has already been estimated. The process of DOA estimation involves the prediction of the angle of arrival by means of monitoring the output produced by the antennas in the array, given that the number of antennas is higher than the number of signals to be detected. Even though signal subspace techniques have made a good job in DOA estimation, they present some important drawbacks that will be alleviated here using a supervised learning approach, in the form of a multiclass LS-SVM classification problem. The main contribution of this paper is twofold: a step-by-step description of the complete set of algebraic manipulation for data preprocessing and for the synthesis of the classification device, and an analysis of the effect in performance when relevant parameters vary in a given operational interval. © 2005 IEEE.5 32263231Liberti Jr., J.C., Rappaport, T.S., Smart antennas for wireless communications (1999) IS-95 and Third Generation CDMA Applications, , New Jersey: Prentice HallSchimidt, R.O., Multiple emitter location and signal parameter estimation (1979) Proc. of RADC Spectrum Estimation Workshop, Griffiss AFB, pp. 243-258. , N.YSchimidt, R.O., Multiple emitter location and signal parameter estimation (1986) IEEE Trans. on Antennas and Propagation, AP-34 (3), pp. 281-290. , MarRoy, R., Kailath, T., ESPRIT - Estimation pf signal parameters via rotational invariance techniques (1990) Optical Engineering, 29 (4), pp. 296-313. , AprRohwer, J.A., (2003) Learning Methods for CDMA Power Control and Direction of Arrival Estimation, , Ph.D. Thesis, The University of New Mexico. Albuquerque, New Mexico, MayRohwer, J.A., Abdallah, C.T., Christodoulou, C.G., Least square support vector machines for direction of arrival estimation with error control and validation (2003) IEEE 2003 Global Telecommunications Conference, pp. 2172-2176Christodoulou, C.G., Rohwer, J.A., Abdallah, C.T., The use of machine learning in smart antennas (2004) IEEE Antennas and Propagation Society Symposium, pp. 321-324Rappaport, T.S., (1996) Wireless Communication: Principles and Practice, , New Jersey. Prentice HallJunqueira, C.C.M., (2003) Schemes and Algorithms for Adaptive Arrays Applied to GPS, 244p. , PhD. Thesis, State University of Campinas, FEEC, UNICAMP (in Portuguese)Dandekar, K.R., Ling, H., Xu, G., Fye, D., Smart antenna array calibration procedure including amplitude and phase mismatch and mutual coupling effects (2000) IEEE International Conference on Personal Wireless CommunicationTyler, N., Alien, B., Aghvami, H., Adaptive antennas: The calibration problem (2004) IEEE Communications Magazine, 42 (12), pp. 114-122. , DecVapnik, V.N., (1998) Statistical Learning Theory, , John Willey & SonsVapnik, V.N., (1995) The Nature of Statistical Learning Theory, , Springer-VerlagSchölkopf, B., Sung, K., Burges, C., Girosi, F., Niyogi, P., Vapnik, V.N., Comparing support vector machines with Gaussian kernels to radial basis function classifiers (1997) IEEE Transactions on Signal Processing, 45 (11), pp. 2758-2765(1998) Advance in Kernel Methods - Support Vector Learning, , B. Schölkopf, C. Burges, C.Smola, (Eds.), MIT Press(1998) Nonlinear Modeling: Advance Black-box Techniques, , J. A. K. Suykens, J. Vanderwalle, (Eds.), Kluwer Academic Publishers, BostonHaykin, S., (1999) Neural Networks: A Comprehensive Foundation, , Prentice Hall, 2nd. editionBishop, C.M., (1995) Neural Networks for Pattern Recognition, , Oxford University PressSuykens, J.A.K., Vanderwalle, J., Least squares support vector machine classifiers (1999) Neural Processing Letters, 9 (3), pp. 293-300Suykens, J.A.K., Van Gestel, T., De Brabater, J., De Moor, B., Vanderwalle, J., (2002) Least Squares Support Vector Machines, , World ScientificSaunders, C., Gammerman, A., Vovk, V., Ridge regression learning algorithm in dual variables (1998) Proc. of the 15th Int. Conf. on Machine Learning (ICML '98), pp. 515-521. , Morgan KaufmannFletcher, R., (1987) Pratical Methods of Optimization, , New York: WileySmola, A., (1999) Learning with Kernels, , Ph.D. Thesis, published by: GMD, BirlinghovenSuykens, J.A.K., Lukas, L., Van Dooren, P., De Moor, B., Vanderwalle, J., Least squares support vector machine classifiers: A large scale algorithm (1999) European Conference on Circuit Theory and Design, (ECCTD '99), pp. 839-842. , Stresa Italy, AugustPlatt, J.C., Cristianini, N., Shawe-Taylor, J., Large margin DAGs for multiclass classification (2000) Advances in Neural Information Processing Systems, 12, pp. 547-553. , MIT Press