论文信息 - Detection of changes in the spectrum of a multidimensional process

Detection of changes in the spectrum of a multidimensional process

An algorithm is presented for the sequential detection of changes in the spectrum of a multidimensional process. The asymptotic properties of the statistic used are investigated in the case of a real Gaussian process. The algorithm of detection is based on a sequential likelihood-ratio test. Simulations show very good behavior of the algorithm in the case of Gaussian and non-Gaussian processes. In both cases, changes are detected with good accuracy, while the number of false alarms is small. >

Marc Lavielle

[1] John F. Canny,et al. A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2] D. Picard. Testing and estimating change-points in time series , 1985, Advances in Applied Probability.

[3] Rainer Dahlhaus. Asymptotic normality of spectral estimates , 1985 .

[4] David V. Hinkley,et al. Inference about the change-point in a sequence of binomial variables , 1970 .

[5] C. H. Chen. On a segmentation algorithm for seismic signal analysis , 1984 .

[6] Ildar Ibragimov. On Estimation of the Spectral Function of a Stationary Gaussian Process , 1963 .

[7] G. Bodenstein,et al. Feature extraction from the electroencephalogram by adaptive segmentation , 1977, Proceedings of the IEEE.

[8] S. Panchapakesan,et al. Inference about the Change-Point in a Sequence of Random Variables: A Selection Approach , 1988 .

[9] S. Kullback,et al. Topics in statistical information theory , 1987 .

[10] M. Rosenblatt,et al. Asymptotic Normality, Strong Mixing and Spectral Density Estimates , 1984 .

[11] Ian B. MacNeill,et al. Limit Processes for Co-Spectral and Quadrature Spectral Distribution Functions , 1971 .