Toward a tight upper bound for the error probability of the binary Gaussian classification problem

Pattern Recognition

Volumn 41, Issue 6, 2008, Pages 2120-2132

  El Ayadi, Moataz M H ^a   Kamel, Mohamed S ^a   Karray, Fakhri ^a  

^a UNIVERSITY OF WATERLOO   (Canada)

Author keywords

Bayesian decision rule; Binary classification; Decision boundary; Error probability; Monte Carlo simulations; Multivariate normal distribution; Quadratic surfaces

Indexed keywords

ASYMPTOTIC ANALYSIS; BINARY SEQUENCES; CLASSIFICATION (OF INFORMATION); COMPUTATIONAL COMPLEXITY; COMPUTER SIMULATION; PROBLEM SOLVING;

BAYESIAN DECISION RULE; BINARY CLASSIFICATION; DECISION BOUNDARY; MULTIVARIATE NORMAL DISTRIBUTION; QUADRATIC SURFACES;

ERRORS;

EID: 38949188954     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.patcog.2007.10.028     Document Type: Article

References (23)

1. Chernoff H. A measure for asymptotic efficiency of a hypothesis based on a sum of observations. Ann. Math. Statist. 23 (1952) 493-507
2. Fukunaga K. Introduction to statistical pattern recognition (1990), Academic Press, New York
3. Hashlamoun W., Varshney P., and Samarasooriya V. A tight upper bound on the bayesian probability of error. IEEE Trans. Pattern Anal. Mach. Intell. 16 2 (1994) 220-225
4. De Vore M. Estimates of error probability for complex gaussian channels with generalized likelihood ratio detection. IEEE Trans. Pattern Anal. Mach. Intell. 27 10 (2005) 1580-1591
5. Raphaeli D. Noncoherent coded modulation. IEEE Trans. Commun. 44 2 (1996) 172-183
6. J. Ni, On the chernoff bound for linear quadratic receivers, IEEE Wireless Communications and Networking Conference (WCNC), 2004, vol. 1, 2004, pp. 83-86.
7. J. Ni, R. Barton, Adaptive linear-quadratic receivers for time-varying, frequency-selective code-division-multiple-access channels, Asilomar Conference on Signals, Systems, and Computers, 1999, vol. 2, 1999, pp. 945-949.
8. Poor H. An introduction to siganl detection and estimation (1994), Springer, Berlin
9. Ito T. Approximate error bounds in pattern recognition. Mach. Intell. 7 (1972) 369-372
10. Hellman M. Probability of error, equivocation, and chemoff bound. IEEE Trans. Inform. Theory 16 (1970) 368-372
11. Deijver P. On a new class of bounds on bayes risk in multihypothesis pattern recognition. IEEE Trans. Comput. 23 (1974) 70-80
12. Avi-Itzhak H., and Diep T. Arbitrarily tight upper and lower bounds on the bayesian probability of error. IEEE Trans. Pattern Anal. Mach. Intell. 18 1 (1996) 89-91
13. Michell R. Importance sampling applied to simulation of false alarm statistics. IEEE Trans. Aerospace Electron. Systems 17 1 (1981) 15-24
14. Herro M., and Nowack M. Simulated viterbi decoding using importance sampling. IEE Proc. Radar Signal Process. 135 2 (1988) 133-142
15. Chen C. On information and distance measures. and feature selection, Inform. Sci. 10 (1976) 159-171
16. Beaulieu N. A simple series for personal computer computation of the error function. IEEE Trans. Commun. 37 (1989) 989-991
17. Rueda L. A one-dimensional analysis for the probability of error of linear classifiers for normally distributed classes. Pattern Recognition 38 8 (2005) 1197-1207
18. Ruben H. Probability content of regions under spherical under spherical normal distribution, iv: The distribution of homogeneous and non-homogeneous quadratic functions of random variables. Ann. Math. Statist. 33 2 (1962) 547-570
19. Shah B. Distribution of definite and of indefinite quadratic forms from a non-central normal distribution. Ann. Math. Statist. 34 1 (1963) 186-190
20. Press S. Linear combination of non-central chi-squared variates. Ann. Math. Statist. 37 2 (1966) 480-487
21. Raphaeli D. Distribution of noncentral quadratic forms in complex normal variables. IEEE Trans. Inform. Theory 42 3 (1996) 1002-1007
22. Anderson T., and Bahadur R. Classification into two multivariate normal distributions with different covariance matrices. Ann. Math. Statist. 33 2 (1962) 420-431
23. D.J. Newman, A. Asuncion, UCI machine learning repository, 2007.