Browsing by Author "Papantoni-Kazakos, P."

Now showing 1 - 8 of 8
  • Thumbnail Image
    Item
    Concentration of Binary FM Spectra
    (1974-11-20) Papantoni-Kazakos, P.; Kazakos, D.
    The spectrum of a digital FM signal can be considered as an indicator of the resistance of the signal to distortions caused by band-limitation. The study in this paper is oriented toward the design of a signaling pulses that will achieve a concentrated about the carrier frequency FM signal spectrum. Convenient spectrum expressions and general guarantees of optimality are found for FSK signals.
  • Thumbnail Image
    Item
    The Effect of Intersymbol Interference on the Performance of a Digital FM System
    (1974-10-20) Papantoni-Kazakos, P.; Paz, I.
    The error performance of a digital FM system is studied in the presence of additive Gaussian noise. The digital system considered is a conventional one employing a voltage-controlled oscillator as the modulator and a limiter-discriminator followed by a low-pass filter as the demodulator. The notion of
  • Thumbnail Image
    Item
    The Limiting Density of a Nonlinear System
    (1974-10-20) Papantoni-Kazakos, P.; Kazakos, D.
    The RC filter-hard limiter-RC filter nonlinear system shown in Fig. 1 is the subject of this paper. Because of computational difficulties implicated in the analysis of the above system, only its response to the zero mean Gaussian system input has been analytically investigated [2,3,5]. An approximate output density has also been found for nonzero mean Gaussian, while verified to be "close" to the real one for finite means [4]. In the present paper, a close form of the system output density is obtained when the input mean tends to infinity. for that, xi-upcrossing methods were used.
  • Thumbnail Image
    Item
    Moments and Error Expressions in Polynomial Minimum Mean Square Estimation
    (1975-05-20) Kazakos, D.; Papantoni-Kazakos, P.
    The mathematical complexity of the minimum mean square estimators made inevitable the consideration of suboptimal solutions, such as the linear minimum mean square estimators. The compromise between performance and complexity can be in general less serious if the estimator that will substitute the optimum one is polynomial. If the minimum mean square estimator happens to be equal to a polynomial one, the polynomial substitution does not involve any compromise with respect to performance. Balakrishnan [1] found a necessary and sufficient condition satisfied by the joint characteristic functions of observations and variable to be estimated, so that the m.m.s. estimiate is a polynomial. The equivalent relationships in this case were found in the present paper. A matrix expression of the error difference from two different m.m.s. polynomial estimators was also found. This form involves much fewer calculations than required for finding separately the two errors.
  • Thumbnail Image
    Item
    p-Efficient Estimators
    (1975-08-20) Papantoni-Kazakos, P.
    This paper is concerned with estimates of an unknown vector parameter S based on observations X. A generalized error autocorrelation matrix with components the error moments of order 2p, is defined. A lower bound for this matrix is found and the p-efficient P(X/S) statistics realizing it are determined. The cases of i) X and S real, ii) S scalar real, and iii) X real and S complex are examined.
  • Thumbnail Image
    Item
    Robustness in Parameter Estimation
    (1975-10-20) Papantoni-Kazakos, P.
    Due to vagueness in the definition of robustness, there has been no natural transition between robust and nonparametric parameter estimators. In this work, qualitative ideas first expressed by Hampel [1] are extended in an effort to present a theory that unifies the nonparametric and robust concepts. Robustness is definied in a precise mathematical way that transists to nonparametricness naturally. As a result, some general constructive characteristics of robust estimators are studied.
  • Thumbnail Image
    Item
    Some Distance Measures and Their Use in Feature Selection
    (1976-11-20) Papantoni-Kazakos, P.
    The Bhattacharyya, I-divergence, Vasershtein, variational and Levy distances are evaluated, compared and used for the reduction of n data to one feature. This reduction is obtained through a restricted linear transformation and the original data are assumed to be originating from two different jointly Gaussian classes. It is found that the Bhattacharyya, I-divergence and Vasershtein distances give the same "optimal" linear transformation that applied on the original n data result in one feature with maximum possible distance between classes. The distortion measures considered in the Vasershtein distance are |x-y| and (x-y)2. For the same distance measures and classes with equal covariances the Levy distance results in the same "optimal" linear transformation.
  • Thumbnail Image
    Item
    Some New Performance Criteria in Robust Statistics-Small Sample Robustness
    (1977-01-20) Papantoni-Kazakos, P.
    In this paper the analysis of estimates operating on dependent data is considered. Special dependent data structures are considered and the analysis is made for three different choices of contamination and performance distance measures. For contamination and performance measures both being Levy (Hampel model), an analysis that is particularly oriented toward fast convergence of the estimate to a value that is stable (robust) inside the contaminated family is undertaken. The minimum sample size to satisfy certain performance is investigated and it is found that the problem reduces to finding continuous, absolutely bounded estimates with logarithms of their moment generating function slowly increasing with the absolute value of the argument for all data distributions considered.