 Research
 Open Access
Blind estimation of statistical properties of nonstationary random variables
 Ali Mansour^{1}Email author,
 Raed Mesleh^{2} and
 elHadi M Aggoune^{2}
https://doi.org/10.1186/16876180201421
© Mansour et al.; licensee Springer. 2014
 Received: 1 July 2013
 Accepted: 7 February 2014
 Published: 20 February 2014
Abstract
To identify or equalize wireless transmission channels, or alternatively to evaluate the performance of many wireless communication algorithms, coefficients or statistical properties of the used transmission channels are often assumed to be known or can be estimated at the receiver end. For most of the proposed algorithms, the knowledge of transmission channel statistical properties is essential to detect signals and retrieve data. To the best of our knowledge, most proposed approaches assume that transmission channels are static and can be modeled by stationary random variables (uniform, Gaussian, exponential, Weilbul, Rayleigh, etc.). In the majority of sensor networks or cellular systems applications, transmitters and/or receivers are in motion. Therefore, the validity of static transmission channels and the underlying assumptions may not be valid. In this case, coefficients and statistical properties change and therefore the stationary model falls short of making an accurate representation. In order to estimate the statistical properties (represented by the highorder statistics and probability density function, PDF) of dynamic channels, we firstly assume that the dynamic channels can be modeled by shortterm stationary but longterm nonstationary random variable (RV), i.e., the RVs are stationary within unknown successive periods but they may suddenly change their statistical properties between two successive periods. Therefore, this manuscript proposes an algorithm to detect the transition phases of nonstationary random variables and introduces an indicator based on highorder statistics for nonstationary transmission which can be used to alter channel properties and initiate the estimation process. Additionally, PDF estimators based on kernel functions are also developed. The first part of the manuscript provides a brief introduction for unbiased estimators of the second and fourthorder cumulants. Then, the nonstationary indicators are formulated. Finally, simulation results are presented and conclusions are derived.
Keywords
 Wireless communication
 Dynamic transmission channel
 Higherorder statistics
 Cumulants
 Cumulative distribution function
 Kernel density estimators
 Hermite basis set
 Spline functions
 Characteristic functions
 Nonstationary signals
1 Introduction
Unlike discrete transmission channels which have limited practical value, continuous random transmission channels are widely accepted and used to illustrate practical concepts [1]. In numerous proposed algorithms, statistical properties or probability density function (PDF) of transmission channels are assumed to be perfectly known or already estimated [2–6]. To analyze the performance of various wireless transmission schemes, Simon and Alouini in [7] have used channel statistical models and PDF properties. It is widely believed that wireless transmission channels can be modeled using stationary random variables [1, 8, 9]. We should highlight the fact that various PDFs have been used in the context of wireless communications, such as Gausssian, Rayleigh, lognormal, exponential, onesided Gaussian distribution, Hoyt, Weibull, Rice, Nakagamim, αμ, and ηκ (see [10–21] and the references therein). It is worth pointing out that parametrical estimation methods can be used if the channel model (or a PDF for the real random variable (RV)) is selected or identified. Additionally, nonparametrical estimation methods can also be found in the literature [22–27]. However, these methods are hard to be implemented and mostly time consuming and they strongly relate to the proposed models and applications. For this main reason, a generic method and few required assumptions about the transmission channel are proposed and discussed in this manuscript.
The recent spread of cellular systems (smart sensors, mobile phones, base stations, satellites, surveillance devices, traffic radars, etc.) has increased the complexity of processing algorithms as well as the model of transmission channels. In fact, in various applications, transceiver units are in motion. For such systems, the transmission channels can no longer be considered as static channels, i.e., they cannot be modeled by stationary random variables. To overcome this difficulty, most researchers assume that the transmission channels are static during the processing time^{a}[28–30].
In this manuscript, the proposed models are improved by considering that transmission channels are dynamic channels that can be modeled as nonstationary variables. It is worth mentioning that for antennas mounted on moving vehicles or drones, the transmission channels can be approximated by almost static or slowly evolutionary dynamic channels over certain periods. The transition among these periods can be very fast. In addition, during two adjacent periods, transmission channels can have completely different statistical properties and/or PDFs. This scenario illustrates a typical scenario of a mobile phone used in a moving car which is moving among big buildings in a modern city. It can represent as well the scenario of a drone flying at low altitude in a mountainous area.
In what follows, we consider that transmission channels can be modeled as shortterm stationary signals and longterm nonstationary signals (many natural and physical signals belong to this category, such as speech signals [31, 32]). Herein, we develop an algorithm to accurately estimate the transition times. The algorithm is based on highorder statistics (HOS). In several study cases, HOS are shown to be more promising than the secondorder stochastic methods, namely, power, variance, covariance, and spectra. In fact, HOS have been used to solve many recent and important telecommunication problems [33, 34], such as blind identification or equalization, blind separation of sources, and time delay estimation [35–38]. It is worth mentioning that most of these HOS algorithms are only based on the second and the fourthorder statistics [39]. Once the transition times are estimated, we should be able to estimate the PDF of the local stationary random variable (i.e., during a shortterm period).
It is well known that any random variable can be completely described by its PDF [40]. In many cases, an accurate estimation of the PDF of physical parameters of interest (which are random variables) is essential to achieve our goals. This is while an accurate estimation of PDFs is still challenging to researchers. The estimation of PDFs is a relatively old problem that has been considered since the beginning of the last century with the rise and the development of new and modern complex systems (radars, sonar, and wireless communication systems). However, in late 1950s, systematic mathematical approaches have been proposed. One of the pioneering work in this field is the work presented by Rosenblatt in [41]. Parzen in [42] formulated the estimation of PDFs using kernel approaches. Later on, new approaches emerged to overcome the specification of diverse applications such as the sum of Gamma densities in Risk Theory [43] or the sum of exponential random variables in wireless communication [44]. Other researchers have focused on the choice of the kernel and smoothing functions [45, 46]. The estimation of PDFs using orthogonal series has been introduced by Schwartz in [47]. In more recent work, wavelets have been used as a nonparametric estimation of PDFs [48]. Similar to previous work, Engel used Haar’s series to estimate PDFs [49]. Using autoregressive (AR) models, Kay in [50] proved that PDFs can be estimated by appealing the theory of power spectral density (PSD). More recent work reintroduced the estimation of PDF using a windowed Fourier transform [51] or Hermite’s orthonormal basis set [52]. We should mention that all the abovementioned work assume that the random variables are stationary. In countless applications, the stationarity assumption may be invalid [53]. To the best of our knowledge, there is no such PDF estimator for nonstationary random variables. Hence, it is the aim of this paper to propose a PDF estimator based on a smooth kernel PDF estimator that assumes known transition times.
2 Mathematical model and background
In this paper, we consider the case of real nonstationary random variables^{b}. We also assume (1.1 in Appendix Appendix 1: highorder statistics estimators) that random variables consisting of transmission channels are stationary by part [54, 55]. While this assumption is less strict than the most widely used assumption of stationary transmission channels, its consideration is justified in the case of moving receivers or transmitters.
The HOS are much easier to be estimated than PDF, as will be shown in the next section. For this reason, our nonstationary transition indicator is based on the second and fourthorder statistics. In fact, the transition of nonstationary random variable can generate discontinuity in its HOS. As the variance of any signal should be different than zero, then it can be used to identify the existence of signals. On the other hand, normalized signals have the same unit variance. Therefore, the variance is not enough to identify the transition in a general case. Besides that, the fourthorder cumulants of Gaussian signals are zeros. For these reasons, we developed a nonstationary transition indicator based on the variance and the fourthorder cumulant.
3 Unbiased and adaptive HOS estimators
It is worth mentioning that the above estimators are only unbiased for stationary signals. In case of nonstationary signals, adaptive estimators should be developed.
where 0<γ<1 is another forgetting factor.
4 PDF estimators
with u(x) being the Heaviside step function.
The above equation can be considered as a kernel estimator. Window length and parameters are the key factors which can affect the performance of the estimator [51]. To avoid the problem of this approach and apply the wellestablished theory of power spectral density, Kay in [50] proposed an AR model of order p to estimate the PDF. Parameters of his AR model are estimated using YuleWalker equations and Levinson recursion.
Using GramCharlier series to expand the PDF in terms of the normal density and its derivatives, Bowers in [43] approximated a risk theoretic distribution by the sum of Gamma RVs. In his expansion, the polynomials which multiply the PDF of a zeromean normalized normal PDF are the Hermite polynomials (see Appendix Appendix 2: Hermite’s polynomial functions). This study was generalized by Schwartz in [47].
According to Vannucci [24], there are different types of nonparametric density estimators: delta sequence estimators (such as kernel, histogram, and orthogonal series estimators) and penalized maximum likelihood estimators such as spline estimators. She also proved that scaling functions give a good approximation of smooth functions, while wavelets^{h} can deal with functions which have local fluctuations. In order to practically apply wavelet estimators, a truncation should be made [24]. Therefore, the overall performance depends on the truncation order. An optimal choice of such order can be determined by minimizing the integrated square error or the intergraded mean square error. In realworld applications, another problem can arise related to the evaluation of the scaling and the mother functions at arbitrary points [24]. In [49], Engel used Haar’s functions to estimate the PDF and shows that his estimator is equivalent to a histogram on certain dyadic intervals.
Recently, the authors of [51, 52] have compared their approaches to the abovementioned ones. In fact, Xie and Wang in [51] showed that an estimator based on the Fourier transform of the characteristic function gives similar results to the AR model PDF estimator proposed earlier by Kay in [50]. They also showed that in certain cases, histograms can provide similar overall performance to previously mentioned estimators. However, Howard in [52] showed that the Hermite basis estimator can slightly achieve better results than the estimator based on the Fourier transform of the characteristic function proposed in [51]. For these reasons, we only consider the histogram, the Hermite basis estimator and the smooth kernel density estimator proposed by Bowan in [45, 46]. Our simulations have shown that smooth kernel density has slightly better performance than the previous mentioned ones (see Section 7).

The integrated error$\phantom{\rule{2em}{0ex}}{\epsilon}_{1}=E\left\{\mid {f}_{X}\left(x\right){\widehat{f}}_{X}\left(x\right)\mid \right\}$

The root of the meansquared error$\phantom{\rule{2em}{0ex}}{\epsilon}_{2}=\sqrt{E\left\{\mid {f}_{X}\left(x\right){\widehat{f}}_{X}\left(x\right){\mid}^{2}\right\}}$
5 Representation of nonstationary PDF
In fact, classic PDF estimators cannot provide an accurate estimation of the nonstationary signal PDF. By applying a smooth kernel density estimator over 10,000 independent realization of h(t), a bimodal PDF was obtained (see Figure 1b). It is clear that the obtained PDF cannot correctly represent the PDF shown in Figure 1a.
6 Nonstationary transition indicator
In order to estimate the PDF parts of quasi nonstationary RV, one can easily use the estimator developed in the previous section to detect the number and the size of the stationary parts. Once these parts are well identified and their sizes are relatively enough to estimate a PDF, we can apply any classic PDF estimator. To make this estimation more robust, cumulants of different order (mainly the second and the fourth order) can be used to identify such parts. In fact, Gaussian signals are characterized by their zero fourthorder cumulant (see Appendix Appendix 1: highorder statistics estimators). In these case, the fourth order cannot separate two adjacent Gaussian parts. However, if these two parts represent two normal RVs with different means or variances, then the second or the first moment can be used to identify these parts. If the two Gaussian parts have the same mean and variance then they can describe the same RV due to the basic assumptions about the whiteness of the samples (i.e., the realization of X).
 1.
The first part contains 8,000 samples of uniform random variable included in [ 1,1].
 2.
The second part is made of 6,000 samples of zeromean and unite variance Gaussian signal.
 3.
The 10,000 samples of a uniform random variable in [ 2,2] formed the third part.
 4.
The fourth part is a zeromean Gaussian signal with a standard deviation of $\sqrt{2}$.
 1.
First, the obtained signals are filtered using the smoothing polynomial regression filter proposed by SavitzkyGolay [64–66]. The main idea of the SavitzkyGolay filter is to apply a FIR filter such that its coefficients minimize the meansquared approximation error. This filter is used to filter biomedical signals such as EEG signals (see Figure 4).
While the filtered signals are much better smoothed than the raw signals, they are still relatively noisy to obtain an accurate estimate of transition time. In fact, Figure 6 shows that the obtained filtered estimators are still suffering from the previously mentioned drawbacks, i.e., the inaccuracy in the estimation of the HOS and the transition times.

First, the PDF of the filtered HOS estimators are obtained using the kernel PDF estimator (see Figure 7). Then the maximum values of the obtained PDF are recorded as the coefficients of a vector called maxHOS.

The coefficients of the vector maxHOS are introduced as the center of clusters. By minimizing Euclidean distance among the samples of the filtered HOS estimator, all samples of filtered estimated cumulants are clustered in rectangular signals which represent theoretical values of the HOS (see Figure 8).

Various simulations have been conducted. Our simulations showed that sometimes the rectangular clustered signals suffer from local narrow spurious error windows (see Figure 8). These spurious error windows are normally very narrow. Hence, by supposing that the channel is not a highly dynamic one, i.e., any channel parameter cannot change more than one time in a short period (for example, the short period can be the symbol duration). In this case, one can easily eliminate these windows. In order to clean out the clustered rectangular signals and achieve an accurate nonstationary indicator, the derivative of these signals is evaluated (see Figure 9).

Let us assume 1.2 in Appendix Appendix 1: highorder statistics estimators that the stationary parts of the channels have more than 1,000 samples (in many cases, 500 samples were enough to obtain good results). In this case, each of local narrow spurious error windows generates two Dirac delta functions with equal values and opposite signs. Based on 1.2 in Appendix Appendix 1: highorder statistics estimators, the two delta functions should be close to each other within 1,000 samples. Using this fact, we developed and implemented a recursive filtering procedure called continuity process (CP) to eliminate these spurious windows (see Figure 10). The Matlab code is given in Appendix Appendix 3: continuity process algorithm.

Figure 10 shows that the impact of the local narrow spurious error windows is completely eliminated. However, our nonstationary indicator still suffers from twostep transition problem, i.e., the transition between two valid states of the cluster rectangular signals is not immediate (this case can be shown in Figure 8 around the 14,000th and 24,000th samples). Using 1.2 in Appendix Appendix 1: highorder statistics estimators and the fact that the twostep transition problem generates two Dirac delta functions with different values but sharing the same sign, we developed another process called twostep transition process to deal with this problem (see Appendix Appendix 3: continuity process algorithm).

Finally, a clear and accurate nonstationary indicator is obtained. Our final indicator is the output of an ‘OR’ gate applied on the nonstationary indicator of various HOS (in our case, we used two HOS, i.e., the second and the fourth cumulants). The final indicator is shown in Figure 11. In Figure 12, the synoptic of our proposed algorithm using smoothing filters and nearestneighbor clustering algorithm is presented.
7 PDF estimator for nonstationary signals
where, for example, M∈1,2, and Pr[ M=1]=p_{2}. We proved (see Appendix 4) that the sum should be just over two independent RV and we give the statistical properties of the newly obtained RV.
 1.
It depends on the value of k _{ s },
 2.
It can generate a negative function, see Figure 14.
8 Conclusions
In this manuscript, a transition indicator for nonstationary signals is presented. The new indicator is based on HOS of quasi nonstationary variables (the random variables are considered stationary by parts). To estimate the HOS, unbiased adaptive exponential estimators are presented.
To reduce the noise level of the HOS estimators, we used a cascade filtering procedure based on SavitzkyGolay filters and a truncation of its Walsh Hadamard transform. Then rectangular signals representing the theoretical values of HOS are obtained by using clustering algorithm using the maxima of kernel PDF estimator and minimizing Euclidean distances.
Simulation studies show that the obtained rectangular signals can suffer from local narrow spurious error windows which can be eliminated using a continuity assumption 1.2 in Appendix Appendix 1: highorder statistics estimators and a continuity cleaning procedure called continuity process. In addition to these local narrow spurious error windows, estimated signals suffer another artifact called the twostep transition problem. After solving this problem using assumption 1.2 in Appendix Appendix 1: highorder statistics estimators and a continuity procedure, an accurate transition indicator of nonstationary signals is achieved. Simulation studies corroborate the performance of our proposed algorithm and the accuracy of our nonstationary transition indicator.
Finally, a survey of major PDF estimators is done. A comparative study is also presented and discussed. The advantages and drawbacks of major methods are highlighted and a theoretical study is provided. Simulation results show a slight advantage of smooth kernel estimator methods. It is worth mentioning that the histogram with a large number of samples is still one of the simplest and efficient estimators. The case of nonstationary process was considered and a PDF estimation approach was discussed.
Endnotes
^{a}However, the processing time is not standardized. In fact, different authors claim that the parameters of the channel should remain constant during one frame duration, few hundred symbols, or during the convergence time of their adaptive algorithms.
^{b}The fact that the channel is considered as a real channel is not limiting our approach, as a complex Gaussian channel could be represented by its modulus as a Rayleigh channel.
where the addition operation is over all the set of v_{ i } (1≤i≤p≤r) and v_{ i } constitutes a partition of {1,…,r}, [40].
^{d}In many applications, the stochastic signal X is a zeromean signal. This assumption is not a major one and it has been used in many studies (please see [58] and the cited references therein). In fact, by considering this assumption, the mathematical notations can be simplified. However, all the proposed steps can be straightforwardly derived in the case of a nonzero mean transmission channel. Besides that, the mean can be estimated and canceled out from the other equations.
^{e}Further details are given in Appendix Appendix 1: highorder statistics estimators.
^{g}A function f(x) is called Borel’s function if $\forall y\in \mathcal{A}$ is an open set, the inverse of f(x), and x=f^{1}(y) is an element of a Borel’s set, i.e., Lebesgue measurable set [62].
^{h}Wavelets are basis functions which have quite interesting properties such as their localization in space and frequency [24].
Appendix 1: highorder statistics estimators
In this section, HOS estimators are developed. Generally, HOS estimators can be divided into main families: the arithmetic and the exponential estimators.
1.1 Arithmetic estimators
where $\hat{{\mu}_{r}}\left\{k\right\}$ is the estimator of the r th order moment at the k th iteration.
1.2 Exponential estimators
1.3 Adaptive unbiased estimators of the fourthorder cumulants
Appendix 2: Hermite’s polynomial functions
Appendix 3: continuity process algorithm
Appendix 4
The PDF of a moderate sum of two uncorrelated RVs
where * represents the convolution product. If X_{1} and X_{2} are two uncorrelated mutually Gaussian RVs, then Z=X_{1}+X_{2} is another normal RV with $\mathcal{N}\left({m}_{1}+{m}_{2},\sqrt{{\sigma}_{1}^{2}+{\sigma}_{2}^{2}}\right)$, which proves the proposed statement.
Authors’ information
AM received his M.Sc. and Ph.D. degrees in Signal, Image and Speech Processing from the ‘Institut National Polytechnique de Grenoble  INPG’ (Grenoble, France) on July 1993 and January 1997, respectively, and his HDR degree (Habilitation a Diriger des Recherches; in the French system, this is the highest of the higher degrees) on November 2006 from the Universite de Bretagne Occidentale  UBO (Brest, France). His research interests are in the areas of blind separation of sources, highorder statistics, signal processing, passive acoustics, cognitive radio, robotics, and telecommunication. From January 1997 to July 1997, he held a postdoc position at Lab. de Traitement d’Images et Reconnaissance de Forme, France. From August 1997 to September 2001, he was a research scientist at the BioMimetic Control Research Center (BMC) in Riken, Nagoya, Japan. From October 2001 to January 2008, he was holding a teacherresearcher position at the Ecole Nationale Supérieure des Ingénieurs des Etudes et Techniques d’Armement (ENSIETA) in Brest, France. From February 2008 to August 2010, he was a senior lecturer at the ECE Department of Curtin University, Perth, Australia. During January 2009, he held an invited professor position at the Universite du Littoral Cote d’Opale in Calais, France. From September 2010 till June 2012, he was a professor at University of Tabuk, Kingdom of Saudi Arabia. He also served as the electrical department head at the University of Tabuk. Since September 2012, he has been a professor at Ecole Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne) in Brest, France. He is the author and the coauthor of three books. He is the first author of several papers published in international journals. He is also the first author of many papers published in the proceedings of various international conferences. Finally, he was elected to the grade of IEEE Senior Member in February 2006. He has been a member of Technical Program Committees (TPC) and he was a chair, cochair, and a scientific committee member in various international conferences. He is an active reviewer for a variety of international journals. He was a lead guest editor of EURASIP Journal on Advances in Signal Processing.
RM (S’00M’08SM’13) holds a Ph.D. in Electrical Engineering from Jacobs University in Bremen, Germany and several years of postdoctoral wireless communication and optical wireless communication research experience in Germany. In October 2010, he joined University of Tabuk in Saudi Arabia where he is now an assistant professor and the director of research excellence unit. His main research interests are in spatial modulation, MIMO cooperative wireless communication techniques, and optical wireless communication. His publications received more than 800 citations since 2007. He has published more than 50 publications in toptier journals and conferences, and he holds seven granted patents. He also serves as on the TPC for academic conferences and is a regular reviewer for most of IEEE/OSA Communication Society’s journals and IEEE/OSA Photonics Society’s journals.
HMA received his M.S. and Ph.D. degrees in Electrical Engineering from the University of Washington (UW), Seattle, WA, USA. He is a professional engineer registered in the State of Washington and a senior member of the Institute of the IEEE. He has taught graduate and undergraduate courses in Electrical Engineering at a number of universities in the USA and abroad. He served at many academic ranks including Endowed Chair Professor and Vice President and Provost. He was the winner of the Boeing Supplier Excellence Award. He was also the winner of the IEEE Professor of the Year Award, UW Branch. He is listed as inventor in a major patent assigned to the Boeing Company. His research work is referred to in many patents including patents assigned to ABB, Switzerland, and EPRI, USA. Currently, he is a professor and director of the Sensor Networks and Cellular Systems (SNCS) Research Center, University of Tabuk, Tabuk, Saudi Arabia. He authored many papers in IEEE and other journals and conferences. His research interests include modeling and simulation of large scale networks, sensors and sensor networks, scientific visualization, and control and energy systems.
Declarations
Acknowledgements
The authors gratefully acknowledge the support for this work by SNCS Research Center at the University of Tabuk under the grant from the Saudi Ministry of Higher Education.
Authors’ Affiliations
References
 Proakis J, Salehi M: Digital Communications. New York: McGrawHill; 2007.Google Scholar
 Tarokh V, Jafarkhani H, Calderbank AR: Spacetime codes high data rate wireless communication: performance crirterion and construction. IEEE Trans. Inf. Theory 1998, 44(2):744. 10.1109/18.661517MATHView ArticleGoogle Scholar
 Bradaric I, Petropulu AP, Diamantaras K: On blind identification of FIRMIMO systems with cyclostationary inputs using second order statistics. IEEE Trans. Signal Process 2003, 51(2):434. 10.1109/TSP.2002.806998View ArticleGoogle Scholar
 Srar JA, Chung KS, Mansour A: Adaptive array beamforming using a combined LMSLMS algorithm. IEEE Trans. Antennas Propagation 2010, 58: 3545.View ArticleGoogle Scholar
 Mesleh R, Ikki S, Aggoune H, Mansour A: Performance analysis of space shift keying (SSK) modulation with multiple cooperative relays. EURASIP J. Adv. Signal Process 2012., 1: doi:10.1186/168761802012201Google Scholar
 Abaza M, Mesleh R, Mansour A, Alfalou A: MIMO techniques for high data rate free space optical communication system in lognormal channel. In International Conference on Technological Advances in Electrical, Electronics and Computer Engineering. Konya: TAEECE,; 9–11 May 2013:161166.Google Scholar
 Simon M, Alouini MS: Digital Communication over Fading Channels: a Unified Approach to Performance Analysis. New York: Wiley; 2000.View ArticleGoogle Scholar
 Haykin S, Moher M: Communication Systems. New York: Wiley; 2009.Google Scholar
 Abaza M, Mesleh R, Mansour A, Aggoune HA: Diversity techniques for FSO communication system in correlated lognormal channels. Opt. Eng 2014., 53(1): 10.1117/1.OE.53.1.016102Google Scholar
 Skitovic VP: Linear forms of independent random variables and the normal distribution law. Izvestiya Akademii Nauk SSSR. Seriya Matematiceskaya 1954., 18(185): In RussianMATHGoogle Scholar
 Kendall M, Stuart A: The Advanced Theory of Statistics: Distribution Theory. London: Charles Griffin & Company Limited; 1961.Google Scholar
 Nikias CL, Shao M: Signal Processing with αStable Distribution and Applications. New York: Wiley; 1995.Google Scholar
 Sijbers J, Den Dekker J, Scheunders P, Van Dyck D: Maximumlikelihood estimation of Rician distribution parameters. IEEE Trans. Med. Imaging 1998, 17(3):357. 10.1109/42.712125View ArticleGoogle Scholar
 Karagiannidis GK, Zogas DA, Kotsopoulos SA: On the multivariate Nakagamim distribution with exponential correlation. IEEE Trans. Commun 2003, 51(8):1240. 10.1109/TCOMM.2003.815071View ArticleGoogle Scholar
 Yacoub MD, Fraidenraich G, Santos Filho JCS: Nakagamim phaseenvelope joint distribution. Electron. Lett 2005., 41(5): doi:10.1049/el:20057014Google Scholar
 Yacoub MD, Fraidenraich G, Tercius HB, Martins FC: The symmetrical on the η  κ distribution: a general fading distribution. IEEE Trans. Broadcasting 2005, 51: 504. 10.1109/TBC.2005.859240View ArticleGoogle Scholar
 Fraidernraich G, Daoud Yacoub M: The α  η  μ and α  k  μ fading distributions. In IEEE 9th International Symposium on Spread Spectrum Techniques and Applications. Manaus; 28–31 August 2006:255263.Google Scholar
 Nadarajah S, Kotz S: On the η  κ distribution. IEEE Trans. Broadcasting 2006, 52(3):411. 10.1109/TBC.2006.879862View ArticleGoogle Scholar
 Yacoub MD: The α  η distribution: a physical fading model for the Stacy distribution. IEEE Trans. Vehicular Technol 2007, 56(1):27.View ArticleGoogle Scholar
 Cotton SL, Scanlon WG, Guy J: The k  μ distribution: applied to the analysis of fading in body to body communication channels for fire and rescue personnel. IEEE Antennas Wireless Propagation Lett 2008, 7: 66.View ArticleGoogle Scholar
 Yacoub MD: Nakagamim phaseenvelope joint distribution: an improved model. In Microwave and Optoelectronics Conference, IMOC’2009. Belem; 3–9 November 2009:335339.Google Scholar
 Cox DD: A penalty method for nonparametric estimation of the logarithmic derivative of a density function. Ann. Instit. Stat. Math 1985, 37: 271. 10.1007/BF02481097MATHView ArticleMathSciNetGoogle Scholar
 Vidal J, Bonafonte A, Fonollosa AR, De Losada NF: Parametric modeling of PDF using a convolution of onesided exponentials: application to HMM. In European Signal Processing Conference, ed. by M Holt, C Cowan, P Grant, W Sandham, European Signal Processing Conference. Edinburgh: Elsevier,; 1994:5457.Google Scholar
 Vannucci M: Nonparametric density estimation using wavelets. Discussion Paper, Duke University, 1998Google Scholar
 Archambeau A, Verleysen M: Fully nonparametric probability density function estimation with finite gausssian mixture models. In 5th International Conference on Advances in Pattern Recognition Calcultta, ICAPR’2003. Allied, New Delhi, Calcultta; 2003:8184.Google Scholar
 Boscolo R, Pan H, Roychowdhury VP: IEEE Trans. Neural Netw. 2004, 15(1):55.View ArticleGoogle Scholar
 Roueff F, Rydén T: Nonparametric estimation of mixing densities for discrete distributions. Ann. Stat 2005, 33(5):2066. 10.1214/009053605000000381MATHView ArticleMathSciNetGoogle Scholar
 Alamouti S: A simple transmit diversity technique for wireless communication. IEEE J. Selected Areas Commun 1998, 16(8):1451. 10.1109/49.730453View ArticleGoogle Scholar
 Larsson EG, Stoica P: Spacetime Block Coding for Wireless Communications. Cambridge: The Press Syndicate of the University of Cambridge; 2003.MATHView ArticleGoogle Scholar
 Choqueuse V, Mansour A, Burel G, Collin L, Yao K: Blind channel estimation for STBC systems using higherorder statistics. IEEE Trans. Wireless Commun 2011, 10: 495.View ArticleGoogle Scholar
 Mansour A, Jutten C, Ohnishi N: Kurtosis: definition and properties. In International Conference on MultisourceMultisensor Information Fusion. Edited by: Arabnia HR, Zhu DD. Las Vegas; 6–9 July 1998:4046.Google Scholar
 Mansour A, Jutten C: What should we say about the kurtosis. IEEE Signal Process. Lett 1999, 6(12):321.View ArticleGoogle Scholar
 Mendel JM: Tutorial on higherorder statistics (Spectra) in signal processing and system theory: theoretical results and some applications. IEEE Proc 1991, 79: 277.View ArticleGoogle Scholar
 Cichocki A, Amari SI: Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications. New York: Wiley; 2002.View ArticleGoogle Scholar
 Cardoso JF: Source separation using higher order moments. In Proceedings of International Conference on Speech and Signal Processing 1989, ICASSP 1989. Glasgow; 22–25 May 1989:21092212.Google Scholar
 Comon P: Independent component analysis, a new concept. Signal Process 1994, 36(3):287. 10.1016/01651684(94)900299MATHView ArticleGoogle Scholar
 Mansour A, Jutten C: A direct solution for blind separation of sources. IEEE Trans. Signal Process 1996, 44(3):746. 10.1109/78.489054View ArticleGoogle Scholar
 Hyvärinen A, Karhunen J, Oja E: Independent Component Analysis. New York: Wiley; 2001.View ArticleGoogle Scholar
 Mansour A, Kardec Barros A, Ohnishi N: Blind separation of sources: methods, assumptions and applications. IEICE Trans. Fundamentals Electron. Commun. Comput. Sci 2000, E83A(8):1498.Google Scholar
 Papoulis A: Probability, Random Variables, and Stochastic Processes. New York: McGrawHill; 1991.MATHGoogle Scholar
 Rosenblatt M: Remarks on some nonparametric estimates of a density function. Ann. Math. Stat 1956, 27(3):832. 10.1214/aoms/1177728190MATHMathSciNetView ArticleGoogle Scholar
 Parzen E: On the estimation of a probability density function and mode. Ann. Math. Stat 1962, 33(3):1065. 10.1214/aoms/1177704472MATHMathSciNetView ArticleGoogle Scholar
 Bowers LN: Expansion of probability density functions as a sum of gamma densities with applications in risk theory. Trans. Soc. Actuaries 1966, 18 PT 1(52):125.Google Scholar
 Khuong HV, Kong HY: General expression for pdf of a sum of independent exponential random variables. IEEE Commun. Lett 2006, 10(3):159. 10.1109/LCOMM.2006.1603370View ArticleGoogle Scholar
 Reinsch CH, Smoothing by spline functions: Numer. Math. 1967, 10: 177. 10.1007/BF02162161MATHMathSciNetView ArticleGoogle Scholar
 Bowman AW, Azzalini A: Applied Smoothing Techniques for Data Analysis. New York: Oxford University; 1997.MATHGoogle Scholar
 Schwartz SC: Estimation of probability density by an orthogonal series. Ann. Math. Stat 1967, 38(3):1261.MATHView ArticleMathSciNetGoogle Scholar
 Vannucci M: On the application of wavelets in statistics. Ph.D. thesis, Dipartimento di Statistica, University of Florence, 1996Google Scholar
 Engel J: Density estimation with, Haar series. Stat. Probability Lett 1990, 9: 111. 10.1016/01677152(92)90003NMATHMathSciNetView ArticleGoogle Scholar
 Kay S: Modelbased probability density function estimation. IEEE Signal Process. Lett 2001, 5(12):318.View ArticleGoogle Scholar
 Xie J, Wang Z: Probability density function estimation based on windowed Fourier transform of characteristic function. In Proceedings of the 2nd International Congress on Image and Signal Processing. Tianjin; 17–19 October 2009.Google Scholar
 Howard RM: PDF estimation via characteristic function and an orthonormal basis set. In Proceedings of the 14th WSEAS International Conference on Systems. Corfu; 23–25 July 2010:100105.Google Scholar
 Mansour A: Probabilités et statistiques pour les ingénieurs: cours, exercices et programmation. Paris: Hermes Science; 2007.Google Scholar
 Mesleh R, Haas H, Sinanovic S, Ahn CW, Yun S: Spatial modulation. IEEE Trans. Vehicule Technol 2008, 57(4):2228.View ArticleGoogle Scholar
 Wang Z, Giannakis GB: A simple general parameterization quantifying performance in fading channels. IEEE Trans. Commun 2003, 51(8):1389. 10.1109/TCOMM.2003.815053View ArticleGoogle Scholar
 McCullagh P: Tensor Methods in Statistics. London: Chapman and Hall; 1987.MATHGoogle Scholar
 Shiryayev AN: Probability. London: Springer; 1984.MATHView ArticleGoogle Scholar
 Vu MH: Exploiting transmit channel side information in MIMO wireless systems. Ph.D. thesis, Stanford University, 2006Google Scholar
 Kotz S, Johnson NL: Encyclopedia of Statistical Sciences. Amesterdam: University of Amesterdam; 1993.Google Scholar
 Lacoume JL, Amblard PO, Comon P: Statistiques d’ordre supérieur pour le traitement du signal. Paris: Mason; 1997.Google Scholar
 Bass J: Cours de Mathématiques: Tome 1, Fasicule 2. Masson, Paris, New York, Barcelone et Milan; 1977.Google Scholar
 Bass J: Cours de Mathématiques: Tome 2. Masson, Paris, New York, Barcelone et Milan; 1977.MATHGoogle Scholar
 Mansour A, Kawamoto M: ICA papers classified according to their applications & performances. IEICE Trans. Fundamentals Electron. Commun. Comput. Sci 2003, E86A(3):620.Google Scholar
 Savitzky A, Golay MJE: Soothing and differentiation of data by simplified least squares procedures. Anal. Chem 1994, 36: 16271639.View ArticleGoogle Scholar
 Orfanidis SJ: Introduction to Signal Processing. New Jersey: PrenticeHall; 1995.Google Scholar
 Schafer RW: What is a SavitzkyGolay filter? IEEE Signal Process. Mag 2011, 111117.Google Scholar
 Beauchamp K: Applications of Walsh and Related Functions. New York: Academic; 1984.Google Scholar
 Kendall M, Stuart A: The Advanced Theory of Statistics: Design and Analysis, and Timeseries. London: Charles Griffin & Company Limited; 1961.MATHGoogle Scholar
 Mansour A, Kardec Barros A, Ohnishi N: Comparison among three estimators for high order statistics. In Fifth International Conference on Neural Information Processing (ICONIP’98). Edited by: Usui S, Omori T. Kitakyushu; 21–23 October 1998:899902.Google Scholar
 Martin A, Mansour A: Comparative study of high order statistics estimators. In International Conference on Software, Telecommunications and Computer Networks. Split, Dubrovnik, Venice; 10–13 October 2004:511515.Google Scholar
 Bouvier A, George M, Le Lionnais F: Dictionnaire des mathématiques. Paris: Presses Universitaires De France,; 1993.MATHGoogle Scholar
Copyright
This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.