Aline Neves - Academia.edu (original) (raw)

Papers by Aline Neves

Research paper thumbnail of Análise De Critérios De Equalização Cega Baseados Em Aprendizagem Por Teoria Da Informação

Research paper thumbnail of Unsupervised Signal Processing: Concepts, Applications and Trends

Research paper thumbnail of Analysis of ITL Criteria in the Context of FIR Channel Equalization

Journal of Communication and Information Systems, 2016

Research paper thumbnail of An algebraic receiver for full response CPM demodulation

2006 International Telecommunications Symposium, Sep 1, 2006

This paper proposes a new algebraic demodulation method for full response CPM signals in AWGN cha... more This paper proposes a new algebraic demodulation method for full response CPM signals in AWGN channel. The method is based in a new estimation/identification theory that has also already been used for channel identification and signal deconvolution. The signals and noise are considered to be deterministic and we find an explicit formula for the recovery of the transmitted symbols. Based on this formula, the symbols are recovered blindly, needing only the knowledge of the modulation index. The method is not only simple and robust to noise, but also very fast, what enables its implementation on-line. It can also be equally used for coherent or non-coherent demodulations. The method is applied to the CPFSK and LRC families of signals showing good results.

Research paper thumbnail of Lower Bound of the Constant Modulus Criterion for Multilevel Modulations

The recently proposed lower bound of the classical blind CM criterion was shown to be able to wor... more The recently proposed lower bound of the classical blind CM criterion was shown to be able to work as an excellent blind equalizability index, which is a practical performance assessment metric in the context of inverse problems. However, there still remains the need of complementary studies aiming to cover a wider range of circumstances. Based on this, we present in this work an extension of the analysis of the lower bound by considering scenarios with multilevel modulated signals. For an 8-PAM and a 16-QAM signal, the simulations revealed the presence of a residual error offset, but even so, the validity of the index was preserved.

Research paper thumbnail of A Novel Entropy-based Equalization Performance Measure and Relations to Lp -Norm Deconvolution

A crucial performance measure in the context of the problem of deconvolution is the level of resi... more A crucial performance measure in the context of the problem of deconvolution is the level of residual intersymbol interference (ISI), a metric that is classically understood and formulated in terms of an L2-norm perspective. In order to enhance the scope of ISI quantification, we propose a novel entropy-based performance measure, which is called Entropybased Intersymbol Interference (HISI). Interestingly, this metric is related to an information-theoretic relationship between source distribution and Lp-norms when the error entropy is used as a basis for optimal filtering. The new metric is analytically investigated and illustrated with some simulations.

Research paper thumbnail of An Algebraic Receiver for Full Response CPM

This paper proposes a new algebraic demodulation method for full response CPM signals in AWGN cha... more This paper proposes a new algebraic demodulation method for full response CPM signals in AWGN channel. The method is based in a new estimation/identification theory that has also already been used for channel identification and signal deconvolution. The signals and noise are considered to be deterministic and we find an explicit formula for the recovery of the transmitted symbols. Based

Research paper thumbnail of Algebraic Parameter Estimation of Damped Exponentials

The parameter estimation of a sum of exponentials or the exponential fitting of data is a well kn... more The parameter estimation of a sum of exponentials or the exponential fitting of data is a well known problem with a rich history. It is a nonlinear problem which presents sev- eral difficulties as the ill-conditioning when roots have close values and the order of the estimated parameters, among oth- ers. One of the best existing methods is the modified

Research paper thumbnail of An Algebraic Identification Method for the Demodulation of QPSK Signal Through a Convolutive Channel

We present a straightforward algebraic setting for the de- modulation of a QPSK (Quadrature Phase... more We present a straightforward algebraic setting for the de- modulation of a QPSK (Quadrature Phase Shift Keying) signal over a convolutive and additive noise channel. Our method exploits the form of the continuous-time received signal without questioning the digital nature of the commu- nication system. The developments rely on classical deter- ministic numerical analysis. No assumption is required for the

Research paper thumbnail of Restoration of the voice timbre in telephone networks based on both voice and line properties

First International Symposium on Control, Communications and Signal Processing, 2004., 2004

The voice timbre suffers from different forms of distorsions in a telephone link. In this paper, ... more The voice timbre suffers from different forms of distorsions in a telephone link. In this paper, we propose a new blind equalizer for correcting these distortions, based on the combination of two different methods. The first one is a blind equalization method consisting in matching the long term spectrum of the processed signal to a reference spectrum, while the second one is a precompensation method, based on the physical characteristics of transmission lines. The new method is compared to the first one, showing a significant gain in performance.

Research paper thumbnail of Blind Equalization Based on a Cascade of Optimal Two-Tap CM Equalizers

This article introduces a blind equalization methodology based on a cascade of two-tap finite imp... more This article introduces a blind equalization methodology based on a cascade of two-tap finite impulse response filters globally optimal with respect to the constant modulus (CM) criterion. It is shown that a formulation of the CM cost function in terms of a mean squared error (MSE) metric and of Volterra-like constraints allow the optimization process to be carried out, when two parameters are to be adapted, with the aid of a one-dimensional search process that suits quite well an exhaustive framework. The proposal will be compared to a similar cascade of two-tap Wiener solutions and also with conventional Wiener filters.

Research paper thumbnail of Lower Bound of the Constant Modulus Criterion for Multilevel Modulations

The recently proposed lower bound of the classical blind CM criterion was shown to be able to wor... more The recently proposed lower bound of the classical blind CM criterion was shown to be able to work as an excellent blind equalizability index, which is a practical performance assessment metric in the context of inverse problems. However, there still remains the need of complementary studies aiming to cover a wider range of circumstances. Based on this, we present in this work an extension of the analysis of the lower bound by considering scenarios with multilevel modulated signals. For an 8-PAM and a 16-QAM signal, the simulations revealed the presence of a residual error offset, but even so, the validity of the index was preserved.

Research paper thumbnail of Uma Visão Geométrica da Formulação Polinomial do Critério CM

Recentemente, concebeu-se uma formulação polinomial do critério CM, a qual permitiu a obtenção de... more Recentemente, concebeu-se uma formulação polinomial do critério CM, a qual permitiu a obtenção de um limitante inferior para a função custo CM e de soluções analíticas baseadas na relaxação de restrições [1]. Neste trabalho, apresentaremos uma visão geométrica dessa formulação. Métodos: A formulação toma como ponto de partida a função custo CM, e adota, como elemento chave, o termo quadrático υ c (n) = y 2 (n), em que y(n) = w T x(n) é a saída do filtro linear com vetor de parâmetros w e x(n) é o vetor de entrada. Particularmente, υ c (n) pode ser expresso como υ(n) = θ c T ξ(n), sendo ξ(n) o vetor de entrada no domínio de Volterra e θ c o filtro polinomial com restrições. Isto permite a representação do custo, como

Research paper thumbnail of An Analysis of Unsupervised Signal Processing Methods in the Context of Correlated Sources

Lecture Notes in Computer Science, 2009

In light of the recently proposed generalized correlation function named correntropy, which explo... more In light of the recently proposed generalized correlation function named correntropy, which exploits higher-order statistics and the time structure of signals, we have, in this work, two main objectives: 1) to give a new interpretation – founded on the relationships between the constant modulus (CM) and Shalvi-Weinstein criteria and between the latter and methods for ICA based on nongaussianity –

Research paper thumbnail of A volterra filtering approach for the polynomial formulation of the constant modulus criterion

2014 International Telecommunications Symposium (ITS), 2014

ABSTRACT In this work, an extended polynomial formulation of the constant modulus (CM) criterion ... more ABSTRACT In this work, an extended polynomial formulation of the constant modulus (CM) criterion under quadratic constraints is presented. Based on the method of Lagrange Multipliers, this `Volterra-CM formulation' brings very relevant information about the structure of the null-gradient CM solutions in the equalizer parameter space, including a conjecture regarding the relationship between the smallest multiplier and the optimal CM receiver. In the case of a two-tap filter, the proposed formulation allows that the solutions be obtained in terms of a single parameter, the corresponding Lagrange multiplier. For filters with more than two taps, the problem requires that a nonlinear system be solved, which is done with the aid of an iterative algorithm. The obtained global convergence rates show that the formulation is an effective tool to describe the structure of the optimal CM solution.

Research paper thumbnail of Multivariate PDF matching via kernel density estimation

2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP), 2014

ABSTRACT In this work, a measure of similarity based on the matching of multivariate probability ... more ABSTRACT In this work, a measure of similarity based on the matching of multivariate probability density functions (PDFs) is proposed. In consonance with the information theoretic learning (ITL) framework, the affinity comparison between the joint PDFs is performed using a quadratic distance, estimated with the aid of the Parzen window method with Gaussian kernels. The motivation underlying this proposal is to introduce a criterion capable of quantifying, to a significant extent, the statistical dependence present on information sources endowed with temporal and/or spatial structure, like audio, images and coded data. The measure is analyzed and compared with the canonical ITL-based approach - correntropy - for a set of blind equalization scenarios. The comparison includes elements like surface analysis, performance comparison in terms of bit error rate and a qualitative discussion concerning image processing. It is also important to remark that the study includes the application of two computational intelligence paradigms: extreme learning machines and differential evolution. The results indicate that the proposal can be, in some scenarios, a more informative formulation than correntropy.

Research paper thumbnail of An algebraic receiver for full response CPM demodulation

2006 International Telecommunications Symposium, 2006

This paper proposes a new algebraic demodulation method for full response CPM signals in AWGN cha... more This paper proposes a new algebraic demodulation method for full response CPM signals in AWGN channel. The method is based in a new estimation/identification theory that has also already been used for channel identification and signal deconvolution. The signals and noise are considered to be deterministic and we find an explicit formula for the recovery of the transmitted symbols. Based on this formula, the symbols are recovered blindly, needing only the knowledge of the modulation index. The method is not only simple and robust to noise, but also very fast, what enables its implementation on-line. It can also be equally used for coherent or non-coherent demodulations. The method is applied to the CPFSK and LRC families of signals showing good results.

Research paper thumbnail of Sobre critérios para equalização não-supervisionada

Sba: Controle & Automação Sociedade Brasileira de Automatica, 2006

In this work, we study the criteria used to solve the blind equalization problem. Two approaches ... more In this work, we study the criteria used to solve the blind equalization problem. Two approaches are considered in detail: the constant modulus and the Shalvi-Weinstein criteria. In the course of our exposition, a more recent and less studied technique, the generalized constant modulus criterion, is also discussed. Some of the most important results found in the literature are presented together with some recent contributions related to the comparison between blind criteria and between unsupervised techniques and the Wiener criterion.

Research paper thumbnail of Blind Deconvolution of Correlated Sources Based on Second-Order Statistics

SBrT 2013, 2013

The blind deconvolution of signals composed of statistically dependent samples is an important pr... more The blind deconvolution of signals composed of statistically dependent samples is an important practical problem whose understanding still requires the clarification of many theoretical points. In this work, we present an analysis of this problem that includes two well-established methods -the canonical constant modulus algorithm (CMA) and a correntropybased method -and two novel strategies that explore the temporal profile of the signal of interest. These techniques are compared in a number of representative scenarios, where it will be possible to form a clearer view of their potentialities and also of some peculiarities of the problem itself.

Research paper thumbnail of A Novel Entropy-based Equalization Performance Measure and Relations to Lp-Norm Deconvolution

SBrT 2013, 2013

A crucial performance measure in the context of the problem of deconvolution is the level of resi... more A crucial performance measure in the context of the problem of deconvolution is the level of residual intersymbol interference (ISI), a metric that is classically understood and formulated in terms of an L2-norm perspective. In order to enhance the scope of ISI quantification, we propose a novel entropy-based performance measure, which is called Entropybased Intersymbol Interference (HISI). Interestingly, this metric is related to an information-theoretic relationship between source distribution and Lp-norms when the error entropy is used as a basis for optimal filtering. The new metric is analytically investigated and illustrated with some simulations.

Research paper thumbnail of Análise De Critérios De Equalização Cega Baseados Em Aprendizagem Por Teoria Da Informação

Research paper thumbnail of Unsupervised Signal Processing: Concepts, Applications and Trends

Research paper thumbnail of Analysis of ITL Criteria in the Context of FIR Channel Equalization

Journal of Communication and Information Systems, 2016

Research paper thumbnail of An algebraic receiver for full response CPM demodulation

2006 International Telecommunications Symposium, Sep 1, 2006

This paper proposes a new algebraic demodulation method for full response CPM signals in AWGN cha... more This paper proposes a new algebraic demodulation method for full response CPM signals in AWGN channel. The method is based in a new estimation/identification theory that has also already been used for channel identification and signal deconvolution. The signals and noise are considered to be deterministic and we find an explicit formula for the recovery of the transmitted symbols. Based on this formula, the symbols are recovered blindly, needing only the knowledge of the modulation index. The method is not only simple and robust to noise, but also very fast, what enables its implementation on-line. It can also be equally used for coherent or non-coherent demodulations. The method is applied to the CPFSK and LRC families of signals showing good results.

Research paper thumbnail of Lower Bound of the Constant Modulus Criterion for Multilevel Modulations

The recently proposed lower bound of the classical blind CM criterion was shown to be able to wor... more The recently proposed lower bound of the classical blind CM criterion was shown to be able to work as an excellent blind equalizability index, which is a practical performance assessment metric in the context of inverse problems. However, there still remains the need of complementary studies aiming to cover a wider range of circumstances. Based on this, we present in this work an extension of the analysis of the lower bound by considering scenarios with multilevel modulated signals. For an 8-PAM and a 16-QAM signal, the simulations revealed the presence of a residual error offset, but even so, the validity of the index was preserved.

Research paper thumbnail of A Novel Entropy-based Equalization Performance Measure and Relations to Lp -Norm Deconvolution

A crucial performance measure in the context of the problem of deconvolution is the level of resi... more A crucial performance measure in the context of the problem of deconvolution is the level of residual intersymbol interference (ISI), a metric that is classically understood and formulated in terms of an L2-norm perspective. In order to enhance the scope of ISI quantification, we propose a novel entropy-based performance measure, which is called Entropybased Intersymbol Interference (HISI). Interestingly, this metric is related to an information-theoretic relationship between source distribution and Lp-norms when the error entropy is used as a basis for optimal filtering. The new metric is analytically investigated and illustrated with some simulations.

Research paper thumbnail of An Algebraic Receiver for Full Response CPM

This paper proposes a new algebraic demodulation method for full response CPM signals in AWGN cha... more This paper proposes a new algebraic demodulation method for full response CPM signals in AWGN channel. The method is based in a new estimation/identification theory that has also already been used for channel identification and signal deconvolution. The signals and noise are considered to be deterministic and we find an explicit formula for the recovery of the transmitted symbols. Based

Research paper thumbnail of Algebraic Parameter Estimation of Damped Exponentials

The parameter estimation of a sum of exponentials or the exponential fitting of data is a well kn... more The parameter estimation of a sum of exponentials or the exponential fitting of data is a well known problem with a rich history. It is a nonlinear problem which presents sev- eral difficulties as the ill-conditioning when roots have close values and the order of the estimated parameters, among oth- ers. One of the best existing methods is the modified

Research paper thumbnail of An Algebraic Identification Method for the Demodulation of QPSK Signal Through a Convolutive Channel

We present a straightforward algebraic setting for the de- modulation of a QPSK (Quadrature Phase... more We present a straightforward algebraic setting for the de- modulation of a QPSK (Quadrature Phase Shift Keying) signal over a convolutive and additive noise channel. Our method exploits the form of the continuous-time received signal without questioning the digital nature of the commu- nication system. The developments rely on classical deter- ministic numerical analysis. No assumption is required for the

Research paper thumbnail of Restoration of the voice timbre in telephone networks based on both voice and line properties

First International Symposium on Control, Communications and Signal Processing, 2004., 2004

The voice timbre suffers from different forms of distorsions in a telephone link. In this paper, ... more The voice timbre suffers from different forms of distorsions in a telephone link. In this paper, we propose a new blind equalizer for correcting these distortions, based on the combination of two different methods. The first one is a blind equalization method consisting in matching the long term spectrum of the processed signal to a reference spectrum, while the second one is a precompensation method, based on the physical characteristics of transmission lines. The new method is compared to the first one, showing a significant gain in performance.

Research paper thumbnail of Blind Equalization Based on a Cascade of Optimal Two-Tap CM Equalizers

This article introduces a blind equalization methodology based on a cascade of two-tap finite imp... more This article introduces a blind equalization methodology based on a cascade of two-tap finite impulse response filters globally optimal with respect to the constant modulus (CM) criterion. It is shown that a formulation of the CM cost function in terms of a mean squared error (MSE) metric and of Volterra-like constraints allow the optimization process to be carried out, when two parameters are to be adapted, with the aid of a one-dimensional search process that suits quite well an exhaustive framework. The proposal will be compared to a similar cascade of two-tap Wiener solutions and also with conventional Wiener filters.

Research paper thumbnail of Lower Bound of the Constant Modulus Criterion for Multilevel Modulations

The recently proposed lower bound of the classical blind CM criterion was shown to be able to wor... more The recently proposed lower bound of the classical blind CM criterion was shown to be able to work as an excellent blind equalizability index, which is a practical performance assessment metric in the context of inverse problems. However, there still remains the need of complementary studies aiming to cover a wider range of circumstances. Based on this, we present in this work an extension of the analysis of the lower bound by considering scenarios with multilevel modulated signals. For an 8-PAM and a 16-QAM signal, the simulations revealed the presence of a residual error offset, but even so, the validity of the index was preserved.

Research paper thumbnail of Uma Visão Geométrica da Formulação Polinomial do Critério CM

Recentemente, concebeu-se uma formulação polinomial do critério CM, a qual permitiu a obtenção de... more Recentemente, concebeu-se uma formulação polinomial do critério CM, a qual permitiu a obtenção de um limitante inferior para a função custo CM e de soluções analíticas baseadas na relaxação de restrições [1]. Neste trabalho, apresentaremos uma visão geométrica dessa formulação. Métodos: A formulação toma como ponto de partida a função custo CM, e adota, como elemento chave, o termo quadrático υ c (n) = y 2 (n), em que y(n) = w T x(n) é a saída do filtro linear com vetor de parâmetros w e x(n) é o vetor de entrada. Particularmente, υ c (n) pode ser expresso como υ(n) = θ c T ξ(n), sendo ξ(n) o vetor de entrada no domínio de Volterra e θ c o filtro polinomial com restrições. Isto permite a representação do custo, como

Research paper thumbnail of An Analysis of Unsupervised Signal Processing Methods in the Context of Correlated Sources

Lecture Notes in Computer Science, 2009

In light of the recently proposed generalized correlation function named correntropy, which explo... more In light of the recently proposed generalized correlation function named correntropy, which exploits higher-order statistics and the time structure of signals, we have, in this work, two main objectives: 1) to give a new interpretation – founded on the relationships between the constant modulus (CM) and Shalvi-Weinstein criteria and between the latter and methods for ICA based on nongaussianity –

Research paper thumbnail of A volterra filtering approach for the polynomial formulation of the constant modulus criterion

2014 International Telecommunications Symposium (ITS), 2014

ABSTRACT In this work, an extended polynomial formulation of the constant modulus (CM) criterion ... more ABSTRACT In this work, an extended polynomial formulation of the constant modulus (CM) criterion under quadratic constraints is presented. Based on the method of Lagrange Multipliers, this `Volterra-CM formulation' brings very relevant information about the structure of the null-gradient CM solutions in the equalizer parameter space, including a conjecture regarding the relationship between the smallest multiplier and the optimal CM receiver. In the case of a two-tap filter, the proposed formulation allows that the solutions be obtained in terms of a single parameter, the corresponding Lagrange multiplier. For filters with more than two taps, the problem requires that a nonlinear system be solved, which is done with the aid of an iterative algorithm. The obtained global convergence rates show that the formulation is an effective tool to describe the structure of the optimal CM solution.

Research paper thumbnail of Multivariate PDF matching via kernel density estimation

2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP), 2014

ABSTRACT In this work, a measure of similarity based on the matching of multivariate probability ... more ABSTRACT In this work, a measure of similarity based on the matching of multivariate probability density functions (PDFs) is proposed. In consonance with the information theoretic learning (ITL) framework, the affinity comparison between the joint PDFs is performed using a quadratic distance, estimated with the aid of the Parzen window method with Gaussian kernels. The motivation underlying this proposal is to introduce a criterion capable of quantifying, to a significant extent, the statistical dependence present on information sources endowed with temporal and/or spatial structure, like audio, images and coded data. The measure is analyzed and compared with the canonical ITL-based approach - correntropy - for a set of blind equalization scenarios. The comparison includes elements like surface analysis, performance comparison in terms of bit error rate and a qualitative discussion concerning image processing. It is also important to remark that the study includes the application of two computational intelligence paradigms: extreme learning machines and differential evolution. The results indicate that the proposal can be, in some scenarios, a more informative formulation than correntropy.

Research paper thumbnail of An algebraic receiver for full response CPM demodulation

2006 International Telecommunications Symposium, 2006

This paper proposes a new algebraic demodulation method for full response CPM signals in AWGN cha... more This paper proposes a new algebraic demodulation method for full response CPM signals in AWGN channel. The method is based in a new estimation/identification theory that has also already been used for channel identification and signal deconvolution. The signals and noise are considered to be deterministic and we find an explicit formula for the recovery of the transmitted symbols. Based on this formula, the symbols are recovered blindly, needing only the knowledge of the modulation index. The method is not only simple and robust to noise, but also very fast, what enables its implementation on-line. It can also be equally used for coherent or non-coherent demodulations. The method is applied to the CPFSK and LRC families of signals showing good results.

Research paper thumbnail of Sobre critérios para equalização não-supervisionada

Sba: Controle & Automação Sociedade Brasileira de Automatica, 2006

In this work, we study the criteria used to solve the blind equalization problem. Two approaches ... more In this work, we study the criteria used to solve the blind equalization problem. Two approaches are considered in detail: the constant modulus and the Shalvi-Weinstein criteria. In the course of our exposition, a more recent and less studied technique, the generalized constant modulus criterion, is also discussed. Some of the most important results found in the literature are presented together with some recent contributions related to the comparison between blind criteria and between unsupervised techniques and the Wiener criterion.

Research paper thumbnail of Blind Deconvolution of Correlated Sources Based on Second-Order Statistics

SBrT 2013, 2013

The blind deconvolution of signals composed of statistically dependent samples is an important pr... more The blind deconvolution of signals composed of statistically dependent samples is an important practical problem whose understanding still requires the clarification of many theoretical points. In this work, we present an analysis of this problem that includes two well-established methods -the canonical constant modulus algorithm (CMA) and a correntropybased method -and two novel strategies that explore the temporal profile of the signal of interest. These techniques are compared in a number of representative scenarios, where it will be possible to form a clearer view of their potentialities and also of some peculiarities of the problem itself.

Research paper thumbnail of A Novel Entropy-based Equalization Performance Measure and Relations to Lp-Norm Deconvolution

SBrT 2013, 2013

A crucial performance measure in the context of the problem of deconvolution is the level of resi... more A crucial performance measure in the context of the problem of deconvolution is the level of residual intersymbol interference (ISI), a metric that is classically understood and formulated in terms of an L2-norm perspective. In order to enhance the scope of ISI quantification, we propose a novel entropy-based performance measure, which is called Entropybased Intersymbol Interference (HISI). Interestingly, this metric is related to an information-theoretic relationship between source distribution and Lp-norms when the error entropy is used as a basis for optimal filtering. The new metric is analytically investigated and illustrated with some simulations.