Diego B Haddad - Academia.edu (original) (raw)

Papers by Diego B Haddad

Diamond and related materials, Apr 1, 2024

Anais do XLI Simpósio Brasileiro de Telecomunicações e Processamento de Sinais

Learning and Nonlinear Models, 2012

This paper reviews Independent Components Analysis (ICA) and Blind Signal Separation (BSS) proble... more This paper reviews Independent Components Analysis (ICA) and Blind Signal Separation (BSS) problems. An overview on the main statistical principles that guide the search for the independent components is formulated, methods for blind signal separation that require both high-order and second-order statistics are also illustrated. Some of the most successful algorithms for both ICA and BSS are derived. Experimental applications in different signal processing tasks such as passive sonar, nondestructive ultrasound inspection and electrical-load time series are presented.

Dye-sensitized solar cells, termed as DSSC’s have been gaining interest from researchers and indu... more Dye-sensitized solar cells, termed as DSSC’s have been gaining interest from researchers and industry in the last few years. Such an interest derives from their low-cost manufacturing and easy processing to replace conventional silicon cells. A DSSC operating system consists of three steps: a photoelectrode (anode), an electrolyte solution and a counter electrode (cathode). The dyes aims to expand the absorption band of the device. The most popular dyes are those containing anthocyanins that exist in leaves, fruits, roots, among others. Two photosensitizing natural dyes are proposed in this paper: a passion fruit (Passi-flora eduris) and green coconut (Cocos n ucifera). Measurements such as structural and morphological, optical characterization and electrochemical analyzes of the photoelectrode coated with TiO2 and platinum were performed. The photo-voltaic efficient performance were measured and compared with the literature. The electrolytic solution made in laboratory fulfilled its function, regenerating the dye with ions. The results showed that Passiflora eduris dye showed the best efficiency 0.52% compared to other types of fruits in the literature. The results reveal that both present good performance for DSSC’s manufacturing.

Research Square (Research Square), May 18, 2023

Distributed inference tasks could be performed by adaptive filtering techniques. Several enhancem... more Distributed inference tasks could be performed by adaptive filtering techniques. Several enhancement strategies for such techniques were proposed, such as sparsity-aware algorithms, coefficients reuse and correntropy-based cost functions in the case of impulsive noise. In this paper, a general framework based on Lagrange multipliers for the derivation of sophisticated algorithms that incorporate most of these improvements is described. A new general identification algorithm is derived as an example of the proposed approach and its performance is assessed in a distributed setting.

Electronics Letters, Apr 1, 2023

This paper presents a new heuristic for the analysis of adaptive filtering algorithms. It combine... more This paper presents a new heuristic for the analysis of adaptive filtering algorithms. It combines Price's Theorem (which is strictly valid when the random variables are jointly Gaussian) with a probabilistic model of the input data that assumes statistical independence between the radial and angular distributions. Moreover, the last distribution is modeled as discrete, which allows obtaining concise and useful closed‐form estimates of the algorithm's performance. The proposed method directly provides a derivation of a traditional result for the steady state performance of the Sign Least Mean Squares algorithm. Furthermore, it can be used to gain new insights into the asymptotic performance of the Block Sign Least Mean Squares algorithm. The analysis results are confirmed through simulations.

arXiv (Cornell University), Oct 30, 2018

Stochastic models that predict adaptive filtering algorithms performance usually employ several a... more Stochastic models that predict adaptive filtering algorithms performance usually employ several assumptions in order to simplify the analysis. Although these simplifications facilitate the recursive update of the statistical quantities of interest, they by themselves may hamper the modeling accuracy. This paper simultaneously avoids for the first time the employment of two ubiquitous assumptions often adopted in the analysis of the least mean squares algorithm. The first of them is the so-called independence assumption, which presumes statistical independence between adaptive coefficients and input data. The second one assumes a sufficient-order configuration, in which the lengths of the unknown plant and the adaptive filter are equal. State equations that characterize both the mean and mean square performance of the deficient-length configuration without using the independence assumption are provided. The devised analysis, encompassing both transient and steady-state regimes, is not restricted neither to white nor to Gaussian input signals and is able to provide a proper step size upper bound that guarantees stability.

Proceedings of the 26th International Congress of Mechanical Engineering, 2021

Resumo-Métodos de separação cega de fontes têm sido propostos para melhoria de desempenho em sist... more Resumo-Métodos de separação cega de fontes têm sido propostos para melhoria de desempenho em sistemas automáticos de reconhecimento de fala, sistemas de auxílioà audição e análise de sinais biomédicos, entre outros. Neste artigo empregamos técnicas recentes, baseadas na análise de componentes independentes (ICA), para separação de sinais misturados de forma convolutiva e avaliamos experimentalmente a melhoria de desempenho destas estruturas quando os filtros de separação têm comprimento maior que os filtros de mistura e também quando a função custo contempla estatísticas de ordem superior.

Engineering Applications of Artificial Intelligence, Sep 1, 2023

An adaptive algorithm should ideally present high convergence rate, good steady-state performance... more An adaptive algorithm should ideally present high convergence rate, good steady-state performance, and robustness against impulsive noise. Few algorithms can simultaneously meet these requirements. This paper proposes a local and deterministic optimization problem whose solution gives rise to an adaptive algorithm that presents a higher convergence rate in the identification of sparse systems due to the use of the proportionate adaptation technique. In addition, a correntropy-based cost function is employed in order to enhance its robustness against non-Gaussian noise. Finally, the adoption of coefficient reuse approach results in a good system identification performance in steady-state conditions, especially in low SNR scenarios.

European Signal Processing Conference, Aug 1, 2008

ABSTRACT

In this work we consider a scenario in which several dispersed nodes intend to identify a nonline... more In this work we consider a scenario in which several dispersed nodes intend to identify a nonlinear Volterra system. Such system is represented by a series that has sparse kernels, with few non-zero coefficients. This sparse feature of Volterra series allows us to propose distributed and sparsity- aware adaptive filtering algorithms, that aim at identifying such nonlinear system. We consider a network composed by agents, called Wireless Sensor Network (WSN), containing sensor nodes that have energy and computational constraints. We evaluate the performance of the proposed algorithm by means of the Mean-Squared Deviation (MSD) metric, and we verified that the distributed scheme provides a higher convergence rate and steady-state performance.

2018 International Joint Conference on Neural Networks (IJCNN)

Computer models have been an important tool to determine soil bulk density. This soil property is... more Computer models have been an important tool to determine soil bulk density. This soil property is fundamental to estimate soil carbon reserves and consequently to understand the global carbon cycle. The estimation of soil bulk density is not a trivial task since it demands an intensive and often impractical work. The purpose of this paper is to evaluate the performance of a pedotransfer function against an Artificial Neural Networks to estimate soil bulk density for soils at Brazilian biomes. The first one consists of a linear model composed of a Least Square method. The latter employs a robust committee of multilayer perceptron networks and a model selection procedure based on k-fold cross-validation. The data are composed of 3404 soil layers distributed in different Brazilian regions and with different uses. The proposed non-linear regressor presents higher precision when compared to the linear model, and requires less information to do so. Additionally, the developed solution brings to light the assumed relationship between soil bulk density and some soil chemical properties. Index Terms-Soil properties, Soil bulk density, Pedotransfer functions, Multilayer perceptron artificial neural network.

Journal of Control, Automation and Electrical Systems

2020 IEEE ANDESCON

Journal of Intelligent & Robotic Systems