Marcio Eisencraft

Tackling EEG signal classification with least squares support vector machines: A sensitivity analysis study

The electroencephalogram (EEG) signal captures the electrical activity of the brain and is an important source of information for studying neurological disorders. The proper analysis of this biological signal plays an important role in the domain of brain-computer interface, which aims at the construction of communication channels between human brain and computers. In this paper, we investigate the application of least squares support vector machines (LS-SVM) to the task of epilepsy diagnosis through automatic EEG signal classification. More specifically, we present a sensitivity analysis study by means of which the performance levels exhibited by standard and least squares SVM classifiers are contrasted, taking into account the setting of the kernel function and of its parameter value. Results of experiments conducted over different types of features extracted from a benchmark EEG signal dataset evidence that the sensitivity profiles of the kernel machines are qualitatively similar, both showing notable performance in terms of accuracy and generalization. In addition, the performance accomplished by optimally configured LS-SVM models is also quantitatively contrasted with that obtained by related approaches for the same dataset.

Synchronization of Discrete-Time Chaotic Systems in Bandlimited Channels

Over the last couple of decades, many methods for synchronizing chaotic systems have been proposed with communications applications in view. Yet their performance has proved disappointing in face of the nonideal character of usual channels linking transmitter and receiver, that is, due to both noise and signal propagation distortion. Here we consider a discrete-time master-slave system that synchronizes despite channel bandwidth limitations and an allied communication system. Synchronization is achieved introducing a digital filter that limits the spectral content of the feedback loop responsible for producing the transmitted signal.

Fast communication: Spectral properties of chaotic signals generated by the skew tent map

Chaotic signals have been considered potentially attractive in many signal processing applications ranging from wideband communication systems to cryptography and watermarking. Besides, some devices as nonlinear adaptive filters and phase-locked loops can present chaotic behavior. In this paper, we derive analytical expressions for the autocorrelation sequence, power spectral density and essential bandwidth of chaotic signals generated by the skew tent map. From these results, we suggest possible applications in communication systems.

Chaotic Synchronization in Discrete-Time Systems Connected by Bandlimited Channels

Due to the broadband characteristic of chaotic signals, many of the methods that have been proposed for synchronizing chaotic systems do not usually present a satisfactory performance when applied to bandlimited communication channels. Here, the effects of bandwidth limitations imposed by the channel on the synchronous solution of a discrete-time chaotic master-slave network are investigated. The discrete-time system considered in this study is the Hénon map. It is analytically shown that synchronism can be achieved in such a network by introducing a digital filter in the feedback loop responsible for generating the chaotic signal that will be sent to the slave node. Numerical simulations relating the filter parameters, such as its order and cut-off frequency, to the maximum Lyapunov exponent of the master node, which determines if the transmitted signal is chaotic or not, are also presented. These results can be useful for practical communication schemes based on chaos.

Chaotic Signals in Digital Communications

Chaotic Signals in Digital Communications combines fundamental background knowledge with state-of-the-art methods for using chaotic signals and systems in digital communications. The book builds a bridge between theoretical works and practical implementation to help researchers attain consistent performance in realistic environments. It shows the possible shortcomings of the chaos-based communication systems proposed in the literature, particularly when they are subjected to non-ideal conditions. It also presents a toolbox of techniques for researchers working to actually implement such systems. A Combination of Tutorials and In-Depth, Cutting-Edge Research Featuring contributions by active leading researchers, the book begins with an introduction to communication theory, dynamical systems, and chaotic communications suitable for those new to the field. This lays a solid foundation for the more applied chapters that follow. A Toolbox of TechniquesIncluding New Ways to Tackle Channel Imperfections The book covers typical chaos communication methods, namely chaotic masking, chaotic modulation, chaotic shift key, and symbolic message bearing, as well as bidirectional communication and secure communication. It also presents novel methodologies to deal with communication channel imperfections. These tackle band-limited channel chaos communication, radio channels with fading, and the resistance of a special chaotic signal to multipath propagations. In addition, the book addresses topics related to engineering applications, such as optical communications, chaotic matched filters and circuit implementations, and microwave frequency-modulated differential chaos shift keying (FM-DCSK) systems. Insights for Both Theoretical and Experimental Researchers Combining theory and practice, this book offers a unique perspective on chaotic communication in the context of non-ideal conditions. Written for theoretical and experimental researchers, it tackles the practical issues faced in implementing chaos-based signals and systems in digital communications applications.

Fast communication: Discrete-time chaotic systems synchronization performance under additive noise

In recent decades many articles have discussed the possibilities of chaos applied in communications. However, the vast majority consider in practical terms the ideal channel condition, which is clearly a restringing condition. Some papers show that when there is an additive noise, the synchronization error often disrupts communication. In this work, we present results of a comparison between synchronization error due to additive Gaussian noise when the transmitter and receiver are implemented by single or coupled maps.

Fast communication: Route to chaos in a third-order phase-locked loop network

Phase-locked loops (PLLs) are widely used in applications related to control systems and telecommunication networks. Here we show that a single-chain master-slave network of third-order PLLs can exhibit stationary, periodic and chaotic behaviors, when the value of a single parameter is varied. Hopf, period-doubling and saddle-saddle bifurcations are found. Chaos appears in dissipative and non-dissipative conditions. Thus, chaotic behaviors with distinct dynamical features can be generated. A way of encoding binary messages using such a chaos-based communication system is suggested.

Channel equalization for synchronization of chaotic maps

Abstract Many communication systems applying synchronism of chaotic systems have been proposed as an alternative spread spectrum modulation that improves the level of privacy in data transmission. However, due to the lack of robustness of chaos synchronization, even minor channel imperfections are enough to hinder communication. In this paper, we propose an adaptive equalization scheme based on a modified normalized least-mean-squares (NLMS) algorithm, which enables chaotic synchronization when the communication channel is not ideal. As an example of application, this scheme is used to recover a binary sequence modulated by a chaotic signal generated by the Henon map. Simulation results show that the modified NLMS can successfully equalize the channel in different scenarios.

Do chaos-based communication systems really transmit chaotic signals?

Many communication systems based on the synchronism of chaotic systems have been proposed as an alternative spread spectrum modulation that improves the level of privacy in data transmission. However, depending on the map and on the encoding function, the transmitted signal may cease to be chaotic. Therefore, the sensitive dependence on initial conditions, which is one of the most interesting properties for employing chaos in telecommunications, may disappear. In this paper, we numerically analyze the chaotic nature of signals modulated using a system that employs the Ikeda map. Additionally, we propose changes in the communication system in order to guarantee that the modulated signals are in fact chaotic. HighlightsWe analyze a chaos-based communication system to verify if the signals are chaotic.An analysis concerning the presence of co-existing attractors in the Ikeda map is performed.We compute Lyapunov exponents of the orbits of the Ikeda map, including an encoded message.We propose a strategy to guarantee a truly chaos-based system.

Chaos-Based Communication Systems: Current Trends and Challenges

Chaotic communication can be regarded as a paradigm shift. The intensive use of the inherent complexity of chaotic oscillators allows the deployment of highly efficient codification and modulation schemes in the chaotic evolution, while the simplicity of chaos-generating devices permits simple and cost-effective hardware implementation. This paper outlines the current trends of chaos-based communication and points the challenging topics that require further attention towards the realization of widespread chaos communication.