Asoke K. Nandi

Algorithms for automatic modulation recognition of communication signals

This paper introduces two algorithms for analog and digital modulations recognition. The first algorithm utilizes the decision-theoretic approach in which a set of decision criteria for identifying different types of modulations is developed. In the second algorithm the artificial neural network (ANN) is used as a new approach for the modulation recognition process. Computer simulations of different types of band-limited analog and digitally modulated signals corrupted by band-limited Gaussian noise sequences have been carried out to measure the performance of the developed algorithms. In the decision-theoretic algorithm it is found that the overall success rate is over 94% at the signal-to-noise ratio (SNR) of 15 dB, while in the ANN algorithm the overall success rate is over 96% at the SNR of 15 dB.

Noninvasive fetal electrocardiogram extraction: blind separation versus adaptive noise cancellation

The problem of the fetal electrocardiogram (FECG) extraction from maternal skin electrode measurements can be modeled from the perspective of blind source separation (BSS). Since no comparison between BSS techniques and other signal processing methods has been made, the authors compare a BSS procedure based on higher-order statistics and Widrows multireference adaptive noise cancelling approach. As a best-case scenario for this latter method, optimal Wiener-Hopf solutions are considered. Both procedures are applied to real multichannel ECG recordings obtained from a pregnant woman. The experimental outcomes demonstrate the more robust performance of the blind technique and, in turn, verify the validity of the BSS model in this important biomedical application.

Automatic identification of digital modulation types

Abstract In both covert and overt operations, modulation identification plays an important role. In communication intelligence (COMINT) applications the main objective is the perfect monitoring of the intercepted signals and one of the parameters that affect the perfect monitoring is the modulation type of the intercepted signal. In this paper, a set of decision criteria for identifying different types of digital modulation is developed. Also, all the key features used in the identification algorithm are calculated using the conventional signal processing methods. Computer simulations for different types of band-limited digitally modulated signals corrupted by band-limited Gaussian noise have been carried out. Expressions for the instantaneous amplitude, and phase of different types of digitally modulated signals are derived. Also, two software solutions for estimating the instantaneous phase in the weak segments of a signal are introduced and analyzed. Finally, it is found that all modulation types of interest have been classified with success rate ≥90% at SNR = 10 dB.

Feature generation using genetic programming with application to fault classification

One of the major challenges in pattern recognition problems is the feature extraction process which derives new features from existing features, or directly from raw data in order to reduce the cost of computation during the classification process, while improving classifier efficiency. Most current feature extraction techniques transform the original pattern vector into a new vector with increased discrimination capability but lower dimensionality. This is conducted within a predefined feature space, and thus, has limited searching power. Genetic programming (GP) can generate new features from the original dataset without prior knowledge of the probabilistic distribution. A GP-based approach is developed for feature extraction from raw vibration data recorded from a rotating machine with six different conditions. The created features are then used as the inputs to a neural classifier for the identification of six bearing conditions. Experimental results demonstrate the ability of GP to discover automatically the different bearing conditions using features expressed in the form of nonlinear functions. Furthermore, four sets of results-using GP extracted features with artificial neural networks (ANN) and support vector machines (SVM), as well as traditional features with ANN and SVM-have been obtained. This GP-based approach is used for bearing fault classification for the first time and exhibits superior searching power over other techniques. Additionally, it significantly reduces the time for computation compared with genetic algorithm (GA), therefore, makes a more practical realization of the solution.

Automatic digital modulation recognition using artificial neural network and genetic algorithm

Automatic recognition of digital modulation signals has seen increasing demand nowadays. The use of artificial neural networks for this purpose has been popular since the late 1990s. Here, we include a variety of modulation types for recognition, e.g. QAM16, V29, V32, QAM64 through the addition of a newly proposed statistical feature set. Two training algorithms for multi-layer perceptron (MLP) recogniser, namely Backpropagation with Momentum and Adaptive Learning Rate is investigated, while resilient backpropagation (RPROP) is proposed for this problem, are employed in this work. In particular, the RPROP algorithm is applied for the first time in this area. In conjunction with these algorithms, we use a separate data set as validation set during training cycle to improve generalisation. Genetic algorithm (GA) based feature selection is used to select the best feature subset from the combined statistical and spectral feature set. RPROP MLP recogniser achieves about 99% recognition performance on most SNR values with only six features selected using GA.

Blind estimation using higher-order statistics

1. Higher-order Statistics A. McCormick, A.K. Nandi. 2. Blind Signal Equalisation S.N. Anfinsen, et al. 3. Blind System Identification J.K. Richardson, A.K. Nandi. 4. Blind Source Separation V. Zarzoso, A.K. Nandi. 5. Robust Cumulant Estimation D. Mampel, A.K. Nandi. Epilogue. Index.

Blind Source Separation

A myriad of applications require the extraction of a set of signals which are not directly accessible. Instead, this extraction must be carried out from another set of measurements which were generated as mixtures of the initial set. Since usually neither the original signals — called sources — nor the mixing transformation are known, this is certainly a challenging problem of multichannel blind estimation. One of the most typical examples is the socalled “ cocktail party” problem. In this situation, any person attending the party can hear the speech of the speaker they want to listen to, together with surrounding sounds coming from other ’ competing’ speakers, music, background noises, etc. Everybody has experienced how the human brain is able to separate all these incoming sound signals and to ’ switch’ to the desired one. Similar results can be achieved by adequately processing the output signals of an array of microphones, as long as the signals to be extracted fulfil certain conditions [62, 63] . Wireless communications is another usual application field of signal separation techniques. In a CDMA (Code Division Multiple Access) environment several users share the same radio channel by transmitting their signal after modifying it according to an appropriate code. Traditionally, the extraction of the desired signal at the receiving end requires the knowledge of the corresponding code.

Blind separation of independent sources for virtually any source probability density function

The blind source separation (BSS) problem consists of the recovery of a set of statistically independent source signals from a set of measurements that are mixtures of the sources when nothing is known about the sources and the mixture structure. In the BSS scenario, of two noiseless real-valued instantaneous linear mixtures of two sources, an approximate maximum-likelihood (ML) approach has been suggested in the literature, which is only valid under certain constraints on the probability density function (pdf) of the sources. In the present paper, the expression for this ML estimator is reviewed and generalized to include virtually any source distribution. An intuitive geometrical interpretation of the new estimator is also given in terms of the scatter plots of the signals involved. An asymptotic performance analysis is then carried out, yielding a closed-form expression for the estimator asymptotic pdf. Simulations illustrate the behavior of the suggested estimator and show the accuracy of the asymptotic analysis. In addition, an extension of the method to the general BSS scenario of more than two sources and two sensors is successfully implemented.

Automatic analogue modulation recognition

Abstract For several reasons, modulation recognition is extremely important in communication intelligence (COMINT). In this paper, a global procedure for recognition of analogue modulation types is developed. Computer simulations for different types of band-limited analogue modulated signals corrupted by band-limited Gaussian noise have been carried out. Expressions for the instantaneous amplitude and phase as well as the Fourier transform of different analogue modulation types are derived and used to set up a recognition procedure. It is found that all types of analogue modulation have been classified with success rate ⩾ 90% at SNR = 10 dB.

Modulation recognition using artificial neural networks

In this chapter the artificial neural networks (ANNs) approach as another solution for the modulation recognition process is studied in some detail. Unlike in other algorithms, especially those which utilise the decision-theoretic (DT) approach (Chapters 2–4), where a suitable threshold for each key feature has to be chosen, the threshold at each node (neuron) is chosen automatically and adaptively. Furthermore, in the DT approach, many algorithms based on the same key features can be developed by applying the extracted key features in different order in the classification algorithm and they perform with different success rates at the same SNR. In the DT algorithms, it was found that only one key feature is considered at a time. As a result, the probability of correct decision about a modulation type in these algorithms is based on the time-ordering of the key features used as well as probability of correct decision derived from each key feature. On the other hand, in the ANN algorithms all the key features are considered simultaneously. So, the time order of the key features does not affect on the probability of correct decision of on the modulation type of a signal. For that reason, it is suggested that the use of the ANN approach for solving the modulation recognition process may have better performance than the DT approach.