Auditory attention identification methods attempt to identify the sound source of a listener's interest by analyzing measurements of electrophysiological data. We present a tutorial on the numerous techniques that have been developed in recent decades, and we present an overview of current trends in multivariate correlation-based and model-based learning frameworks. The focus is on the use of linear relations between electrophysiological and audio data. The way in which these relations are computed differs. For example, canonical correlation analysis (CCA) finds a linear subset of electrophysiological data that best correlates to audio data and a similar subset of audio data that best correlates to electrophysiological data. Model-based (encoding and decoding) approaches focus on either of these two sets. We investigate the similarities and differences between these linear model philosophies. We focus on (1) correlation-based approaches (CCA), (2) encoding/decoding models based on dense estimation, and (3) (adaptive) encoding/decoding models based on sparse estimation. The specific focus is on sparsity-driven adaptive encoding models and comparing the methodology in state-of-the-art models found in the auditory literature. Furthermore, we outline the main signal processing pipeline for how to identify the attended sound source in a cocktail party environment from the raw electrophysiological data with all the necessary steps, complemented with the necessary MATLAB code and the relevant references for each step. Our main aim is to compare the methodology of the available methods, and provide numerical illustrations to some of them to get a feeling for their potential. A thorough performance comparison is outside the scope of this tutorial.

Sleep scoring is used as a diagnostic technique in the diagnosis and treatment of sleep disorders. Automated sleep scoring is crucial, since the large volume of data should be analyzed visually by the sleep specialists which is burdensome, time-consuming tedious, subjective, and error prone. Therefore, automated sleep stage classification is a crucial step in sleep research and sleep disorder diagnosis. In this paper, a robust system, consisting of three modules, is proposed for automated classification of sleep stages from the single-channel electroencephalogram (EEG). In the first module, signals taken from Pz-Oz electrode were denoised using multiscale principal component analysis. In the second module, the most informative features are extracted using discrete wavelet transform (DWT), and then, statistical values of DWT subbands are calculated. In the third module, extracted features were fed into an ensemble classifier, which can be called as rotational support vector machine (RotSVM). The proposed classifier combines advantages of the principal component analysis and SVM to improve classification performances of the traditional SVM. The sensitivity and accuracy values across all subjects were 84.46% and 91.1%, respectively, for the five-stage sleep classification with Cohen’s kappa coefficient of 0.88. Obtained classification performance results indicate that, it is possible to have an efficient sleep monitoring system with a single-channel EEG, and can be used effectively in medical and home-care applications.

We still have very little knowledge about how our brains decouple different sound sources, which is known as solving the cocktail party problem. Several approaches; including ERP, time-frequency analysis and, more recently, regression and stimulus reconstruction approaches; have been suggested for solving this problem. In this work, we study the problem of correlating of EEG signals to different sets of sound sources with the goal of identifying the single source to which the listener is attending. Here, we propose a method for finding the number of parameters needed in a regression model to avoid overlearning, which is necessary for determining the attended sound source with high confidence in order to solve the cocktail party problem.

Electrocardiogram (ECG) signals are affected by different types of noise and artifacts which can hide significant information related to heart functioning. Therefore, denoising of signals is essential for accurate diagnosis of different heart diseases. This study examines and compares three different denoising techniques, namely Principal Component Analysis (PCA), Independent Component Analysis (ICA) and Multiscale Principal Component Analysis (MSPCA), and their influence on ECG signal classification. In order to extract significant features from ECG signals, wavelet packet decomposition (WPD) technique is employed. To classify ECG signals, ensemble machine learning classifier called Rotation Forest is proposed for classification task. In this study, three different systems, namely PCA-WPD-Rotation Forest, ICA-WPD-Rotation Forest and MSPCA-WPD-Rotation Forest were analyzed and evaluated in terms of three different statistical metrics, namely F-measure, AUC value and overall accuracy. To evaluate performances of proposed systems, MIT-BIH database is used. Obtained experimental results showed that MSPCA-WPD-Rotation Forest system resulted in the highest performances when compared to PCA-WPD-Rotation Forest and ICA-WPD-Rotation Forest. Therefore, in this study following system for classification of ECG signals is proposed: MSPCA as the first component for denoising, WPD as the second component which extracts important features from ECG signals and Rotation Forest as the third component which performs classification of ECG signals. The comparison to other systems for classification of EEG signals shown that proposed system outperforms other systems on the MIT-BIH arrhythmia database under investigated conditions.