Sharif Digital Repository

The efficiency of a learning process directly depends on how well the students are attentive. Detecting the level of attention can help to improve the learning quality. In recent years, there have been several attempts to leverage EEG signal processing as a tool to detect whether a student is attentive or not. In such work, the level of attention is determined by analyzing the EEG power spectrum, which is mostly followed by machine learning approaches. However, the efficiency of such methods for detecting auditory attention of blind or visually-impaired students has not been analyzed. This study aims to investigate such a scenario. To this end, we propose an EEG recording protocol to... 

Tensors are valuable tools to represent Electroencephalogram (EEG) data. Tucker decomposition is the most used tensor decomposition in multidimensional discriminant analysis and tensor extension of Linear Discriminant Analysis (LDA), called Higher Order Discriminant Analysis (HODA), is a popular tensor discriminant method used for analyzing Event Related Potentials (ERP). In this paper, we introduce a new tensor-based feature reduction technique, named Higher Order Spectral Regression Discriminant Analysis (HOSRDA), for use in a classification framework for ERP detection. The proposed method (HOSRDA) is a tensor extension of Spectral Regression Discriminant Analysis (SRDA) and casts the... 

Denoising is an important preprocessing stage in some ElectroEncephaloGraphy (EEG) applications. For this purpose, Blind Source Separation (BSS) methods, such as Independent Component Analysis (ICA) and Decorrelated and Colored Component Analysis (DCCA), are commonly used. Although ICA and DCCA-based methods are powerful tools to extract sources of interest, the procedure of eliminating the effect of sources of non-interest is usually manual. It should be noted that some methods for automatic selection of artifact sources after BSS methods exist, although they imply a training supervised step. On the other hand, in cases where there are some a prioriinformation about the subspace of... 

Removing muscle activity from ictal ElectroEncephaloGram (EEG) data is an essential preprocessing step in diagnosis and study of epileptic disorders. Indeed, at the very beginning of seizures, ictal EEG has a low amplitude and its morphology in the time domain is quite similar to muscular activity. Contrary to the time domain, ictal signals have specific characteristics in the time-frequency domain. In this paper, we use the time-frequency signature of ictal discharges as a priori information on the sources of interest. To extract the time-frequency signature of ictal sources, we use the Canonical Correlation Analysis (CCA) method. Then, we propose two time-frequency based semi-blind source... 

Detection of seizure periods in an epileptic patient is an important part of health care. However, due to the variety in types of seizures and location of them, real-time seizure detection is not straight forward. In this paper, we propose a method for seizure detection from EEG signals in datasets which have both generalized and focal seizures. The proposed method is useful in the situations that we have no prior knowledge about the location of the patient's seizure and the pattern of evolution of seizure location. In the proposed method, first, the artifacts are automatically reduced by Blind Source Separation (BSS) methods. Then, the channels are clustered into two clusters. After that,... 

Attention as a cognitive aspect of brain activity is one of the most popular areas of brain studies. It has significant impact on the quality of other activities such as learning process and critical activities (e.g. driving vehicles). Because of its crucial influence on the learning process, it is one of the main aspects of research in education. In this study, we propose a brand new protocol of brain signal recording in order to classify human attention in educational environments. Unlike other protocols used to record EEG signals, our protocol does not require strong memory and strong language knowledge to carry out. To this end, we have recorded EEG signals of 12 subjects using the... 

Common Spatial Pattern (CSP) is a powerful feature extraction method in brain-computer interface (BCI) systems. However, the CSP method has some deficiencies that limit its beneficiary. First, this method is not useful when data is noisy, and it is necessary to have a large dataset because CSP is inclined to overfit. Second, the CSP method uses just the spatial information of the data, and it cannot incorporate the temporal and spectral information. In this paper, we propose a new CSP-based algorithm which is capable of employing the information in all dimensions of data. Also, by defining the regularization term for each mode of information, we can diminish the noise effects and overfitting... 

The smoothness of the graph signals on predefined/constructed graphs appears in many natural applications of processing unstructured (i.e., graph-based) data. In the case of latent sources being smooth graph signals, blind source separation (BSS) quality can be significantly improved by exploiting graph signal smoothness along with the classic measures of statistical independence. In this paper, we propose a BSS method benefiting from the minimization of mutual information as a well-known independence criterion and also graph signal smoothness term of the estimated latent sources, and show that its performance is superior and fairly robust to the state-of-the-art classic and Graph Signal... 

The smoothness of graph signals has found desirable real applications for processing irregular (graph-based) signals. When the latent sources of the mixtures provided to us as observations are smooth graph signals, it is more efficient to use graph signal smoothness terms along with the classic independence criteria in Blind Source Separation (BSS) approaches. In the case of underlying graphs being known, Graph Signal Processing (GSP) provides valuable tools; however, in many real applications, these graphs can not be well-defined a priori and need to be learned from data. In this paper, a GSP-based approach for joint Graph Learning (GL) and BSS of smooth graph signal sources is proposed,... 

Graph Learning (GL) is at the core of leveraging connections in machine learning (ML). By observing a dataset of graph signals and considering specific assumptions, Graph Signal Processing (GSP) provides practical constraints in GL. Inferring a graph with desired frequency signatures, i.e., spectral templates, from stationary graph signals has gained great attention. However, a severe computational burden is a challenging barrier, especially for inference from high-dimensional product graph signals, i.e., graph signals live on the product of smaller factor graphs. Few product GLmethods have been proposed formostly inference with smoothness assumption, while they are limited to learning only... 

The aim of a brain-computer interface (BCI) system is to establish a new communication system that translates human intentions, reflected by measures of brain signals such as magnetoencephalogram (MEG), into a control signal for an output device. In this paper, an algorithm is proposed for discriminating MEG signals, which were recorded during hand movements in four directions. These signals were presented as data set 3 of BCI competition IV. The proposed algorithm has four main stages: pre-processing, primary feature extraction, the selection of efficient features, and classification. The classification stage was a combination of linear SVM and linear discriminant analysis classifiers. The... 

Common spatial pattern (CSP) analysis and its extensions have been widely used as feature extraction approaches in the brain-computer interfaces (BCIs). However, most of the CSP-based approaches do not use any prior knowledge that might be available about the two conditions (classes) to be classified. Therefore, their applications are limited to datasets that contain enough variance information about the two conditions. For example, in some event-related potential (ERP) detection applications, such as P300 speller, the information is in the time domain but not in the variance of spatial components. To address this problem, first, we present a novel feature extraction method termed extended... 

Semi-blind source separation (SBSS) approaches are good alternatives to blind source separation (BSS) approaches in applications in which prior knowledge is available about the sources to be extracted. However, their usage has been limited to two-dimensional data sets so far. Therefore, in case of high-dimensional data sets, approaches such as canonical polyadic decomposition (CPD) have been mostly used as a BSS method. The aim of this work is to address this problem by proposing three novel high-dimensional semi-blind source separation methods in the CPD framework. To this end, our first proposed method termed semi-blind alternative least squares (SBALS) is an extension of alternative least...