Sharif Digital Repository

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... 

Diffusion weighted imaging is a non-invasive method for investigation of brain fiber bundles. In diffusion tensor imaging (DTI), the diffusion of water molecules is assumed Gaussian, therefore, it can just show a single fiber direction in a voxel. To overcome this limitation, a number of high angular resolution diffusion imaging methods have been proposed. One of these techniques is Q-ball imaging. Using this method, we can extract orientation distribution function (ODF) that shows the orientations of multiple fibers in a voxel. For extracting the fiber directions, the maxima of the ODFs are conventionally determined. However, the results of this approach are sensitive to noise. To improve... 

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... 

Feature extraction and classification are the most important parts of BCI systems. The new branch of BCI studies focuses on the design of a classifier that is trained to function properly for each individual. This problem is known as Transfer Learning. In between-subject classification, due to the differences in the neural signals' distribution of different individuals, using the common methods of feature extraction for training the classifier, does not lead to high accuracy for the test subject. As a result, in this study, we present a method for extracting features that perform well in between subjects classifications. The data that we used in this study are EEG signals recorded during... 

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,... 

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... 

In this paper, a new stimulation protocol is proposed to detect the P300 component. In this protocol visual oddball paradigm is used to evoke Event Related Potentials (ERPs). Two types of stimulation protocol for P300 detection (the proposed and standard protocols) are compared in terms of the R-square coefficient and the amplitude of the P300 component. Statistical analysis (paired t-test) is applied to determine the significant differences between the two protocols. The proposed method can enhance the ability to detect the P300 component in comparison to the common protocol that has been provided so far (standard protocol)  

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... 

Background and objective: Steady-state visual evoked potential (SSVEP) and rapid serial visual presentation (RSVP) are useful methods in the brain-computer interface (BCI) systems. Hybrid BCI systems that combine these two approaches can enhance the proficiency of the P300 spellers. Methods: In this study, a new hybrid RSVP/SSVEP BCI is proposed to increase the classification accuracy and information transfer rate (ITR) as compared with the other RSVP speller paradigms. In this paradigm, RSVP (eliciting a P300 response) and SSVEP stimulations are presented in such a way that the target group of characters is identified by RSVP stimuli, and the target character is recognized by SSVEP stimuli.... 

When our sources are graph signals, a more efficient algorithm for Blind Source Separation (BSS) can be provided by using structural graph information along with statistical independence and/or non-Gaussianity. To the best of our knowledge, the GraphJADE and GraDe algorithms are the only BSS methods addressing this issue in the case of known underlying graphs. However, in many real-world applications, these graphs are not necessarily a priori known. In this paper, we propose a method called GraphJADE-GL (GraphJADE with Graph Learning) that jointly separates the graph signal sources and learns the graphs related to them accurately, in an alternating style. © 1994-2012 IEEE  

The primary aim in pre-surgical evaluations in patients with neurological disorders such as epilepsy is determining the precise location of the cortical region responsible for the malfunctions which is called source localization. Different modalities unravel different views of brain activity. Combining these complementary aspects of the brain yields more accurate source localization. In this paper, a method is proposed for combining localization methods in different modalities based on the theory of evidence, the result of some localization methods in modalities are integrated using weights in accordance to their relative performance and are combined using Dempster's rule of combination and... 

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...