Ashkan Yazdani

Classification of EEG signals using Dempster Shafer theory and a k-nearest neighbor classifier

A brain computer interface (BCI) is a communication system, which translates brain activity into commands for a computer or other devices. Nearly all BCIs contain as a core component a classification algorithm, which is employed to discriminate different brain activities using previously recorded examples of brain activity. In this paper, we study the classification accuracy achievable with a k-nearest neighbor (KNN) method based on Dempster-Shafer theory. To extract features from the electroencephalogram (EEG), autoregressive (AR) models and wavelet decomposition are used. To test the classification method an EEG dataset containing signals recorded during the performance of five different mental tasks is used. We show that the Dempster-Shafer KNN classifier achieves a higher correct classification rate than the classical voting KNN classifier and the distance-weighted KNN classifier.

Fisher linear discriminant based person identification using visual evoked potentials

Biometrics is the technique of uniquely recognizing a person among a group of people. It is usually performed based on one or more of humanpsilas intrinsic physical or behavioral traits. One such trait is the electroencephalogram (EEG) signal. In this paper, the feasibility of visual evoked potential (VEP) in the gamma band of EEG signal, as a physiological trait, is studied, and used to identify individuals in a group of 20 people. To this end, the parameters of the AR model together with the peak of the power spectrum density (PSD) of the gamma band VEP signal (GMVEP) are considered as main useful features. Next, the Fisherpsilas linear discriminant (FLD) is used to reduce the feature vector dimensions. Finally, the k nearest neighborhood (KNN) technique is employed to classify the data and the leave-one-out cross validation method is used for accuracy assessment. A correct classification rate of 100% is achieved.

Multimedia content analysis for emotional characterization of music video clips

Nowadays, tags play an important role in the search and retrieval process in multimedia content sharing social networks. As the amount of multimedia contents explosively increases, it is a challenging problem to find a content that will be appealing to the users. Furthermore, the retrieval of multimedia contents, which can match users’ current mood or affective state, can be of great interest. One approach to indexing multimedia contents is to determine the potential affective state, which they can induce in users. In this paper, multimedia content analysis is performed to extract affective audio and visual cues from different music video clips. Furthermore, several fusion techniques are used to combine the information extracted from the audio and video contents of music video clips. We show that using the proposed methodology, a relatively high performance (up to 90%) of affect recognition is obtained.

Affect recognition based on physiological changes during the watching of music videos

Assessing emotional states of users evoked during their multimedia consumption has received a great deal of attention with recent advances in multimedia content distribution technologies and increasing interest in personalized content delivery. Physiological signals such as the electroencephalogram (EEG) and peripheral physiological signals have been less considered for emotion recognition in comparison to other modalities such as facial expression and speech, although they have a potential interest as alternative or supplementary channels. This article presents our work on: (1) constructing a dataset containing EEG and peripheral physiological signals acquired during presentation of music video clips, which is made publicly available, and (2) conducting binary classification of induced positive/negative valence, high/low arousal, and like/dislike by using the aforementioned signals. The procedure for the dataset acquisition, including stimuli selection, signal acquisition, self-assessment, and signal processing is described in detail. Especially, we propose a novel asymmetry index based on relative wavelet entropy for measuring the asymmetry in the energy distribution of EEG signals, which is used for EEG feature extraction. Then, the classification systems based on EEG and peripheral physiological signals are presented. Single-trial and single-run classification results indicate that, on average, the performance of the EEG-based classification outperforms that of the peripheral physiological signals. However, the peripheral physiological signals can be considered as a good alternative to EEG signals in the case of assessing a users preference for a given music video clip (like/dislike) since they have a comparable performance to EEG signals while being more easily measured.

Electroencephalogram alterations during perception of pleasant and unpleasant odors

The olfactory system enables humans and many animals recognize and categorize different odors and can determine many behavioral and social reactions. For human beings, odor stimuli are highly associated with many processes such as emotions, attraction, mood, etc. One approach to understanding the olfaction is to monitor and analyze human brain activity during perception of odors. In this paper, we analyze electroencephalogram (EEG) of five participants during perception of unpleasant and pleasant odor stimuli. We identify the regions of the brain cortex that are active during discrimination of unpleasant and pleasant odor stimuli. We also show that, classification of EEG signals during perception of odors can reveal the pleasantness of the odor with relatively high accuracy.

Multivariate spectral analysis for identifying the brain activations during olfactory perception

Olfactory perception is a complex phenomenon associated with other processes such as cognition and emotion. Due to this complexity, there are still open issues and challenges regarding olfactory psychophysiology. One challenge concerns the investigation of the hedonic dimension of olfaction, and how it affects the power of the brain oscillations. Although there are some EEG studies exploring the changes in the power of the brain oscillations during olfactory perception, they use simple power spectral analysis techniques and vary much in terms of the reported findings. To reduce this variability, we propose the use of multivariate spectral analysis, to reveal only the frequency patterns of the EEG signals that contribute the most to olfactory perception. The goal is to investigate how these frequency patterns are affected by hedonically different odors throughout the cortex.

Manifold Learning Applied on EEG Signal of the Epileptic Patients for Detection of Normal and Pre-Seizure States

In this paper, several manifold learning (ML) techniques for dimension reduction of EEG feature vectors are introduced and applied on set of epileptic EEG signals. These include principal component analysis (PCA), multidimensional scaling (MDS), isometric mapping (ISOMAP) and locally linear embedding (LLE). While EEG signals of epileptic patients contain necessary information with regards to the various brain states of epileptic patients, for extraction of useful information in the EEG signals and for detection, often construction of high-dimensional feature vectors is utilized. Analysis of such high-dimensional feature vectors are complex and time consuming. This paper deals with dimension reduction of the extracted feature vectors and comparative analysis of the performance of several manifold learning techniques as applied on EEG signals of epileptic patients.

Classification of EEG signals correlated with alcohol abusers

The availability of quantitative biological markers that are correlated with qualitative psychiatric phenotypes helps us utilize automatic methods to diagnose and classify these phenotypes. EEG signals are appropriate means for extraction of these quantitative markers. According to the literature, many brain disorders and/or mental tasks can be detected by analyzing EEG signals. One such a psychiatric phenotype is alcoholism. In this paper different statistical classifiers including Bayes classifier with Gaussian kernel, Bayes classifier with KNN pdf estimator, k-nearest neighbor classifier and minimum mean distance classifier have been used in order to classify alcoholics and normal people by analyzing their EEG signals. Then by applying PCA to the feature vector and reducing the number of features to only one feature it is shown that an accuracy of 100% can be achieved for separating the two classes.

EEG Correlates of Pleasant and Unpleasant Odor Perception

Olfaction-enhanced multimedia experience is becoming vital for strengthening the sensation of reality and the quality of user experience. One approach to investigate olfactory perception is to analyze the alterations in brain activity during stimulation with different odors. In this article, the changes in the electroencephalogram (EEG) when perceiving hedonically-different odors are studied. Results of within and across-subject analysis are presented. We show that EEG-based odor classification using brain activity is possible and can be used to automatically recognize odor pleasantness when a subject-specific classifier is trained. However, it is a challenging problem to design a generic classifier.

Implicit retrieval of salient images using Brain Computer Interface

Space missions are often equipped with several high definition sensors that can autonomously collect a potentially enormous amount of data. The bottleneck in retrieving these often precious datasets is the onboard data storing capability and the communication bandwidth, which limit the amount of data that can be sent back to Earth. In this paper, we propose a method based on the analysis of brain electrical activity to identify the scientific interest of experts towards a given image in a large set of images. Such a method can be used to efficiently create an abundant training set (images and whether they are scientifically interesting) with a considerably faster image presentation rate that can go beyond expert consciousness, with less interrogation time for experts and relatively high performance.