Kavitha P. Thomas

A New Discriminative Common Spatial Pattern Method for Motor Imagery Brain–Computer Interfaces

Event-related desynchronization/synchronization patterns during right/left motor imagery (MI) are effective features for an electroencephalogram-based brain-computer interface (BCI). As MI tasks are subject-specific, selection of subject-specific discriminative frequency components play a vital role in distinguishing these patterns. This paper proposes a new discriminative filter bank (FB) common spatial pattern algorithm to extract subject-specific FB for MI classification. The proposed method enhances the classification accuracy in BCI competition III dataset IVa and competition IV dataset IIb. Compared to the performance offered by the existing FB-based method, the proposed algorithm offers error rate reductions of 17.42% and 8.9% for BCI competition datasets III and IV, respectively.

Design of an online EEG based neurofeedback game for enhancing attention and memory

Brain-Computer Interface (BCI) is an alternative communication and control channel between brain and computer which finds applications in neuroprosthetics, brain wave controlled computer games etc. This paper proposes an Electroencephalogram (EEG) based neurofeedback computer game that allows the player to control the game with the help of attention based brain signals. The proposed game protocol requires the player to memorize a set of numbers in a matrix, and to correctly fill the matrix using his attention. The attention level of the player is quantified using sample entropy features of EEG. The statistically significant performance improvement of five healthy subjects after playing a number of game sessions demonstrates the effectiveness of the proposed game in enhancing their concentration and memory skills.

An adaptive filter bank for motor imagery based Brain Computer Interface

Brain Computer Interface (BCI) provides an alternative communication and control method for people with severe motor disabilities. Motor imagery patterns are widely used in Electroencephalogram (EEG) based BCIs. These motor imagery activities are associated with variation in alpha and beta band power of EEG signals called Event Related Desynchronization/synchronization (ERD/ERS). The dominant frequency bands are subject-specific and therefore performance of motor imagery based BCIs are sensitive to both temporal filtering and spatial filtering. As the optimum filter is strongly subject-dependent, we propose a method that selects the subject-specific discriminative frequency components using time-frequency plots of Fisher ratio of two-class motor imagery patterns. We also propose a low complexity adaptive Finite Impulse Response (FIR) filter bank system based on coefficient decimation technique which can realize the subject-specific bandpass filters adaptively depending on the information of Fisher ratio map. Features are extracted only from the selected frequency components. The proposed adaptive filter bank based system offers average classification accuracy of about 90%, which is slightly better than the existing fixed filter bank system.

Adaptive tracking of discriminative frequency components in electroencephalograms for a robust brain?computer interface

In an electroencephalogram (EEG)-based brain-computer interface (BCI), motor imagery has been successfully used as a communication strategy. Motor imagery causes detectable amplitude changes in certain frequency bands of EEGs, which are dubbed event-related desynchronization\synchronization. The frequency components that give effective discrimination between different types of motor imagery are subject specific and identification of these subject-specific discriminative frequency components (DFCs) is important for the accurate classification of motor imagery activities. In this paper, we propose a new method to estimate the DFC using the Fisher criterion and investigate the variability of these DFCs over multiple sessions of EEG recording. Observing the variability of DFC over sessions in the analysis, a new BCI approach called the Adaptively Weighted Spectral-Spatial Patterns (AWSSP) algorithm is proposed. AWSSP tracks the variation in DFC over time adaptively based on the deviation of discriminative weight values of frequency components. The classification performance of the proposed AWSSP is compared with a static BCI approach that employs fixed DFCs. In the offline and online experiments, AWSSP offers better classification performance than the static approach, emphasizing the significance of tracking the variability of DFCs in EEGs for developing robust motor imagery-based BCI systems. A study of the effect of feedback on the variation in DFCs is also performed in online experiments and it is found that the presence of visual feedback results in increased variation in DFCs.

Enhancement of attention and cognitive skills using EEG based neurofeedback game

Neurofeedback, the self-regulation of brain signals recorded using Electroencephalogram (EEG), allows Brain-Computer Interface (BCI) users to enhance cognitive as well as motor functions using specific training strategies. Therapeutic effects of neurofeedback (by the induction of neuroplasticity) on treatment of people with neurological disorders such as Attention-Deficit Hyperactive Disorder (ADHD), dementia and stroke have been reported in literature. In this paper, we investigate the impact of a neurofeedback based BCI game on the enhancement of attention and cognitive skills of healthy subjects. The BCI game is controlled by players attention-related EEG signal. In the proposed training paradigm, subjects play the neurofeedback game regularly for a period of 5 days. The experimental analysis of players attention level (measured by entropy values of EEG) and the comparison of cognitive test results demonstrate the benefits of practicing BCI based neurofeedback game in the enhancement of attention/cognitive skills.

An electrooculogram based assistive communication system with improved speed and accuracy using multi-directional eye movements

Human-Computer Interface (HCI) enables people to control computer applications using bio-electric signals recorded from the body. HCI can be a potential tool for people with severe motor disabilities to communicate to external world through bio-electric signals. In an Electrooculogram (EOG) based HCI, signals during various eye (cornea) movements are employed to generate control signals. This paper presents the design of an EOG-based typing system which uses a virtual keyboard for typing letters on the monitor using 8 types of distinct EOG patterns. Identification of EOG pattern is based on the amplitude and timing of positive and negative components within the signal. Experimental results show that proposed EOG-based typing system achieves a higher typing speed of 15 letters/min and an improved accuracy of 95.2% compared to the state-of art method that has a typing speed of 12.1 letters/min and accuracy of 90.4%.

Two player EEG-based neurofeedback ball game for attention enhancement

Brain computer interface (BCI) based neurofeedback games have the potential to enhance the cognitive skills of healthy people as well as subjects with cognitive and memory impairment. Electroencephalogram (EEG) has been used as a common brain imaging modality as it is easy and cheap among all the other non-invasive techniques. This paper proposes an EEG driven gaming interface where the subjects attention (concentration) is used to control the game successfully. The proposed game scenario requires the player to push a ball from one end of games graphical user interface to the other end using his attention level. Attention level of the player is quantified using the ratio of theta to beta band power in EEG signals. The experimental analysis shows that the proposed game is capable of enhancing players attention skill as well as enhances the ability of the player to sustain attention for longer duration. This “ball game” can be effectively used in neurofeedback training for attention deficit children.

BCI based multi-player 3-D game control using EEG for enhancing attention and memory

Brain-Computer Interface (BCI) technique is considered as an efficient alternative modality for improving brain functions such as attention and cognition, based on real time feedback of Electroencephalogram (EEG) signals and their self-regulation. Commercialization of EEG headsets provides tremendous opportunities and possibilities for this technology to employ EEG in video games for cognitive-skill enhancement. This paper proposes a multi-player video game in 3-D environment controlled by EEG features related to 3 different levels of attention. A number of conventional control mechanisms present in commercial games such as keyboard strokes have also been integrated in the game. Three different levels of attention have been detected from players based on their sample entropy features and band power values in alpha, beta and theta bands of EEG. Three subjects have successfully navigated in the designed 3-D environment using EEG based controls as well as keyboard inputs. Experimental results reveal the feasibility of integrating brain signal based inputs along with conventional control inputs in the context of multi-player neurofeedback games for improving brain functions.

A study on the impact of neurofeedback in EEG based attention-driven game

Multi-disciplinary study of human computer interaction has provided significant impact in the fields of neural engineering, cognitive neuroscience, rehabilitation and brain-computer interaction. This paper evaluates the impact of neurofeedback in the context of a simple computer game controlled by attention based brain signals. The designed game protocol requires the player to memorize a set of numbers displayed in a matrix format, and to correctly fill the matrix using his attention based brain patterns. Attention level of the player, quantified using sample entropy values of Electroencephalogram (EEG) signals, is the core control parameter of the game. A comparative study using a single neurofeedback group and 2 control groups (each group consists of 8 subjects) has been carried out to examine the impact of neurofeedback on enhancing attention score and cognitive skill in the context of the attention-driven game. Experimental results explicitly demonstrate the significance and usefulness of neurofeedback in EEG based games.

Utilizing individual alpha frequency and delta band power in EEG based biometric recognition

Brain activities are inherently determined by a persons unique pattern of neural pathways and are closely associated with his/her genetic personality traits. Brain activity recorded by electroencephalogram (EEG), has recently been regarded as potential candidate in future generation biometric systems. In this paper, a biometric identification system is proposed, combining subject-specific alpha peak frequency, peak power and delta band power values to form discriminative feature vectors and templates. A public dataset of EEG signals recorded from 109 healthy subjects during eyes open/closed (EO/EC) relaxed rest states, has been analyzed here. Using simple similarity measurements based on correlation and distance measures of the test EEG sequences from the template vectors, an average recognition rate of up to 90 % is achieved, by combining spectral features from delta and alpha bands extracted from selected 19 EEG channels. Experimental results explicitly show the usefulness of combining subject-specific alpha and delta bands in future biometric recognition systems. Further investigation is essential to precisely analyze the system and to improve recognition accuracy.