Individuals with limited motor control are often unable to interact with their environment. Recently, near-infrared spectroscopy (NIRS) systems have been investigated as potential brain-computer interfaces (BCI). Previous studies examined data offline, preventing users from understanding how their thoughts triggered the NIRS system. This thesis focused on understanding the short-term effects of feedback on user’s ability to learn how to control BCIs. Data were collected from control and experimental groups over seven sessions, as they performed fast singing imagery or mental arithmetic. Significant differences were observed between the control group’s results in non-feedback sessions and the experimental group’s results in feedback sessions. Qualitative results from 3 of the 10 participants suggested they had control of the feedback system. They performed the task with online accuracies of 61% - 88% in the final 2 sessions with feedback. These results suggest that continued investigation of NIRS feedback systems is warranted.

A Human-Machine Interface is a device that allows humans to inter- act with and use machines. One such device is a Brain-Computer Interface which allows the user to communicate to a computer system through thought patterns. A commonly used technique, electroencephalography, uses multiple sensors positioned on the subject’s cranium to extract electrical changes as a representation of thought patterns. This report investigates the use of a single EEG sensor as a user-friendly BCI implementation. The primary goal of this report is to determine if specific mental tasks can be reliably detected with such a system. / text

Session ID: SA-B1-2 / SCIS & ISIS 2010, Joint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent Systems. December 8-12, 2010, Okayama Convention Center, Okayama, Japan

Brain-computer interface (BCI) technologies allow users to control external devices through brain activity alone, circumventing the somatic nervous system and the need for overt physical movement. BCIs may potentially benefit individuals with severe neuromuscular disorders who experience significant, and often total, loss of voluntary muscle control (e.g. amyotrophic lateral sclerosis, multiple sclerosis, brainstem stroke). Though a majority of BCI research to date has focused on electroencephalography (EEG) for brain signal acquisition, recently researchers have noted the potential of an optical imaging technology called near-infrared spectroscopy (NIRS) for BCI applications. This thesis investigates the feasibility of a practical, online optical BCI based on conscious modulation of prefrontal cortex activity through the performance of different cognitive tasks, specifically mental arithmetic (MA) and mental singing (MS). The thesis comprises five studies, each representing a step toward the realization of a practical optical BCI. The first study demonstrates the feasibility of a two-choice synchronized optical BCI based on intentional control states corresponding to MA and MS. The second study explores a more user-friendly alternative - a two-choice system-paced BCI supporting a single intentional control state (either MA or MS) and a natural baseline, or "no-control (NC)", state. The third study investigates the feasibility of a three-choice system-paced BCI supporting both MA and MS, as well as the NC state. The fourth study examines the consistency with which the relevant mental states can be differentiated over multiple sessions. The first four studies involve healthy adult participants; in the final study, the feasibility of optical BCI use by a user with Duchenne muscular dystrophy is explored. In the first study, MA and MS were classified with an average accuracy of 77.2% (n=10), while in the second, MA and MS were differentiated individually from the NC state with average accuracies of 71.2% and 62.7%, respectively (n=7). In the third study, an average accuracy of 62.5% was obtained for the MA vs. MS vs. NC problem (n=4). The fourth study demonstrated that the ability to classify mental states (specifically MA vs. NC) remains consistent across multiple sessions (p=0.67), but that there is intersession variability in the spatiotemporal characteristics that best discriminate the states. In the final study, a two-session average accuracy of 71.1% was achieved in the MA vs. NC classification problem for the participant with Duchenne muscular dystrophy.

Severe motor impairments can severely restrict interaction with one's surroundings. Brain computer interfaces combined with text-based communication systems, such as the P300 Speller, have allowed individuals with motor disabilities to spell messages with their EEG signals. Although providing full composition flexibility, they enable communication rates of only a few characters per minute. Utterance-based communication systems have been developed for individuals with disability and have greatly increased communication speeds, but have yet to be applied to BCIs. This paper proposes an utterance-based communication system using the P300-BCI in which words are organized in a network structure that facilitates rapid retrieval. In trials with able-bodied participants, the proposed system achieved greater message speeds, but rated lower in effectiveness than the P300 Speller. Nonetheless, subject preferences and reports of self-perceived effectiveness suggested an inclination towards the proposed word system and thus further investigation of word-based networks is warranted in brain-controlled AAC systems.

Neuroimaging techniques can give novel insights into the nature of human cognition. We do not wish only to label patterns of activity as potentially associated with a cognitive process, but also to probe this in detail, so as to better examine how it may inform mechanistic theories of cognition. A possible approach towards this goal is to extend EEG 'brain-computer interface' (BCI) tools - where motor movement intent is classified from brain activity - to also investigate visual cognition experiments. We hypothesised that, building on BCI techniques, information from visual object tasks could be classified from EEG data. This could allow novel experimental designs to probe visual information processing in the brain. This can be tested and falsified by application of machine learning algorithms to EEG data from a visual experiment, and quantified by scoring the accuracy at which trials can be correctly classified. Further, we hypothesise that ICA can be used for source-separation of EEG data to produce putative activity patterns associated with visual process mechanisms. Detailed profiling of these ICA sources could be informative to the nature of visual cognition in a way that is not accessible through other means. While ICA has been used previously in removing 'noise' from EEG data, profiling the relation of common ICA sources to cognitive processing appears less well explored. This can be tested and falsified by using ICA sources as training data for the machine learning, and quantified by scoring the accuracy at which trials can be correctly classified using this data, while also comparing this with the equivalent EEG data. We find that machine learning techniques can classify the presence or absence of visual stimuli at 85% accuracy (0.65 AUC) using a single optimised channel of EEG data, and this improves to 87% (0.7 AUC) using data from an equivalent single ICA source. We identify data from this ICA source at time period around 75-125 ms post-stimuli presentation as greatly more informative in decoding the trial label. The most informative ICA source is located in the central occipital region and typically has prominent 10-12Hz synchrony and a -5 μV ERP dip at around 100ms. This appears to be the best predictor of trial identity in our experiment. With these findings, we then explore further experimental designs to investigate ongoing visual attention and perception, attempting online classification of vision using these techniques and IC sources. We discuss how these relate to standard EEG landmarks such as the N170 and P300, and compare their use. With this thesis, we explore this methodology of quantifying EEG neuroimaging data with machine learning separation and classification and discuss how this can be used to investigate visual cognition. We hope the greater information from EEG analyses with predictive power of each ICA source quantified by machine learning separation and classification and discuss how this can be used to investigate visual cognition. We hope the greater information from EEG analyses with predictive power of each ICA source quantified by machine learning might give insight and constraints for macro level models of visual cognition.

P300 spellers provide a noninvasive method of communication for people who may not be able to use other communication aids due to severe neuromuscular disabilities. However, P300 spellers rely on event-related potentials (ERPs) which often have low signal-to-noise ratios (SNRs). In order to improve detection of the ERPs, P300 spellers typically collect multiple measurements of the electroencephalography (EEG) response for each character. The amount of collected data can affect both the accuracy and the communication rate of the speller system. The goal of the present study was to develop an algorithm that would automatically determine the necessary amount of data to collect during operation. Dynamic data collection was controlled by a threshold on the probabilities that each possible character was the target character, and these probabilities were continually updated with each additional measurement. This Bayesian technique differs from other dynamic data collection techniques by relying on a participant-independent, probability-based metric as the stopping criterion. The accuracy and communication rate for dynamic and static data collection in P300 spellers were compared for 26 users. Dynamic data collection resulted in a significant increase in accuracy and communication rate.

Event-related potential (ERP)-based brain-computer interfacing (BCI) is an effective method of basic communication. However, collecting calibration data, and classifier training, detracts from the amount of time allocated for online communication. Decreasing calibration time can reduce preparation time thereby allowing for additional online use, potentially lower fatigue, and improved performance. Previous studies, using generic online training models which avoid offline calibration, afford more time for online spelling. Such studies have not examined the direct effects of the model on individual performance, and the training sequence exceeded the time reported here.The first goal of this work is to survey whether one generic model works for all subjects and the second goal is to show the performance of a generic model using an online training strategy when participants could use the generic model. The generic model was derived from 10 participant's data. An additional 11 participants were recruited for the current study. Seven of the participants were able to use the generic model during online training. Moreover, the generic model performed as well as models obtained from participant specific offline data with a mean training time of less than 2. min. However, four of the participants could not use this generic model, which shows that one generic mode is not generic for all subjects. More research on ERPs of subjects with different characteristics should be done, which would be helpful to build generic models for subject groups. This result shows a potential valuable direction for improving the BCI system.

P300 spellers provide a noninvasive method of communication for people who may not be able to use other communication aids due to severe neuromuscular disabilities. However, P300 spellers rely on event-related potentials (ERPs) which often have low signal-to-noise ratios (SNRs). In order to improve detection of the ERPs, P300 spellers typically collect multiple measurements of the electroencephalography (EEG) response for each character. The amount of collected data can affect both the accuracy and the communication rate of the speller system. The goal of the present study was to develop an algorithm that would automatically determine the necessary amount of data to collect during operation. Dynamic data collection was controlled by a threshold on the probabilities that each possible character was the target character, and these probabilities were continually updated with each additional measurement. This Bayesian technique differs from other dynamic data collection techniques by relying on a participant-independent, probability-based metric as the stopping criterion. The accuracy and communication rate for dynamic and static data collection in P300 spellers were compared for 26 users. Dynamic data collection resulted in a significant increase in accuracy and communication rate.

Event-related potential (ERP)-based brain-computer interfacing (BCI) is an effective method of basic communication. However, collecting calibration data, and classifier training, detracts from the amount of time allocated for online communication. Decreasing calibration time can reduce preparation time thereby allowing for additional online use, potentially lower fatigue, and improved performance. Previous studies, using generic online training models which avoid offline calibration, afford more time for online spelling. Such studies have not examined the direct effects of the model on individual performance, and the training sequence exceeded the time reported here.The first goal of this work is to survey whether one generic model works for all subjects and the second goal is to show the performance of a generic model using an online training strategy when participants could use the generic model. The generic model was derived from 10 participant's data. An additional 11 participants were recruited for the current study. Seven of the participants were able to use the generic model during online training. Moreover, the generic model performed as well as models obtained from participant specific offline data with a mean training time of less than 2. min. However, four of the participants could not use this generic model, which shows that one generic mode is not generic for all subjects. More research on ERPs of subjects with different characteristics should be done, which would be helpful to build generic models for subject groups. This result shows a potential valuable direction for improving the BCI system.