Brain Computer Interfaces (BCI) are devices that translate acquired neural signals to command and control signals. Applications of BCI include neural rehabilitation and neural prosthesis (thought controlled wheelchair, thought controlled speller etc.) to aid patients with disabilities and to augment human computer interaction. A successful practical BCI requires a faithful acquisition modality to record high quality neural signals; a signal processing system to construct appropriate features from these signals; and an algorithm to translate these features to appropriate outputs. Intracortical recordings like local field potentials provide reliable high SNR signals over long periods and suit BCI applications well. However, the non-stationarity of neural signals poses a challenge in robust decoding of subject behavior. Most BCI research focuses either on developing daily re-calibrated decoders that require exhaustive training sessions; or on providing cross-validation results. Such results ignore the variation of signal characteristics over different sessions and provide an optimistic estimate of BCI performance. Specifically, traditional BCI algorithms fail to perform at the same level on chronological data recordings. Neural signals are susceptible to variations in signal characteristics due to changes in subject behavior and learning, and variability in electrode characteristics due to tissue interactions. While training day-specific BCI overcomes signal variability, BCI re-training causes user frustration and exhaustion. This dissertation presents contributions to solve these challenges in BCI research. Specifically, we developed decoders trained on a single recording session and applied them on subsequently recorded sessions. This strategy evaluates BCI in a practical scenario with a potential to alleviate BCI user frustration without compromising performance. The initial part of the dissertation investigates extracting features that remain robust to changes in neural signal over several days of recordings. It presents a qualitative feature extraction technique based on ranking the instantaneous power of multichannel data. These qualitative features remain robust to outliers and changes in the baseline of neural recordings, while extracting discriminative information. These features form the foundation in developing robust decoders. Next, this dissertation presents a novel algorithm based on the hypothesis that multiple neural spatial patterns describe the variation in behavior. The presented algorithm outperforms the traditional methods in decoding over chronological recordings. Adapting such a decoder over multiple recording sessions (over 6 weeks) provided > 90% accuracy in decoding eight movement directions. In comparison, performance of traditional algorithms like Common Spatial Patterns deteriorates to 16% over the same time. Over time, adaptation reinforces some spatial patterns while diminishing others. Characterizing these spatial patterns reduces model complexity without user input, while retaining the same accuracy levels. Lastly, this dissertation provides an algorithm that overcomes the variation in recording quality. Chronic electrode implantation causes changes in signal-to-noise ratio (SNR) of neural signals. Thus, some signals and their corresponding features available during training become unavailable during testing and vice-versa. The proposed algorithm uses prior knowledge on spatial pattern evolution to estimate unknown neural features. This algorithm overcomes SNR variations and provides up to 93% decoding of eight movement directions over 6 weeks. Since model training requires only one session, this strategy reduces user frustration. In a practical closed-loop BCI, the user learns to produce stable spatial patterns, which improves performance of the proposed algorithms. / text

Emotions are thought to be one of the key factors that critically influences human decision-making. Emotion regulation can help to mitigate emotion related decision biases and eventually lead to a better decision performance. Serious games emerged as a new angle introducing technological methods to learning emotion regulation, where meaningful biofeedback information communicates player's emotional state. Games are a series of interesting choices, where design of those choices could support an educational platform to learning emotion regulation. Such design could benefit digital serious games as those choices could be informed though player's physiology about emotional states in real time. This thesis explores design and evaluation methods for creating serious games where emotion regulation can be learned and practiced. Design of a digital serious game using physiological measures of emotions was investigated and evaluated. Furthermore, it investigates emotions and the effect of emotion regulation on decision performance in digital serious games. The scope of this thesis was limited to digital serious games for emotion regulation training using psychophysiological methods to communicate player's affective information. Using the psychophysiological methods in design and evaluation of digital serious games, emotions and their underlying neural mechanism have been explored. Effects of emotion regulation have been investigated where decision performance has been measured and analyzed. The proposed metrics for designing and evaluating such affective serious games have been extensively evaluated. The research methods used in this thesis were based on both quantitative and qualitative aspects, with true experiment and evaluation research, respectively. Digital serious games approach to emotion regulation was investigated, player's physiology of emotions informs design of interactions where regulation of those emotions could be practiced. The results suggested that two different emotion regulation strategies, suppression and cognitive reappraisal, are optimal for different decision tasks contexts. With careful design methods, valid serious games for training those different strategies could be produced. Moreover, using psychophysiological methods, underlying emotion neural mechanism could be mapped. This could inform a digital serious game about an optimal level of arousal for a certain task, as evidence suggests that arousal is equally or more important than valence for decision-making. The results suggest that it is possible to design and develop digital serious game applications that provide helpful learning environment where decision makers could practice emotion regulation and subsequently improve their decision-making. If we assume that physiological arousal is more important than physiological valence for learning purposes, results show that digital serious games designed in this thesis elicit high physiological arousal, suitable for use as an educational platform.

The goal of the study was to use electrical signals from primary motor cortex to generate accurate predictions of the movement onset time of performed movements, for potential use in asynchronous brain-machine interface (BMI) systems. Four subjects, two with electroencephalogram and two with electrocorticogram electrodes, performed various movements while activity from their primary motor cortices was recorded. An analysis program used several criteria (change point, fractal dimension, spectral entropy, sum of differences, bandpower, bandpower integral, phase, and variance), derived from the neural recordings, to generate predictions of movement onset time, which it compared to electromyogram activity onset time, determining prediction accuracy by receiver operating characteristic curve areas. All criteria, excepting phase and change-point analysis, generated accurate predictions in some cases.

A brain-machine interface (BMI) uses signals from the brain to control electronic devices. One application of this technology is the control of assistive devices to facilitate movement after paralysis. Ideally, the BMI would identify an intended movement and control an assistive device to produce the desired movement. To implement such a system, it is necessary to identify different movements involving a single limb and users must be able to issue commands at any instant instead of only during specific time windows determined by the BMI itself. A novel processing technique to identify voluntary movements using only four electrodes is presented. Histograms containing the spectral components of intracranial neural signals displaying power changes correlated with movement were unique for each of three movements performed with one limb. Off-line classification of the histograms allowed the identification of the performed movement with an accuracy of 89%. This movement identification system was interfaced with a neuroprosthesis for grasping, fitted to a tetraplegic individual. The user pressed a button triggering the random selection and classification of a brain signal previously recorded intracranially from a different person while performing specific arm movements. Correct identification of the movement triggered grasping functions. Movement identification accuracy was 94% allowing successful operation of the neuroprosthesis. Finally, two BMIs for the real-time asynchronous control of two-dimensional movements were created using a single electrode. One EEG-based system was tested by a healthy participant. A second system was implemented and tested using recordings from an individual undergoing clinical intracranial electrode implantation. The users modulated their 7 Hz-13 Hz oscillatory rhythm through motor imagery. A power decrease below a threshold activated a ``brain-switch''. This switch was coupled with a novel asynchronous control strategy to control a miniature remotely-controlled vehicle as well as a computer cursor. Successful operation of the EEG system required 6 hrs of training. ECoG control was achieved after only 15 minutes. The operation of the BMI was simple enough to allow users to focus on the task at hand rather than on the actual operation of the BMI.

A brain-machine interface (BMI) uses signals from the brain to control electronic devices. One application of this technology is the control of assistive devices to facilitate movement after paralysis. Ideally, the BMI would identify an intended movement and control an assistive device to produce the desired movement. To implement such a system, it is necessary to identify different movements involving a single limb and users must be able to issue commands at any instant instead of only during specific time windows determined by the BMI itself. A novel processing technique to identify voluntary movements using only four electrodes is presented. Histograms containing the spectral components of intracranial neural signals displaying power changes correlated with movement were unique for each of three movements performed with one limb. Off-line classification of the histograms allowed the identification of the performed movement with an accuracy of 89%. This movement identification system was interfaced with a neuroprosthesis for grasping, fitted to a tetraplegic individual. The user pressed a button triggering the random selection and classification of a brain signal previously recorded intracranially from a different person while performing specific arm movements. Correct identification of the movement triggered grasping functions. Movement identification accuracy was 94% allowing successful operation of the neuroprosthesis. Finally, two BMIs for the real-time asynchronous control of two-dimensional movements were created using a single electrode. One EEG-based system was tested by a healthy participant. A second system was implemented and tested using recordings from an individual undergoing clinical intracranial electrode implantation. The users modulated their 7 Hz-13 Hz oscillatory rhythm through motor imagery. A power decrease below a threshold activated a ``brain-switch''. This switch was coupled with a novel asynchronous control strategy to control a miniature remotely-controlled vehicle as well as a computer cursor. Successful operation of the EEG system required 6 hrs of training. ECoG control was achieved after only 15 minutes. The operation of the BMI was simple enough to allow users to focus on the task at hand rather than on the actual operation of the BMI.

Brain-Computer Interface (BCI) systems aim to provide a non-muscular channel for the brain to control external devices using electrical activities of the brain. These BCI systems can be used in various applications, such as controlling a wheelchair, neuroprosthesis, or speech synthesizer for disabled individuals, navigation in virtual environment, and assisting healthy individuals in performing highly demanding tasks. Motor-imagery BCI systems in particular are based on decoding imagination of motor tasks, e.g., to control the movement of a wheelchair or a mouse curser on the computer screen and move it to the right or left directions by imagining right/left hand movement. During the past decade, there has been a growing interest in utilization of electroencephalogram (EEG) signals for non-invasive motor-imagery BCI systems, due to their low cost, ease of use, and widespread availability. During motor-imagery tasks, multichannel EEG signals exhibit task-specific features in both spatial domain and spectral (or frequency) domain. This thesis studies the statistical characteristics of the multichannel EEG signals in these two domains and proposes a new approach for spatio-spectral feature extraction in motor-imagery BCI systems. This approach is based on the fact that due to the multichannel structure of the EEG data, its spatio-spectral features have a matrix-variate structure. This structure, which has been overlooked in the literate, can be exploited to design more efficient feature extraction methods for motor-imagery BCIs. Towards this end, this research work adopts a matrix-variate Gaussian model for the spatio-spectral features, which assumes a separable Kronecker product structure for the covariance of these features. This separable structure, together with the general properties of the Gaussian model, enables us to design new feature extraction schemes which can operate on the data in its inherent matrix-variate structure to reduce the computational cost of the BCI system while improving its performance. Throughout this thesis, the proposed matrix-variate model and its implications will be studied in various different feature extraction scenarios.

No description available.

Evidence suggests that cerebral blood flow patterns accompanying a mental activity are retained in many locked-in patients. Thus, real-time monitoring with functional transcranial Doppler (TCD) together with a specific mental task could control a brain-computer interface (BCI), thereby providing self-initiated interaction. The objective of this study was to create an automatic detection algorithm to differentiate hemodynamic responses coincident with one's performance of verbal fluency (VF) versus counting tasks. We recruited 10 healthy adults who each silently performed up to 30 VF tasks and counted between each. Both middle cerebral arteries were simultaneously imaged using TCD. Linear Discriminant Analyses (LDA) successfully differentiated between VF and both prior and post counting tasks. For every participant, LDA achieved the 70% classification accuracy sufficient for BCIs. Results demonstrate automatic detection of a VF task by TCD and warrant further investigation of TCD as a BCI.

Evidence suggests that cerebral blood flow patterns accompanying a mental activity are retained in many locked-in patients. Thus, real-time monitoring with functional transcranial Doppler (TCD) together with a specific mental task could control a brain-computer interface (BCI), thereby providing self-initiated interaction. The objective of this study was to create an automatic detection algorithm to differentiate hemodynamic responses coincident with one's performance of verbal fluency (VF) versus counting tasks. We recruited 10 healthy adults who each silently performed up to 30 VF tasks and counted between each. Both middle cerebral arteries were simultaneously imaged using TCD. Linear Discriminant Analyses (LDA) successfully differentiated between VF and both prior and post counting tasks. For every participant, LDA achieved the 70% classification accuracy sufficient for BCIs. Results demonstrate automatic detection of a VF task by TCD and warrant further investigation of TCD as a BCI.

Near-infrared spectroscopy (NIRS) in an imaging technique that has gained much attention in brain-computer interfaces (BCIs). Previous NIRS-BCI studies have primarily employed temporal features, derived from the time course of hemodynamic activity, despite potential value contained in the spatial attributes of a response. In an initial offline study, we investigated the value of using joint spatial-temporal pattern classification with dynamic NIR topograms to differentiate intentional cortical activation from rest. With the inclusion of spatiotemporal features, we demonstrated a significant increase in achievable classification accuracies from those obtained using temporal features alone (p < 10-4). In a second study, we evaluated the feasibility of implementing joint spatial-temporal pattern classification in an online system. We developed an online system-paced NIRS-BCI, and were able to differentiate two cortical states with high accuracy (77.4±10.5%). Collectively, these findings demonstrate the value of including spatiotemporal features in the classification of functional NIRS data for BCI applications.