Andrea Biasiucci

On the use of brain decoded signals for online user adaptive gesture recognition systems

Activity and context recognition in pervasive and wearable computing ought to continuously adapt to changes typical of open-ended scenarios, such as changing users, sensor characteristics, user expectations, or user motor patterns due to learning or aging. System performance inherently relates to the users perception of the system behavior. Thus, the user should be guiding the adaptation process. This should be automatic, transparent, and unconscious. We capitalize on advances in electroencephalography (EEG) signal processing that allow for error related potentials (ErrP) recognition. ErrP are emitted when a human observes an unexpected behavior in a system. We propose and evaluate a hand gesture recognition system from wearable motion sensors that adapts online by taking advantage of ErrP. Thus the gesture recognition system becomes self-aware of its performance, and can self-improve through re-occurring detection of ErrP signals. Results show that our adaptation technique can improve the accuracy of a user independent gesture recognition system by 13.9% when ErrP recognition is perfect. When ErrP recognition errors are factored in, recognition accuracy increases by 4.9%. We characterize the boundary conditions of ErrP recognition guaranteeing beneficial adaptation. The adaptive algorithms are applicable to other forms of activity recognition, and can also use explicit user feedback rather than ErrP.

Motor Recovery After Stroke by Means of BCI-Guided Functional Electrical Stimulation

Brain-Computer Interfaces (BCIs) provide a mean to access the damaged motor network of the brain after stroke, and could be used to drive and promote beneficial plasticity. Among the available therapeutic approaches, Functional Electrical Stimulation (FES) is often applied during rehabilitation to directly engage muscles of the affected side of the body, especially when the residual functionality is weak or absent. In this paper, we describe a BCI system for stroke rehabilitation that decodes the attempt to execute a sustained hand extension movement from non-invasive human EEG and activates FES of affected arm muscles, accordingly. The system allows the physical therapist to monitor current brain activity through an EEG-guided visualization. Preliminary results on 4 chronic stroke patients show consistency in the EEG features selected for further training. Three of the patients completed the testing, and they all show recovery of target muscle function. Our results support the idea that BCI can be used to promote beneficial plasticity even during chronic phase, and justify further testing on a larger population.

Adaptation of hybrid human-computer interaction systems using EEG error-related potentials

Performance improvement in both humans and artificial systems strongly relies in the ability of recognizing erroneous behavior or decisions. This paper, that builds upon previous studies on EEG error-related signals, presents a hybrid approach for human computer interaction that uses human gestures to send commands to a computer and exploits brain activity to provide implicit feedback about the recognition of such commands. Using a simple computer game as a case study, we show that EEG activity evoked by erroneous gesture recognition can be classified in single trials above random levels. Automatic artifact rejection techniques are used, taking into account that subjects are allowed to move during the experiment. Moreover, we present a simple adaptation mechanism that uses the EEG signal to label newly acquired samples and can be used to re-calibrate the gesture recognition system in a supervised manner. Offline analysis show that, although the achieved EEG decoding accuracy is far from being perfect, these signals convey sufficient information to significantly improve the overall system performance.

Combining discriminant and topographic information in BCI: Preliminary results on stroke patients

Non-Invasive Brain-Computer Interfaces (BCI) convey a great potential in the field of stroke rehabilitation, where the continuous monitoring of mental tasks execution could support the positive effects of standard therapies. In this paper we combine time-frequency analysis of EEG with the topographic analysis to identify and track task-related patterns of brain activity emerging during a single BCI session. 6 Stroke patients executed Motor Imagery of the affected and unaffected hands: EEG sites were ranked depending on their discriminant power (DP) at different time instants and the resulting discriminant periods were used as a prior to extract EEG Microstates. Results show that the combination of these two techniques can provide insights about specific motor-related processes happening at a fine grain temporal resolution. Such events, represented by EEG microstates, can be tracked and used both to quantify changes of underlying neural structures and to provide feedback to patients and therapists.

tDCS Modulates Motor Imagery-Related BCI Features

Transcranial Direct Current Stimulation (tDCS) induces selective modulation of cortical excitability. This technique, as well as Brain–Computer Interfaces (BCIs), has been proposed as a supporting tool for neurorehabilitation. Here we show evidence that tDCS in SCI patients and control subjects modulates spectral features related to motor-imagery, yielding consistent discrimination. This suggests that tDCS can have beneficial effects for BCI-assisted neurorehabilitation.

Brain-actuated functional electrical stimulation elicits lasting arm motor recovery after stroke

Brain-computer interfaces (BCI) are used in stroke rehabilitation to translate brain signals into intended movements of the paralyzed limb. However, the efficacy and mechanisms of BCI-based therapies remain unclear. Here we show that BCI coupled to functional electrical stimulation (FES) elicits significant, clinically relevant, and lasting motor recovery in chronic stroke survivors more effectively than sham FES. Such recovery is associated to quantitative signatures of functional neuroplasticity. BCI patients exhibit a significant functional recovery after the intervention, which remains 6–12 months after the end of therapy. Electroencephalography analysis pinpoints significant differences in favor of the BCI group, mainly consisting in an increase in functional connectivity between motor areas in the affected hemisphere. This increase is significantly correlated with functional improvement. Results illustrate how a BCI–FES therapy can drive significant functional recovery and purposeful plasticity thanks to contingent activation of body natural efferent and afferent pathways.Brain-computer interface (BCI) can improve motor skills on stroke patients. This study shows that BCI-controlled neuromuscular electrical stimulation therapy can cause cortical reorganization due to activation of efferent and afferent pathways, and this effect can be long lasting in a brain region specific manner.

Electrically Assisted Movement Therapy in Chronic Stroke Patients With Severe Upper Limb Paresis: A Pilot, Single-Blind, Randomized Crossover Study.

OBJECTIVE To evaluate the effects of electrically assisted movement therapy (EAMT) in which patients use functional electrical stimulation, modulated by a custom device controlled through the patients unaffected hand, to produce or assist task-specific upper limb movements, which enables them to engage in intensive goal-oriented training. DESIGN Randomized, crossover, assessor-blinded, 5-week trial with follow-up at 18 weeks. SETTING Rehabilitation university hospital. PARTICIPANTS Patients with chronic, severe stroke (N=11; mean age, 47.9y) more than 6 months poststroke (mean time since event, 46.3mo). INTERVENTIONS Both EAMT and the control intervention (dose-matched, goal-oriented standard care) consisted of 10 sessions of 90 minutes per day, 5 sessions per week, for 2 weeks. After the first 10 sessions, group allocation was crossed over, and patients received a 1-week therapy break before receiving the new treatment. MAIN OUTCOME MEASURES Fugl-Meyer Motor Assessment for the Upper Extremity, Wolf Motor Function Test, spasticity, and 28-item Motor Activity Log. RESULTS Forty-four individuals were recruited, of whom 11 were eligible and participated. Five patients received the experimental treatment before standard care, and 6 received standard care before the experimental treatment. EAMT produced higher improvements in the Fugl-Meyer scale than standard care (P<.05). Median improvements were 6.5 Fugl-Meyer points and 1 Fugl-Meyer point after the experimental treatment and standard care, respectively. The improvement was also significant in subjective reports of quality of movement and amount of use of the affected limb during activities of daily living (P<.05). CONCLUSIONS EAMT produces a clinically important impairment reduction in stroke patients with chronic, severe upper limb paresis.

BCI controlled neuromuscular electrical stimulation enables sustained motor recovery in chronic stroke victims

Introduction: Recently, it has been shown that brain-computer interfaces (BCI) can be used in stroke rehabilitation to decode motor attempts from brain signals and to trigger movements of the paralyzed limb [1]. Among other available practices in rehabilitation, neuromuscular electrical stimulation (NMES) is often used to directly engage muscles on the affected parts of the body during physical therapy. Nevertheless, the benefits of a combined approach, to directly link the brain intention with a muscular response, are not yet fully validated. In this abstract, we report first results of a BCI-NMES system for stroke rehabilitation.

Transferring BCI skills to successful application controls

The goal of our research is to enable various end-users to control applications by using a brain-computer interface (BCI). Since applications–like telepresence robots, wheelchairs or text entry systems–are quite demanding a good level of BCI control is needed. However, little is known on how much training is needed to achieve such a level. A second open issue is, if this can be done at rehabilitation clinics or user-centers, without BCI experts present? In this work we wanted to train BCI-naive end-users within 10 days to successfully control such applications and present results of 23 severely motor-disabled participants.

BCI-NMES therapy enhances effective connectivity in the damaged hemisphere in stroke patients

Introduction: In stroke rehabilitation, one of the key components for motor improvement is brain plasticity and, in particular, the reestablishment of cortical and subcortical networks [1] that can be studied with connectivity analysis. Despite recent advances in brain-computer interface (BCI)-driven stroke therapy [2], it is still unclear what are the underlying changes that lead to a clinical improvement.