China
Africa
Explore chapters and articles related to this topic
Transfer Learning for BCIs
Published in Chang S. Nam, Anton Nijholt, Fabien Lotte, Brain–Computer Interfaces Handbook, 2018
Vinay Jayaram, Karl-Heinz Fiebig, Jan Peters, Moritz Grosse-Wentrup
The second benefit to this hierarchical approach is that it allows for model adaptation on-the-fly. As new data come in, each point can be used to adapt the classifier to the current time or subject. What this means in practice is that one can start with a middling classifier (the prior mean) and then update it successively such that it quickly becomes a well-optimized, session-specific classifier. In fact, empirical evaluation of this approach with a sensorimotor rhythm paradigm shows very promising results. All MTL approaches started out with a calibration-free performance above chance and increase accuracy with more and more session-specific data. Figure 22.3 indicates that especially with few samples to train on, MTL clearly outperforms the standard classification method by making effective use of the shared prior distribution trained from other subjects.
Efficacy of Neurofeedback for Pain Management
Published in Mark V. Boswell, B. Eliot Cole, Weiner's Pain Management, 2005
Siegfried Othmer, Susan Othmer
Three main strategies of remediation have emerged in the field. The first targets known physiological mechanisms such as the alpha and sensorimotor rhythm. This was historically the first approach and is referred to as mechanisms-based training. It still dominates the field, and benefits from the most robust literature support. The second strategy attempts to normalize steady-state EEG deviations as discerned by comparison with normative databases. This is referred to as QEEG-based training. As it is very strongly data-driven, this approach has flourished particularly in the medical applications such as traumatic brain injury, stroke, dementia, and seizure disorder. Finally, an approach based on brain function as a nonlinear dynamical system has emerged, in which the targets are dynamically established through a multivariate assessment of the quality of self-regulation manifested in the EEG at any moment. This is referred to as NLD-based training. There has now been considerable cross-fertilization between these disparate approaches, and the distinctions among them will be obscured in what follows. We refer the reader to other resources for more detailed discussion. The entire issue of Clinical Encephalography, 31(1), January 2000, is devoted to neurofeedback and serves as a comprehensive reference (see also Othmer, 2002a, b).
Wheels of Motion: Oscillatory Potentials in the Motor Cortex
Published in Alexa Riehle, Eilon Vaadia, Motor Cortex in Voluntary Movements, 2004
The l2-l5 c/s range spans the transition between mu and beta rhythms, and most often is ignored, being considered neither one nor the other but a fuzzy mix of both. Some studies, however, indicate otherwise; that it is, in fact, a functionally important rhythm in its own right. It has even been called the "sensorimotor rhythm."56 Roth et al. related this oscillatory frequency in sensorimotor cortex strictly to the development of inhibitory behavior, e.g., when a cat suppressed bar-pressing, or expressly delayed a response.56 Similarly, in cats operantly trained to enhance l2-l4 c/s sensorimotor cortical activity, the occurence of this rhythm was associated with
Action observation training and brain-computer interface controlled functional electrical stimulation enhance upper extremity performance and cortical activation in patients with stroke: a randomized controlled trial
Published in Physiotherapy Theory and Practice, 2022
Su-Hyun Lee, Seong Sik Kim, Byoung-Hee Lee
The attention threshold to initiate BCI-FES for each patient was determined before each training session. To obtain the threshold value, the patients were asked to watch wrist extension DVD and to imagine performing the task. While concentrating for imagination, the EEG was measured and the value was calculated using the (SMR+mid beta)/theta formula. If patients correctly imagined the movement, their attention threshold level went up. The attention threshold used the average of the value obtained by repeating 10 times the task. In a state of concentration, the theta rhythm decreases, while the sensory motor rhythm (SMR) and mid-beta rhythms increase (de Zambotti et al., 2012). Increased SMR implies unfocused attention, whereas mid-beta rhythms connote focused attention and cautiousness. SMR was in the range of 12–15 Hz (unfocused attention) and mid-beta rhythm was in the range of 15–18 Hz (focused attention) (Mohammadi, Malmir, Khaleghi, and Aminiorani, 2015). SMR was observed when a subject focused on solving problems without being nervous or stressed.
Non-pharmacological treatments for pediatric refractory epilepsies
Published in Expert Review of Neurotherapeutics, 2022
Eleonora Rotondo, Antonella Riva, Alessandro Graziosi, Noemi Pellegrino, Caterina Di Battista, Vincenzo Di Stefano, Pasquale Striano
Neurofeedback, also known as EEG biofeedback, is a type of biofeedback therapy that aims to train individuals to regulate their brainwave patterns by providing them with real-time EEG data. Sterman and colleagues [96] conducted the first official research in this area focusing on the sensory-motor rhythm (SMR), an EEG rhythm recorded over the sensory-motor cortex with a frequency in the range of 12–20 Hz. Using the neurofeedback technique, patients learned how to change intentionally this component of the EEG to reduce the amount and frequency of seizure activity. Although acting over the SMR remains the most common neurofeedback training for epilepsy, a different method is based on the Slow Cortical Potentials (SCPs) which has recently gained popularity. The SCPs reflect cortical excitability and some studies have demonstrated that training patients to control the amplitude of cortical potential changes can lead to a decrease in the rate of seizures [73,91,95]. Overall, neurofeedback is considered a secure treatment; however, mild side effects such as fatigue, headache, and tiredness have also been described.
The Ability of Forensic Psychiatric Patients with Substance Use Disorder to Learn Neurofeedback
Published in International Journal of Forensic Mental Health, 2019
Sandra Fielenbach, Franc C.L. Donkers, Marinus Spreen, Stefan Bogaerts
For forensic psychiatric patients, the combination of SUD and comorbid major mental disorders also has a negative impact on treatment (Van Nieuwenhuizen et al., 2011), as high levels of impulsivity increase chances for relapse in substance abuse and treatment drop-out (Van der Veeken, Lucieer, & Bogaerts, 2016). Most likely, chronic substance abuse results in neurocognitive and neurophysiological changes, causing a structural state of reduced inhibitory control and high levels of impulsivity (Jentsch, & Taylor, 1999; Lyvers, 2000). Neurofeedback protocols aimed at enhancing the sensorimotor rhythm (SMR; 12–15 Hz) and reducing slower waves such as theta (3.5–7.5 Hz) have shown promising results in reducing levels of impulsivity in ADHD (Fuchs, Birbaumer, Lutzenberger, Gruzelier, & Kaiser, 2003). A reduction in levels of impulsivity through neurofeedback training could possibly also have a positive effect on SUD, as both impulsivity and SUD are characterized by a lack of inhibitory control (Tomko, Bountress, & Gray, 2016).