Objective: A user-friendly steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) prefers no calibration for its target recognition algorithm, however, the existing calibration-free schemes perform still far behind their calibration-based counterparts. To tackle this issue, learning online from the subject's unlabeled data is investigated as a potential approach to boost the performance of the calibration-free SSVEP-based BCIs.
Methods: An online adaptation scheme is developed to tune the spatial filters using the online unlabeled data from previous trials, and then developing the online adaptive canonical correlation analysis (OACCA) method.
Results: A simulation study on two public SSVEP datasets (Dataset I and II) with a total of 105 subjects demonstrated that the proposed online adaptation scheme can boost the CCA's averaged information transfer rate (ITR) from 94.60 to 158.87 bits/min in Dataset I and from 85.80 to 123.91 bits/min in Dataset II. Furthermore, in our online experiment it boosted the CCA's ITR from 55.81 bits/min to 95.73 bits/min. More importantly, this online adaptation scheme can be easily combined with any spatial filtering-based algorithms to achieve online learning.
Conclusion: By online adaptation, the proposed OACCA performed much better than the calibration-free CCA, and comparable to the calibration-based algorithms.
Significance: This work provides a general way for the SSVEP-based BCIs to learn online from unlabeled data and thus avoid calibration.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TBME.2021.3133594 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Mindfulness Training vs Recovery Support for Opioid Use, Craving, and Anxiety During Buprenorphine Treatment: A Randomized Clinical Trial.
JAMA Netw Open
January 2025
Department of Psychiatry, Harvard Medical School, Boston, Massachusetts.
Importance: During buprenorphine treatment for opioid use disorder (OUD), risk factors for opioid relapse or treatment dropout include comorbid substance use disorder, anxiety, or residual opioid craving. There is a need for a well-powered trial to evaluate virtually delivered groups, including both mindfulness and evidence-based approaches, to address these comorbidities during buprenorphine treatment.
Objective: To compare the effects of the Mindful Recovery Opioid Use Disorder Care Continuum (M-ROCC) vs active control among adults receiving buprenorphine for OUD.
Adapting to the emotional complexity of palliative care communication: Palliative care clinicians' experiences.
Palliat Support Care
January 2025
Institute of Social and Preventive Medicine (ISPM), University of Bern, Bern, Switzerland.
Objectives: Communication is essential to medical care and is key in improving patient outcomes. We aimed to understand clinicians' emotions when communicating with patients in palliative care (PC) and the evolution of their communication skills.
Methods: Between October and November 2021, 231 Swiss PC clinicians participated in an online cross-sectional survey (65% nurses, 35% physicians).
Clinical Experiences Using Family Based Treatment for Eating Disorders.
Int J Eat Disord
January 2025
Department of Psychiatry, University of California, san Francisco, San Francisco, California, USA.
Objective: Despite the availability of several evidence-based treatments for eating disorders (EDs), including Family-Based Treatment (FBT), therapist drift from evidence-based treatments in real-life clinical settings is common. This study explores clinicians' use of FBT techniques and identifies clinician-reported barriers to their use in real-world settings.
Methods: Clinicians (N = 54) who self-identified as using FBT for EDs were recruited through social media, professional listservs, and mental health provider databases.
A multigrained preference analysis method for product iterative design incorporating AI-generated review detection.
Sci Rep
January 2025
Key Laboratory of Ministry of Industrial Design and Ergonomics, Northwestern Polytechnical University, Xi'an, 710072, China.
Online reviews significantly influence consumer purchasing decisions and serve as a vital reference for product improvement. With the surge of generative artificial intelligence (AI) technologies such as ChatGPT, some merchants might exploit them to fabricate deceptive positive reviews, and competitors may also fabricate negative reviews to influence the opinions of consumers and designers. Attention must be paid to the trustworthiness of online reviews.
View Article and Find Full Text PDFYarning about vaccinations: Empowering individuals to have supportive conversations with Aboriginal peoples about vaccinations, using a community-engaged approach.
Aust N Z J Public Health
December 2024
Population Health, Hunter New England Local Health District, New South Wales, Australia; Euahlayi nation.
Objective: This study assessed the effectiveness of Aboriginal-led vaccine workshops to enhance knowledge, confidence and supportive conversations regarding scheduled and recommended vaccinations for Aboriginal and Torres Strait Islander people in Hunter New England, New South Wales, Australia.
Methods: We adapted and indigenised an existing vaccine conversation program. Aboriginal and Torres Strait Islander and non-Indigenous people were recruited to workshops delivered either online or face to face.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!