Categorized Free Recall with Closed-Loop Stimulation at Encoding (Encoding Classifier)
…feature matrix, and the label vector is the recalled status of the…
- Participants
- 9
- Size
- 12.2 GB
- Version
- v1.0.0
- Updated
- Aug 19, 2026
50 results for "relevance vector machines" · page 4 of 5 · ranked by relevance
…feature matrix, and the label vector is the recalled status of the…
This dataset contains 128-channel EEG recordings from 20 observers (19 included in final analysis) viewing object images at 3.33 Hz to investigate how contextual associations, perceptual attributes, and conceptual properties of objects are represented in neural activity. One participant was excluded due to a technical error in EEG recording. Time-resolved neural decoding was applied to disentangle these distinct representational dimensions from the EEG signals.
…eeg signal in C2) → .nf (vector of NF scores -4 per s…
A multicenter intracranial electroencephalography (iEEG) dataset comprising segmented 3-second single-channel clips from epilepsy patients, annotated for graphoelement classification and artifact detection. The dataset includes clinical metadata such as seizure onset zone (SOZ) flags, electrode anatomy, and reviewer annotations, making it suitable for developing and validating automated signal classification algorithms in clinical neurophysiology.
This dataset comprises intracranial EEG (iEEG) recordings from 12 epilepsy surgery patients enrolled in the RESPect (Registry for Epilepsy Surgery Patients) study at the University Medical Center of Utrecht. The collection includes intraoperative electrocorticography (ECoG) recordings from six patients and long-term iEEG monitoring data from six patients (three with ECoG and three with stereo-encephalography). All data are organized according to the Brain Imaging Data Structure (BIDS) specification to facilitate standardized access and analysis of clinical neurophysiology data. This dataset is derived from the larger RESPect iEEG collection and has been curated for BIDS compliance.
This dataset comprises event-related potential (ERP) recordings from 13 healthy subjects performing a visual matrix speller task using a calibrationless brain-computer interface approach. The study introduces learning from label proportions (LLP), an unsupervised classification method that exploits known target/non-target stimulus ratios to enable online BCI operation without prior calibration. Subjects performed copy-spelling tasks using a 6×7 character grid across three sessions, achieving 84.5% character accuracy without labeled training data.
This dataset comprises multimodal physiological recordings from 86 participants during resting state and a digit span working memory task. It includes 64-channel EEG, electrocardiography, photoplethysmography, pupillometry, and behavioral performance data. The dataset enables investigation of neural and peripheral physiological correlates of cognitive load, working memory capacity, and cognitive overload detection across fine temporal scales.
EEG dataset from Experiment 2 of Grootswagers et al. (2021) investigating neural dynamics of task-relevant information prioritization. Participants performed a rapid serial visual presentation (RSVP) task with small objects embedded in large letters while EEG was recorded. This dataset examines how the brain prioritizes and processes behaviorally relevant stimuli in visual attention tasks.
Imported from OpenNeuro ds005262