50 results for "relevance vector machines" · page 1 of 5 · ranked by relevance
…Data were analyzed using Riemannian manifold methods and relevance vector machines for…
…Riemannian manifold methods and relevance vector machines for brain-computer interface applications…
…manifold-based feature extraction and relevance vector machine classification, achieving approximately 49…
…Using Support Vector Machines (SVMs) with L1 regularization, we achieved cross-context…
…analyzed using Riemannian manifold and relevance vector machine approaches for brain-computer…
This dataset comprises EEG recordings from 24 participants across two related studies (2019 and 2021) investigating phoneme discrimination during concurrent transcranial magnetic stimulation (TMS) of motor and speech-related cortical regions. Participants listened to speech sounds—including single phonemes, phoneme pairs, and phoneme triplets (real and pseudowords)—and responded via button press, enabling exploration of articulation and coarticulation effects on neural speech decoding. The dataset supports research into cortical mechanisms underlying speech perception and motor cortex involvement in phoneme processing.
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 10,000+ clips from multiple subjects with preserved clinical metadata including seizure onset zone (SOZ) flags, electrode anatomy, and reviewer annotations. This resource supports the development and validation of automated signal processing algorithms for clinical neurophysiology applications.
This dataset comprises magnetoencephalography (MEG) recordings of auditory single word recognition in human subjects. Participants listened to isolated words while neural activity was recorded, providing insights into the temporal dynamics of auditory word comprehension. The dataset is described in Gaston et al. (2022) 'Auditory word comprehension is less incremental in isolated words' published in Neurobiology of Language. The dataset includes raw MEG data, stimulus information, and associated metadata organized according to the Brain Imaging Data Structure (BIDS) standard. This is a NEMAR-converted version of OpenNeuro dataset ds004276.
This dataset comprises high-density and sparse functional near-infrared spectroscopy (fNIRS) measurements acquired during a Word-Color Stroop task. The study investigates whether high-density multi-distance fNIRS configurations enhance detection of brain activity compared to conventional sparse probe arrangements. Raw neuroimaging data from multiple participants are provided in BIDS format to support reproducible analysis of cognitive control mechanisms.
Imported from OpenNeuro ds004368