An EEG pipeline combining transformer-based denoising with graph Ricci flow and a GCN reports 0.97 accuracy for digit versus non-digit thought classification, but without baselines or code.
MindBigData 2022 A Large Dataset of Brain Signals
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Understanding our brain is one of the most daunting tasks, one we cannot expect to complete without the use of technology. MindBigData aims to provide a comprehensive and updated dataset of brain signals related to a diverse set of human activities so it can inspire the use of machine learning algorithms as a benchmark of 'decoding' performance from raw brain activities into its corresponding (labels) mental (or physical) tasks. Using commercial of the self, EEG devices or custom ones built by us to explore the limits of the technology. We describe the data collection procedures for each of the sub datasets and with every headset used to capture them. Also, we report possible applications in the field of Brain Computer Interfaces or BCI that could impact the life of billions, in almost every sector like healthcare game changing use cases, industry or entertainment to name a few, at the end why not directly using our brains to 'disintermediate' senses, as the final HCI (Human-Computer Interaction) device? simply what we call the journey from Type to Touch to Talk to Think.
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Geometric Machine Learning on EEG Signals
An EEG pipeline combining transformer-based denoising with graph Ricci flow and a GCN reports 0.97 accuracy for digit versus non-digit thought classification, but without baselines or code.