NeuroHAGWO-Net: Multimodal EEG and Text Data for Mental Health Detection

A multimodal dataset integrating electroencephalogram (EEG) signals and behavioral textual data for automated mental health status detection. The dataset was created by Sunil Kumar Sharma and last updated on April 13, 2026. It is stored in an XLS file with a size of 5.5 KB.

Use Cases

• Training AI models for mental health detection based on integrated EEG and behavioral text data.
• Benchmarking feature selection algorithms using the described Hybrid Ant-Grey Wolf Optimization (HAGWO) approach.
• Evaluating hybrid deep learning architectures like BiLSTM-CNN for temporal and spatial pattern recognition in EEG data.
• Testing multimodal fusion techniques for combining signal and text embeddings from BERT models.

Strengths

• Model validation reported high accuracy (0.9945) and precision (0.9874) on behavioral data.
• Dataset integrates two distinct modalities: EEG signals and behavioral text, enabling multimodal analysis.
• Data is shared under a permissive CC-BY-4.0 license.

Limitations

• Row count and column-level documentation are unknown, limiting suitability assessment.
• The dataset is very small (5.5 KB), suggesting limited scope or a sample.
• Description metadata is limited; actual data quality and structure require manual inspection after download.

Provenance

Source

figshare, author Sunil Kumar Sharma.

Collection Method

Data likely gathered for research proposing the NeuroHAGWO-Net AI framework, involving EEG and behavioral text processing.

Time Range

null

Freshness

Last updated 2026-04-13 17:44:02; freshness should be verified.

Geography

null