NeuroHAGWO-Net Model Performance Metrics for Mental Health Detection

A study by Sunil Kumar Sharma proposes NeuroHAGWO-Net, an AI framework for mental health detection using EEG and behavioral text data. The dataset, last updated in April 2026, contains performance metrics from model validation on behavioral data, achieving an accuracy of 0.9945 and other detailed scores. The data is stored in an XLS file with a size of 5.5 KB.

Use Cases

• Benchmarking AI model performance for mental health classification based on reported accuracy and F1-score metrics.
• Analyzing the efficacy of hybrid optimization techniques like HAGWO based on the feature selection method described.
• Comparing multimodal (EEG and text) versus unimodal (behavioral data) detection approaches based on the study's framework.
• Evaluating clinical support tool potential based on the reported sensitivity and specificity for mental health screening.

Strengths

• Performance metrics are highly detailed, including accuracy (0.9945), precision (0.9874), sensitivity (0.9935), and 6 other specific scores.
• Dataset has a clear, permissive license (CC-BY-4.0) for reuse.
• The underlying model methodology is described in detail, including data modalities and AI architectures.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small (5.5 KB), indicating limited scope, likely containing only summary performance statistics.

Provenance

Source

Sunil Kumar Sharma via figshare.

Collection Method

Performance results from validating the proposed NeuroHAGWO-Net AI model on behavioral data.

Time Range

The study and data were last updated in April 2026.

Freshness

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

Geography

Global challenge scope is mentioned, but specific data geography is unknown.