<p>FOLD AND BS WISE TIME COMPLEXITY REPORT.</p>

Ashik Mostafa Alvi's research dataset, last updated April 20, 2026, contains performance metrics for a proposed deep learning framework to diagnose Alzheimer's disease (AD), mild cognitive impairment (MCI), and healthy subjects using electroencephalography (EEG) data. The dataset, stored in an XLS file of 9.5 KB, reports cross-validated classification accuracy, sensitivity, and specificity results for the Cognitive Decline Recognition Network (CDR-Net) architecture.

Use Cases

• Benchmarking multiclass classification models for EEG-based diagnosis based on reported accuracy, sensitivity, and specificity metrics.
• Analyzing model stability and overfitting concerns based on the use of 10-fold and leave-one-out cross-validations mentioned in the description.
• Evaluating the performance of deep learning architectures like CDR-Net for cognitive decline recognition against traditional ML classifiers.

Strengths

• Reported high multiclass performance metrics of 99.25% accuracy, 99.13% sensitivity, and 99.32% specificity.
• Model validation addressed stability and overfitting using 10-fold and leave-one-out cross-validations.
• Dataset is openly shared under a CC-BY-4.0 license.

Limitations

• Row count and specific column-level documentation are unknown, limiting suitability assessment.
• The dataset is very small at 9.5 KB, suggesting it contains summary results rather than raw EEG data or features.
• Freshness should be verified as the last update date is in the future (2026).

Provenance

Source

Ashik Mostafa Alvi via figshare

Collection Method

Proposed framework involving EEG data acquisition, preprocessing, feature extraction, and classification using the CDR-Net architecture.

Time Range

null

Freshness

Last updated 2026-04-20 17:58:11; freshness should be verified.

Geography

null