Skip to main content
zenodoopen

Confusion Matrices for Person Identification using E-Nose

<p>The Validation results folder contains results from the classification problem. This zip file contains confusion matrices for each participant with each configuration and the cumulative classifier for each configuration. Each confusion matrix shows the detailed classification results of a test set containing 18 positive and 486 negative samples.</p> <p>The CrossValidation results folder contains results from cross-validation. This zip file only contains cumulative confusion matrices for each configuration. The confusion matrices here show the test set which should contain approximately 54 positive samples and 1456 negative samples.</p> <p>The filename for each confusion matrix shows what they represent, and are in the form of 'CM_&lt;Classifier name&gt;_P&lt;Participant No./Cumulative&gt;_BL&lt;Breath Length&gt;_REF &lt;Reference Value used&gt;'</p> <p>Reference value refers to using either relative, absolute, or both signals together.</p>

ShareScore

32/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
4
Harmonization
4
Access
16
Reuse readiness
8
Engagement
0