I found numerous internal evaluation applicable to DBSCAN. Some researchers said that there is no available internal evaluation for DBSCAN, while some papers utilized the indexes such as DBI, DUNN, or S_Dbw.
Can I use the classical indexes for the internal evaluation of DBSCAN? Or, are there any limitations or challenges to apply those metrics?
Please refer to the paper (link below). It compares different internal measures under various scenarios. For example, it shows that Calinski-Harabasz and Dunn's Indices did not perform well for noisy data. Overall, S_Dbw was shown to be reliable under all scenarios.
https://ieeexplore.ieee.org/abstract/document/5694060
In addition to the well-written paper that Sakib Shahriar suggested you could also have a look at that one:
Conference Paper Density-Based Clustering Validation
- Badges
- Science topic