Thanks Abhineet Pandey.

I believe one way to estimate the epsilon parameter is to calculate a KNN distance (for different K) for each data point to understand how your data is distributed. You can visualize the results by plotting the data based on distance ranges, for example:

K = 1
(distance range) — total points found
(0.00–10.0) — 200 points
(10.0–20.0) — 100 points
(20.0–30.0) — 50 points
(30.0–40.0) — 20 points
(40.0–50.0) — 5 points

Based on it you may have at least an insight on which eps to choose.

I have also found some articles which may be useful:
- http://ijiset.com/v1s4/IJISET_V1_I4_48.pdf
- https://iopscience.iop.org/article/10.1088/1755-1315/31/1/012012/pdf