Semi-supervised deep learning for molecular clump verification

Open Access

Table 6

Number of molecular clumps detected by the FellWalker and Fell+SS-3D-Clump algorithms, as well as a comparison with manual verification results.

Algorithm	FellWalker		Fell+SS-3D-clump
Detected clump number	3395		2655
Manual verification	True	False	True	False

Number	2832	583	2648	7
Precision	0.834		0.997
False detection	0.166		0.003

Notes. The SS-3D-Clump model effectively improves the detection accuracy of FellWalker and reduces the false detection rate.

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.