Teaching artificial intelligence to read electropherograms.

摘要: Electropherograms are produced in great numbers forensic DNA laboratories as part of everyday criminal casework. Before the results these electropherograms can be used they must scrutinised by analysts to determine what identified data tells us about underlying sequences and is purely an artefact profiling process. A technique that lends itself well such a task classification face vast amounts use artificial neural networks. These networks, inspired workings human brain, have been increasingly successful analysing large datasets, performing medical diagnoses, identifying handwriting, playing games, or recognising images. In this work we demonstrate network which train 'read' show it generalise unseen profiles.