Automatic classification of single-molecule charge transport data with an unsupervised machine-learning algorithm

Single-molecule electrical characterization reveals the events occurring at the nanoscale, which provides guidelines for molecular materials and devices. However, data analysis to extract valuable information from the nanoscale measurement data remained as a major challenge. Herein, an unsupervised...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Physical chemistry chemical physics : PCCP Jg. 22; H. 3; S. 1674
Hauptverfasser:	Huang, Feifei, Li, Ruihao, Wang, Gan, Zheng, Jueting, Tang, Yongxiang, Liu, Junyang, Yang, Yang, Yao, Yuan, Shi, Jia, Hong, Wenjing
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	England 22.01.2020
ISSN:	1463-9084, 1463-9084
Online-Zugang:	Weitere Angaben
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Single-molecule electrical characterization reveals the events occurring at the nanoscale, which provides guidelines for molecular materials and devices. However, data analysis to extract valuable information from the nanoscale measurement data remained as a major challenge. Herein, an unsupervised deep leaning method, a deep auto-encoder K-means (DAK) algorithm, is developed to distinguish different events from single-molecule charge transport measurements. As validated by three single-molecule junction systems, the method applies to the recognition for multiple compounds with various events and offers an effective data analysis method to track reaction kinetics at the single-molecule scale. This work opens the possibility of using deep unsupervised approaches to studying the physical and chemical processes at the single-molecule level.
Bibliographie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	1463-9084 1463-9084
DOI:	10.1039/c9cp04496e