An Efficient Deep Learning Framework for Revealing the Evolution of Characterization Methods in Nanoscience

An Efficient Deep Learning Framework for Revealing the Evolution of Characterization Methods in Nanoscience

Highlights A framework combining the citation analysis with topic modeling is designed to construct the knowledge graph of a research field. An extensible tokenizer is designed to improve the universality of the framework, and the performance of topic recognition is superior to that of the tradition...

Full description

Saved in:
Bibliographic Details
Main Authors: Hui-Cong Duan, Long-Xing Lin, Ji-Chun Wang, Tong-Ruo Diao, Sheng-Jie Qiu, Bi-Jun Geng, Jia Shi, Shu Hu, Yang Yang
Format: Article
Language:English
Published: SpringerOpen 2025-06-01
Series:Nano-Micro Letters
Subjects:
Nanostructure
Deep learning
Data-driven
Raman
Nanoscience
Online Access:https://doi.org/10.1007/s40820-025-01807-z
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Highlights A framework combining the citation analysis with topic modeling is designed to construct the knowledge graph of a research field. An extensible tokenizer is designed to improve the universality of the framework, and the performance of topic recognition is superior to that of the traditional method. The detailed evolutionary paths of Raman spectroscopy technology are demonstrated, and the significant publications in the Raman spectroscopy are identified.
ISSN:2311-6706
2150-5551

Similar Items