Mechanical exfoliation of graphene and its identification by optical inspection is one of the mile- stones in condensed matter physics that sparked the field of 2D materials. Finding regions of interest from the entire sample space and identification of layer number is a routine task potentially amenable to automatization. We propose supervised pixel-wise classification methods showing a high perfor- mance even with a small number of training image datasets that require short computational time without GPU. We introduce four different tree-based machine learning algorithms – decision tree, random forest, extreme gradient boost, and light gradient boosting machine. We train them with five optical microscopy images of graphene, and evaluate their performances with multiple metrics and indices. We also discuss combinatorial machine learning models between the three single classi- fiers and assess their performances in identification and reliability. The code developed in this paper is open to the public and will be released at github.com/gjung-group/Graphene_segmentation.
Mechanical exfoliation of graphene and its identification by optical inspection is one of the milestones in condensed matter physics that sparked the field of 2D materials. Finding regions of interest from the entire sample space and identification of layer number is a routine task potentially amenable to automatization. We propose supervised pixel-wise classification methods showing a high performance even with a small number of training image datasets that require short computational time without GPU. We introduce four different tree-based machine learning algorithms -decision tree, random forest, extreme gradient boost, and light gradient boosting machine. We train them with five optical microscopy images of graphene, and evaluate their performances with multiple metrics and indices. We also discuss combinatorial machine learning models between the three single classifiers and assess their performances in identification and reliability. The code developed in this paper is open to the public and will be released at github.com/gjung-group/Graphene_segmentation.
Abstract-This paper develops and studies a traffic-aware inter-domain routing (TIDR) protocol, which drastically improves the stability of the BGP-based inter-domain routing system. TIDR is designed based on two important Internet properties-the Internet access non-uniformity and the prevalence of transient failures. In TIDR, a network prefix is classified at an AS as either significant or insignificant from the viewpoint of a neighboring AS, depending on the amount of traffic exchanged between the prefix and the neighbor (including transit traffic). While BGP updates of significant prefixes are propagated with a higher priority, the propagation of updates of insignificant prefixes is aggressively slowed down. In particular, TIDR tries to localize the effect of transient failures on insignificant prefixes instead of propagating it onto the whole Internet. Importantly, TIDR will not create traffic black-holes due to the localization of transient failures. In this paper we present the design of TIDR and perform simulation experiments to study the performance of TIDR. Our simulation results show that TIDR can greatly improve the stability of BGP and also outperforms other existing schemes including Ghost Flushing and EPIC.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.