English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Raman spectroscopy is a powerful analytical tool with applications rangingfrom quality control to cutting edge biomedical research. One particular areawhich has seen tremendous advances in the past decade is the development ofpowerful handheld Raman spectrometers. They have been adopted widely by firstresponders and law enforcement agencies for the field analysis of unknownsubstances. Field detection and identification of unknown substances with Ramanspectroscopy rely heavily on the spectral matching capability of the devices onhand. Conventional spectral matching algorithms (such as correlation, dotproduct, etc.) have been used in identifying unknown Raman spectrum bycomparing the unknown to a large reference database. This is typically achievedthrough brute-force summation of pixel-by-pixel differences between thereference and the unknown spectrum. Conventional algorithms have noticeabledrawbacks. For example, they tend to work well with identifying pure compoundsbut less so for mixture compounds. For instance, limited reference spectrainaccessible databases with a large number of classes relative to the number ofsamples have been a setback for the widespread usage of Raman spectroscopy forfield analysis applications. State-of-the-art deep learning methods(specifically convolutional neural networks CNNs), as an alternative approach,presents a number of advantages over conventional spectral comparison algorism.With optimization, they are ideal to be deployed in handheld spectrometers forfield detection of unknown substances. In this study, we present acomprehensive survey in the use of one-dimensional CNNs for Raman spectrumidentification. Specifically, we highlight the use of this powerful deeplearning technique for handheld Raman spectrometers taking into considerationthe potential limit in power consumption and computation ability of handheldsystems.

A Review of 1D Convolutional Neural Networks toward Unknown Substance Identification in Portable Raman Spectrometer