{"title":"基于机器学习方法的拉曼光谱峰值感知自适应去噪技术","authors":"Juhyung Lee, Woonghee Lee","doi":"10.1002/jrs.6648","DOIUrl":null,"url":null,"abstract":"<p>Raman spectroscopy can be effectively used for detection and analysis of chemical agents that are serious threats in modern warfare, but the detection and analysis performance is prone to deterioration due to noise. The existing denoising technique has limitations that there is no criterion for selecting the window length and that the filtering distorts the peaks, key features for Raman spectral data analysis. To overcome such limitations, in this paper, we propose the peak-aware adaptive denoising for Raman spectroscopy based on machine learning approach. The proposed technique utilizes the information of detected peaks to eliminate noise effectively using different window values optimal for each region in the Raman spectrum while preserving the shape of peaks. We conducted the various analyses and experiments, and the proposed technique showed a 28% lower Euclidean distance and a 48% lower Fréchet inception distance compared to the existing technique, meaning the proposed technique outperformed the existing one.</p>","PeriodicalId":16926,"journal":{"name":"Journal of Raman Spectroscopy","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Peak-aware adaptive denoising for Raman spectroscopy based on machine learning approach\",\"authors\":\"Juhyung Lee, Woonghee Lee\",\"doi\":\"10.1002/jrs.6648\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Raman spectroscopy can be effectively used for detection and analysis of chemical agents that are serious threats in modern warfare, but the detection and analysis performance is prone to deterioration due to noise. The existing denoising technique has limitations that there is no criterion for selecting the window length and that the filtering distorts the peaks, key features for Raman spectral data analysis. To overcome such limitations, in this paper, we propose the peak-aware adaptive denoising for Raman spectroscopy based on machine learning approach. The proposed technique utilizes the information of detected peaks to eliminate noise effectively using different window values optimal for each region in the Raman spectrum while preserving the shape of peaks. We conducted the various analyses and experiments, and the proposed technique showed a 28% lower Euclidean distance and a 48% lower Fréchet inception distance compared to the existing technique, meaning the proposed technique outperformed the existing one.</p>\",\"PeriodicalId\":16926,\"journal\":{\"name\":\"Journal of Raman Spectroscopy\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2024-01-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Raman Spectroscopy\",\"FirstCategoryId\":\"92\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/jrs.6648\",\"RegionNum\":3,\"RegionCategory\":\"化学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"SPECTROSCOPY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Raman Spectroscopy","FirstCategoryId":"92","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/jrs.6648","RegionNum":3,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"SPECTROSCOPY","Score":null,"Total":0}
Peak-aware adaptive denoising for Raman spectroscopy based on machine learning approach
Raman spectroscopy can be effectively used for detection and analysis of chemical agents that are serious threats in modern warfare, but the detection and analysis performance is prone to deterioration due to noise. The existing denoising technique has limitations that there is no criterion for selecting the window length and that the filtering distorts the peaks, key features for Raman spectral data analysis. To overcome such limitations, in this paper, we propose the peak-aware adaptive denoising for Raman spectroscopy based on machine learning approach. The proposed technique utilizes the information of detected peaks to eliminate noise effectively using different window values optimal for each region in the Raman spectrum while preserving the shape of peaks. We conducted the various analyses and experiments, and the proposed technique showed a 28% lower Euclidean distance and a 48% lower Fréchet inception distance compared to the existing technique, meaning the proposed technique outperformed the existing one.
期刊介绍:
The Journal of Raman Spectroscopy is an international journal dedicated to the publication of original research at the cutting edge of all areas of science and technology related to Raman spectroscopy. The journal seeks to be the central forum for documenting the evolution of the broadly-defined field of Raman spectroscopy that includes an increasing number of rapidly developing techniques and an ever-widening array of interdisciplinary applications.
Such topics include time-resolved, coherent and non-linear Raman spectroscopies, nanostructure-based surface-enhanced and tip-enhanced Raman spectroscopies of molecules, resonance Raman to investigate the structure-function relationships and dynamics of biological molecules, linear and nonlinear Raman imaging and microscopy, biomedical applications of Raman, theoretical formalism and advances in quantum computational methodology of all forms of Raman scattering, Raman spectroscopy in archaeology and art, advances in remote Raman sensing and industrial applications, and Raman optical activity of all classes of chiral molecules.