Non-destructive analysis of Ganoderma lucidum composition using hyperspectral imaging and machine learning.

IF 4.2 3区化学 Q2 CHEMISTRY, MULTIDISCIPLINARY Frontiers in Chemistry Pub Date : 2025-02-26 eCollection Date: 2025-01-01 DOI:10.3389/fchem.2025.1534216

Jing Ran, Hui Xu, Zhilong Wang, Wei Zhang, Xueyuan Bai

{"title":"Non-destructive analysis of Ganoderma lucidum composition using hyperspectral imaging and machine learning.","authors":"Jing Ran, Hui Xu, Zhilong Wang, Wei Zhang, Xueyuan Bai","doi":"10.3389/fchem.2025.1534216","DOIUrl":null,"url":null,"abstract":"Background: Ganoderma lucidum is a widely used medicinal fungus whose quality is influenced by various factors, making traditional chemical detection methods complex and economically challenging. This study addresses the need for fast, noninvasive testing methods by combining hyperspectral imaging with machine learning to predict polysaccharide and ergosterol levels in Ganoderma lucidum cap and powder.Methods: Hyperspectral images in the visible near-infrared (385-1009 nm) and short-wave infrared (899-1695 nm) ranges were collected, with ergosterol measured by high-performance liquid chromatography and polysaccharides assessed via the phenol-sulfuric acid method. Three machine learning models-a feedforward neural network, an extreme learning machine, and a decision tree-were tested.Results: Notably, the extreme learning machine model, optimized by a genetic algorithm with voting, provided superior predictions, achieving R 2 values of 0.96 and 0.97 for polysaccharides and ergosterol, respectively.Conclusion: This integration of hyperspectral imaging and machine learning offers a novel, nondestructive approach to assessing Ganoderma lucidum quality.","PeriodicalId":12421,"journal":{"name":"Frontiers in Chemistry","volume":"13 ","pages":"1534216"},"PeriodicalIF":4.2000,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11897918/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Chemistry","FirstCategoryId":"92","ListUrlMain":"https://doi.org/10.3389/fchem.2025.1534216","RegionNum":3,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Ganoderma lucidum is a widely used medicinal fungus whose quality is influenced by various factors, making traditional chemical detection methods complex and economically challenging. This study addresses the need for fast, noninvasive testing methods by combining hyperspectral imaging with machine learning to predict polysaccharide and ergosterol levels in Ganoderma lucidum cap and powder.

Methods: Hyperspectral images in the visible near-infrared (385-1009 nm) and short-wave infrared (899-1695 nm) ranges were collected, with ergosterol measured by high-performance liquid chromatography and polysaccharides assessed via the phenol-sulfuric acid method. Three machine learning models-a feedforward neural network, an extreme learning machine, and a decision tree-were tested.

Results: Notably, the extreme learning machine model, optimized by a genetic algorithm with voting, provided superior predictions, achieving R ² values of 0.96 and 0.97 for polysaccharides and ergosterol, respectively.

Conclusion: This integration of hyperspectral imaging and machine learning offers a novel, nondestructive approach to assessing Ganoderma lucidum quality.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

利用高光谱成像和机器学习对灵芝成分进行无损分析。

背景：灵芝是一种应用广泛的药用真菌，其质量受多种因素影响，传统的化学检测方法复杂且经济困难。本研究通过将高光谱成像与机器学习相结合来预测灵芝瓶盖和粉末中的多糖和麦角甾醇水平，解决了对快速、无创检测方法的需求。方法：采集可见光近红外（385 ~ 1009 nm）和短波红外（899 ~ 1695 nm）高光谱图像，高效液相色谱法测定麦角甾醇含量，苯酚-硫酸法测定多糖含量。测试了三种机器学习模型——前馈神经网络、极限学习机和决策树。结果：值得注意的是，通过带有投票的遗传算法优化的极限学习机模型提供了更好的预测，多糖和麦角甾醇的r2分别为0.96和0.97。结论：高光谱成像和机器学习的结合为评估灵芝质量提供了一种新颖的、无损的方法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Frontiers in Chemistry Chemistry-General Chemistry

CiteScore

8.50

自引率

3.60%

发文量

1540

审稿时长

12 weeks

期刊介绍： Frontiers in Chemistry is a high visiblity and quality journal, publishing rigorously peer-reviewed research across the chemical sciences. Field Chief Editor Steve Suib at the University of Connecticut is supported by an outstanding Editorial Board of international researchers. This multidisciplinary open-access journal is at the forefront of disseminating and communicating scientific knowledge and impactful discoveries to academics, industry leaders and the public worldwide. Chemistry is a branch of science that is linked to all other main fields of research. The omnipresence of Chemistry is apparent in our everyday lives from the electronic devices that we all use to communicate, to foods we eat, to our health and well-being, to the different forms of energy that we use. While there are many subtopics and specialties of Chemistry, the fundamental link in all these areas is how atoms, ions, and molecules come together and come apart in what some have come to call the “dance of life”. All specialty sections of Frontiers in Chemistry are open-access with the goal of publishing outstanding research publications, review articles, commentaries, and ideas about various aspects of Chemistry. The past forms of publication often have specific subdisciplines, most commonly of analytical, inorganic, organic and physical chemistries, but these days those lines and boxes are quite blurry and the silos of those disciplines appear to be eroding. Chemistry is important to both fundamental and applied areas of research and manufacturing, and indeed the outlines of academic versus industrial research are also often artificial. Collaborative research across all specialty areas of Chemistry is highly encouraged and supported as we move forward. These are exciting times and the field of Chemistry is an important and significant contributor to our collective knowledge.