4.6 Article

Feature Fusion of ICP-AES, UV-Vis and FT-MIR for Origin Traceability of Boletus edulis Mushrooms in Combination with Chemometrics

Journal

SENSORS
Volume 18, Issue 1, Pages -

Publisher

MDPI
DOI: 10.3390/s18010241

Keywords

origin traceability; Boletus edulis; ICP-AES; UV-Vis; FT-MIR

Funding

  1. National Natural Science Foundation of China [21667031, 31660591]
  2. Science Foundation of the Yunnan Province Department of Education [2016ZZX106]
  3. University Key Laboratory of Development and Utilization of Edible Mushroom Resources in Yunnan Province

Ask authors/readers for more resources

Origin traceability is an important step to control the nutritional and pharmacological quality of food products. Boletus edulis mushroom is a well-known food resource in the world. Its nutritional and medicinal properties are drastically varied depending on geographical origins. In this study, three sensor systems (inductively coupled plasma atomic emission spectrophotometer (ICP-AES), ultraviolet-visible (UV-Vis) and Fourier transform mid-infrared spectroscopy (FT-MIR)) were applied for the origin traceability of 184 mushroom samples (caps and stipes) in combination with chemometrics. The difference between cap and stipe was clearly illustrated based on a single sensor technique, respectively. Feature variables from three instruments were used for origin traceability. Two supervised classification methods, partial least square discriminant analysis (FLS-DA) and grid search support vector machine (GS-SVM), were applied to develop mathematical models. Two steps (internal cross-validation and external prediction for unknown samples) were used to evaluate the performance of a classification model. The result is satisfactory with high accuracies ranging from 90.625% to 100%. These models also have an excellent generalization ability with the optimal parameters. Based on the combination of three sensory systems, our study provides a multi-sensory and comprehensive origin traceability of B. edulis mushrooms.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

Article Agriculture, Multidisciplinary

Verified the rapid evaluation of the edible safety of wild porcini mushrooms, using deep learning and PLS-DA

Li Wang, Honggao Liu, Tao Li, Jieqing Li, Yuanzhong Wang

Summary: The study shows that deep learning based on FT-NIR spectroscopy is the most effective method to identify the edible safety of porcini mushrooms, with a recognition accuracy of 100%. By comparing deep learning with partial least square discriminant analysis (PLS-DA), it was found that while the accuracy of PLS-DA test set is 96.10%, poisonous porcini cannot be wrongly judged. Additionally, deep learning can trace the geographic origin of Leccinum rugosiceps in the Midu area with 100% accuracy.

JOURNAL OF THE SCIENCE OF FOOD AND AGRICULTURE (2022)

Article Biochemical Research Methods

Extended application of deep learning combined with 2DCOS: Study on origin identification in the medicinal plant of Paris polyphylla var. yunnanensis

Jia Qi Yue, Heng Yu Huang, Yuan Zhong Wang

Summary: This study proposed a method combining deep learning and 2DCOS for rapid identification of medicinal plants, achieving 100% accuracy in origin identification for Paris polyphylla var. yunnanensis. The ResNet models are stable, reliable, and robust, expanding the application field of deep learning and providing practical reference for related research of other medicinal plants.

PHYTOCHEMICAL ANALYSIS (2022)

Article Automation & Control Systems

Multisource information fusion strategies of mass spectrometry and Fourier transform infrared spectroscopy data for authenticating the age and parts of Vietnamese ginseng

Lu Liu, Wan-Yi Li, Zhi-Tian Zuo, Yuan-Zhong Wang

Summary: Based on different complementary analysis techniques, a data fusion strategy was studied for quality evaluation of Vietnamese ginseng, showing effective differentiation of age and parts. Low-level and mid-level fusion methods achieved optimal results in different models for classification.

JOURNAL OF CHEMOMETRICS (2021)

Article Biochemical Research Methods

Identification of geographical origin and different parts of Wolfiporia cocos from Yunnan in China using PLS-DA and ResNet based on FT-NIR

Lian Li, Zhi-Tian Zuo, Yuan-Zhong Wang

Summary: This study successfully identified the geographical traceability of different parts of Wolfiporia cocos using two-dimensional correlation spectroscopy and multivariate statistical analysis methods such as residual convolutional neural network and partial least square discriminant analysis. The results showed that synchronous SD 2DCOS was more suitable for identifying complex mixed systems. These methods can provide technical support for the identification and quality evaluation of herbal geographical origins.

PHYTOCHEMICAL ANALYSIS (2022)

Article Food Science & Technology

Rapid identification of the storage duration and species of sliced boletes using near-infrared spectroscopy

Jian Chen, Jie qing Li, Tao Li, Hong gao Liu, Yuan zhong Wang

Summary: This study developed a rapid method using near-infrared spectroscopy to identify the storage duration and species of sliced boletes. A strategy based on two-dimensional correlation spectroscopy images and residual convolutional neural network model showed superior classification performance, providing a promising way for authenticity testing in the supply chain of boletes.

JOURNAL OF FOOD SCIENCE (2022)

Article Biochemical Research Methods

Anticoagulant activity analysis and origin identification of Panax notoginseng using HPLC and ATR-FTIR spectroscopy

Zhi-Ying Cui, Chun-Lu Liu, Dan-Dan Li, Yuan-Zhong Wang, Fu-Rong Xu

Summary: This study aimed to analyze the correlation of components and activities of P. notoginseng from different origins and develop a rapid identification method. Pharmacological experiments, HPLC, and spectroscopy combined with chemometrics methods were conducted to analyze the main roots of P. notoginseng from four different origins in Yunnan Province. The results showed that the saponin content of P. notoginseng main roots was not significantly different, but the anticoagulant activity was positively correlated with the contents of the three saponins. The variable selection method improved the performance of the model, and the variable importance in projection had the best ability to identify the origins of P. notoginseng.

PHYTOCHEMICAL ANALYSIS (2022)

Article Environmental Sciences

Occurrence, distribution, and associations of essential and non-essential elements in the medicinal and edible fungus Fuling from southern China

Ji Zhang, Jerzy Falandysz, Anetta Hanc, Wiktor Lorenc, Yuanzhong Wang, Danuta Baralkiewicz

Summary: This study investigated the occurrence, distribution, and associations of various elements in the inner and outer parts of Pachyma hoelen sclerotia in Southern China. The quality of forest and agricultural soil was found to be the main factor determining the occurrence of minerals in sclerotia. The concentration of elements was generally higher in the outer part compared to the inner part, except for silver. Additionally, there were different association patterns of elements in different morphological parts of the sclerotia. Further research should be conducted to assess the relationship between minerals and bioactive organic compounds produced by P. hoelen.

SCIENCE OF THE TOTAL ENVIRONMENT (2022)

Article Automation & Control Systems

ResNet models for rapid identification of species and geographical origin of wild boletes from Yunnan, and MaxEnt model for delineation of potential distribution

Xiong Chen, Hong Gao Liu, Jie Qing Li, Yuan Zhong Wang

Summary: This study developed a method to simultaneously identify the species and geographical origins of boletes. By combining Fourier transform near-infrared data and residual neural network image analysis model, reliable identification of boletes can be achieved. In addition, the important environmental factors affecting the distribution of boletes were identified using the maximum entropy model, highlighting the crucial role of precipitation factors in the distribution and chemical composition differences of boletes.

JOURNAL OF CHEMOMETRICS (2022)

Review Microbiology

Research Progress on Elements of Wild Edible Mushrooms

Shuai Liu, Honggao Liu, Jieqing Li, Yuanzhong Wang

Summary: Wild edible mushrooms are delicious seasonal foods that are rich in nutrients but may also contain harmful heavy metals. This paper reviews the content of essential trace elements and harmful heavy metals in nearly 400 species of wild edible mushrooms, and analyzes the internal and external factors that affect elemental content.

JOURNAL OF FUNGI (2022)

Article Biochemical Research Methods

Network pharmacology and fingerprint for the integrated analysis of mechanism, identification and prediction in Panax notoginseng

Chunlu Liu, Furong Xu, Zhitian Zuo, Yuanzhong Wang

Summary: This study conducted a comprehensive analysis on the action mechanism, component content, origin identification, and content prediction of Panax notoginseng. Four saponins were identified as Q-markers, and exerted pharmacological effects on signaling pathways through 24 core targets. HPLC analysis revealed differences among groups and different origins. Suitable producing areas were determined through the mechanism of action and the required saponin content. The low-level data fusion successfully identified the origin and predicted the content of Panax notoginseng from different origins.

PHYTOCHEMICAL ANALYSIS (2023)

Article Food Science & Technology

ResNet Model Automatically Extracts and Identifies FT-NIR Features for Geographical Traceability of Polygonatum kingianum

Yulin Xu, Weize Yang, Xuewei Wu, Yuanzhong Wang, Jinyu Zhang

Summary: This study compares traditional models with a deep learning model called ResNet and finds that ResNet has significant advantages in feature extraction and recognition. Preprocessing plays a crucial role in feature extraction and model performance, and VIP features yield the best results in traditional modelling. This research is practically significant for the application development of ResNet model in foods, spices, and medicinal plants.

FOODS (2022)

Article Chemistry, Analytical

Discrimination and Evaluation of Wild Paris Using UHPLC-QTOF-MS and FT-IR Spectroscopy in Combination with Multivariable Analysis

Yuangui Yang, Fan Li, Hongbo Xu, Zhishu Tang, Yuanzhong Wang

Summary: In this study, UHPLC-QTOF-MS and FT-IR combined with multivariable analysis were used to discriminate different species of Paris. The midlevel data fusion showed good performance in classification. A total of 47 compounds were identified using UHPLC-QTOF-MS. The results suggested that PM could be a substitute for PPY.

INTERNATIONAL JOURNAL OF ANALYTICAL CHEMISTRY (2023)

Article Chemistry, Multidisciplinary

Rapid and Accurate Authentication of Porcini Mushroom Species Using Fourier Transform Near-Infrared Spectra Combined with Machine Learning and Chemometrics

Hong Liu, Honggao Liu, Jieqing Li, Yuanzhong Wang

Summary: This research collected Fourier transform near-infrared (FT-NIR) spectral information of different species of porcini mushroom stipe and cap and used chemometric methods and machine learning for accurate evaluation and identification. The results showed high accuracies of the models based on support vector machine and partial least-squares discriminant analysis (PLS-DA), reaching 98.73-99.04% and 98.73-99.68%, respectively. The models based on low-level data fusion and residual neural network achieved the highest accuracies of 99.68% and 100%, respectively. The study suggests that different models should be selected for different spectral data matrices of porcini mushrooms, and FT-NIR spectra are promising in food safety control.

ACS OMEGA (2023)

Article Food Science & Technology

Building deep learning and traditional chemometric models based on Fourier transform mid- infrared spectroscopy: Identification of wild and cultivated Gastrodia elata

Shuai Liu, Honggao Liu, Jieqing Li, Yuanzhong Wang

Summary: This study combines three-dimensional correlation spectroscopy (3DCOS) images with deep learning models to quickly and accurately identify wild and cultivated Gastrodia elata. The spectral data used for model building do not require preprocessing and are converted into three-dimensional spectral images. A partial least squares discriminant analysis (PLS-DA) model and a support vector machine (SVM) model are also built for comparison. The deep learning model outperforms the traditional chemometric models, achieving 100% accuracy in multiple sets without preprocessing.

FOOD SCIENCE & NUTRITION (2023)

Article Food Science & Technology

Comparison of Metabolites and Species Classification of Thirteen Zingiberaceae Spices Based on GC-MS and Multi-Spectral Fusion Technology

Hui Wen, Tianmei Yang, Weize Yang, Meiquan Yang, Yuanzhong Wang, Jinyu Zhang

Summary: In this study, the differences in metabolites in thirteen Zingiberaceae spices were explored using GC-MS and combined spectroscopy. A total of 81 metabolites were identified by GC-MS, with 37 differential metabolites screened using VIP >= 1. However, the OPLS-DA model established with GC-MS data only explained about 30% of the variation. On the other hand, the PLS-DA models with three spectral data fusion strategies achieved a classification accuracy of 100%. The mid-level data fusion model based on latent variables performed the best. This study provides a powerful tool for distinguishing different Zingiberaceae spices and helps reduce the occurrence of substitution and adulteration phenomena.

FOODS (2023)

No Data Available