Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2023, 6(13); doi: 10.25236/AJCIS.2023.061323.

Identification of Cultivated and Wild Mushrooms Using Laser-Induced Breakdown Spectroscopy Technology Combined with Machine Learning Algorithms

Author(s)

Jiayuan Tang, Shaohua Tang

Corresponding Author:
Jiayuan Tang
Affiliation(s)

School of Physics and Electronic Information Engineering, Zhejiang Normal University, Jinhua, 321000, China

Abstract

This study aimed to identify the cultivated and wild growth modes of mushrooms using Laser-Induced Breakdown Spectroscopy (LIBS) combined with machine learning algorithms. A total of 230 mushroom slice samples were collected, and their LIBS spectral data were analyzed. Multiple machine learning algorithms, including Multilayer Perceptron (MLP), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN), were employed for classification. The results showed that the integration of Principal Component Analysis (PCA) significantly reduced the modeling analysis time for MLP, SVM, and KNN. Among the six classification methods, PCA+KNN achieved the highest average accuracy of 94.7%. This indicates the feasibility of using LIBS combined with machine learning algorithms for distinguishing different types of mushroom samples. The innovation of this study lies in the utilization of PCA for dimensionality reduction and the combination of various machine learning algorithms for mushroom sample classification, leading to improved accuracy and modeling speed.

Keywords

Laser-induced breakdown spectroscopy, Mushroom, Machine learning algorithm, Principal component analysis

Cite This Paper

Jiayuan Tang, Shaohua Tang. Identification of Cultivated and Wild Mushrooms Using Laser-Induced Breakdown Spectroscopy Technology Combined with Machine Learning Algorithms. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 13: 161-168. https://doi.org/10.25236/AJCIS.2023.061323.

References

[1] Shi Yu, Sun Dong, Gao Qingwei, Lu Yixiang, Ji Mingwei. Mushroom Classification Method Based on Texture Features[J]. Foreign Electronic Measurement Technology, 2022, 41(01): 158-162. DOI: 10.19652/j.cnki.femt.2103035.

[2] Xia Zhenzhen, Zheng Dan, Xia Hong, Yao Jingjing, Wang Shengpeng, Qiu Jianfei. Rapid Identification of Cultivated Mushrooms' Origin by Near-Infrared Spectroscopy Analysis[J]. Chinese Journal of Analysis and Testing, 2020, 39(11): 1371-1377.

[3] Wu Xueqian, Li Haibo, Wei Hailong, Fu Lizhong, Wu Qingqi, Peng Huazheng, Zhu Muyuan. Application of SCAR Molecular Marker Technology in Mushroom Strain Identification[J]. Mycosystema, 2005(02): 259-266. DOI: 10.13346/j.mycosystema.2005.02.016.

[4] Wang Dali, Bian Yinbing, Huang Chenyang, Zhang Jinxia. Application of Functional Gene SNP Markers in Discrimination of Mushroom Varieties[C]//. Abstracts of the 5th Membership Representative Conference of the Chinese Mycological Society and the 2011 Academic Annual Meeting. [Publisher not specified], 2011: 100-101.

[5] A, Ryota Sugawara, et al. "Rapid and reliable species identification of wild mushrooms by matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS)." Analytica Chimica Acta 934(2016):163-169.

[6] Liu Shiming. Research on Elemental Analysis Method in Metal Oxide Nanofilm Based on LIBS Technology [D]. Shandong University of Technology, 2021. DOI: 10.27276/d.cnki.gsdgc.2021.000303.

[7] Chen Boyang. Research on Analysis Method of Partial Metal Elements in Iron Ore Based on LIBS Technology [D]. Xi'an Shiyou University, 2020. DOI: 10.27400/d.cnki.gxasc.2020.000012.

[8] Zhang Ranran. LIBS Detection of Heavy Metal Elements in Aquatic Products [D]. Zhejiang Normal University, 2021. DOI: 10.27464/d.cnki.gzsfu.2021.000203.

[9] Sun Miao. Research on Industrial Heavy Metal Pollution Detection Model Based on Machine Learning and LIBS [D]. Zhejiang University of Science and Technology, 2020. DOI: 10.27840/d.cnki. gzjkj.2020.000097.

[10] Yang Sibo. Research on Elemental Imaging and Cluster Analysis of Breast Cancer Tissues Based on LIBS Technology [D]. Harbin Institute of Technology, 2019. DOI: 10.27061/d.cnki. ghgdu.2019. 002308.

[11] Liu Xianyun, Wang Zhenya, Hao Liqing, Zhao Wenwu, Huang Mingqiang, Long Bo, Zhang Weijun. Application of Laser-Induced Breakdown Spectroscopy in Biomedicine [J]. Laser Technology, 2008(02): 134-136.

[12] M. Darby Dyar et al. Strategies for Mars Remote Laser-Induced Breakdown Spectroscopy Analysis of Sulfur in Geological Samples [J]. Spectrochimica Acta Part B: Atomic Spectroscopy, 2010, 66(1): 39-56.

[13] Lu Yonghua. Research on Plastic Classification Based on LIBS Combined with GA-BP Neural Network and GA-SVM [J]. Laser & Infrared, 2022, 52(02): 273-279.

[14] Sun Miao, Guindo Mahamed Lamine, Zhuang Zhenhua, Zhong Haipeng, Zhao Yun. Rapid Classification of Soil Lead Content Levels Based on LIBS Technology and Convolutional Neural Network [J]. Journal of Zhejiang University of Science and Technology, 2019, 31(05): 373-380.

[15] Li Chenyang, Chen Xiongfei, Zhang Yong, Wang Yawen, Tian Zhongchao, Wang Shigong, Zhao Zhenyang, Liu Ying, Liu Pengyu. Aluminum Alloy LIBS Spectrum Classification and Recognition Method Based on XGBoost [J]. Spectroscopy and Spectral Analysis, 2021, 41(02): 624-628.

[16] Bilge G, et al. "Identification of meat species by using laser-induced breakdown spectroscopy." Meat Science 119.sep. (2016):118-122.