College of Agronomy and Biotechnology, Yunnan Agricultural University, Kunming 650201, China; Medicinal Plants Research Institute, Yunnan Academy of Agricultural Sciences, Kunming 650200, China.
College of Resources and Environmental, Yunnan Agricultural University, Kunming 650201, China.
Spectrochim Acta A Mol Biomol Spectrosc. 2022 Jun 5;274:121137. doi: 10.1016/j.saa.2022.121137. Epub 2022 Mar 10.
Wild mushroom market is an important economic source of Yunnan province in China, and its wild mushroom resources are also valuable wealth in the world. This work will put forward a method of species identification and optimize the method in order to maintain the market order and protect the economic benefits of wild mushrooms. Here we establish deep learning (DL) models based on the two-dimensional correlation spectroscopy (2DCOS) images of near-infrared spectroscopy from boletes, and optimize the identification effect of the model. The results show that synchronous 2DCOS is the best method to establish DL model, and when the learning rate was 0.01, the epochs were 40, using stipes and caps data, the identification effect would be further improved. This method retains the complete information of the samples and can provide a fast and noninvasive method for identifying boletes species for market regulators.
野生蘑菇市场是中国云南省的一个重要经济来源，其野生蘑菇资源也是世界上有价值的财富。这项工作将提出一种物种鉴定方法，并对其进行优化，以维持市场秩序，保护野生蘑菇的经济效益。在这里，我们基于牛肝菌的近红外光谱二维相关光谱 (2DCOS) 图像建立了深度学习 (DL) 模型，并优化了模型的识别效果。结果表明，同步 2DCOS 是建立 DL 模型的最佳方法，当学习率为 0.01，时，迭代次数为 40 次，使用菌柄和菌盖数据，识别效果将进一步提高。该方法保留了样品的完整信息，可为市场监管人员识别牛肝菌物种提供一种快速、无损的方法。
