Synergistic strategy for the geographical traceability of wild Boletus tomentipes by means of data fusion analysis

文献类型： 外文期刊

第一作者： Li, Yun

作者： Li, Yun;Wang, Yuanzhong

作者机构：

关键词： Boletus tomentipes; Geographical traceability; FT-MIR; ICP-AES; Data fusion; Quality control

期刊名称：MICROCHEMICAL JOURNAL （ 影响因子：4.821； 五年影响因子：4.364 ）

ISSN： 0026-265X

年卷期： 2018 年 140 卷

页码：

收录情况： SCI

摘要： Due to the worldwide importance and public interest concerning to the food quality and safety, there is a growing trend in the geographical trace of food products with various techniques. The purpose of the present study is to evaluate integrated information as an effective strategy for the geographical traceability of wild Boletus tomentipes. To this goal, 76 fruiting bodies were collected, and two mushroom parts (pileus and stipe) were analyzed by Fourier transform-mid infrared (FT-MIR) spectroscopy and inductively coupled plasma-atomic emission spectrometry (ICP-AES). Five related data matrices (FT-MIR_P, FT-MIR_S, ELE_P, ELE_S and ELE_Q(C/S)) were fused at low- and mid-level, support vector machine (SVM) and random forest (RF) classification algorithms combined with data matrices were used for authenticating the geographical origin. The results of multivariate statistical analysis indicate that data fusion, taking advantage of the information synergy, shows the better classification performance than individual decision making. Also, the comparison of categorized result between two fusion levels suggests that, mid-level data fusion is more stable than low-level among different type models, which could be used as a reliable method for the geographical authentication purposes of wild porcini mushrooms. (C) 2018 Elsevier B.V. All rights reserved.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序