周博, 代雨婷, 李超, 王俊. 花龄期棉花虫害的电子鼻检测[J]. 农业工程学报, 2020, 36(21): 194-200. DOI: 10.11975/j.issn.1002-6819.2020.21.023
    引用本文: 周博, 代雨婷, 李超, 王俊. 花龄期棉花虫害的电子鼻检测[J]. 农业工程学报, 2020, 36(21): 194-200. DOI: 10.11975/j.issn.1002-6819.2020.21.023
    Zhou Bo, Dai Yuting, Li Chao, Wang Jun. Electronic nose for detection of cotton pests at the flowering stage[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2020, 36(21): 194-200. DOI: 10.11975/j.issn.1002-6819.2020.21.023
    Citation: Zhou Bo, Dai Yuting, Li Chao, Wang Jun. Electronic nose for detection of cotton pests at the flowering stage[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2020, 36(21): 194-200. DOI: 10.11975/j.issn.1002-6819.2020.21.023

    花龄期棉花虫害的电子鼻检测

    Electronic nose for detection of cotton pests at the flowering stage

    • 摘要: 棉花害虫具有隐蔽性、迁飞性和突发性特点,并且影响因素众多,棉花虫害准确地诊断是农业领域的难点问题。该研究以受到棉铃虫侵害的花铃期棉花为研究对象,采用电子鼻对不同处理的棉花挥发物进行检测。研究表明,主成分分析(Principal Component Analysis, PCA)和聚类分析结果显示健康棉花释放的挥发物具有明显的昼夜节律性,健康棉花与虫害棉花差异性显著。径向基函数神经网络(Radial Basis Function Neural Network, RBFNN)对8个不同时间的4组虫害棉花处理进行分析,测试集判别总的正确率为73.4%,健康棉花对照组测试集判别正确率100%,误判样本出现在3个虫害处理之间。当不考虑时间因素建立虫害棉花统一的预测模型,RBFNN模型对健康棉花对照组的预测正确率均达到了100%,分析结果可以作为花铃期棉花是否遭受棉铃虫侵害的依据,说明电子鼻可以作为棉花虫害发生的有效监测手段,在农作物虫害监测领域具有潜在的应用价值。

       

      Abstract: The cotton pests have the characteristics of concealment, migration, and sudden burst, and there are many influencing factors involved. The accurate diagnosis of cotton pests is a difficult problem in the agricultural field. Previous studies have demonstrated that cotton plants produce blends of volatile compounds in response to herbivores serve as cues for parasitic and predatory insects. Therefore, it is possible to obtain information about cotton pests by detecting volatile compounds in cotton. In this study, an electronic nose was used to detect the volatiles emitted by cotton plants damaged by cotton bollworm at the flowering period. The cotton samples were divided into four infested cotton treatments. According to the number of pests in each pot of cotton seedlings, the treatments inoculated with 0, 1, 2, and 3 bollworm larvae were marked as 0-P, 1-P, 2-P, and 3-P, respectively. The 0-P was healthy cotton as a control treatment. The cotton bollworm feeding lasted 48 h. During this period, the electronic nose detection tests were performed every 6 h, and a total of 8 repeated tests were performed. Appropriate pattern recognition techniques were applied to construct reliable algorithms for interpreting the acquired signal in cotton. Principal Component Analysis (PCA), discriminant function analysis, cluster analysis, and Radial Basis Function Neural Network (RBFNN) were applied to evaluate the data. The results of PCA and discrimination values of the healthy cotton treatment showed that the volatiles released by healthy cotton had obvious circadian rhythm. For the three infested cotton treatments, whereas the distribution patterns of cotton samples were different from that of the healthy cotton treatment. The three infested cotton treatments had regular distribution trends that cotton samples changed along the direction of the first and second principal components. Cluster analysis results showed that the four cotton treatments were all finally divided into two categories, the healthy cotton treatment, and the three infested cotton treatments. All these results suggested that there was a significant difference between healthy and damaged cotton samples. Then RBFNN was used to analyze four treatments of cotton samples at 8 different times. The results showed that the total correct rate of the test sets was 73.4%, the correct rate of the healthy cotton treatment was 100%, and the misjudgment samples appeared among the three infested cotton treatments. Moreover, two unified consecutive prediction models were established regardless of the time factor. The RBFNN model was established by using four treatments of cotton samples. The correct rate of the training sets was 66.1%, and the correct rates of the test sets were 100 %, 79.7 %, 32.8 %, and 20.3 % for the 0-P, 1-P, 2-P, and 3-P treatments, respectively. In another RBFNN model based on 0-P, 1-P, and 3-P treatments, the correct rate of the training sets was 87.8%, and the correct rates of the test sets were 100 %, 78.1%, and 82.8% for the 0-P, 1-P, and 3-P treatments, respectively. Comparing the results of the two RBFNN models, the prediction accuracy of the second model had been greatly improved. At the same time, it was also found that the prediction accuracy of all RBFNN models for healthy cotton treatment reached 100%. Therefore, the electronic nose could be used as an effective monitoring method for the occurrence of cotton bollworm in the cotton plants. It should have a potential application for crop pest monitoring in the field.

       

    /

    返回文章
    返回