当前位置: X-MOL 学术IEEE Sens. J. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
The e-nose prototype to monitoring the growth and maturation of peaches in the orchard
IEEE Sensors Journal ( IF 4.3 ) Pub Date : 2020-10-15 , DOI: 10.1109/jsen.2020.3000070
Henike Guilherme Jordan Voss , Ricardo Antonio Ayub , Sergio Luiz Stevan

Indication of peach maturity and inspection of fruit quality in an orchard are generally analyzed based on the farmer’s experience, which may be subject to failure and result in financial losses due to negligence or late harvest. Volatile organic compounds (VOCs) vary in quantity and type, depending on the different phases of fruit growth. Thus, the electronic noses are an alternative, since they allow the online monitoring of the VOCs generated by the culture. The correlate works found in the literature focus on the detection of post-harvest peach maturation, not the monitoring of fruits in the orchard, to detect the stage of growth and maturation, and that, when measuring these properties, methods are generally used destructive instruments. Analyzing this context, we developed a prototype for the identification of the maturation of the Eragil peach in the pre-harvest growth cycle. The prototype was built containing thirteen metal oxide semiconductor gas sensors. The pre-processing method for feature selection was applied, Pearson’s Chi-square test, which provided the reduction for six sensors. Based on the Random Forest method with a Linear Discriminant Analysis, we reduced the dataset for six sensors and obtained a 1.92% error rate in the sample test step. It shows that the device could be optimized to this application and confirm that it is promising for local monitoring of fruit ground-based on the emission of VOCs and that several devices of this in-network can provide information for an optimized harvest.

中文翻译:

用于监测果园桃子生长和成熟的电子鼻原型

果园桃子成熟度指标和果实品质检验一般根据农民的经验进行分析,可能会因疏忽或晚收而失败并造成经济损失。挥发性有机化合物 (VOC) 的数量和类型因水果生长的不同阶段而异。因此,电子鼻是一种替代方法,因为它们允许在线监测培养物产生的 VOC。文献中发现的相关工作侧重于桃采后成熟的检测,而不是果园果实的监测,以检测生长和成熟的阶段,并且在测量这些特性时,通常使用破坏性仪器的方法. 分析这个背景,我们开发了一个原型,用于鉴定 Eragil 桃在收获前生长周期中的成熟度。该原型包含 13 个金属氧化物半导体气体传感器。应用了特征选择的预处理方法,Pearson 的卡方检验,它提供了六个传感器的减少。基于带有线性判别分析的随机森林方法,我们减少了六个传感器的数据集,并在样本测试步骤中获得了 1.92% 的错误率。它表明该设备可以针对此应用进行优化,并确认它有希望基于 VOC 的排放对果园进行本地监测,并且该网络中的几个设备可以为优化收获提供信息。该原型包含 13 个金属氧化物半导体气体传感器。应用了特征选择的预处理方法,Pearson 的卡方检验,它提供了六个传感器的减少。基于带有线性判别分析的随机森林方法,我们减少了六个传感器的数据集,并在样本测试步骤中获得了 1.92% 的错误率。它表明该设备可以针对该应用进行优化,并确认它有希望基于 VOC 的排放对果园进行本地监测,并且该网络内的几个设备可以为优化收获提供信息。该原型包含 13 个金属氧化物半导体气体传感器。应用了特征选择的预处理方法,Pearson 的卡方检验,它提供了六个传感器的减少。基于带有线性判别分析的随机森林方法,我们减少了六个传感器的数据集,并在样本测试步骤中获得了 1.92% 的错误率。它表明该设备可以针对该应用进行优化,并确认它有希望基于 VOC 的排放对果园进行本地监测,并且该网络内的几个设备可以为优化收获提供信息。基于带有线性判别分析的随机森林方法,我们减少了六个传感器的数据集,并在样本测试步骤中获得了 1.92% 的错误率。它表明该设备可以针对该应用进行优化,并确认它有希望基于 VOC 的排放对果园进行本地监测,并且该网络内的几个设备可以为优化收获提供信息。基于带有线性判别分析的随机森林方法,我们减少了六个传感器的数据集,并在样本测试步骤中获得了 1.92% 的错误率。它表明该设备可以针对该应用进行优化,并确认它有希望基于 VOC 的排放对果园进行本地监测,并且该网络内的几个设备可以为优化收获提供信息。
更新日期:2020-10-15
down
wechat
bug