Recognition of Crop Diseases Based on Depthwise Separable Convolution in Edge Computing
Recognition of Crop Diseases Based on Depthwise Separable Convolution in Edge Computing
复制标题
边缘计算中基于深度可分离卷积的作物病害识别
DOI：
10.3390/s20154091
复制
发表时间：
2020-07
期刊：
影响因子：
3.9
通讯作者：
Fan Wenjie
中科院分区：
文献类型：
--
作者：
Gu Musong;Li Kuan-Ching;Li Zhongwen;Han Qiyi;Fan Wenjie
原来的农作物病害模式识别和分类需要在田间采集大量的数据，通过网络发送到旁边的计算机服务器上进行识别和分类。这种方法通常需要很长时间，价格昂贵，并且难以及时监测作物病害，导致诊断和治疗延迟。随着边缘计算的出现，人们可以尝试将模式识别算法部署到农田环境中，并及时监测作物的生长。然而，由于边缘设备的资源有限，原始的深度识别模型在应用上具有挑战性。基于此，本文提出了一种基于深度可分离卷积神经网络（DSCNN）的识别模型，该模型的运算特性包括参数数量和计算量的显著减少，使得所提出的设计非常适合于边缘。为了证明其有效性，仿真结果与主要的卷积神经网络（CNN）模型LeNet和视觉几何组网络（VGGNet）进行了比较，并表明，在高识别精度的基础上，该模型的识别时间分别减少了80.9%和94.4%。该模型具有识别速度快、识别精度高的特点，通过配置远程嵌入式设备，利用边缘计算部署该模型，可实现农作物病害的实时监测和识别。
The original pattern recognition and classification of crop diseases needs to collect a large amount of data in the field and send them next to a computer server through the network for recognition and classification. This method usually takes a long time, is expensive, and is difficult to carry out for timely monitoring of crop diseases, causing delays to diagnosis and treatment. With the emergence of edge computing, one can attempt to deploy the pattern recognition algorithm to the farmland environment and monitor the growth of crops promptly. However, due to the limited resources of the edge device, the original deep recognition model is challenging to apply. Due to this, in this article, a recognition model based on a depthwise separable convolutional neural network (DSCNN) is proposed, which operation particularities include a significant reduction in the number of parameters and the amount of computation, making the proposed design well suited for the edge. To show its effectiveness, simulation results are compared with the main convolution neural network (CNN) models LeNet and Visual Geometry Group Network (VGGNet) and show that, based on high recognition accuracy, the recognition time of the proposed model is reduced by 80.9% and 94.4%, respectively. Given its fast recognition speed and high recognition accuracy, the model is suitable for the real-time monitoring and recognition of crop diseases by provisioning remote embedded equipment and deploying the proposed model using edge computing.
登录
查看更多内容
影响因子：
5.6
作者：
Mutka AM;Bart RS
通讯作者：
Bart RS
影响因子：
3.9
作者：
Jing Long;W. Liang;Kuan-Ching Li;Dafang Zhang;Mingdong Tang;Haibo Luo
通讯作者：
Jing Long;W. Liang;Kuan-Ching Li;Dafang Zhang;Mingdong Tang;Haibo Luo
DOI：
10.1109/tetc.2020.2993032
发表时间：
2021-07-01
影响因子：
5.9
作者：
Liang, Wei;Zhang, Dafang;Zomaya, Albert Y.
通讯作者：
Zomaya, Albert Y.
影响因子：
3.9
作者：
Zhu, Xiaojuan;Li, Kuan-Ching;Zhang, Shunxiang
通讯作者：
Zhang, Shunxiang
DOI：
10.2991/ijndc.2013.1.1.2
发表时间：
2013
期刊：
Int. J. Networked Distributed Comput.
影响因子：
--
作者：
Juhnyoung Lee
通讯作者：
Juhnyoung Lee