Pest Early Detection in Greenhouse Using Machine Learning

Revue d intelligence artificielle, vol. 36, pp. 209–214

Abstract

Greenhouses are considered to be a favorable artificial environment separated from the outside. However, pests can still exist by the same plant sources that bring the pathogen. The conditions and abundant food in a greenhouse provide a stable environment for the pest development. Normally, the natural enemies that serve to keep pests under control outside are not present in the greenhouse, pest situations often develop in this indoor environment more rapidly and with greater severity than outdoors. Early detection and diagnosis of pests and diseases are key to managing greenhouse pests as well as selecting and applying appropriate pesticides when needed. The aim of this invention is to develop an intelligent pest early detection system using a convolutional neural network in the greenhouse. By using a pre-trained disease recognition model, we were able to perform deep transfer learning to produce a network that can predict with the precision above 90%.

Authors 5

1. Lê Quang Thảo

   Vietnam National University, Hanoi · VNU University of Science

   Affiliation as printed

   Faculty of Physics , VNU University of Science , Hanoi 100000 , Vietnam

   Vietnam National University , Hanoi 100000 , Vietnam

2. Duong Duc Cuong
3. Nguyen Tuan Anh

   Vietnam Atomic Energy Instiute

   Affiliation as printed

   Nguyen Sieu High School , Hanoi 100000 , Vietnam

   Nguyen Sieu High School, Hanoi 100000, Vietnam

4. Nguyen Trieu Hoang Minh
   Affiliation as printed

   Chu Van An High School, Hanoi 100000, Vietnam

5. Nguyen Duc Tam Aachen

   FH Aachen

   Affiliation as printed

   Aachen University of Applied Sciences, Aachen 52066, North Rhine-Westphalia, Germany