TRiP: a transfer learning based rice disease phenotype recognition platform using SENet and microservices
Classification of rice disease is one significant research topics in rice phenotyping. Recognition of rice diseases such as Bacterialblight, Blast, Brownspot, Leaf smut, and Tungro are a critical research field in rice phenotyping. However, accurately identifying these diseases is a challenging issu...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2024-01-01
|
Series: | Frontiers in Plant Science |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2023.1255015/full |
_version_ | 1797347886217822208 |
---|---|
author | Peisen Yuan Ye Xia Yongchao Tian Yongchao Tian Huanliang Xu |
author_facet | Peisen Yuan Ye Xia Yongchao Tian Yongchao Tian Huanliang Xu |
author_sort | Peisen Yuan |
collection | DOAJ |
description | Classification of rice disease is one significant research topics in rice phenotyping. Recognition of rice diseases such as Bacterialblight, Blast, Brownspot, Leaf smut, and Tungro are a critical research field in rice phenotyping. However, accurately identifying these diseases is a challenging issue due to their high phenotypic similarity. To address this challenge, we propose a rice disease phenotype identification framework which utilizing the transfer learning and SENet with attention mechanism on the cloud platform. The pre-trained parameters are transferred to the SENet network for parameters optimization. To capture distinctive features of rice diseases, the attention mechanism is applied for feature extracting. Experiment test and comparative analysis are conducted on the real rice disease datasets. The experimental results show that the accuracy of our method reaches 0.9573. Furthermore, we implemented a rice disease phenotype recognition platform based microservices architecture and deployed it on the cloud, which can provide rice disease phenotype recognition task as a service for easy usage. |
first_indexed | 2024-03-08T11:54:23Z |
format | Article |
id | doaj.art-61e9521787ac4de098ee0f38da4c9417 |
institution | Directory Open Access Journal |
issn | 1664-462X |
language | English |
last_indexed | 2024-03-08T11:54:23Z |
publishDate | 2024-01-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Plant Science |
spelling | doaj.art-61e9521787ac4de098ee0f38da4c94172024-01-24T04:49:03ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2024-01-011410.3389/fpls.2023.12550151255015TRiP: a transfer learning based rice disease phenotype recognition platform using SENet and microservicesPeisen Yuan0Ye Xia1Yongchao Tian2Yongchao Tian3Huanliang Xu4College of Artificial Intelligence, Nanjing Agricultural University, Nanjing, ChinaCollege of Artificial Intelligence, Nanjing Agricultural University, Nanjing, ChinaCollege of Artificial Intelligence, Nanjing Agricultural University, Nanjing, ChinaCollege of Agriculture, Nanjing Agricultural University, Nanjing, ChinaCollege of Artificial Intelligence, Nanjing Agricultural University, Nanjing, ChinaClassification of rice disease is one significant research topics in rice phenotyping. Recognition of rice diseases such as Bacterialblight, Blast, Brownspot, Leaf smut, and Tungro are a critical research field in rice phenotyping. However, accurately identifying these diseases is a challenging issue due to their high phenotypic similarity. To address this challenge, we propose a rice disease phenotype identification framework which utilizing the transfer learning and SENet with attention mechanism on the cloud platform. The pre-trained parameters are transferred to the SENet network for parameters optimization. To capture distinctive features of rice diseases, the attention mechanism is applied for feature extracting. Experiment test and comparative analysis are conducted on the real rice disease datasets. The experimental results show that the accuracy of our method reaches 0.9573. Furthermore, we implemented a rice disease phenotype recognition platform based microservices architecture and deployed it on the cloud, which can provide rice disease phenotype recognition task as a service for easy usage.https://www.frontiersin.org/articles/10.3389/fpls.2023.1255015/fullrice disease recognitionSENettransfer learningmachine learning as servicemicroservices framework |
spellingShingle | Peisen Yuan Ye Xia Yongchao Tian Yongchao Tian Huanliang Xu TRiP: a transfer learning based rice disease phenotype recognition platform using SENet and microservices Frontiers in Plant Science rice disease recognition SENet transfer learning machine learning as service microservices framework |
title | TRiP: a transfer learning based rice disease phenotype recognition platform using SENet and microservices |
title_full | TRiP: a transfer learning based rice disease phenotype recognition platform using SENet and microservices |
title_fullStr | TRiP: a transfer learning based rice disease phenotype recognition platform using SENet and microservices |
title_full_unstemmed | TRiP: a transfer learning based rice disease phenotype recognition platform using SENet and microservices |
title_short | TRiP: a transfer learning based rice disease phenotype recognition platform using SENet and microservices |
title_sort | trip a transfer learning based rice disease phenotype recognition platform using senet and microservices |
topic | rice disease recognition SENet transfer learning machine learning as service microservices framework |
url | https://www.frontiersin.org/articles/10.3389/fpls.2023.1255015/full |
work_keys_str_mv | AT peisenyuan tripatransferlearningbasedricediseasephenotyperecognitionplatformusingsenetandmicroservices AT yexia tripatransferlearningbasedricediseasephenotyperecognitionplatformusingsenetandmicroservices AT yongchaotian tripatransferlearningbasedricediseasephenotyperecognitionplatformusingsenetandmicroservices AT yongchaotian tripatransferlearningbasedricediseasephenotyperecognitionplatformusingsenetandmicroservices AT huanliangxu tripatransferlearningbasedricediseasephenotyperecognitionplatformusingsenetandmicroservices |