Disease Identification of Lentinus Edodes Sticks Based on Deep Learning Model
Lentinus edodes sticks are susceptible to mold infection during the culture process, and manual identification of infected sticks is heavy, untimely, and inaccurate. Aiming to solve this problem, this paper proposes a method for identifying infected Lentinus edodes sticks based on improved ResNeXt-5...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2022/9504055 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832556414541758464 |
|---|---|
| author | Dawei Zu Feng Zhang Qiulan Wu Wenyan Wang Zimeng Yang Zhengpeng Hu |
| author_facet | Dawei Zu Feng Zhang Qiulan Wu Wenyan Wang Zimeng Yang Zhengpeng Hu |
| author_sort | Dawei Zu |
| collection | DOAJ |
| description | Lentinus edodes sticks are susceptible to mold infection during the culture process, and manual identification of infected sticks is heavy, untimely, and inaccurate. Aiming to solve this problem, this paper proposes a method for identifying infected Lentinus edodes sticks based on improved ResNeXt-50(32 × 4d) deep transfer learning. First, a dataset of Lentinus edodes stick diseases was constructed. Second, based on the ResNeXt-50(32 × 4d) model and the pretraining weight of the ImageNet dataset, the influence of pretraining weight parameters on recognition accuracy was studied. Finally, six fine-tuning strategies of the fully connected layer were designed to modify the fully connected layer of ResNeXt-50(32 × 4d). The experimental results show that the recognition accuracy of the method proposed in this paper can reach 94.27%, which is higher than the Vgg16, GoogLeNet, ResNet50, and MobileNet v2 models by 8.47%, 6.49%, 4.68%, and 9.38%, respectively, and the F1-score can reach 0.9422. The improved method proposed in this paper can reduce the calculation pressure and overfitting problem of the model, improve the accuracy of the model in the identification of Lentinus edodes stick mold diseases, and provide an effective solution for the selection of diseased sticks. |
| format | Article |
| id | doaj-art-dbbf49f632d448b9b1b46e32ff6a3f52 |
| institution | Kabale University |
| issn | 1099-0526 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-dbbf49f632d448b9b1b46e32ff6a3f522025-02-03T05:45:29ZengWileyComplexity1099-05262022-01-01202210.1155/2022/9504055Disease Identification of Lentinus Edodes Sticks Based on Deep Learning ModelDawei Zu0Feng Zhang1Qiulan Wu2Wenyan Wang3Zimeng Yang4Zhengpeng Hu5School of Information Science & EngineeringSchool of Information Science & EngineeringSchool of Information Science & EngineeringSchool of Information Science & EngineeringSchool of Information Science & EngineeringShandong Qihe Bio-Technology Limited CompanyLentinus edodes sticks are susceptible to mold infection during the culture process, and manual identification of infected sticks is heavy, untimely, and inaccurate. Aiming to solve this problem, this paper proposes a method for identifying infected Lentinus edodes sticks based on improved ResNeXt-50(32 × 4d) deep transfer learning. First, a dataset of Lentinus edodes stick diseases was constructed. Second, based on the ResNeXt-50(32 × 4d) model and the pretraining weight of the ImageNet dataset, the influence of pretraining weight parameters on recognition accuracy was studied. Finally, six fine-tuning strategies of the fully connected layer were designed to modify the fully connected layer of ResNeXt-50(32 × 4d). The experimental results show that the recognition accuracy of the method proposed in this paper can reach 94.27%, which is higher than the Vgg16, GoogLeNet, ResNet50, and MobileNet v2 models by 8.47%, 6.49%, 4.68%, and 9.38%, respectively, and the F1-score can reach 0.9422. The improved method proposed in this paper can reduce the calculation pressure and overfitting problem of the model, improve the accuracy of the model in the identification of Lentinus edodes stick mold diseases, and provide an effective solution for the selection of diseased sticks.http://dx.doi.org/10.1155/2022/9504055 |
| spellingShingle | Dawei Zu Feng Zhang Qiulan Wu Wenyan Wang Zimeng Yang Zhengpeng Hu Disease Identification of Lentinus Edodes Sticks Based on Deep Learning Model Complexity |
| title | Disease Identification of Lentinus Edodes Sticks Based on Deep Learning Model |
| title_full | Disease Identification of Lentinus Edodes Sticks Based on Deep Learning Model |
| title_fullStr | Disease Identification of Lentinus Edodes Sticks Based on Deep Learning Model |
| title_full_unstemmed | Disease Identification of Lentinus Edodes Sticks Based on Deep Learning Model |
| title_short | Disease Identification of Lentinus Edodes Sticks Based on Deep Learning Model |
| title_sort | disease identification of lentinus edodes sticks based on deep learning model |
| url | http://dx.doi.org/10.1155/2022/9504055 |
| work_keys_str_mv | AT daweizu diseaseidentificationoflentinusedodessticksbasedondeeplearningmodel AT fengzhang diseaseidentificationoflentinusedodessticksbasedondeeplearningmodel AT qiulanwu diseaseidentificationoflentinusedodessticksbasedondeeplearningmodel AT wenyanwang diseaseidentificationoflentinusedodessticksbasedondeeplearningmodel AT zimengyang diseaseidentificationoflentinusedodessticksbasedondeeplearningmodel AT zhengpenghu diseaseidentificationoflentinusedodessticksbasedondeeplearningmodel |