PotatoPestNet: A CTInceptionV3-RS-based neural network for accurate identification of potato pests
Potatoes are the third-largest food crop globally, but their production frequently encounters difficulties because of aggressive pest infestations. Early classification those potato pests plays an important role in the detection and prevention of their notorious attack. The aim of this study is to i...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375523001260 |
| _version_ | 1797741422686765056 |
|---|---|
| author | Md. Simul Hasan Talukder Rejwan Bin Sulaiman Mohammad Raziuddin Chowdhury Musarrat Saberin Nipun Taminul Islam |
| author_facet | Md. Simul Hasan Talukder Rejwan Bin Sulaiman Mohammad Raziuddin Chowdhury Musarrat Saberin Nipun Taminul Islam |
| author_sort | Md. Simul Hasan Talukder |
| collection | DOAJ |
| description | Potatoes are the third-largest food crop globally, but their production frequently encounters difficulties because of aggressive pest infestations. Early classification those potato pests plays an important role in the detection and prevention of their notorious attack. The aim of this study is to investigate the various types and characteristics of these pests and propose an efficient PotatoPestNet AI-based automatic potato pest identification system. To accomplish this, we curated a reliable dataset consisting of eight types of potato pests. We leveraged the power of transfer learning by employing five customized, pre-trained transfer learning models: CMobileNetV2, CNASLargeNet, CXception, CDenseNet201, and CInceptionV3, in proposing a robust PotatoPestNet model to accurately classify potato pests. To improve the models' performance, we applied various augmentation techniques, incorporated a global average pooling layer, and implemented proper regularization methods. To further enhance the performance of the models, we utilized random search (RS) optimization for hyperparameter tuning. This optimization technique played a significant role in fine-tuning the models and achieving improved performance. We evaluated the models both visually and quantitatively, utilizing different evaluation metrics. The robustness of the models in handling imbalanced datasets was assessed using the Receiver Operating Characteristic (ROC) curve. Among the models, the Customized Tuned Inception V3 (CTInceptionV3) model, optimized through random search, demonstrated outstanding performance. It achieved the highest accuracy (91%), precision (91%), recall (91%), and F1-score (91%), showcasing its superior ability to accurately identify and classify potato pests. |
| first_indexed | 2024-03-12T14:26:29Z |
| format | Article |
| id | doaj.art-96734bc72a62456b9184f1849388cc42 |
| institution | Directory Open Access Journal |
| issn | 2772-3755 |
| language | English |
| last_indexed | 2024-03-12T14:26:29Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj.art-96734bc72a62456b9184f1849388cc422023-08-18T04:31:41ZengElsevierSmart Agricultural Technology2772-37552023-10-015100297PotatoPestNet: A CTInceptionV3-RS-based neural network for accurate identification of potato pestsMd. Simul Hasan Talukder0Rejwan Bin Sulaiman1Mohammad Raziuddin Chowdhury2Musarrat Saberin Nipun3Taminul Islam4Bangladesh Atomic Energy Regulatory Authority, BangladeshNorthumbria University, UK; Corresponding author.Jahangirnagar University, BangladeshBrunel University London, UKDepartment of Computer Science and Engineering, Daffodil International University, BangladeshPotatoes are the third-largest food crop globally, but their production frequently encounters difficulties because of aggressive pest infestations. Early classification those potato pests plays an important role in the detection and prevention of their notorious attack. The aim of this study is to investigate the various types and characteristics of these pests and propose an efficient PotatoPestNet AI-based automatic potato pest identification system. To accomplish this, we curated a reliable dataset consisting of eight types of potato pests. We leveraged the power of transfer learning by employing five customized, pre-trained transfer learning models: CMobileNetV2, CNASLargeNet, CXception, CDenseNet201, and CInceptionV3, in proposing a robust PotatoPestNet model to accurately classify potato pests. To improve the models' performance, we applied various augmentation techniques, incorporated a global average pooling layer, and implemented proper regularization methods. To further enhance the performance of the models, we utilized random search (RS) optimization for hyperparameter tuning. This optimization technique played a significant role in fine-tuning the models and achieving improved performance. We evaluated the models both visually and quantitatively, utilizing different evaluation metrics. The robustness of the models in handling imbalanced datasets was assessed using the Receiver Operating Characteristic (ROC) curve. Among the models, the Customized Tuned Inception V3 (CTInceptionV3) model, optimized through random search, demonstrated outstanding performance. It achieved the highest accuracy (91%), precision (91%), recall (91%), and F1-score (91%), showcasing its superior ability to accurately identify and classify potato pests.http://www.sciencedirect.com/science/article/pii/S2772375523001260PotatopestnetPotato pestTunningTransfer learningDeep LearningRandom Search |
| spellingShingle | Md. Simul Hasan Talukder Rejwan Bin Sulaiman Mohammad Raziuddin Chowdhury Musarrat Saberin Nipun Taminul Islam PotatoPestNet: A CTInceptionV3-RS-based neural network for accurate identification of potato pests Smart Agricultural Technology Potatopestnet Potato pest Tunning Transfer learning Deep Learning Random Search |
| title | PotatoPestNet: A CTInceptionV3-RS-based neural network for accurate identification of potato pests |
| title_full | PotatoPestNet: A CTInceptionV3-RS-based neural network for accurate identification of potato pests |
| title_fullStr | PotatoPestNet: A CTInceptionV3-RS-based neural network for accurate identification of potato pests |
| title_full_unstemmed | PotatoPestNet: A CTInceptionV3-RS-based neural network for accurate identification of potato pests |
| title_short | PotatoPestNet: A CTInceptionV3-RS-based neural network for accurate identification of potato pests |
| title_sort | potatopestnet a ctinceptionv3 rs based neural network for accurate identification of potato pests |
| topic | Potatopestnet Potato pest Tunning Transfer learning Deep Learning Random Search |
| url | http://www.sciencedirect.com/science/article/pii/S2772375523001260 |
| work_keys_str_mv | AT mdsimulhasantalukder potatopestnetactinceptionv3rsbasedneuralnetworkforaccurateidentificationofpotatopests AT rejwanbinsulaiman potatopestnetactinceptionv3rsbasedneuralnetworkforaccurateidentificationofpotatopests AT mohammadraziuddinchowdhury potatopestnetactinceptionv3rsbasedneuralnetworkforaccurateidentificationofpotatopests AT musarratsaberinnipun potatopestnetactinceptionv3rsbasedneuralnetworkforaccurateidentificationofpotatopests AT taminulislam potatopestnetactinceptionv3rsbasedneuralnetworkforaccurateidentificationofpotatopests |