Federated Learning: Crop classification in a smart farm decentralised network
In this paper, the application of federated learning to smart farming has been investigated. The Federated averaging model has been used to carry out crop classification using climatic parameters as independent variables and crop types as labels. The decentralised machine learning models have been u...
| 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/S2772375523001065 |
| _version_ | 1797782602639212544 |
|---|---|
| author | Godwin Idoje Tasos Dagiuklas Muddesar Iqbal |
| author_facet | Godwin Idoje Tasos Dagiuklas Muddesar Iqbal |
| author_sort | Godwin Idoje |
| collection | DOAJ |
| description | In this paper, the application of federated learning to smart farming has been investigated. The Federated averaging model has been used to carry out crop classification using climatic parameters as independent variables and crop types as labels. The decentralised machine learning models have been used to predict chickpea crops. Through experimentation, it has been observed the model converges when learning rates of 0.001 and 0.01 are considered using the Stochastic gradient descent (SGD) and the Adam optimizers. The model using the Adam optimizer converged faster than the SGD optimizer, this was achieved after 100 epochs. Analysis from the farm dataset has shown that the decentralised models achieve faster convergence and higher accuracy than the centralised network models. |
| first_indexed | 2024-03-13T00:13:16Z |
| format | Article |
| id | doaj.art-1d30526e7864467096bdbfa9fb7d9d83 |
| institution | Directory Open Access Journal |
| issn | 2772-3755 |
| language | English |
| last_indexed | 2024-03-13T00:13:16Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj.art-1d30526e7864467096bdbfa9fb7d9d832023-07-12T04:20:44ZengElsevierSmart Agricultural Technology2772-37552023-10-015100277Federated Learning: Crop classification in a smart farm decentralised networkGodwin Idoje0Tasos Dagiuklas1Muddesar Iqbal2Corresponding author at: Computer Science and Informatics Department, London South Bank University, 103 Borough Road, London, Se1 0AA, UK.; Computer Science and Informatics Division, London South Bank University, United KingdomComputer Science and Informatics Division, London South Bank University, United KingdomComputer Science and Informatics Division, London South Bank University, United KingdomIn this paper, the application of federated learning to smart farming has been investigated. The Federated averaging model has been used to carry out crop classification using climatic parameters as independent variables and crop types as labels. The decentralised machine learning models have been used to predict chickpea crops. Through experimentation, it has been observed the model converges when learning rates of 0.001 and 0.01 are considered using the Stochastic gradient descent (SGD) and the Adam optimizers. The model using the Adam optimizer converged faster than the SGD optimizer, this was achieved after 100 epochs. Analysis from the farm dataset has shown that the decentralised models achieve faster convergence and higher accuracy than the centralised network models.http://www.sciencedirect.com/science/article/pii/S2772375523001065Federated LearningClassifier chain Gaussian (CCGNB)Binary Relevance Gaussian (BRGNB)Label powerset Gaussian Naïve Bayes (LPGNB) |
| spellingShingle | Godwin Idoje Tasos Dagiuklas Muddesar Iqbal Federated Learning: Crop classification in a smart farm decentralised network Smart Agricultural Technology Federated Learning Classifier chain Gaussian (CCGNB) Binary Relevance Gaussian (BRGNB) Label powerset Gaussian Naïve Bayes (LPGNB) |
| title | Federated Learning: Crop classification in a smart farm decentralised network |
| title_full | Federated Learning: Crop classification in a smart farm decentralised network |
| title_fullStr | Federated Learning: Crop classification in a smart farm decentralised network |
| title_full_unstemmed | Federated Learning: Crop classification in a smart farm decentralised network |
| title_short | Federated Learning: Crop classification in a smart farm decentralised network |
| title_sort | federated learning crop classification in a smart farm decentralised network |
| topic | Federated Learning Classifier chain Gaussian (CCGNB) Binary Relevance Gaussian (BRGNB) Label powerset Gaussian Naïve Bayes (LPGNB) |
| url | http://www.sciencedirect.com/science/article/pii/S2772375523001065 |
| work_keys_str_mv | AT godwinidoje federatedlearningcropclassificationinasmartfarmdecentralisednetwork AT tasosdagiuklas federatedlearningcropclassificationinasmartfarmdecentralisednetwork AT muddesariqbal federatedlearningcropclassificationinasmartfarmdecentralisednetwork |