| dc.creator | Ahumada García, Roberto | |
| dc.creator | Zabala-Blanco, David | |
| dc.creator | Soto, Ismael | |
| dc.creator | López-Cortés, Xaviera A. | |
| dc.creator | Barrientos, Ricardo | |
| dc.date | 2023-03-08T13:27:46Z | |
| dc.date | 2023-03-08T13:27:46Z | |
| dc.date | 2022 | |
| dc.date.accessioned | 2024-05-02T20:30:38Z | |
| dc.date.available | 2024-05-02T20:30:38Z | |
| dc.identifier | http://repositorio.ucm.cl/handle/ucm/4493 | |
| dc.identifier.uri | https://repositorioslatinoamericanos.uchile.cl/handle/2250/9274737 | |
| dc.description | Diseases in agricultural crops are a risk for fruit productivity and quality. Chile is a fruit exporting country; that needs the development of technologies for diseases prevention and treatment. Farmers have been exploring how to use Artificial Intelligence to solve problems. Nowadays, deep artificial intelligence models have a great performance. However, farmers need to reduce economic costs, thus, it is important to explore artificial intelligence models. These models should be easy to implement on low-cost electronic devices. Extreme Learning Machines (ELM) stand out for their fast and stable training, and the models’ implementation is accessible to all public. This work presents the first approach to the binary classification of diseased and healthy apple leaves through ELM. In this research, it was used: 1) standard ELM; 2) regularized ELM; 3) weighted ELM. The weighted ELM performance reaches an accuracy = 0.66 and geometric mean = 0.6. The ELM models results show that are potential and feasible to classify complex images of diseased and healthy leaves. However, ELMs do not perform as well with this data compared to CNN. | |
| dc.language | en | |
| dc.rights | Atribución-NoComercial-SinDerivadas 3.0 Chile | |
| dc.rights | http://creativecommons.org/licenses/by-nc-nd/3.0/cl/ | |
| dc.source | International Conference on Automation/XXV Congress of the Chilean Association of Automatic Control (ICA-ACCA), Curicó, Chile, 1-7 | |
| dc.subject | Training | |
| dc.subject | Productivity | |
| dc.subject | Performance evaluation | |
| dc.subject | Costs | |
| dc.subject | Extreme learning machines | |
| dc.subject | Biological system modeling | |
| dc.subject | Crops | |
| dc.title | Classification of diseased and healthy apple leaves through extreme learning machines | |
| dc.type | Article | |
