Testing the Suitability of Automated Machine Learning for Weeds Identification
In the past years, several machine-learning-based techniques have arisen for providing effective crop protection. For instance, deep neural networks have been used to identify different types of weeds under different real-world conditions. However, these techniques usually require extensive involvem...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | AI |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-2688/2/1/4 |
| _version_ | 1797412322465021952 |
|---|---|
| author | Borja Espejo-Garcia Ioannis Malounas Eleanna Vali Spyros Fountas |
| author_facet | Borja Espejo-Garcia Ioannis Malounas Eleanna Vali Spyros Fountas |
| author_sort | Borja Espejo-Garcia |
| collection | DOAJ |
| description | In the past years, several machine-learning-based techniques have arisen for providing effective crop protection. For instance, deep neural networks have been used to identify different types of weeds under different real-world conditions. However, these techniques usually require extensive involvement of experts working iteratively in the development of the most suitable machine learning system. To support this task and save resources, a new technique called Automated Machine Learning has started being studied. In this work, a complete open-source Automated Machine Learning system was evaluated with two different datasets, (i) The Early Crop Weeds dataset and (ii) the Plant Seedlings dataset, covering the weeds identification problem. Different configurations, such as the use of plant segmentation, the use of classifier ensembles instead of Softmax and training with noisy data, have been compared. The results showed promising performances of 93.8% and 90.74% F<sub>1</sub> score depending on the dataset used. These performances were aligned with other related works in AutoML, but they are far from machine-learning-based systems manually fine-tuned by human experts. From these results, it can be concluded that finding a balance between manual expert work and Automated Machine Learning will be an interesting path to work in order to increase the efficiency in plant protection. |
| first_indexed | 2024-03-09T05:00:31Z |
| format | Article |
| id | doaj.art-d9f8c72668554c7cb12b5a9ea2d3ec68 |
| institution | Directory Open Access Journal |
| issn | 2673-2688 |
| language | English |
| last_indexed | 2024-03-09T05:00:31Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AI |
| spelling | doaj.art-d9f8c72668554c7cb12b5a9ea2d3ec682023-12-03T13:00:55ZengMDPI AGAI2673-26882021-02-0121344710.3390/ai2010004Testing the Suitability of Automated Machine Learning for Weeds IdentificationBorja Espejo-Garcia0Ioannis Malounas1Eleanna Vali2Spyros Fountas3Agricultural University of Athens, 11855 Athens, GreeceAgricultural University of Athens, 11855 Athens, GreeceAgricultural University of Athens, 11855 Athens, GreeceAgricultural University of Athens, 11855 Athens, GreeceIn the past years, several machine-learning-based techniques have arisen for providing effective crop protection. For instance, deep neural networks have been used to identify different types of weeds under different real-world conditions. However, these techniques usually require extensive involvement of experts working iteratively in the development of the most suitable machine learning system. To support this task and save resources, a new technique called Automated Machine Learning has started being studied. In this work, a complete open-source Automated Machine Learning system was evaluated with two different datasets, (i) The Early Crop Weeds dataset and (ii) the Plant Seedlings dataset, covering the weeds identification problem. Different configurations, such as the use of plant segmentation, the use of classifier ensembles instead of Softmax and training with noisy data, have been compared. The results showed promising performances of 93.8% and 90.74% F<sub>1</sub> score depending on the dataset used. These performances were aligned with other related works in AutoML, but they are far from machine-learning-based systems manually fine-tuned by human experts. From these results, it can be concluded that finding a balance between manual expert work and Automated Machine Learning will be an interesting path to work in order to increase the efficiency in plant protection.https://www.mdpi.com/2673-2688/2/1/4automated machine learningAutoMLweeds identificationdeep learningprecision agriculture |
| spellingShingle | Borja Espejo-Garcia Ioannis Malounas Eleanna Vali Spyros Fountas Testing the Suitability of Automated Machine Learning for Weeds Identification AI automated machine learning AutoML weeds identification deep learning precision agriculture |
| title | Testing the Suitability of Automated Machine Learning for Weeds Identification |
| title_full | Testing the Suitability of Automated Machine Learning for Weeds Identification |
| title_fullStr | Testing the Suitability of Automated Machine Learning for Weeds Identification |
| title_full_unstemmed | Testing the Suitability of Automated Machine Learning for Weeds Identification |
| title_short | Testing the Suitability of Automated Machine Learning for Weeds Identification |
| title_sort | testing the suitability of automated machine learning for weeds identification |
| topic | automated machine learning AutoML weeds identification deep learning precision agriculture |
| url | https://www.mdpi.com/2673-2688/2/1/4 |
| work_keys_str_mv | AT borjaespejogarcia testingthesuitabilityofautomatedmachinelearningforweedsidentification AT ioannismalounas testingthesuitabilityofautomatedmachinelearningforweedsidentification AT eleannavali testingthesuitabilityofautomatedmachinelearningforweedsidentification AT spyrosfountas testingthesuitabilityofautomatedmachinelearningforweedsidentification |