Feature selection and performance assessment of machine learning algorithms for sunflower oil yield prediction
2022
Аутори
Cvejić, SandraHrnjaković, Olivera
Jocković, Milan
Kupusinac, Aleksandar
Doroslovački, Ksenija
Radeka, Ilija
Jocić, Siniša
Miladinović, Dragana
Miklič, Vladimir
Конференцијски прилог (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
Rapid innovation and liberalized market economy in agriculture require a fast and accurate Sunflower Oil Yield Prediction (SOYP). SOYP is a complex task since it depends on multiple factors. Machine Learning (ML) algorithms and the selection of important features could play a significant role in an accurate oil yield prediction. In this study, we developed ML models to predict oil yield by using two different sets of features. Moreover, we evaluated the most relevant features for accurate SOYP. ML algorithms that were used and compared, were Artificial Neural Network, Support Vector Regression, K-Nearest Neighbour, and Random Forest Regressor (RFR). The dataset consisted of 1250 samples of which 70% were randomly selected and were used to train the model and 30% were used to test the model and assess its performance. The results show that the RFR algorithm achieved the highest accuracy for both feature subsets. These research results indicate that ML has great potential for application... as an alternative method for genotypic selection.
Кључне речи:
machine learning / algorithms / sunflower / oil yield / prediction modelsИзвор:
Proceedings, 20th International Sunflower Conference, 20-23 June 2022, Novi Sad, Serbia, 2022, 105-105Издавач:
- Paris : International Sunflower Association
- Novi Sad : Institute of Field and Vegetable Crops
Финансирање / пројекти:
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200032 (Научни институт за ратарство и повртарство, Нови Сад) (RS-MESTD-inst-2020-200032)
- SmartSun - Creating climate smart sunflower for future challenges (RS-ScienceFundRS-Ideje-7732457)
- Climate Crops - Centre of Excellence for Innovations in Breeding of Climate-Resilient Crops, Institute of Field and Vegetable Crops
Колекције
Институција/група
FiVeRTY - CONF AU - Cvejić, Sandra AU - Hrnjaković, Olivera AU - Jocković, Milan AU - Kupusinac, Aleksandar AU - Doroslovački, Ksenija AU - Radeka, Ilija AU - Jocić, Siniša AU - Miladinović, Dragana AU - Miklič, Vladimir PY - 2022 UR - http://fiver.ifvcns.rs/handle/123456789/2889 AB - Rapid innovation and liberalized market economy in agriculture require a fast and accurate Sunflower Oil Yield Prediction (SOYP). SOYP is a complex task since it depends on multiple factors. Machine Learning (ML) algorithms and the selection of important features could play a significant role in an accurate oil yield prediction. In this study, we developed ML models to predict oil yield by using two different sets of features. Moreover, we evaluated the most relevant features for accurate SOYP. ML algorithms that were used and compared, were Artificial Neural Network, Support Vector Regression, K-Nearest Neighbour, and Random Forest Regressor (RFR). The dataset consisted of 1250 samples of which 70% were randomly selected and were used to train the model and 30% were used to test the model and assess its performance. The results show that the RFR algorithm achieved the highest accuracy for both feature subsets. These research results indicate that ML has great potential for application as an alternative method for genotypic selection. PB - Paris : International Sunflower Association PB - Novi Sad : Institute of Field and Vegetable Crops C3 - Proceedings, 20th International Sunflower Conference, 20-23 June 2022, Novi Sad, Serbia T1 - Feature selection and performance assessment of machine learning algorithms for sunflower oil yield prediction EP - 105 SP - 105 UR - https://hdl.handle.net/21.15107/rcub_fiver_2889 ER -
@conference{ author = "Cvejić, Sandra and Hrnjaković, Olivera and Jocković, Milan and Kupusinac, Aleksandar and Doroslovački, Ksenija and Radeka, Ilija and Jocić, Siniša and Miladinović, Dragana and Miklič, Vladimir", year = "2022", abstract = "Rapid innovation and liberalized market economy in agriculture require a fast and accurate Sunflower Oil Yield Prediction (SOYP). SOYP is a complex task since it depends on multiple factors. Machine Learning (ML) algorithms and the selection of important features could play a significant role in an accurate oil yield prediction. In this study, we developed ML models to predict oil yield by using two different sets of features. Moreover, we evaluated the most relevant features for accurate SOYP. ML algorithms that were used and compared, were Artificial Neural Network, Support Vector Regression, K-Nearest Neighbour, and Random Forest Regressor (RFR). The dataset consisted of 1250 samples of which 70% were randomly selected and were used to train the model and 30% were used to test the model and assess its performance. The results show that the RFR algorithm achieved the highest accuracy for both feature subsets. These research results indicate that ML has great potential for application as an alternative method for genotypic selection.", publisher = "Paris : International Sunflower Association, Novi Sad : Institute of Field and Vegetable Crops", journal = "Proceedings, 20th International Sunflower Conference, 20-23 June 2022, Novi Sad, Serbia", title = "Feature selection and performance assessment of machine learning algorithms for sunflower oil yield prediction", pages = "105-105", url = "https://hdl.handle.net/21.15107/rcub_fiver_2889" }
Cvejić, S., Hrnjaković, O., Jocković, M., Kupusinac, A., Doroslovački, K., Radeka, I., Jocić, S., Miladinović, D.,& Miklič, V.. (2022). Feature selection and performance assessment of machine learning algorithms for sunflower oil yield prediction. in Proceedings, 20th International Sunflower Conference, 20-23 June 2022, Novi Sad, Serbia Paris : International Sunflower Association., 105-105. https://hdl.handle.net/21.15107/rcub_fiver_2889
Cvejić S, Hrnjaković O, Jocković M, Kupusinac A, Doroslovački K, Radeka I, Jocić S, Miladinović D, Miklič V. Feature selection and performance assessment of machine learning algorithms for sunflower oil yield prediction. in Proceedings, 20th International Sunflower Conference, 20-23 June 2022, Novi Sad, Serbia. 2022;:105-105. https://hdl.handle.net/21.15107/rcub_fiver_2889 .
Cvejić, Sandra, Hrnjaković, Olivera, Jocković, Milan, Kupusinac, Aleksandar, Doroslovački, Ksenija, Radeka, Ilija, Jocić, Siniša, Miladinović, Dragana, Miklič, Vladimir, "Feature selection and performance assessment of machine learning algorithms for sunflower oil yield prediction" in Proceedings, 20th International Sunflower Conference, 20-23 June 2022, Novi Sad, Serbia (2022):105-105, https://hdl.handle.net/21.15107/rcub_fiver_2889 .