Data mining for ranking sorghum seed lots

Luciana Dias Rocha; Gizele Ingrid Gadotti; Ruan Bernardy; Romario de Mesquita Pinheiro; Rita de Cassia Mota Monteiro

doi:10.1590/1983-21252023v36n224rc

Authors

Luciana Dias Rocha Faculty of Agronomy Eliseu Maciel, Universidade Federal de Pelotas, Pelotas, RS https://orcid.org/0000-0003-0974-1289
Gizele Ingrid Gadotti Engineering Center, Universidade Federal de Pelotas, Pelotas, RS https://orcid.org/0000-0001-9545-6577
Ruan Bernardy Engineering Center, Universidade Federal de Pelotas, Pelotas, RS https://orcid.org/0000-0001-9285-1993
Romario de Mesquita Pinheiro Faculty of Agronomy Eliseu Maciel, Universidade Federal de Pelotas, Pelotas, RS https://orcid.org/0000-0003-0484-8351
Rita de Cassia Mota Monteiro Faculty of Agronomy Eliseu Maciel, Universidade Federal de Pelotas, Pelotas, RS https://orcid.org/0000-0001-9342-2779

DOI:

https://doi.org/10.1590/1983-21252023v36n224rc

Keywords:

Quality, Post-harvest technology, Artificial intelligence. Image processing. Seeds.

Abstract

The ranking of seed lots is a fundamental process for all companies in the seed industry. This work aims to demonstrate data mining methods for ranking sorghum seed lots during the seed processing through analysis of quality control data. Germination and cold tests were performed to verify the physiological quality of the lots. Seed samples from each lot were evaluated in two moments: post-cleaning and finished product (ready for marketing). The results after pre-processing totaled 188 rows of data with six attributes, encompassing 150 lots accepted for marketing, 6 rejected, and 32 intermediate lots. The classifiers used were J48, Random Forest, Classification Via Regression, Naive Bayes, Multilayer Perceptron, and IBk. The Resample filter was used for adjustment of the data. The k-fold technique was used for training, with ten folds. The metrics of Accuracy, Precision, Recall, F-measure, and ROC Area were used to verify the accuracy of the algorithms. The results obtained were used to determine the best machine-learning algorithm. IBk and J48 presented the highest accuracy of data; the IBk technique presented the best results. The Resample filter was essential for solving the data imbalance problem. Sorghum seed lots can be classified with great accuracy and precision through artificial intelligence and machine learning technique.

Downloads

Download data is not yet available.

References

BENIWAL, S.; ARORA, J. Classification and feature selection techniques in data mining, International Journal of Engineering Research & Technology, 1: 1-6, 2012.

BRASIL. Ministério da Agricultura, Pecuária e Abastecimento. Regras para análise de sementes. 1. ed. Brasília, DF: MAPA, 2009. 398 p.

BRASIL. Ministério da Agricultura, Pecuária e Abastecimento. Instrução Normativa nº45 de 17 de setembro de 2013. 2013. Disponível em: <https://www.gov.br/agricultura/pt-br/assuntos/insumos-agropecuarios

/insumos-agricolas/sementes-e-mudas/publicacoes-sementes-e-mudas/ copy_of_INN45de17desetembrode2013.pdf>. Acesso em: 22 out. 2021.

CAÑIZARES, L. C. C. et al. Tecnologia e industrialização de grãos de canola, girassol, linhaça, algodão, amendoim, sorgo, milho pipoca, lentilha e ervilha. In: FERREIRA, C. D.; OLIVEIRA, M. de; ZIEGLER, V. (Eds.). Tecnologia industrial de grãos e derivados. 1 ed. Curitiba, PR: Editora CRV, 2020. v. 1, cap. 9, p. 225-276.

CARVALHO, N. M.; NAKAGAWA, J. Sementes: ciência, tecnologia e produção. 5. ed. Jaboticabal, SP: Funep, 2012. 590 p.

GADOTTI, G. I. et al. Aprendizado de máquina para classificação de lotes de sementes de soja. Engenharia Agrícola, 42: e20210101, 2022a.

GADOTTI, G. I. et al. Prediction of ranking of lots of corn seeds by artificial intelligence. Engenharia Agrícola, 42: e20210005, 2022b.

JAGTAP, S. T. et al. Towards application of various machine learning techniques in agriculture. Materials Today, 51: 793-797, 2022.

JIN, B. et al. Determination of viability and vigor of naturally-aged rice seeds using hyperspectral imaging with machine learning. Infrared Physics & Technology, 122: e104097, 2022.

LEVER, J.; KRZYWINSKI, M.; ALTMAN, N. Classification evaluation. Nature Methods, 13: 603-604, 2016.

MARCOS-FILHO, J. Seed vigor testing: an overview of the past, present and future perspective. Scientia Agricola, 72: 363-374, 2015.

MARCOS-FILHO, J. Teste de envelhecimento acelerado. In: KRZYZANOWSKI, F. C. et al. (Eds.). Vigor de sementes: conceitos e testes. Londrina, PR: ABRATES, 2021. cap. 2, p. 1-24.

MEDEIROS, A. D. et al. Interactive machine learning for soybean seed and seedling quality classification. Scientific Reports, 10: 1-10, 2020.

MONARD, M. C.; BARANAUSKAS, J. A. Conceitos sobre aprendizado de máquina. In: SOLANGE, O. R. (Ed.) Sistemas Inteligentes: fundamentos e aplicações. Barueri, SP: Manole Ltda, 2003. v. 1, cap. 4, p. 89-114.

OLIVEIRA, L. M. et al. Qualidade de sementes de feijão-caupi tratadas com produtos químicos e armazenadas em condições controladas e não controladas de temperatura e umidade. Semina: Ciências Agrárias, 36: 1263-1276, 2015.

PEREIRA FILHO, I. A.; RODRIGUES, J. A. S. O produtor pergunta, a Embrapa responde. Brasília, DF: Embrapa Cerrados, 2015. 332 p.

PINHEIRO, R. M. et al. Inteligência artificial na agricultura com aplicabilidade no setor sementeiro. Diversitas Journal, 6: 2984-2995, 2021.

ROHR, L. A. et al. Soybean seeds treated with zinc evaluated by X-ray micro-fluorescence spectroscopy. Scientia Agricola, 80: e20210131, 2023.

RUTAYISIRE, A. et al. Response of sorghum to cold stress at early developmental stage. International Journal of Agronomy, 2021: 1-10, 2021.

SCHEEREN, B. R. et al. Qualidade fisiológica e produtividade de sementes de soja. Revista Brasileira de Sementes, 32: 35-41, 2010.

SILVA, R. S. et al. Qualidade fisiológica de sementes de sorgo biomassa (Sorghum bicolor L. Moench). Revista Espacios, 37: 12-19, 2016.

TILLMANN, M. A. A.; TUNES, L. M.; ALMEIDA, A. S. Análise de Sementes. In: PESKE, S. T.; VILLELA, F. A.; MENEGHELLO, G. E. (Eds.). Sementes: fundamentos científicos e tecnológicos. Pelotas, RS: Becker, 2019. v. 4, cap. 3, p. 147–257.

VASCONCELOS, L. M. R.; CARVALHO, C. L. de. Aplicação de regras de associação para mineração de dados na web. Technical Report, 1: 1-20, 2018.

WITTEN, I. H.; FRANK, E.; HALL, M. A. Data Mining: pratical machine learning tools and techniques. 3. ed. Burlington: Morgan Kaufmann Publishers, 2011. 665 p.