Application of unsupervised learning in the early detection of late blight in potato crops using image processing
Aplicación del aprendizaje no supervisado en la detección temprana del tizón tardío en cultivos de papa mediante procesamiento de imágenes
| dc.creator | Garcia Ariza, Juana Valentina | |
| dc.creator | SUAREZ BARON, MARCO JAVIER | |
| dc.creator | JUNCO ORDUZ, EDMUNDO ARTURO | |
| dc.creator | González-Sanabria, Juan-Sebastián | |
| dc.date | 2023-04-17T20:24:48Z | |
| dc.date | 2023-04-17T20:24:48Z | |
| dc.date | 2022 | |
| dc.date.accessioned | 2023-10-03T19:31:25Z | |
| dc.date.available | 2023-10-03T19:31:25Z | |
| dc.identifier | J. García-Ariza, M. Suarez-Barón, E. Junco-Orduz & González-Sanabria, “Application of Unsupervised Learning in the Early Detection of Late Blight in Potato Crops Using Image Processing”, INGECUC, vol. 18, no. 2, pp. 89–100. DOI: http://doi.org/10.17981/ingecuc.18.2.2022.07 | |
| dc.identifier | 0122-6517 | |
| dc.identifier | https://hdl.handle.net/11323/9988 | |
| dc.identifier | 10.17981/ingecuc.18.2.2022.07 | |
| dc.identifier | 2382-4700 | |
| dc.identifier | Corporación Universidad de la Costa | |
| dc.identifier | REDICUC - Repositorio CUC | |
| dc.identifier | https://repositorio.cuc.edu.co/ | |
| dc.identifier.uri | https://repositorioslatinoamericanos.uchile.cl/handle/2250/9170389 | |
| dc.description | Introducción— La detección automática puede ser útil en la búsqueda de grandes campos de cultivo simplemente detectando la enfermedad con los síntomas que aparecen en la hoja. Objetivo— Este artículo presenta la aplicación de técnicas de aprendizaje automático destinadas a detectar la enfermedad del tizón tardío utilizando métodos de aprendizaje no supervisados como K-Means y agrupamiento jerárquico. Método— La metodología utilizada está compuesta por las siguientes fases— adquisición del dataset, procesamiento de la imagen, extracción de características, selección de características, implementación del modelo de aprendizaje, medición del rendimiento del algoritmo, finalmente se obtuvo una tasa de acierto del 68.24% siendo este el mejor resultado de los algoritmos de aprendizaje no supervisados implementados, usando 3 clusters para el agrupamiento. Resultados— De acuerdo con los resultados obtenidos, se puede evaluar el desempeño del algoritmo K-Means, es decir, 202 aciertos y 116 errores. Conclusiones— Los algoritmos de aprendizaje no supervisado son muy eficientes al momento de procesar una gran cantidad de datos, en este caso una gran cantidad de imágenes sin necesidad de etiquetas predefinidas, su uso para solucionar problemas locales como afectaciones de tizón tardío en cultivos de papa es novedoso. | |
| dc.description | Introduction— Automatic detection can be useful in the search of large crop fields by simply detecting the disease with the symptoms appearing on the leaf. Objective— This paper presents the application of machine learning techniques aimed at detecting late blight disease using unsupervised learning methods such as K-Means and hierarchical clustering. Method— The methodology used is composed by the following phases— acquisition of the dataset, image processing, feature extraction, feature selection, implementation of the learning model, performance measurement of the algorithm, finally a 68.24% hit rate was obtained being this the best result of the unsupervised learning algorithms implemented, using 3 clusters for clustering. Results— According to the results obtained, the performance of the K-Means algorithm can be evaluated, i.e. 202 hits and 116 misses. Conclusions— Unsupervised learning algorithms are very efficient when processing a large amount of data, in this case a large amount of images without the need for predefined labels, its use to solve local problems such as late blight affectations in potato crops are novel. | |
| dc.format | 12 páginas | |
| dc.format | application/pdf | |
| dc.format | application/pdf | |
| dc.language | eng | |
| dc.publisher | Corporación Universidad de la Costa | |
| dc.publisher | Colombia | |
| dc.relation | INGE CUC | |
| dc.relation | [1] Minagricultura, Estrategia de ordenamiento de la producción cadena productiva de la papa y su industria. BOG, CO: Minagricultura, 2019. Recuperado de https://sioc.minagricultura.gov.co/Papa/Normatividad/Plan%20de%20Ordenamiento%20papa%202019-2023.pdf | |
| dc.relation | [2] C. Ortiz, “Desarrollo de una herramienta computacional basada en redes neuronales para el diagnóstico del tizón tardío en cultivos de papa”, Proyecto de grado, Fac Ing Mec Electron Biomed, UAN, BOG, CO, 2021. Disponible en http://repositorio.uan.edu.co/handle/123456789/5156 | |
| dc.relation | [3] D. Rodríguez, M. Rico, L. Rodríguez y C. Ñústez, “Efecto de diferentes niveles y épocas de defoliación sobre el rendimiento de la papa (Solanum tuberosum cv. Parda Pastusa),” Rev Fac Nal Agr MED, vol. 63, no. 2, pp. 5521–5531, Sept. 2009. Disponibl en https://repositorio.unal.edu.co/handle/unal/37086 | |
| dc.relation | [4] A.-K. Mahlein, E.-C. Oerke, U. Steiner & H.-W. Dehne, “Recent advances in sensing plant diseases for precision crop protection,” Eur J Plant Pathol, vol. 133, no. 1, pp. 197–209, Mar. 2012. https://doi. org/10.1007/s10658-011-9878-z | |
| dc.relation | [5] S. Maity, S. Sarkar, A. Tapadar, A. Dutta, S. Biswas, S. Nayek & P. Saha, “Fault Area Detection in Leaf Diseases Using K-Means Clustering,” presented 2nd International Conference on Trends in Electronics and Informatics, ICOEI, TIRUN, IN, 11-12 May. 2018. https://doi.org/10.1109/ICOEI.2018.8553913 | |
| dc.relation | [6] J. Johnson, G. Sharma, S. Srinivasan, S. Masakapalli, S. Sharma, J. Sharma & V. Dua, “Enhanced field-based detection of potato blight in complex backgrounds using deep learning,” Plant Phenomics, pp. 1–13, May. 2021. https://doi.org/10.34133/2021/9835724 | |
| dc.relation | [7] P. Sharma, Singh, B. & R. Singh, “Prediction of Potato Late Blight Disease Based Upon Weather Parameters Using Artificial Neural Network Approach,” presented 9th International Conference on Computing, Communication and Networking Technologies, ICCCNT, BLR, IND, 10-12 July 2018. https://doi. org/10.1109/ICCCNT.2018.8494024 | |
| dc.relation | [8] R. Hasan, S. Yusuf & L. Alzubaidi, “Review of the state of the art of deep learning for plant diseases: A broad analysis and discussion,” Plants, vol. 9, no. 10, pp. 1–25, Oct. 2020. https://doi.org/10.3390/ plants9101302 | |
| dc.relation | [9] L. Li, S. Zhang & B. Wang, “Plant Disease Detection and Classification by Deep Learning - A Review,” IEEE Access, vol. 9, pp. 56683–56698, Apr. 2021. https://doi.org/10.1109/ACCESS.2021.3069646 | |
| dc.relation | [10] H. Pardede, E. Suryawati, R. Sustika & V. Zilvan, “Unsupervised Convolutional Autoencoder-Based Feature Learning for Automatic Detection of Plant Diseases,” presented 2018 International Conference on Computer, Control, Informatics and its Applications, IC3INA, TANG, ID, 1-2 Nov. 2018. https://doi. org/10.1109/IC3INA.2018.8629518 | |
| dc.relation | [11] B. Małysiak-Mrozek, D. Mrozek & S. Kozielski, “Data Grouping Process in Extended SQL Language Containing Fuzzy Elements,” in K.A. Cyran, S. Kozielski, J. F. Peters, U. Stańczyk & A. Wakulicz-Deja, Man-Machine Interactions, vol. 59, BE, DE, Springer, 2009, pp. 247–256. https://doi.org/10.1007/978-3- 642-00563-3_25 | |
| dc.relation | [12] Z. Khan, T. Akram, S. Naqvi, S. Haider, M. Kamran & N. Muhammad, “Automatic detection of plant diseases; utilizing an unsupervised cascaded design,” presented 15th International Bhurban Conference on Applied Sciences and Technology, IBCAST, ISB, PK, 9-13 Jan. 2018. https://doi.org/10.1109/IBCAST.2018.8312246 | |
| dc.relation | 100 | |
| dc.relation | 89 | |
| dc.relation | 2 | |
| dc.relation | 18 | |
| dc.rights | Derechos de autor 2022 INGE CUC | |
| dc.rights | Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0) | |
| dc.rights | https://creativecommons.org/licenses/by-nc-nd/4.0/ | |
| dc.rights | info:eu-repo/semantics/openAccess | |
| dc.rights | http://purl.org/coar/access_right/c_abf2 | |
| dc.source | https://revistascientificas.cuc.edu.co/ingecuc/article/view/4468 | |
| dc.subject | Aprendizaje automático | |
| dc.subject | Aprendizaje no supervisado | |
| dc.subject | Agrupamiento jerárquico | |
| dc.subject | Tizón tardío | |
| dc.subject | K-Means | |
| dc.subject | Machine learning | |
| dc.subject | Unsupervised learning | |
| dc.subject | Hierarchical clustering | |
| dc.subject | Late blight | |
| dc.title | Application of unsupervised learning in the early detection of late blight in potato crops using image processing | |
| dc.title | Aplicación del aprendizaje no supervisado en la detección temprana del tizón tardío en cultivos de papa mediante procesamiento de imágenes | |
| dc.type | Artículo de revista | |
| dc.type | http://purl.org/coar/resource_type/c_6501 | |
| dc.type | http://purl.org/coar/resource_type/c_2df8fbb1 | |
| dc.type | Text | |
| dc.type | info:eu-repo/semantics/article | |
| dc.type | http://purl.org/redcol/resource_type/ART | |
| dc.type | info:eu-repo/semantics/publishedVersion | |
| dc.type | http://purl.org/coar/version/c_970fb48d4fbd8a85 |