Soil type classification and estimation of soil properties using support vector machines
Само за регистроване кориснике
2010
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
Quantitative techniques for prediction and classification in soil survey are developing rapidly. The paper introduces application of Support Vector Machines in the estimate of values of soil properties and soil type classification based on known values of particular chemical and physical properties in sampled profiles. Comparison of proposed approach with other linear regression models shows that Support Vector Machines are the model of choice for estimation of values of physical properties and pH value when using only chemical data inputs. They are also the model of choice in the cases where chemical data inputs are not strongly correlated to the estimated property. However, in classification task, their performance is similar to that of the other compared methods, with an increasing advantage when a data set consists of a small number of training samples per each soil type.
Кључне речи:
Support vector machines / Classification / Regression / Soil types / Chemical properties / Physical propertiesИзвор:
Geoderma, 2010, 154, 3-4, 340-347Издавач:
- Elsevier, Amsterdam
DOI: 10.1016/j.geoderma.2009.11.005
ISSN: 0016-7061
WoS: 000275009400022
Scopus: 2-s2.0-72549110480
Институција/група
Poljoprivredni fakultetTY - JOUR AU - Kovacević, Milos AU - Bajat, Branislav AU - Gajić, Boško PY - 2010 UR - http://aspace.agrif.bg.ac.rs/handle/123456789/2363 AB - Quantitative techniques for prediction and classification in soil survey are developing rapidly. The paper introduces application of Support Vector Machines in the estimate of values of soil properties and soil type classification based on known values of particular chemical and physical properties in sampled profiles. Comparison of proposed approach with other linear regression models shows that Support Vector Machines are the model of choice for estimation of values of physical properties and pH value when using only chemical data inputs. They are also the model of choice in the cases where chemical data inputs are not strongly correlated to the estimated property. However, in classification task, their performance is similar to that of the other compared methods, with an increasing advantage when a data set consists of a small number of training samples per each soil type. PB - Elsevier, Amsterdam T2 - Geoderma T1 - Soil type classification and estimation of soil properties using support vector machines EP - 347 IS - 3-4 SP - 340 VL - 154 DO - 10.1016/j.geoderma.2009.11.005 ER -
@article{ author = "Kovacević, Milos and Bajat, Branislav and Gajić, Boško", year = "2010", abstract = "Quantitative techniques for prediction and classification in soil survey are developing rapidly. The paper introduces application of Support Vector Machines in the estimate of values of soil properties and soil type classification based on known values of particular chemical and physical properties in sampled profiles. Comparison of proposed approach with other linear regression models shows that Support Vector Machines are the model of choice for estimation of values of physical properties and pH value when using only chemical data inputs. They are also the model of choice in the cases where chemical data inputs are not strongly correlated to the estimated property. However, in classification task, their performance is similar to that of the other compared methods, with an increasing advantage when a data set consists of a small number of training samples per each soil type.", publisher = "Elsevier, Amsterdam", journal = "Geoderma", title = "Soil type classification and estimation of soil properties using support vector machines", pages = "347-340", number = "3-4", volume = "154", doi = "10.1016/j.geoderma.2009.11.005" }
Kovacević, M., Bajat, B.,& Gajić, B.. (2010). Soil type classification and estimation of soil properties using support vector machines. in Geoderma Elsevier, Amsterdam., 154(3-4), 340-347. https://doi.org/10.1016/j.geoderma.2009.11.005
Kovacević M, Bajat B, Gajić B. Soil type classification and estimation of soil properties using support vector machines. in Geoderma. 2010;154(3-4):340-347. doi:10.1016/j.geoderma.2009.11.005 .
Kovacević, Milos, Bajat, Branislav, Gajić, Boško, "Soil type classification and estimation of soil properties using support vector machines" in Geoderma, 154, no. 3-4 (2010):340-347, https://doi.org/10.1016/j.geoderma.2009.11.005 . .