2015
DOI: 10.1016/j.geoderma.2015.04.008
|View full text |Cite
|
Sign up to set email alerts
|

Comparing data mining classifiers to predict spatial distribution of USDA-family soil groups in Baneh region, Iran

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

7
57
1

Year Published

2017
2017
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 104 publications
(65 citation statements)
references
References 79 publications
7
57
1
Order By: Relevance
“…It is able to model non-linear relationships between predictors and the response variable to handle noise data (observations with missing covariate data) and other situations in which a small dataset is associated with a large number of covariates (Collard et al, 2014). Although RF has shown better performance for soil class mapping when compared to a set of other classifiers (Pahlavan-Rad et al, 2016;Heung et al, 2017), the studies performed by Collard et al (2014), Taghizadeh-Mehrjardi et al (2015), and Camera et al (2017) showed that MLR performed better than RF.…”
Section: Random Forest (Rf)mentioning
confidence: 99%
See 1 more Smart Citation
“…It is able to model non-linear relationships between predictors and the response variable to handle noise data (observations with missing covariate data) and other situations in which a small dataset is associated with a large number of covariates (Collard et al, 2014). Although RF has shown better performance for soil class mapping when compared to a set of other classifiers (Pahlavan-Rad et al, 2016;Heung et al, 2017), the studies performed by Collard et al (2014), Taghizadeh-Mehrjardi et al (2015), and Camera et al (2017) showed that MLR performed better than RF.…”
Section: Random Forest (Rf)mentioning
confidence: 99%
“…Some studies addressed the comparison of data mining approaches for predicting soil classes by different predictive models. Nevertheless, despite the broad success of DSM techniques using tree-based model and logistic regression, few studies have compared the performance of promising classifiers for soil class mapping, such as logistic regression and Random Forest (Hengl et al, 2007;Collard et al, 2014;Taghizadeh-Mehrjardi et al, 2015;Pahlavan-Rad et al, 2016;Camera et al, 2017;Heung et al, 2017). Under similar conditions of western Haiti, this kind of studies is rarer.…”
Section: Introductionmentioning
confidence: 99%
“…Data from wir sensors for the job of physical movement recognition is taken for comparing the p AdaBoostM1 as the classifier of meta level with base level classifier C4.5 Graft in [9] classifier performance with optimization to categorize non-randomized readings and c biomedical quotations for text selection using organized reviews are studied in [10]. Cla Support vector machines, Conditional Random fields and Latent Dynamic conditional ran compared for user intention understanding in analysing web search engines was shown in [1 were analysed, sampled, selected and predicted for taxonomic soil class after investigating th power of data mining classifiers in [12]. Chi-Square Methods and R-Square techniques wer dimensional curve fitting using machine learning in [36].…”
Section: Support Vector Machines With Kernel Evaluationmentioning
confidence: 99%
“…Soil profiles were analysed, sampled, selected and predicted for taxonomic soil class after investigating the classification power of data mining classifiers in [12]. Chi-Square Methods and R-Square techniques were used for high dimensional curve fitting using machine learning in [36].…”
Section: Support Vector Machines With Kernel Evaluationmentioning
confidence: 99%
See 1 more Smart Citation