Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points

By Yang Shao, Ross S. Lunetta. 2012

600 citations recorded by the source corpus.

Subfields: Atmospheric Science, Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/41fa379fed5fa78d97234c577ee0b473cd76d667

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Ecology

In Media Technology

Citations in the corpus

A review on neuroimaging‐based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages (2017, unknown): “While SVM could have the advantage of achieving high classification accuracy with small training sample size compared to other classification algorithms such as neural networks (Shao and Lunetta, 2012), they might have the disadvantage of the need for parameter tuning (Chapelle et al.”
Assessment of Groundwater Potential Based on Multicriteria Decision Making Model and Decision Tree Algorithms (2016, methodology): “CART decision tree algorithm [39] can divide the sample set into two subsample sets, making the root and intermediate nodes with two branches based on the recursively binary segmentation technology.”
Land cover and land use classification performance of machine learning algorithms in a boreal landscape using Sentinel-2 data (2019, background): “Support vector machines (SVM) has been shown to outperform other classi ﬁ ers due to its overall high capacity to generalize complex features (Shao and Lunetta 2012; Mountrakis, Jungho, and Ogole 2011).”
Automated cropland mapping of continental Africa using Google Earth Engine cloud computing (2017, methodology): “…regression trees (Deng and Wu, 2013; Egorov et al., 2015; Ozdogan and Gutman, 2008), decision tree algorithms (Friedl and Brodley, 1997; Shao and Lunetta, 2012), Fourier harmonic analysis (Zhang et al., 2015), spectral matching techniques (Dheeravath et al., 2010), support vector…”
Nominal 30-m Cropland Extent Map of Continental Africa by Integrating Pixel-Based and Object-Based Algorithms Using Sentinel-2 and Landsat-8 Data on Google Earth Engine (2017, methodology): “In this section, an integrated methodology of pixel-based classifiers (Random Forest, Support Vector Machines) and object-based Recursive Hierarchical Segmentation is outlined in the flowchart (Figure 4) and described in the following sub-sections:”
Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review (2020, background): “Efficiency and computational cost of RS image classification [29] is also influenced by different factors, such as classification algorithms [30]–[33], sensor types [34]–[37], training samples [38]–[41], input features [42]–[46], pre- and post-processing techniques [47],”
Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery (2017, result): “This is consistent with the study of Shao and Lunetta [62].”
A 30-m landsat-derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine cloud computing platform (2018, unknown): “…a) Random forest algorithm (Tatsumi et al., 2015; Wang et al., 2015; Gislason et al, 2006); (b) Support vector machines (Mountrakis et al., 2011; Shao and Lunetta, 2012); (c) decision tree algorithms (Ozdogan and Gutman, 2008; Waldner et al., 2016); (d) Tassel cap brightness-greenness-wetness…”
Intracranial EEG signals disentangle multi-areal neural dynamics of vicarious pain perception (2024, methodology): “SVM (C= 1 111,112 ) algorithm was employed because it was relatively insensitive to the sample size 113,114 and suitable for decoding analysis with a small sample size 115 (for illustrative purpose, we depicted the variations of decoding performance across different sample sizes in our dataset,…”