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

2012 ◽  
Vol 70 ◽  
pp. 78-87 ◽  
Author(s):  
Yang Shao ◽  
Ross S. Lunetta
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Land Cover ◽  
Land Cover Classification ◽  
Training Data ◽  
Support Vector ◽  
Data Points

scholarly journals Support Vector Machine for Land Cover Classification using Lidar Data

2021 ◽  
Vol 873 (1) ◽  
pp. 012095
Author(s):  
M I Hariyono ◽  
Rokhmatuloh ◽  
M P Tambunan ◽  
R S Dewi
Keyword(s):  
Support Vector Machine ◽  
Land Cover ◽  
Prediction Model ◽  
Accuracy Assessment ◽  
Land Cover Classification ◽  
Training Data ◽  
Support Vector ◽  
Surface Model ◽  
Lidar Data ◽  
Topographic Map

Abstract The Lidar technology is widely used in various studies for mapping needs. In this study was to extract land cover using Lidar data by incorporating a support vector machine (SVM) approach. The study was located in the city of Lombok, Nusa Tenggara Barat. Image extraction was performed on single wavelength Lidar data to produce intensity and elevation (Digital Surface Model) features. Feature extraction of Lidar data was implemented by using a pixel-based approach. The extracted features used as an attribute for training data to generate the SVM prediction model. The prediction model to predict the types of land cover in the study area such as buildings, trees, roads, bare soil, and low vegetations. For accuracy assessment purposes, we used topographic map available in shapefile format as the reference map and estimated the accuracies of the resulted classifications. In this study, land cover classification used combination bands which improved the overall accuracy by approximately 20%. The use of the intensity data in this band combination was the reason for the increasing accuracy.

scholarly journals LAND COVER CLASSIFICATION FROM FULL-WAVEFORM LIDAR DATA BASED ON SUPPORT VECTOR MACHINES

2016 ◽  
Vol XLI-B3 ◽  
pp. 447-452
Author(s):  
M. Zhou ◽  
C. R. Li ◽  
L. Ma ◽  
H. C. Guan
Keyword(s):  
Support Vector Machines ◽  
Land Cover ◽  
Prediction Model ◽  
Image Data ◽  
Ground Truth ◽  
Land Cover Classification ◽  
Training Data ◽  
Support Vector ◽  
Vector Machines ◽  
Waveform Lidar

In this study, a land cover classification method based on multi-class Support Vector Machines (SVM) is presented to predict the types of land cover in Miyun area. The obtained backscattered full-waveforms were processed following a workflow of waveform pre-processing, waveform decomposition and feature extraction. The extracted features, which consist of distance, intensity, Full Width at Half Maximum (FWHM) and back scattering cross-section, were corrected and used as attributes for training data to generate the SVM prediction model. The SVM prediction model was applied to predict the types of land cover in Miyun area as ground, trees, buildings and farmland. The classification results of these four types of land covers were obtained based on the ground truth information according to the CCD image data of Miyun area. It showed that the proposed classification algorithm achieved an overall classification accuracy of 90.63%. In order to better explain the SVM classification results, the classification results of SVM method were compared with that of Artificial Neural Networks (ANNs) method and it showed that SVM method could achieve better classification results.

scholarly journals MULTI-TEMPORAL LAND COVER CLASSIFICATION WITH LONG SHORT-TERM MEMORY NEURAL NETWORKS

2017 ◽  
Vol XLII-1/W1 ◽  
pp. 551-558 ◽  
Author(s):  
M. Rußwurm ◽  
M. Körner
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Land Cover ◽  
Short Term Memory ◽  
Land Cover Classification ◽  
Support Vector ◽  
Short Term ◽  
Term Memory ◽  
Classification Techniques ◽  
Long Short Term Memory

<i>Land cover classification (LCC)</i> is a central and wide field of research in earth observation and has already put forth a variety of classification techniques. Many approaches are based on classification techniques considering observation at certain points in time. However, some land cover classes, such as crops, change their spectral characteristics due to environmental influences and can thus not be monitored effectively with classical mono-temporal approaches. Nevertheless, these temporal observations should be utilized to benefit the classification process. After extensive research has been conducted on modeling temporal dynamics by spectro-temporal profiles using vegetation indices, we propose a deep learning approach to utilize these temporal characteristics for classification tasks. In this work, we show how <i>long short-term memory</i> (LSTM) neural networks can be employed for crop identification purposes with SENTINEL 2A observations from large study areas and label information provided by local authorities. We compare these temporal neural network models, <i>i.e.</i>, LSTM and <i>recurrent neural network</i> (RNN), with a classical non-temporal <i>convolutional neural network</i> (CNN) model and an additional <i>support vector machine</i> (SVM) baseline. With our rather straightforward LSTM variant, we exceeded state-of-the-art classification performance, thus opening promising potential for further research.

scholarly journals Perbandingan Quadratic Discriminant Analysis dan Support Vector Machine untuk Klasifikasi Tutupan Lahan di DKI Jakarta

2020 ◽  
Vol 9 (1) ◽  
pp. 12-20
Author(s):  
Kamaluddin Junianto Dimas ◽  
Rahma Anisa ◽  
Itasia Dina Sulvianti
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Support Vector Machine ◽  
Discriminant Analysis ◽  
Land Cover ◽  
Training Data ◽  
Support Vector ◽  
Quadratic Discriminant Analysis ◽  
Remote Sensing Technology ◽  
Sensing Technology

DKI Jakarta is a center of government as well as economy and business of Indonesia, thus development projects in Jakarta continue every year. Therefore, monitoring for land use has to be improved in accordance to DKI Jakarta Spatial Planning. The attempt needs to be supported by continuous data availability regarding land cover condition in Jakarta. The aforementioned data collecting process become easier due to remote sensing technology development. Remote sensing technology can be utilized for analyzing the size of land use area by using classification analysis. It has been found that the level of accuracy depends on the type of classification method and number of training data. This research evaluated the level of overall accuracy, sensitivity, and specificity of Quadratic Discriminant Analysis (QDA) and Support Vector Machine (SVM) along with number of data training used in classifying Jakarta land cover in 2017. The results showed that in both methods, the variance of all the aforementioned criteria were getting smaller along with the increasing number of training data. QDA and SVM had similar performance based on overall accuracy and specificity. However, SVM was better than QDA on sensitivity.

scholarly journals Spatial–Temporal Analysis of Land Cover Change at the Bento Rodrigues Dam Disaster Area Using Machine Learning Techniques

2019 ◽  
Vol 11 (21) ◽  
pp. 2548
Author(s):  
Dong Luo ◽  
Douglas G. Goodin ◽  
Marcellus M. Caldas
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Land Cover ◽  
Decision Tree ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Disaster Area ◽  
Mine Sites

Disasters are an unpredictable way to change land use and land cover. Improving the accuracy of mapping a disaster area at different time is an essential step to analyze the relationship between human activity and environment. The goals of this study were to test the performance of different processing procedures and examine the effect of adding normalized difference vegetation index (NDVI) as an additional classification feature for mapping land cover changes due to a disaster. Using Landsat ETM+ and OLI images of the Bento Rodrigues mine tailing disaster area, we created two datasets, one with six bands, and the other one with six bands plus the NDVI. We used support vector machine (SVM) and decision tree (DT) algorithms to build classifier models and validated models performance using 10-fold cross-validation, resulting in accuracies higher than 90%. The processed results indicated that the accuracy could reach or exceed 80%, and the support vector machine had a better performance than the decision tree. We also calculated each land cover type’s sensitivity (true positive rate) and found that Agriculture, Forest and Mine sites had higher values but Bareland and Water had lower values. Then, we visualized land cover maps in 2000 and 2017 and found out the Mine sites areas have been expanded about twice of the size, but Forest decreased 12.43%. Our findings showed that it is feasible to create a training data pool and use machine learning algorithms to classify a different year’s Landsat products and NDVI can improve the vegetation covered land classification. Furthermore, this approach can provide a venue to analyze land pattern change in a disaster area over time.

Sign in / Sign up

Export Citation Format

Share Document