scholarly journals Comparison of Support Vector Machine and Neural Network Classification Methods in Land Use Information Extraction through Landsat TM Data

2015 ◽  
Vol 19 (72) ◽  
pp. 35-45
Author(s):  
M. Mokhtari ◽  
A. Najafi ◽  
◽  
Keyword(s):  
Neural Network ◽  
Land Use ◽  
Support Vector Machine ◽  
Information Extraction ◽  
Landsat Tm ◽  
Support Vector ◽  
Classification Methods ◽  
Neural Network Classification

scholarly journals Hierarchical attention networks for information extraction from cancer pathology reports

2017 ◽  
Vol 25 (3) ◽  
pp. 321-330 ◽  
Author(s):  
Shang Gao ◽  
Michael T Young ◽  
John X Qiu ◽  
Hong-Jun Yoon ◽  
James B Christian ◽  
...  
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Information Extraction ◽  
Model Performance ◽  
Gradient Boosting ◽  
Support Vector ◽  
Attention Networks ◽  
Cancer Pathology ◽  
Extreme Gradient Boosting ◽  
Pathology Reports

Abstract Objective We explored how a deep learning (DL) approach based on hierarchical attention networks (HANs) can improve model performance for multiple information extraction tasks from unstructured cancer pathology reports compared to conventional methods that do not sufficiently capture syntactic and semantic contexts from free-text documents. Materials and Methods Data for our analyses were obtained from 942 deidentified pathology reports collected by the National Cancer Institute Surveillance, Epidemiology, and End Results program. The HAN was implemented for 2 information extraction tasks: (1) primary site, matched to 12 International Classification of Diseases for Oncology topography codes (7 breast, 5 lung primary sites), and (2) histological grade classification, matched to G1–G4. Model performance metrics were compared to conventional machine learning (ML) approaches including naive Bayes, logistic regression, support vector machine, random forest, and extreme gradient boosting, and other DL models, including a recurrent neural network (RNN), a recurrent neural network with attention (RNN w/A), and a convolutional neural network. Results Our results demonstrate that for both information tasks, HAN performed significantly better compared to the conventional ML and DL techniques. In particular, across the 2 tasks, the mean micro and macroF-scores for the HAN with pretraining were (0.852,0.708), compared to naive Bayes (0.518, 0.213), logistic regression (0.682, 0.453), support vector machine (0.634, 0.434), random forest (0.698, 0.508), extreme gradient boosting (0.696, 0.522), RNN (0.505, 0.301), RNN w/A (0.637, 0.471), and convolutional neural network (0.714, 0.460). Conclusions HAN-based DL models show promise in information abstraction tasks within unstructured clinical pathology reports.

scholarly journals Mapping and Monitoring of Land Cover/Land Use (LCLU) Changes in the Crozon Peninsula (Brittany, France) from 2007 to 2018 by Machine Learning Algorithms (Support Vector Machine, Random Forest, and Convolutional Neural Network) and by Post-classification Comparison (PCC)

2021 ◽  
Vol 13 (19) ◽  
pp. 3899
Author(s):  
Guanyao Xie ◽  
Simona Niculescu
Keyword(s):  
Neural Network ◽  
Land Use ◽  
Support Vector Machine ◽  
Random Forest ◽  
Land Cover ◽  
Convolutional Neural Network ◽  
Coastal Area ◽  
Machine Learning Algorithms ◽  
High Rate ◽  
Support Vector

Land cover/land use (LCLU) is currently a very important topic, especially for coastal areas that connect the land and the coast and tend to change frequently. LCLU plays a crucial role in land and territory planning and management tasks. This study aims to complement information on the types and rates of LCLU multiannual changes with the distributions, rates, and consequences of these changes in the Crozon Peninsula, a highly fragmented coastal area. To evaluate the multiannual change detection (CD) capabilities using high-resolution (HR) satellite imagery, we implemented three remote sensing algorithms: a support vector machine (SVM), a random forest (RF) combined with geographic object-based image analysis techniques (GEOBIA), and a convolutional neural network (CNN), with SPOT 5 and Sentinel 2 data from 2007 and 2018. Accurate and timely CD is the most important aspect of this process. Although all algorithms were indicated as efficient in our study, with accuracy indices between 70% and 90%, the CNN had significantly higher accuracy than the SVM and RF, up to 90%. The inclusion of the CNN significantly improved the classification performance (5–10% increase in the overall accuracy) compared with the SVM and RF classifiers applied in our study. The CNN eliminated some of the confusion that characterizes a coastal area. Through the study of CD results by post-classification comparison (PCC), multiple changes in LCLU could be observed between 2007 and 2018: both the cultivated and non-vegetated areas increased, accompanied by high deforestation, which could be explained by the high rate of urbanization in the peninsula.

scholarly journals Backscattering coefficient measurement and land use land cover classification using ENVI SAT ASAR data

2018 ◽  
Vol 7 (2.14) ◽  
pp. 529
Author(s):  
K V Ramana Rao ◽  
P Rajesh Kumar
Keyword(s):  
Land Use ◽  
Support Vector Machine ◽  
Land Cover ◽  
Supervised Classification ◽  
Land Cover Classification ◽  
Support Vector ◽  
Land Use Land Cover ◽  
Classification Methods ◽  
Backscattering Coefficient ◽  
The Earth

The polarimetric SAR data of the space borne sensor, ENVISAT-ASAR (Environmental Satellite - Academic & Science Astronomy & Space Science) has been used for the land use land cover classification of the study area. It was an earth observing satellite operated by the European Space Agency (ESA). Its mission was to observe the earth and monitor critical aspects of the environment such as climatic changes on the earth at the local, regional and global levels. The data set of this sensor is a dual co-polarization amplitude data consisting of HH and VV channels. Initially various incidence angle images such as sigma naught, beta naught and gamma naught have been generated for both HH and VV polarizations. Then the backscattering coefficients of different features such as water, bare soil, vegetation and urban have been calculated. The backscattering coefficient values of the HH polarization are high compared to the values that are obtained with VV polarization. Then the land use land cover classification has been done by implementing different supervised classification algorithms. These classification methods are Parallelepiped, Minimum Distance, Mahalanobis, Maximum Likelihood, Binary Coding and Support Vector Machine. Then the accuracy measurements have been done for all these classification methods. In the present study the accuracy results obtained with the supervised Support Vector Machine classification algorithm are more compared to the accuracy results obtained with the other supervised classification methods.

Sign in / Sign up

Export Citation Format

Share Document