A rule-based classifier using Classification and Regression Tree (CART) approach for urban landscape dynamics

Manojkumar, P C; Sugumaran, Ramanathan; Zerr, D.

doi:10.1109/igarss.2002.1025880

Cited by 8 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While there are many machine learning approaches to classify the Earth's land surface, the classification and regression tree (CART) is ideal for land classification according to several previous studies (ManojKumar et al 2002;Xu et al 2005). To prepare the training data for the model, we generated reference areas to identify water, vegetation, human construction, and others (see example in Fig.…”

Section: The Green Space Data Processingmentioning

confidence: 99%

The protective effect of green space on heat-related respiratory hospitalization among children under 5 years of age in Hanoi, Vietnam

Nguyen

Doan

Tran

et al. 2022

Environ Sci Pollut Res

View full text Add to dashboard Cite

Combined effects of global warming and rapid urbanization replace green spaces with urban facilities. Children in urban areas are at a higher risk of heat-related adverse health effects. Our study aimed to examine the protective effect of urban green space on heat-related respiratory hospitalization among children under 5 years of age in Hanoi, the capital city of Vietnam. We estimated district-specific meteorological conditions from 2010 to 2014 by using a dynamic downscaling approach with a fine-resolution numerical climate model. The green space in each district was calculated using satellite data. The attributable fraction of heat-related respiratory hospitalization was estimated using a two-stage model, including a distributed lag non-linear model (DLNM) coupled with multivariate meta-analysis. The association between heat-related respiratory hospitalization and green spaces at the district level was explored using a linear regression model. The central districts were more crowded and hotter, with less green spaces than the outer districts. At temperatures > 34 °C (extreme heat threshold), the hospitalizations in the central districts increased significantly; however, in the outer districts, the hospitalization rate was insignificant. On average, extreme heat attributed 0.33% to citywide hospitalization, 0.35% in the center, and 0.32% in the outer region. Every 1% increase in the green space fraction will reduce heat-related respiratory hospitalization risk by 3.8%. Heat significantly increased the risk of respiratory hospitalization among children under 5 years in Hanoi, Vietnam. These findings are valuable for authorities to consider strategies to protect children's health against the effects of heat, including increasing green space.

show abstract

Section: The Green Space Data Processingmentioning

confidence: 99%

The protective effect of green space on heat-related respiratory hospitalization among children under 5 years of age in Hanoi, Vietnam

Nguyen

Doan

Tran

et al. 2022

Environ Sci Pollut Res

View full text Add to dashboard Cite

show abstract

“…The type of structure element (pixel or object), the classification model, and the extraction of texture features are treated as the key issues of a successful classification scheme. 23 Decision tree is another powerful classifier widely used in HSRRS applications, such as landscape mapping 24 and vegetation extracting in urban area. 22 For the classification model, support vector machine (SVM) is a valuable classifier widely used in the classification of HSRRS data for its ability to generalize well even with limited training samples.…”

Section: Introductionmentioning

confidence: 99%

Support vector machine-based decision tree for snow cover extraction in mountain areas using high spatial resolution remote sensing image

Zhu

Xiao²,

Xia³

et al. 2014

J. Appl. Remote Sens

View full text Add to dashboard Cite

Snow cover extraction in mountain areas is a complex task, especially from high spatial resolution remote sensing (HSRRS) data. The influence of mountain shadows in HSRRS is severe and normalized difference snow index-based snow cover extraction methods are inaccessible. A decision tree building method for snow cover extraction (DTSE) integrated with an efficiency feature selection algorithm is proposed. The severe influence of terrain shadows is eliminated by extracting snow in sunlight and snow in shadow separately in different nodes. In the feature selection algorithm, deviation of fuzzy grade matrix is proposed as a class-specific criterion which improves the efficiency and robustness of the selected feature set, thus making the snow cover extraction accurate. Two experiments are carried out based on ZY-3 image of two regions (regions A and B) located in Tianshan Mountains, China. The experiment on region A achieves an adequate accuracy demonstrating the robustness of the DTSE building method. The experiment on region B shows that a general DTSE model achieves an unsatisfied accuracy for snow in shadow and DTSE rebuilding evidently improves the performance, thus providing an accurate and fast way to extract snow cover in mountain areas. © 2014 Society of Photo-Optical Instrumentation Engineers (SPIE)

show abstract

“…Pavuluri Manoj Kumar [21]comparison of CART and ML classifications for urban land cover showed that ML performs better than CART in this study area. CART can improve classification accuracy if there is a higher variance in the additional data used.…”

Section: Literature Reviewmentioning

confidence: 99%

Development of Data Mining Techniques for Data Partitioning to Generate Classification and Regression Trees.

2017

IJAERD

View full text Add to dashboard Cite

show abstract

A rule-based classifier using Classification and Regression Tree (CART) approach for urban landscape dynamics

Cited by 8 publications

References 2 publications

The protective effect of green space on heat-related respiratory hospitalization among children under 5 years of age in Hanoi, Vietnam

The protective effect of green space on heat-related respiratory hospitalization among children under 5 years of age in Hanoi, Vietnam

Support vector machine-based decision tree for snow cover extraction in mountain areas using high spatial resolution remote sensing image

Development of Data Mining Techniques for Data Partitioning to Generate Classification and Regression Trees.

Contact Info

Product

Resources

About