1999
DOI: 10.1016/s0168-1699(99)00046-0
|View full text |Cite
|
Sign up to set email alerts
|

Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables

Abstract: This study compared two alternative techniques for predicting forest cover types from cartographic variables. The study evaluated four wilderness areas in the Roosevelt National Forest, located in the Front Range of northern Colorado. Cover type data came from US Forest Service inventory information, while the cartographic variables used to predict cover type consisted of elevation, aspect, and other information derived from standard digital spatial data processed in a geographic information system (GIS). The … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

2
209
2
2

Year Published

2001
2001
2020
2020

Publication Types

Select...
7
1
1

Relationship

0
9

Authors

Journals

citations
Cited by 401 publications
(215 citation statements)
references
References 13 publications
2
209
2
2
Order By: Relevance
“…This spatial data set contains 581,012 examples with 54 attributes and 7 target classes and represents the forest cover type for 30 x 30 meter cells obtained from US Forest Service (USFS) Region 2 Resource Information System [14]. In Covertype data set, 40 attributes are binary columns representing soil type, 4 attributes are binary columns representing wilderness area, and the remaining 10 are continuous topographical attributes.…”
Section: Resultsmentioning
confidence: 99%
“…This spatial data set contains 581,012 examples with 54 attributes and 7 target classes and represents the forest cover type for 30 x 30 meter cells obtained from US Forest Service (USFS) Region 2 Resource Information System [14]. In Covertype data set, 40 attributes are binary columns representing soil type, 4 attributes are binary columns representing wilderness area, and the remaining 10 are continuous topographical attributes.…”
Section: Resultsmentioning
confidence: 99%
“…The RUSBoost (Random Under Sampling) algorithm is designed to classify when one class has many more observations than another and good reference results have been obtained (Seiffert et al 2010). Blackard and Dean (1999) describe an ANN classification of an imbalanced dataset achieving 70.6% accuracy, whereas RUSBoost obtained over 76% classification accuracy. The majority of class-imbalance learning techniques currently implemented, including RUSBoost, have been designed for two-class problems.…”
Section: Ensemble Design and Algorithm Implementationmentioning
confidence: 99%
“…(22)(23)(24)(25), the term sign(x i × y i ) is common and provides the correlation information between the two vectors x and y. As a result, the computational complexity and power consumption due to signal analysis can be decreased significantly.…”
Section: Similarity Measures Based On Surface Gradientsmentioning
confidence: 99%
“…In the original paper, 58 % success rate is obtained using linear discriminant analysis and 70 % success rate is obtained using neural networks [22]. We use the same setup, which has 11340 training samples.…”
mentioning
confidence: 99%