2014
DOI: 10.5539/apr.v6n5p122
|View full text |Cite
|
Sign up to set email alerts
|

Support Vector Machines Approach for Estimating Work Function of Semiconductors: Addressing the Limitation of Metallic Plasma Model

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
6
0

Year Published

2014
2014
2022
2022

Publication Types

Select...
9

Relationship

0
9

Authors

Journals

citations
Cited by 17 publications
(7 citation statements)
references
References 18 publications
1
6
0
Order By: Relevance
“…Another important observation from our experiment Regularization factor, Well-C HSVR Figure 9: Sensitivity of HSVR model to regularization factor (Well-C). is that while the radial basis function (RBF) (Gaussian) kernel was the best for SVR, which has been observed and reported in many publications [8,10,26,33], we observed that the polynomial kernel (Poly) performed best for HSVR. This observation can be attributed to the reduction in the number of descriptors since HSVR only takes a single descriptor which greatly simplifies the degree of complexity for polynomial kernel and gives it an edge.…”
Section: Validation Set Proceduresupporting
confidence: 77%
“…Another important observation from our experiment Regularization factor, Well-C HSVR Figure 9: Sensitivity of HSVR model to regularization factor (Well-C). is that while the radial basis function (RBF) (Gaussian) kernel was the best for SVR, which has been observed and reported in many publications [8,10,26,33], we observed that the polynomial kernel (Poly) performed best for HSVR. This observation can be attributed to the reduction in the number of descriptors since HSVR only takes a single descriptor which greatly simplifies the degree of complexity for polynomial kernel and gives it an edge.…”
Section: Validation Set Proceduresupporting
confidence: 77%
“…Other areas where AI techniques are adopted include the estimation of atomic radii of elements [13], diagnosing mechanical fault [14], forecasting Saudi Arabia stock prices [15], assessing the thickness of metal plates [16], automatic recognition of off-line handwritten Arabic numbers [17], material characterization [18] among others. The successes of support vector regression in estimating material properties [19,20] coupled with the need to have accurate and reliable means of estimating average surface energies of materials prompted us to delve into this research work.…”
Section: Introductionmentioning
confidence: 99%
“…SVR algorithm was proposed in this study because of its optimal predictive performance even with small dataset [ 41 ] and the ability to learn both linear and non-linear relationships between predictors and outcome (actual) variables [ 42 ]. Such relationships have been used in establishing a pattern whereby unknown outcomes could be predicted accurately [ 21 , 24 ].…”
Section: Methodsmentioning
confidence: 99%