Sie sind auf Seite 1von 15

ANALYSIS OF GEOPOLYMER SLABS USING SUPPORT VECTOR MACHINE

Under the guidance of

R. Mourougane
Dept. of Civil Engineering, MSRIT.

Presented by

Naresh Reddy G.N


2nd Sem. M.Tech.

CONTENTS
1. Definition 2. Usage 3. History 4. Concept of SVM

5. Classification of SVM Models


6. Applications 7. Analysis of GPC Slabs 8. Limitations 9. References

Definition
Support Vector Machine (SVM) is a technique to analyze data and recognize patterns, used for classification and regression analysis.

Usage
Widely used for predictions and forecasting.

History
Originally developed by Vladimir N Vapnik in 1992.

Concept of SVM
Input Data

Hyperplane of Infinite Dimensional Space

Builds 2 categories

Mapping
H3 (green) doesn't separate the two classes. H1 (blue) does, with a small margin H2 (red) with the maximum margin.

Prediction

Classification of SVM Models


Linear SVM Non Linear SVM

Basis of classification
Kernels: Mathematical functions such polynomial, sigmoid, radial basis function. as linear,

Applications of SVM
Text (and hypertext) categorization Image classification Face recognition Bioinformatics (Protein classification, Cancer classification)

Hand-written character recognition


Engineering Applications (Environmental, Traffic data analysis, Remote Sensing)

Versions Available
SVMdark, SVMlight, SVMstruct, mySVM, libSVM.

Using SVMdark for comparison of experimental and predicted values for GPC Slabs. Procedure
1. The experimental data is split into three sets (in the ratio 50%, 25%, 25%) namely training set, validation set and test set. 2. The train set and the validation set are used to fit in a suitable decision boundary based on regression analysis. 3. Further based on the constants obtained through optimizing the data, the test data is used to obtain the predicted values.

Input Exp. Load (in KN) Deflection (in mm)

Output Predicted Load (in KN)

0
2 4 6 Training Set (50%) 8 10 12 14 16 18 20 Validation Set (25%)

0
0.18 0.415 0.842 1.346 1.858 2.429 2.75 3.184 3.622 4.087

Slab Details
M60 Grade GPC Simply Supported
1080X500X65 mm

22
24 26 28 30

4.695
5.104 5,687 6.266 6.786 6.894 6.936 ? ? ? ? ?

Test Set (25%)

32 34

36
38

7.284
7.316

Input Exp. Load (in KN) 0 Deflection (in mm) 0

Output Predicted Load (in KN)

2
4 6 Training Set (50%) 8 10

0.18
0.415 0.842 1.346 1.858

12
14 16 18 20

2.429
2.75 3.184 3.622 4.087 4.695 5.104 5,687 6.266 6.786 6.894 6.936 7.284 7.316 29.701195 31.093738 33.241844 34.502888 36.617127

Validation Set (25%)

22 24 26 28 30

Test Set (25%)

32 34 36 38

Limitations of SVM
Choice of the Kernel. Selection of Kernel function parameters. Depends only on a subset of the training data. Speed

References
A User's Guide to Support Vector Machines. - Asa Ben-Hur & Jason Weston The Solution Path of the Slab Support Vector Machine. - Michael Eigensatz, Joachim Giesen & Madhusudan

Wikipedia

END

Das könnte Ihnen auch gefallen