SlideShare a Scribd company logo
1 of 6
Crop-Type Classification using MLP, RBF
and CCELM
Objective
Multi Spectral Satellite Image Classification of 6 crop types using supervised
learning techniques ie; Multi Layer Perceptron Neural Networks
(MLPnn), Radial Basis Function Neural Networks (RBFnn) and Circular
Complex Extreme Learning Machine
Approach
The 4 bands of the hyper spectral data are used as the input to each of the 3
Neural Network Classifiers. Each of the implemented classifiers are trained by
Back-Propagation algorithm using the same ground truth. Each of the trained
classifiers are tested against the same dataset and the individual performance
are compared.
Crop-Type Classification using MLP,
RBF and CCELM
Multi spectral Data
• The multi spectral image comprises of
4 bands, namely, Red, Blue, Green
and infrared.
• High resolution, four band multi
spectral image of southern part of
India is used to derive the data
samples. It is of the dimension 1375 ×
5929 pixels and it covers an area of
2.748 × 7.973 km2. This image is first
divided into six distinct crop classes
namely, Sugarcane, Ragi, Paddy, Mulb
erry, Groundnut and Mango.
Crop-Type Classification using MLP, RBF
and CCELM
Multi-spectral data
The area selected for classification is the region surrounding Mysore district in
Karnataka, India. This region has the required crop coverage classes and it is also wide
spread and densely cultivated. It provides sufficient data samples to train the neural
classifiers for all the six classes. Therefore, it serves as suitable region for an
experimental study. Quick-Bird’s (operated by Digital Globe) multi-spectral (MSS)
image with the resolution of 2.4m has been used as inputs.
Class Class
no.
name
C1
C2
C3
C4
C5
C6

Sugarcane
Ragi
Paddy
Mulberry
Groundnut
Mango
Total

Number of
pixels for
training
100
100
100
100
100
100
600

Number of
pixels for
validation
400
400
400
400
400
400
2400

Parameter
No of crop types

Value
6

Samples for each
crop type (training)

100

Samples for each
crop type ( testing )

600

No of bands for
each sample

4
Crop-Type Classification using MLP, RBF
and CCELM
Methods:
1. Multilayer Perceptron Neural Network
(MLP-NN) divides the Input vector
space into different classes by means
of Hyper-planes, which is not an
efficient way of classification.
2.

Neural Network Structure Implemented

Radial Basis Function Neural Network
(RBF-NN) divides the input vector
space into multiple classes, using
hyper-spheres. This is a better and
efficient way of classification.
Crop-Type Classification using MLP, RBF
and CCELM
3. Circular Complex Extreme Learning Machine (CCELM): This uses complex
valued activation functions and complex valued weights. Hence for every
hidden neuron, there are 2 decision surfaces that are orthogonal to each
other. So, we have 4 decision boundaries and therefore, better classification.
Advantages of CCELM over MLP and RBF:
• MLP and RBF use Back Propagation algorithm for training, hence their
performance may be hindered from problem of local minima.
• To overcome this problem, we use Circular Complex Extreme Learning
Machine (CCELM)
• Extreme Learning Machine computes the required parameters by
formulating the problem of solving weights as problem of finding inverse
of given matrices. This greatly reduces the computational time.
Crop-Type Classification using MLP, RBF
and CCELM
Performance of MLPnn

C1
C2
C3
C4
C5
C6

Performance of RBFnn

C1 C2 C3 C4 C5 C6
395 0
0
0
0
5
0 400 0
0
0
0
0
0 400 0
0
0
0
0
0 397 0
3
0
0
0
0 400 0
169 7
0
0
0 224

Overall efficiency = 92.33%

C1
C2
C3
C4
C5
C6

C1
400
0
0
0
0
139

C2 C3
0
0
400
0
0
400
0
0
0
1
1
0

C4
0
0
0
399
0
0

C5 C6
0
5
0
0
0
0
0
1
399
0
0
260

Overall efficiency = 92.33%
Performance of CCELM

C1
C2
C3
C4
C5
C6

C1 C2 C3 C4 C5 C6
398 0
0
0
0
2
0 399 1
0
0
0
0
1 399 0
0
0
0
0
0 398 0
2
0
0
0
0 400 0
18
0
2
0
0 380

Overall efficiency = 98.9%

More Related Content

What's hot

An Efficient Clustering Method for Aggregation on Data Fragments
An Efficient Clustering Method for Aggregation on Data FragmentsAn Efficient Clustering Method for Aggregation on Data Fragments
An Efficient Clustering Method for Aggregation on Data FragmentsIJMER
 
Neural networks for the prediction and forecasting of water resources variables
Neural networks for the prediction and forecasting of water resources variablesNeural networks for the prediction and forecasting of water resources variables
Neural networks for the prediction and forecasting of water resources variablesJonathan D'Cruz
 
A cellular network architecture with polynomial weight functions
A cellular network architecture with polynomial weight functions A cellular network architecture with polynomial weight functions
A cellular network architecture with polynomial weight functions Ieee Xpert
 
Learning from data for wind–wave forecasting
Learning from data for wind–wave forecastingLearning from data for wind–wave forecasting
Learning from data for wind–wave forecastingJonathan D'Cruz
 
ENHANCING SEGMENTATION APPROACHES FROM FUZZY K-C-MEANS TO FUZZY-MPSO BASED LI...
ENHANCING SEGMENTATION APPROACHES FROM FUZZY K-C-MEANS TO FUZZY-MPSO BASED LI...ENHANCING SEGMENTATION APPROACHES FROM FUZZY K-C-MEANS TO FUZZY-MPSO BASED LI...
ENHANCING SEGMENTATION APPROACHES FROM FUZZY K-C-MEANS TO FUZZY-MPSO BASED LI...Christo Ananth
 

What's hot (6)

An Efficient Clustering Method for Aggregation on Data Fragments
An Efficient Clustering Method for Aggregation on Data FragmentsAn Efficient Clustering Method for Aggregation on Data Fragments
An Efficient Clustering Method for Aggregation on Data Fragments
 
Neural networks for the prediction and forecasting of water resources variables
Neural networks for the prediction and forecasting of water resources variablesNeural networks for the prediction and forecasting of water resources variables
Neural networks for the prediction and forecasting of water resources variables
 
A cellular network architecture with polynomial weight functions
A cellular network architecture with polynomial weight functions A cellular network architecture with polynomial weight functions
A cellular network architecture with polynomial weight functions
 
Learning from data for wind–wave forecasting
Learning from data for wind–wave forecastingLearning from data for wind–wave forecasting
Learning from data for wind–wave forecasting
 
ENHANCING SEGMENTATION APPROACHES FROM FUZZY K-C-MEANS TO FUZZY-MPSO BASED LI...
ENHANCING SEGMENTATION APPROACHES FROM FUZZY K-C-MEANS TO FUZZY-MPSO BASED LI...ENHANCING SEGMENTATION APPROACHES FROM FUZZY K-C-MEANS TO FUZZY-MPSO BASED LI...
ENHANCING SEGMENTATION APPROACHES FROM FUZZY K-C-MEANS TO FUZZY-MPSO BASED LI...
 
Path loss prediction
Path loss predictionPath loss prediction
Path loss prediction
 

Similar to Crop classification using supervised learning techniques

Study of Parametric Kernels for LSSVM Models in NIR Determination of Fishmeal...
Study of Parametric Kernels for LSSVM Models in NIR Determination of Fishmeal...Study of Parametric Kernels for LSSVM Models in NIR Determination of Fishmeal...
Study of Parametric Kernels for LSSVM Models in NIR Determination of Fishmeal...researchinventy
 
Efficient design of feedforward network for pattern classification
Efficient design of feedforward network for pattern classificationEfficient design of feedforward network for pattern classification
Efficient design of feedforward network for pattern classificationIOSR Journals
 
Application of support vector machines for prediction of anti hiv activity of...
Application of support vector machines for prediction of anti hiv activity of...Application of support vector machines for prediction of anti hiv activity of...
Application of support vector machines for prediction of anti hiv activity of...Alexander Decker
 
Combining Neural Networks for Skin Detection
Combining Neural Networks for Skin DetectionCombining Neural Networks for Skin Detection
Combining Neural Networks for Skin Detectionsipij
 
Radial basis function network ppt bySheetal,Samreen and Dhanashri
Radial basis function network ppt bySheetal,Samreen and DhanashriRadial basis function network ppt bySheetal,Samreen and Dhanashri
Radial basis function network ppt bySheetal,Samreen and Dhanashrisheetal katkar
 
PSO-based Training, Pruning, and Ensembling of Extreme Learning Machine RBF N...
PSO-based Training, Pruning, and Ensembling of Extreme Learning Machine RBF N...PSO-based Training, Pruning, and Ensembling of Extreme Learning Machine RBF N...
PSO-based Training, Pruning, and Ensembling of Extreme Learning Machine RBF N...ijceronline
 
Large Scale Kernel Learning using Block Coordinate Descent
Large Scale Kernel Learning using Block Coordinate DescentLarge Scale Kernel Learning using Block Coordinate Descent
Large Scale Kernel Learning using Block Coordinate DescentShaleen Kumar Gupta
 
An ensemble classification algorithm for hyperspectral images
An ensemble classification algorithm for hyperspectral imagesAn ensemble classification algorithm for hyperspectral images
An ensemble classification algorithm for hyperspectral imagessipij
 
Microarray Data Classification Using Support Vector Machine
Microarray Data Classification Using Support Vector MachineMicroarray Data Classification Using Support Vector Machine
Microarray Data Classification Using Support Vector MachineCSCJournals
 
minimalist-business-slides.v dsgjnejgndjgnejgnjgnrjhgdjgngdngtpptx
minimalist-business-slides.v dsgjnejgndjgnejgnjgnrjhgdjgngdngtpptxminimalist-business-slides.v dsgjnejgndjgnejgnjgnrjhgdjgngdngtpptx
minimalist-business-slides.v dsgjnejgndjgnejgnjgnrjhgdjgngdngtpptxElizanderGalasi1
 
A general frame for building optimal multiple SVM kernels
A general frame for building optimal multiple SVM kernelsA general frame for building optimal multiple SVM kernels
A general frame for building optimal multiple SVM kernelsinfopapers
 
Optimization of Complex SVM Kernels Using a Hybrid Algorithm Based on Wasp Be...
Optimization of Complex SVM Kernels Using a Hybrid Algorithm Based on Wasp Be...Optimization of Complex SVM Kernels Using a Hybrid Algorithm Based on Wasp Be...
Optimization of Complex SVM Kernels Using a Hybrid Algorithm Based on Wasp Be...infopapers
 
Mask RCNN on brain tumor.pptx
Mask RCNN on brain tumor.pptxMask RCNN on brain tumor.pptx
Mask RCNN on brain tumor.pptxDanishKhan643986
 
Optimized Kernel Extreme Learning Machine for Myoelectric Pattern Recognition
Optimized Kernel Extreme Learning Machine for Myoelectric Pattern Recognition Optimized Kernel Extreme Learning Machine for Myoelectric Pattern Recognition
Optimized Kernel Extreme Learning Machine for Myoelectric Pattern Recognition IJECEIAES
 
Hidden Layer Leraning Vector Quantizatio
Hidden Layer Leraning Vector Quantizatio Hidden Layer Leraning Vector Quantizatio
Hidden Layer Leraning Vector Quantizatio Armando Vieira
 
Crude Oil Price Prediction Based on Soft Computing Model: Case Study of Iraq
Crude Oil Price Prediction Based on Soft Computing Model: Case Study of IraqCrude Oil Price Prediction Based on Soft Computing Model: Case Study of Iraq
Crude Oil Price Prediction Based on Soft Computing Model: Case Study of IraqKiogyf
 
ABayesianApproachToLocalizedMultiKernelLearningUsingTheRelevanceVectorMachine...
ABayesianApproachToLocalizedMultiKernelLearningUsingTheRelevanceVectorMachine...ABayesianApproachToLocalizedMultiKernelLearningUsingTheRelevanceVectorMachine...
ABayesianApproachToLocalizedMultiKernelLearningUsingTheRelevanceVectorMachine...grssieee
 
Comparison of image fusion methods
Comparison of image fusion methodsComparison of image fusion methods
Comparison of image fusion methodsAmr Nasr
 

Similar to Crop classification using supervised learning techniques (20)

Study of Parametric Kernels for LSSVM Models in NIR Determination of Fishmeal...
Study of Parametric Kernels for LSSVM Models in NIR Determination of Fishmeal...Study of Parametric Kernels for LSSVM Models in NIR Determination of Fishmeal...
Study of Parametric Kernels for LSSVM Models in NIR Determination of Fishmeal...
 
Efficient design of feedforward network for pattern classification
Efficient design of feedforward network for pattern classificationEfficient design of feedforward network for pattern classification
Efficient design of feedforward network for pattern classification
 
Application of support vector machines for prediction of anti hiv activity of...
Application of support vector machines for prediction of anti hiv activity of...Application of support vector machines for prediction of anti hiv activity of...
Application of support vector machines for prediction of anti hiv activity of...
 
Combining Neural Networks for Skin Detection
Combining Neural Networks for Skin DetectionCombining Neural Networks for Skin Detection
Combining Neural Networks for Skin Detection
 
Radial basis function network ppt bySheetal,Samreen and Dhanashri
Radial basis function network ppt bySheetal,Samreen and DhanashriRadial basis function network ppt bySheetal,Samreen and Dhanashri
Radial basis function network ppt bySheetal,Samreen and Dhanashri
 
PSO-based Training, Pruning, and Ensembling of Extreme Learning Machine RBF N...
PSO-based Training, Pruning, and Ensembling of Extreme Learning Machine RBF N...PSO-based Training, Pruning, and Ensembling of Extreme Learning Machine RBF N...
PSO-based Training, Pruning, and Ensembling of Extreme Learning Machine RBF N...
 
Large Scale Kernel Learning using Block Coordinate Descent
Large Scale Kernel Learning using Block Coordinate DescentLarge Scale Kernel Learning using Block Coordinate Descent
Large Scale Kernel Learning using Block Coordinate Descent
 
An ensemble classification algorithm for hyperspectral images
An ensemble classification algorithm for hyperspectral imagesAn ensemble classification algorithm for hyperspectral images
An ensemble classification algorithm for hyperspectral images
 
Microarray Data Classification Using Support Vector Machine
Microarray Data Classification Using Support Vector MachineMicroarray Data Classification Using Support Vector Machine
Microarray Data Classification Using Support Vector Machine
 
minimalist-business-slides.v dsgjnejgndjgnejgnjgnrjhgdjgngdngtpptx
minimalist-business-slides.v dsgjnejgndjgnejgnjgnrjhgdjgngdngtpptxminimalist-business-slides.v dsgjnejgndjgnejgnjgnrjhgdjgngdngtpptx
minimalist-business-slides.v dsgjnejgndjgnejgnjgnrjhgdjgngdngtpptx
 
Thesis Presentation
Thesis PresentationThesis Presentation
Thesis Presentation
 
H43014046
H43014046H43014046
H43014046
 
A general frame for building optimal multiple SVM kernels
A general frame for building optimal multiple SVM kernelsA general frame for building optimal multiple SVM kernels
A general frame for building optimal multiple SVM kernels
 
Optimization of Complex SVM Kernels Using a Hybrid Algorithm Based on Wasp Be...
Optimization of Complex SVM Kernels Using a Hybrid Algorithm Based on Wasp Be...Optimization of Complex SVM Kernels Using a Hybrid Algorithm Based on Wasp Be...
Optimization of Complex SVM Kernels Using a Hybrid Algorithm Based on Wasp Be...
 
Mask RCNN on brain tumor.pptx
Mask RCNN on brain tumor.pptxMask RCNN on brain tumor.pptx
Mask RCNN on brain tumor.pptx
 
Optimized Kernel Extreme Learning Machine for Myoelectric Pattern Recognition
Optimized Kernel Extreme Learning Machine for Myoelectric Pattern Recognition Optimized Kernel Extreme Learning Machine for Myoelectric Pattern Recognition
Optimized Kernel Extreme Learning Machine for Myoelectric Pattern Recognition
 
Hidden Layer Leraning Vector Quantizatio
Hidden Layer Leraning Vector Quantizatio Hidden Layer Leraning Vector Quantizatio
Hidden Layer Leraning Vector Quantizatio
 
Crude Oil Price Prediction Based on Soft Computing Model: Case Study of Iraq
Crude Oil Price Prediction Based on Soft Computing Model: Case Study of IraqCrude Oil Price Prediction Based on Soft Computing Model: Case Study of Iraq
Crude Oil Price Prediction Based on Soft Computing Model: Case Study of Iraq
 
ABayesianApproachToLocalizedMultiKernelLearningUsingTheRelevanceVectorMachine...
ABayesianApproachToLocalizedMultiKernelLearningUsingTheRelevanceVectorMachine...ABayesianApproachToLocalizedMultiKernelLearningUsingTheRelevanceVectorMachine...
ABayesianApproachToLocalizedMultiKernelLearningUsingTheRelevanceVectorMachine...
 
Comparison of image fusion methods
Comparison of image fusion methodsComparison of image fusion methods
Comparison of image fusion methods
 

Recently uploaded

Dyslexia AI Workshop for Slideshare.pptx
Dyslexia AI Workshop for Slideshare.pptxDyslexia AI Workshop for Slideshare.pptx
Dyslexia AI Workshop for Slideshare.pptxcallscotland1987
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17Celine George
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfAdmir Softic
 
FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024Elizabeth Walsh
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxDenish Jangid
 
How to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSHow to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSCeline George
 
Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibitjbellavia9
 
Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Association for Project Management
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsMebane Rash
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxAreebaZafar22
 
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...Nguyen Thanh Tu Collection
 
Vishram Singh - Textbook of Anatomy Upper Limb and Thorax.. Volume 1 (1).pdf
Vishram Singh - Textbook of Anatomy  Upper Limb and Thorax.. Volume 1 (1).pdfVishram Singh - Textbook of Anatomy  Upper Limb and Thorax.. Volume 1 (1).pdf
Vishram Singh - Textbook of Anatomy Upper Limb and Thorax.. Volume 1 (1).pdfssuserdda66b
 
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...ZurliaSoop
 
Unit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptxUnit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptxVishalSingh1417
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxVishalSingh1417
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxheathfieldcps1
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.pptRamjanShidvankar
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfciinovamais
 
Graduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - EnglishGraduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - Englishneillewis46
 
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...christianmathematics
 

Recently uploaded (20)

Dyslexia AI Workshop for Slideshare.pptx
Dyslexia AI Workshop for Slideshare.pptxDyslexia AI Workshop for Slideshare.pptx
Dyslexia AI Workshop for Slideshare.pptx
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
 
How to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSHow to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POS
 
Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibit
 
Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan Fellows
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptx
 
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
 
Vishram Singh - Textbook of Anatomy Upper Limb and Thorax.. Volume 1 (1).pdf
Vishram Singh - Textbook of Anatomy  Upper Limb and Thorax.. Volume 1 (1).pdfVishram Singh - Textbook of Anatomy  Upper Limb and Thorax.. Volume 1 (1).pdf
Vishram Singh - Textbook of Anatomy Upper Limb and Thorax.. Volume 1 (1).pdf
 
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
 
Unit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptxUnit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptx
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptx
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptx
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.ppt
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
Graduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - EnglishGraduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - English
 
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
 

Crop classification using supervised learning techniques

  • 1. Crop-Type Classification using MLP, RBF and CCELM Objective Multi Spectral Satellite Image Classification of 6 crop types using supervised learning techniques ie; Multi Layer Perceptron Neural Networks (MLPnn), Radial Basis Function Neural Networks (RBFnn) and Circular Complex Extreme Learning Machine Approach The 4 bands of the hyper spectral data are used as the input to each of the 3 Neural Network Classifiers. Each of the implemented classifiers are trained by Back-Propagation algorithm using the same ground truth. Each of the trained classifiers are tested against the same dataset and the individual performance are compared.
  • 2. Crop-Type Classification using MLP, RBF and CCELM Multi spectral Data • The multi spectral image comprises of 4 bands, namely, Red, Blue, Green and infrared. • High resolution, four band multi spectral image of southern part of India is used to derive the data samples. It is of the dimension 1375 × 5929 pixels and it covers an area of 2.748 × 7.973 km2. This image is first divided into six distinct crop classes namely, Sugarcane, Ragi, Paddy, Mulb erry, Groundnut and Mango.
  • 3. Crop-Type Classification using MLP, RBF and CCELM Multi-spectral data The area selected for classification is the region surrounding Mysore district in Karnataka, India. This region has the required crop coverage classes and it is also wide spread and densely cultivated. It provides sufficient data samples to train the neural classifiers for all the six classes. Therefore, it serves as suitable region for an experimental study. Quick-Bird’s (operated by Digital Globe) multi-spectral (MSS) image with the resolution of 2.4m has been used as inputs. Class Class no. name C1 C2 C3 C4 C5 C6 Sugarcane Ragi Paddy Mulberry Groundnut Mango Total Number of pixels for training 100 100 100 100 100 100 600 Number of pixels for validation 400 400 400 400 400 400 2400 Parameter No of crop types Value 6 Samples for each crop type (training) 100 Samples for each crop type ( testing ) 600 No of bands for each sample 4
  • 4. Crop-Type Classification using MLP, RBF and CCELM Methods: 1. Multilayer Perceptron Neural Network (MLP-NN) divides the Input vector space into different classes by means of Hyper-planes, which is not an efficient way of classification. 2. Neural Network Structure Implemented Radial Basis Function Neural Network (RBF-NN) divides the input vector space into multiple classes, using hyper-spheres. This is a better and efficient way of classification.
  • 5. Crop-Type Classification using MLP, RBF and CCELM 3. Circular Complex Extreme Learning Machine (CCELM): This uses complex valued activation functions and complex valued weights. Hence for every hidden neuron, there are 2 decision surfaces that are orthogonal to each other. So, we have 4 decision boundaries and therefore, better classification. Advantages of CCELM over MLP and RBF: • MLP and RBF use Back Propagation algorithm for training, hence their performance may be hindered from problem of local minima. • To overcome this problem, we use Circular Complex Extreme Learning Machine (CCELM) • Extreme Learning Machine computes the required parameters by formulating the problem of solving weights as problem of finding inverse of given matrices. This greatly reduces the computational time.
  • 6. Crop-Type Classification using MLP, RBF and CCELM Performance of MLPnn C1 C2 C3 C4 C5 C6 Performance of RBFnn C1 C2 C3 C4 C5 C6 395 0 0 0 0 5 0 400 0 0 0 0 0 0 400 0 0 0 0 0 0 397 0 3 0 0 0 0 400 0 169 7 0 0 0 224 Overall efficiency = 92.33% C1 C2 C3 C4 C5 C6 C1 400 0 0 0 0 139 C2 C3 0 0 400 0 0 400 0 0 0 1 1 0 C4 0 0 0 399 0 0 C5 C6 0 5 0 0 0 0 0 1 399 0 0 260 Overall efficiency = 92.33% Performance of CCELM C1 C2 C3 C4 C5 C6 C1 C2 C3 C4 C5 C6 398 0 0 0 0 2 0 399 1 0 0 0 0 1 399 0 0 0 0 0 0 398 0 2 0 0 0 0 400 0 18 0 2 0 0 380 Overall efficiency = 98.9%