SlideShare a Scribd company logo
1 of 35
Download to read offline
Outline
Self-Organized Map
Case Study
Want More Information?
Self-Organized Map
Mr.Sanjay Shitole
Department of Information Technology
Usha Mittal Institute of Technology for Women
SNDT Women’s University, Santacruz(w), Mumbai.
27 March 2010
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Outline of Topics
1 Self-Organized Map
Applications
Architectures
Algorithm
2 Case Study
Land-use Classification
Classification of Antarctic Satellite Imagery
3 Want More Information?
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Applications
Statistical pattern recognition, especially recognition of
speech.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Applications
Statistical pattern recognition, especially recognition of
speech.
Control of robot arms, and other problems in robotics.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Applications
Statistical pattern recognition, especially recognition of
speech.
Control of robot arms, and other problems in robotics.
Control of industrial process, especially diffusion processes in
the production of semiconductor substrates.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Applications
Statistical pattern recognition, especially recognition of
speech.
Control of robot arms, and other problems in robotics.
Control of industrial process, especially diffusion processes in
the production of semiconductor substrates.
Automatic synthesis of digital systems.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Applications
Statistical pattern recognition, especially recognition of
speech.
Control of robot arms, and other problems in robotics.
Control of industrial process, especially diffusion processes in
the production of semiconductor substrates.
Automatic synthesis of digital systems.
Adaptive devices for various telecommunications tasks.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Applications
Statistical pattern recognition, especially recognition of
speech.
Control of robot arms, and other problems in robotics.
Control of industrial process, especially diffusion processes in
the production of semiconductor substrates.
Automatic synthesis of digital systems.
Adaptive devices for various telecommunications tasks.
Image compression.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Applications
Statistical pattern recognition, especially recognition of
speech.
Control of robot arms, and other problems in robotics.
Control of industrial process, especially diffusion processes in
the production of semiconductor substrates.
Automatic synthesis of digital systems.
Adaptive devices for various telecommunications tasks.
Image compression.
Radar classification of sea-ice.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Applications
Statistical pattern recognition, especially recognition of
speech.
Control of robot arms, and other problems in robotics.
Control of industrial process, especially diffusion processes in
the production of semiconductor substrates.
Automatic synthesis of digital systems.
Adaptive devices for various telecommunications tasks.
Image compression.
Radar classification of sea-ice.
Optimization problems.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Applications
Statistical pattern recognition, especially recognition of
speech.
Control of robot arms, and other problems in robotics.
Control of industrial process, especially diffusion processes in
the production of semiconductor substrates.
Automatic synthesis of digital systems.
Adaptive devices for various telecommunications tasks.
Image compression.
Radar classification of sea-ice.
Optimization problems.
Sentence understanding.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Applications
Statistical pattern recognition, especially recognition of
speech.
Control of robot arms, and other problems in robotics.
Control of industrial process, especially diffusion processes in
the production of semiconductor substrates.
Automatic synthesis of digital systems.
Adaptive devices for various telecommunications tasks.
Image compression.
Radar classification of sea-ice.
Optimization problems.
Sentence understanding.
Application of expertise in conceptual domain.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Applications
Statistical pattern recognition, especially recognition of
speech.
Control of robot arms, and other problems in robotics.
Control of industrial process, especially diffusion processes in
the production of semiconductor substrates.
Automatic synthesis of digital systems.
Adaptive devices for various telecommunications tasks.
Image compression.
Radar classification of sea-ice.
Optimization problems.
Sentence understanding.
Application of expertise in conceptual domain.
Classification of insect courtship songs.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Architectures
Figure: SOM Architecture
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Algorithm
[1] Initialize the weights Wij (1 < i ≤ n, 1 < j < m) small random
values, where m is the total number of nodes in the map. Set the
initial radius of the neighbourhood around node j as Nj (t).
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Algorithm
[1] Initialize the weights Wij (1 < i ≤ n, 1 < j < m) small random
values, where m is the total number of nodes in the map. Set the
initial radius of the neighbourhood around node j as Nj (t).
2 Present inputs X1(t), X2(t), X3(t), . . . , Xn(t). Where Xi (t) is the
ith input to the node j at time t.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
Algorithm
[1] Initialize the weights Wij (1 < i ≤ n, 1 < j < m) small random
values, where m is the total number of nodes in the map. Set the
initial radius of the neighbourhood around node j as Nj (t).
2 Present inputs X1(t), X2(t), X3(t), . . . , Xn(t). Where Xi (t) is the
ith input to the node j at time t.
3 Calculate the distance dj between the inputs and node j by
dj =
n
i=1
(Xi (t) − Wij (t))2
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
[4] Determine j∗ which minimizes dj .
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
[4] Determine j∗ which minimizes dj .
5 Update weights for j∗ and its neighbours mNj (t), the new weights
for j in Nj∗(t) are Wij (t + 1) = Wij + α(t)(Xi (t) − Wij (t)).
Where α(t) is the learning rate. α(t) and Nj∗(t) are controlled so
as to decrease in t .
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Applications
Architectures
Algorithm
[4] Determine j∗ which minimizes dj .
5 Update weights for j∗ and its neighbours mNj (t), the new weights
for j in Nj∗(t) are Wij (t + 1) = Wij + α(t)(Xi (t) − Wij (t)).
Where α(t) is the learning rate. α(t) and Nj∗(t) are controlled so
as to decrease in t .
6 If process reaches the maximum number of iterations, stop
otherwise go to step 2.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Land-use Classification
Classification of Antarctic Satellite Imagery
Introduction
Rapid growth of City
Planning
To monitor land use, land cover change
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Land-use Classification
Classification of Antarctic Satellite Imagery
New sensor ASTER data and preparation
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Land-use Classification
Classification of Antarctic Satellite Imagery
Conclusions and discussion
Table: Training and testing samples
Classes Land cover types Description Training data Testing data
1 Water River, pond 4132 847
2 Forest Planted, nature trees 2797 670
3 Grass Grass, winter wheat 2643 369
4 Farmland Agriculture 5670 1041
5 Roads Highway, city 2712 332
6 Urban Residents, commercial area 7761 1302
7 Other Construction area 1347 171
Total 27062 4722
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Land-use Classification
Classification of Antarctic Satellite Imagery
Conclusions and discussion
Table: The matrix of KSOM classification result
Class Water Forest Grass Farmland Road Urban Other Accuracy (%)
Water 796 0 0 0 37 1 0 95.44
Forest 0 663 0 6 0 0 0 99.10
Grass 0 7 369 0 0 0 0 98.14
Farmland 0 0 0 1018 0 3 0 99.71
Road 49 0 0 0 276 50 0 73.60
Urban 2 0 0 17 9 1248 23 96.07
Other 0 0 0 0 0 0 148 100
Total 847 670 369 1041 322 1302 171
Ground Ref. (%) 93.98 98.96 100 97.79 85.71 95.85 86.55
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Land-use Classification
Classification of Antarctic Satellite Imagery
New sensor ASTER data and preparation
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Land-use Classification
Classification of Antarctic Satellite Imagery
Conclusions
The quality of ASTER data is good for land use mapping.
The KSOM accomplished 95.68% accuracy
7% more accurate than traditional classifier.
Better results are achived for city and farmland classes.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Land-use Classification
Classification of Antarctic Satellite Imagery
Introduction
1 To study relationship between the Antarctic ice cap and
climatic global warming.
2 Obtain daily analyses of sea ice regions near the Antarctic
bases in order to assist shipping operations.
3 Manual interpretation of remotly sensed data:time-consuming
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Land-use Classification
Classification of Antarctic Satellite Imagery
Figure: Band 1 of the naoo 0.0055 imageMr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Land-use Classification
Classification of Antarctic Satellite Imagery
Figure: Seaice map from noaa.OM image using trained SOM.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Want More Information?
Jacek M.Zurada, 2001. “Introduction to Artificial Neural
Network”’, Fourth edition, Jaico publishing house.
Simon Haykin, “ Neural Networks, A Comprehensive
Foundation”’, Second Edition, Pearson Education.
Kohonen, T. 1990.“ The Self Organizing Map”’, Proc. IEEE
78(9):1464-1480
Ma Jianwen 1, Hasi Bagan. “Land-use classication using
ASTER data and self-organized neutral networks”,
International Journal of Applied Earth Observation and
Geoinformation 7 (2005) 183188.
D. Kilpatrick and R. Willams, Unsupervised Classification of
Antarctic Satellite Imagery using Kohonen’s Self Organising
Feature Map.,0-7803-2768-3/95/1995 IEEE.
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Thank you
Mr.Sanjay Shitole Self-Organized Map
Outline
Self-Organized Map
Case Study
Want More Information?
Doubts???
email: shitoless@rediffmail.com
mobile: 9892301603
Mr.Sanjay Shitole Self-Organized Map

More Related Content

What's hot

شرح مبسط عن الخوارزميات الجينية باستخدام الحاسبات
شرح مبسط عن الخوارزميات الجينية باستخدام الحاسباتشرح مبسط عن الخوارزميات الجينية باستخدام الحاسبات
شرح مبسط عن الخوارزميات الجينية باستخدام الحاسبات
sayAAhmad
 
Linear Systems Gauss Seidel
Linear Systems   Gauss SeidelLinear Systems   Gauss Seidel
Linear Systems Gauss Seidel
Eric Davishahl
 
Stressen's matrix multiplication
Stressen's matrix multiplicationStressen's matrix multiplication
Stressen's matrix multiplication
Kumar
 

What's hot (20)

شرح مبسط عن الخوارزميات الجينية باستخدام الحاسبات
شرح مبسط عن الخوارزميات الجينية باستخدام الحاسباتشرح مبسط عن الخوارزميات الجينية باستخدام الحاسبات
شرح مبسط عن الخوارزميات الجينية باستخدام الحاسبات
 
09. amortized analysis
09. amortized analysis09. amortized analysis
09. amortized analysis
 
strassen matrix multiplication algorithm
strassen matrix multiplication algorithmstrassen matrix multiplication algorithm
strassen matrix multiplication algorithm
 
linear transfermation.pptx
linear transfermation.pptxlinear transfermation.pptx
linear transfermation.pptx
 
Divide and Conquer
Divide and ConquerDivide and Conquer
Divide and Conquer
 
Linear Systems Gauss Seidel
Linear Systems   Gauss SeidelLinear Systems   Gauss Seidel
Linear Systems Gauss Seidel
 
Stressen's matrix multiplication
Stressen's matrix multiplicationStressen's matrix multiplication
Stressen's matrix multiplication
 
cyclic_code.pdf
cyclic_code.pdfcyclic_code.pdf
cyclic_code.pdf
 
Basics of Computer graphics lab
Basics of Computer graphics labBasics of Computer graphics lab
Basics of Computer graphics lab
 
Btech_II_ engineering mathematics_unit1
Btech_II_ engineering mathematics_unit1Btech_II_ engineering mathematics_unit1
Btech_II_ engineering mathematics_unit1
 
DOUBLE INTEGRALS PPT GTU CALCULUS (2110014)
DOUBLE INTEGRALS PPT GTU CALCULUS (2110014) DOUBLE INTEGRALS PPT GTU CALCULUS (2110014)
DOUBLE INTEGRALS PPT GTU CALCULUS (2110014)
 
Amortized Analysis
Amortized Analysis Amortized Analysis
Amortized Analysis
 
Find Transitive closure of a Graph Using Warshall's Algorithm
Find Transitive closure of a Graph Using Warshall's AlgorithmFind Transitive closure of a Graph Using Warshall's Algorithm
Find Transitive closure of a Graph Using Warshall's Algorithm
 
Edge linking in image processing
Edge linking in image processingEdge linking in image processing
Edge linking in image processing
 
Jacobi method
Jacobi methodJacobi method
Jacobi method
 
Application of edge detection
Application of edge detectionApplication of edge detection
Application of edge detection
 
Traveling Salesman Problem
Traveling Salesman Problem Traveling Salesman Problem
Traveling Salesman Problem
 
Power method
Power methodPower method
Power method
 
Image processing on matlab presentation
Image processing on matlab presentationImage processing on matlab presentation
Image processing on matlab presentation
 
Bezier Curve in Computer Graphics.docx
Bezier Curve in Computer Graphics.docxBezier Curve in Computer Graphics.docx
Bezier Curve in Computer Graphics.docx
 

Similar to SOFM based calssification for LU

A novel embedded hybrid thinning algorithm for
A novel embedded hybrid thinning algorithm forA novel embedded hybrid thinning algorithm for
A novel embedded hybrid thinning algorithm for
prjpublications
 
ODSC 2019: Sessionisation via stochastic periods for root event identification
ODSC 2019: Sessionisation via stochastic periods for root event identificationODSC 2019: Sessionisation via stochastic periods for root event identification
ODSC 2019: Sessionisation via stochastic periods for root event identification
Kuldeep Jiwani
 
Ijarcet vol-2-issue-3-938-941
Ijarcet vol-2-issue-3-938-941Ijarcet vol-2-issue-3-938-941
Ijarcet vol-2-issue-3-938-941
Editor IJARCET
 

Similar to SOFM based calssification for LU (20)

IRJET- Different Techniques for Mob Density Evaluation
IRJET- Different Techniques for Mob Density EvaluationIRJET- Different Techniques for Mob Density Evaluation
IRJET- Different Techniques for Mob Density Evaluation
 
Intoduction to Neural Network
Intoduction to Neural NetworkIntoduction to Neural Network
Intoduction to Neural Network
 
Ijetcas14 308
Ijetcas14 308Ijetcas14 308
Ijetcas14 308
 
CLIM: Transition Workshop - A Notional Framework for a Theory of Data Systems...
CLIM: Transition Workshop - A Notional Framework for a Theory of Data Systems...CLIM: Transition Workshop - A Notional Framework for a Theory of Data Systems...
CLIM: Transition Workshop - A Notional Framework for a Theory of Data Systems...
 
AHRI Queensland Analytics Network - The 6 S Analytics Framework
AHRI Queensland Analytics Network - The 6 S Analytics FrameworkAHRI Queensland Analytics Network - The 6 S Analytics Framework
AHRI Queensland Analytics Network - The 6 S Analytics Framework
 
IRJET - Application of Linear Algebra in Machine Learning
IRJET -  	  Application of Linear Algebra in Machine LearningIRJET -  	  Application of Linear Algebra in Machine Learning
IRJET - Application of Linear Algebra in Machine Learning
 
IRJET - Conversion of Ancient Tamil Characters to Modern Tamil Characters
IRJET -  	  Conversion of Ancient Tamil Characters to Modern Tamil CharactersIRJET -  	  Conversion of Ancient Tamil Characters to Modern Tamil Characters
IRJET - Conversion of Ancient Tamil Characters to Modern Tamil Characters
 
QMC: Undergraduate Workshop, Monte Carlo Techniques in Earth Science - Amit A...
QMC: Undergraduate Workshop, Monte Carlo Techniques in Earth Science - Amit A...QMC: Undergraduate Workshop, Monte Carlo Techniques in Earth Science - Amit A...
QMC: Undergraduate Workshop, Monte Carlo Techniques in Earth Science - Amit A...
 
IRJET - Cardless ATM
IRJET -  	  Cardless ATMIRJET -  	  Cardless ATM
IRJET - Cardless ATM
 
A novel embedded hybrid thinning algorithm for
A novel embedded hybrid thinning algorithm forA novel embedded hybrid thinning algorithm for
A novel embedded hybrid thinning algorithm for
 
Implementation and performance evaluation of
Implementation and performance evaluation ofImplementation and performance evaluation of
Implementation and performance evaluation of
 
Dealing with the need for Infrastructural Support in Ambient Intelligence
Dealing with the need for Infrastructural Support in Ambient IntelligenceDealing with the need for Infrastructural Support in Ambient Intelligence
Dealing with the need for Infrastructural Support in Ambient Intelligence
 
Stereo lithography - Report
Stereo lithography - ReportStereo lithography - Report
Stereo lithography - Report
 
IRJET- Next Generation System Assistant
IRJET- Next Generation System AssistantIRJET- Next Generation System Assistant
IRJET- Next Generation System Assistant
 
Self-Learning Systems for Cyber Security
Self-Learning Systems for Cyber SecuritySelf-Learning Systems for Cyber Security
Self-Learning Systems for Cyber Security
 
Fuzzy Type Image Fusion Using SPIHT Image Compression Technique
Fuzzy Type Image Fusion Using SPIHT Image Compression TechniqueFuzzy Type Image Fusion Using SPIHT Image Compression Technique
Fuzzy Type Image Fusion Using SPIHT Image Compression Technique
 
ODSC 2019: Sessionisation via stochastic periods for root event identification
ODSC 2019: Sessionisation via stochastic periods for root event identificationODSC 2019: Sessionisation via stochastic periods for root event identification
ODSC 2019: Sessionisation via stochastic periods for root event identification
 
Criminal Identification using Arm7
Criminal Identification using Arm7Criminal Identification using Arm7
Criminal Identification using Arm7
 
Ijarcet vol-2-issue-3-938-941
Ijarcet vol-2-issue-3-938-941Ijarcet vol-2-issue-3-938-941
Ijarcet vol-2-issue-3-938-941
 
REVIEW OF VIRTUAL ARTICULATED ROBOT
REVIEW OF VIRTUAL ARTICULATED ROBOTREVIEW OF VIRTUAL ARTICULATED ROBOT
REVIEW OF VIRTUAL ARTICULATED ROBOT
 

More from Dr. Sanjay Shitole

More from Dr. Sanjay Shitole (10)

Research_presentation_IIC.pdf
Research_presentation_IIC.pdfResearch_presentation_IIC.pdf
Research_presentation_IIC.pdf
 
importance_RP.pdf
importance_RP.pdfimportance_RP.pdf
importance_RP.pdf
 
IPR.pdf
IPR.pdfIPR.pdf
IPR.pdf
 
Machine Learning based predictive analytics
Machine Learning based predictive analyticsMachine Learning based predictive analytics
Machine Learning based predictive analytics
 
IoT with Python
IoT with PythonIoT with Python
IoT with Python
 
Image Processing Techniques: Remote Sensing Perspective
Image Processing Techniques: Remote Sensing PerspectiveImage Processing Techniques: Remote Sensing Perspective
Image Processing Techniques: Remote Sensing Perspective
 
Modern Trends in Engineering, Science and Technology
Modern Trends in Engineering, Science and TechnologyModern Trends in Engineering, Science and Technology
Modern Trends in Engineering, Science and Technology
 
Scientific Computing with GNU-Octave
Scientific Computing with GNU-OctaveScientific Computing with GNU-Octave
Scientific Computing with GNU-Octave
 
What is Xfig
What is XfigWhat is Xfig
What is Xfig
 
Scientific Paper Writing
Scientific Paper WritingScientific Paper Writing
Scientific Paper Writing
 

Recently uploaded

Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
gajnagarg
 
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
vexqp
 
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
wsppdmt
 
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
nirzagarg
 
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
Health
 
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
nirzagarg
 
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
gajnagarg
 

Recently uploaded (20)

Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
 
RESEARCH-FINAL-DEFENSE-PPT-TEMPLATE.pptx
RESEARCH-FINAL-DEFENSE-PPT-TEMPLATE.pptxRESEARCH-FINAL-DEFENSE-PPT-TEMPLATE.pptx
RESEARCH-FINAL-DEFENSE-PPT-TEMPLATE.pptx
 
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
 
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
 
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
 
Ranking and Scoring Exercises for Research
Ranking and Scoring Exercises for ResearchRanking and Scoring Exercises for Research
Ranking and Scoring Exercises for Research
 
Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book now
Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book nowVadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book now
Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book now
 
7. Epi of Chronic respiratory diseases.ppt
7. Epi of Chronic respiratory diseases.ppt7. Epi of Chronic respiratory diseases.ppt
7. Epi of Chronic respiratory diseases.ppt
 
20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdf20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdf
 
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
 
TrafficWave Generator Will Instantly drive targeted and engaging traffic back...
TrafficWave Generator Will Instantly drive targeted and engaging traffic back...TrafficWave Generator Will Instantly drive targeted and engaging traffic back...
TrafficWave Generator Will Instantly drive targeted and engaging traffic back...
 
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
 
Aspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - AlmoraAspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - Almora
 
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
 
Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...
Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...
Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...
 
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...
 
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
 
Predicting HDB Resale Prices - Conducting Linear Regression Analysis With Orange
Predicting HDB Resale Prices - Conducting Linear Regression Analysis With OrangePredicting HDB Resale Prices - Conducting Linear Regression Analysis With Orange
Predicting HDB Resale Prices - Conducting Linear Regression Analysis With Orange
 

SOFM based calssification for LU

  • 1. Outline Self-Organized Map Case Study Want More Information? Self-Organized Map Mr.Sanjay Shitole Department of Information Technology Usha Mittal Institute of Technology for Women SNDT Women’s University, Santacruz(w), Mumbai. 27 March 2010 Mr.Sanjay Shitole Self-Organized Map
  • 2. Outline Self-Organized Map Case Study Want More Information? Outline of Topics 1 Self-Organized Map Applications Architectures Algorithm 2 Case Study Land-use Classification Classification of Antarctic Satellite Imagery 3 Want More Information? Mr.Sanjay Shitole Self-Organized Map
  • 3. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Applications Statistical pattern recognition, especially recognition of speech. Mr.Sanjay Shitole Self-Organized Map
  • 4. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Applications Statistical pattern recognition, especially recognition of speech. Control of robot arms, and other problems in robotics. Mr.Sanjay Shitole Self-Organized Map
  • 5. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Applications Statistical pattern recognition, especially recognition of speech. Control of robot arms, and other problems in robotics. Control of industrial process, especially diffusion processes in the production of semiconductor substrates. Mr.Sanjay Shitole Self-Organized Map
  • 6. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Applications Statistical pattern recognition, especially recognition of speech. Control of robot arms, and other problems in robotics. Control of industrial process, especially diffusion processes in the production of semiconductor substrates. Automatic synthesis of digital systems. Mr.Sanjay Shitole Self-Organized Map
  • 7. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Applications Statistical pattern recognition, especially recognition of speech. Control of robot arms, and other problems in robotics. Control of industrial process, especially diffusion processes in the production of semiconductor substrates. Automatic synthesis of digital systems. Adaptive devices for various telecommunications tasks. Mr.Sanjay Shitole Self-Organized Map
  • 8. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Applications Statistical pattern recognition, especially recognition of speech. Control of robot arms, and other problems in robotics. Control of industrial process, especially diffusion processes in the production of semiconductor substrates. Automatic synthesis of digital systems. Adaptive devices for various telecommunications tasks. Image compression. Mr.Sanjay Shitole Self-Organized Map
  • 9. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Applications Statistical pattern recognition, especially recognition of speech. Control of robot arms, and other problems in robotics. Control of industrial process, especially diffusion processes in the production of semiconductor substrates. Automatic synthesis of digital systems. Adaptive devices for various telecommunications tasks. Image compression. Radar classification of sea-ice. Mr.Sanjay Shitole Self-Organized Map
  • 10. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Applications Statistical pattern recognition, especially recognition of speech. Control of robot arms, and other problems in robotics. Control of industrial process, especially diffusion processes in the production of semiconductor substrates. Automatic synthesis of digital systems. Adaptive devices for various telecommunications tasks. Image compression. Radar classification of sea-ice. Optimization problems. Mr.Sanjay Shitole Self-Organized Map
  • 11. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Applications Statistical pattern recognition, especially recognition of speech. Control of robot arms, and other problems in robotics. Control of industrial process, especially diffusion processes in the production of semiconductor substrates. Automatic synthesis of digital systems. Adaptive devices for various telecommunications tasks. Image compression. Radar classification of sea-ice. Optimization problems. Sentence understanding. Mr.Sanjay Shitole Self-Organized Map
  • 12. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Applications Statistical pattern recognition, especially recognition of speech. Control of robot arms, and other problems in robotics. Control of industrial process, especially diffusion processes in the production of semiconductor substrates. Automatic synthesis of digital systems. Adaptive devices for various telecommunications tasks. Image compression. Radar classification of sea-ice. Optimization problems. Sentence understanding. Application of expertise in conceptual domain. Mr.Sanjay Shitole Self-Organized Map
  • 13. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Applications Statistical pattern recognition, especially recognition of speech. Control of robot arms, and other problems in robotics. Control of industrial process, especially diffusion processes in the production of semiconductor substrates. Automatic synthesis of digital systems. Adaptive devices for various telecommunications tasks. Image compression. Radar classification of sea-ice. Optimization problems. Sentence understanding. Application of expertise in conceptual domain. Classification of insect courtship songs. Mr.Sanjay Shitole Self-Organized Map
  • 14. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Architectures Figure: SOM Architecture Mr.Sanjay Shitole Self-Organized Map
  • 15. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Mr.Sanjay Shitole Self-Organized Map
  • 16. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Mr.Sanjay Shitole Self-Organized Map
  • 17. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Mr.Sanjay Shitole Self-Organized Map
  • 18. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Algorithm [1] Initialize the weights Wij (1 < i ≤ n, 1 < j < m) small random values, where m is the total number of nodes in the map. Set the initial radius of the neighbourhood around node j as Nj (t). Mr.Sanjay Shitole Self-Organized Map
  • 19. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Algorithm [1] Initialize the weights Wij (1 < i ≤ n, 1 < j < m) small random values, where m is the total number of nodes in the map. Set the initial radius of the neighbourhood around node j as Nj (t). 2 Present inputs X1(t), X2(t), X3(t), . . . , Xn(t). Where Xi (t) is the ith input to the node j at time t. Mr.Sanjay Shitole Self-Organized Map
  • 20. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm Algorithm [1] Initialize the weights Wij (1 < i ≤ n, 1 < j < m) small random values, where m is the total number of nodes in the map. Set the initial radius of the neighbourhood around node j as Nj (t). 2 Present inputs X1(t), X2(t), X3(t), . . . , Xn(t). Where Xi (t) is the ith input to the node j at time t. 3 Calculate the distance dj between the inputs and node j by dj = n i=1 (Xi (t) − Wij (t))2 Mr.Sanjay Shitole Self-Organized Map
  • 21. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm [4] Determine j∗ which minimizes dj . Mr.Sanjay Shitole Self-Organized Map
  • 22. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm [4] Determine j∗ which minimizes dj . 5 Update weights for j∗ and its neighbours mNj (t), the new weights for j in Nj∗(t) are Wij (t + 1) = Wij + α(t)(Xi (t) − Wij (t)). Where α(t) is the learning rate. α(t) and Nj∗(t) are controlled so as to decrease in t . Mr.Sanjay Shitole Self-Organized Map
  • 23. Outline Self-Organized Map Case Study Want More Information? Applications Architectures Algorithm [4] Determine j∗ which minimizes dj . 5 Update weights for j∗ and its neighbours mNj (t), the new weights for j in Nj∗(t) are Wij (t + 1) = Wij + α(t)(Xi (t) − Wij (t)). Where α(t) is the learning rate. α(t) and Nj∗(t) are controlled so as to decrease in t . 6 If process reaches the maximum number of iterations, stop otherwise go to step 2. Mr.Sanjay Shitole Self-Organized Map
  • 24. Outline Self-Organized Map Case Study Want More Information? Land-use Classification Classification of Antarctic Satellite Imagery Introduction Rapid growth of City Planning To monitor land use, land cover change Mr.Sanjay Shitole Self-Organized Map
  • 25. Outline Self-Organized Map Case Study Want More Information? Land-use Classification Classification of Antarctic Satellite Imagery New sensor ASTER data and preparation Mr.Sanjay Shitole Self-Organized Map
  • 26. Outline Self-Organized Map Case Study Want More Information? Land-use Classification Classification of Antarctic Satellite Imagery Conclusions and discussion Table: Training and testing samples Classes Land cover types Description Training data Testing data 1 Water River, pond 4132 847 2 Forest Planted, nature trees 2797 670 3 Grass Grass, winter wheat 2643 369 4 Farmland Agriculture 5670 1041 5 Roads Highway, city 2712 332 6 Urban Residents, commercial area 7761 1302 7 Other Construction area 1347 171 Total 27062 4722 Mr.Sanjay Shitole Self-Organized Map
  • 27. Outline Self-Organized Map Case Study Want More Information? Land-use Classification Classification of Antarctic Satellite Imagery Conclusions and discussion Table: The matrix of KSOM classification result Class Water Forest Grass Farmland Road Urban Other Accuracy (%) Water 796 0 0 0 37 1 0 95.44 Forest 0 663 0 6 0 0 0 99.10 Grass 0 7 369 0 0 0 0 98.14 Farmland 0 0 0 1018 0 3 0 99.71 Road 49 0 0 0 276 50 0 73.60 Urban 2 0 0 17 9 1248 23 96.07 Other 0 0 0 0 0 0 148 100 Total 847 670 369 1041 322 1302 171 Ground Ref. (%) 93.98 98.96 100 97.79 85.71 95.85 86.55 Mr.Sanjay Shitole Self-Organized Map
  • 28. Outline Self-Organized Map Case Study Want More Information? Land-use Classification Classification of Antarctic Satellite Imagery New sensor ASTER data and preparation Mr.Sanjay Shitole Self-Organized Map
  • 29. Outline Self-Organized Map Case Study Want More Information? Land-use Classification Classification of Antarctic Satellite Imagery Conclusions The quality of ASTER data is good for land use mapping. The KSOM accomplished 95.68% accuracy 7% more accurate than traditional classifier. Better results are achived for city and farmland classes. Mr.Sanjay Shitole Self-Organized Map
  • 30. Outline Self-Organized Map Case Study Want More Information? Land-use Classification Classification of Antarctic Satellite Imagery Introduction 1 To study relationship between the Antarctic ice cap and climatic global warming. 2 Obtain daily analyses of sea ice regions near the Antarctic bases in order to assist shipping operations. 3 Manual interpretation of remotly sensed data:time-consuming Mr.Sanjay Shitole Self-Organized Map
  • 31. Outline Self-Organized Map Case Study Want More Information? Land-use Classification Classification of Antarctic Satellite Imagery Figure: Band 1 of the naoo 0.0055 imageMr.Sanjay Shitole Self-Organized Map
  • 32. Outline Self-Organized Map Case Study Want More Information? Land-use Classification Classification of Antarctic Satellite Imagery Figure: Seaice map from noaa.OM image using trained SOM. Mr.Sanjay Shitole Self-Organized Map
  • 33. Outline Self-Organized Map Case Study Want More Information? Want More Information? Jacek M.Zurada, 2001. “Introduction to Artificial Neural Network”’, Fourth edition, Jaico publishing house. Simon Haykin, “ Neural Networks, A Comprehensive Foundation”’, Second Edition, Pearson Education. Kohonen, T. 1990.“ The Self Organizing Map”’, Proc. IEEE 78(9):1464-1480 Ma Jianwen 1, Hasi Bagan. “Land-use classication using ASTER data and self-organized neutral networks”, International Journal of Applied Earth Observation and Geoinformation 7 (2005) 183188. D. Kilpatrick and R. Willams, Unsupervised Classification of Antarctic Satellite Imagery using Kohonen’s Self Organising Feature Map.,0-7803-2768-3/95/1995 IEEE. Mr.Sanjay Shitole Self-Organized Map
  • 34. Outline Self-Organized Map Case Study Want More Information? Thank you Mr.Sanjay Shitole Self-Organized Map
  • 35. Outline Self-Organized Map Case Study Want More Information? Doubts??? email: shitoless@rediffmail.com mobile: 9892301603 Mr.Sanjay Shitole Self-Organized Map