SlideShare una empresa de Scribd logo
1 de 24
Few Statistics…

(Source:
http://www.cbsl.gov.lk/pics_n_docs/10_pub/_doc
s/statistics)

Time and Savings Deposits held by the Public
2010

1,405,808

2011

1,753,896

2012

2,143,136

Crime Rate in Sri Lanka
(Source: http://www.police.lk/index.php/crime-trends)

Health Expenditure in Sri Lanka
(Source: http://www.who.int/gho/countries/lka.pdf)
Introduction
 What is Weave-D?
 Inspired by human brain
 Data Accumulating, Learning and Fusing
System

Supports Multimodal data

 Video

Incremental
learning

Inspiration
source
Why Weave-D?

Apply previous
knowledge to acquire
new knowledge

Heterogeneous

?

Handle
data
Come as chunks

Prevent
catastrophic
forgetting

Incremental
learning

?

Growth of information
Intuitive
Visualizing
information

Simple

Generalization of
acquired knowledge

?

Conceptualization

?
Business Value
 Medical
 What we can mine?
 New patient has a cancer or not?
 Effective medicine for certain diseases
 Diseases distribution in the country
 E.g. Anuradhapura – more kidney diseases
Business Value
 Finance
 Predict customers’ transactional behaviors, so
banks can plan their strategies ahead

 Forensics or Police
 Predict criminal behavior
 Identify crimes with similar
evidence

 And many more…
Similar Products
 IBM Watson
 Developed by IBM to compete in Jeopardy
 A Question answering system
 Consumes “millions” of Wikipedia pages and try
to find answers from the knowledge acquired
 Finance and health care domains
Uniqueness
RapidMiner

IBM Watson

Weave-D

Support heterogeneous
data

x

x



Learn without forgetting
past data

x

x



Support analyzing at
different granularities

x

x



Visualization







Fast response

x



x
What does Weave-D do?
Weave-D architecture
Raw Data

Learning
Component

Link
Generators

Perception
Model

Logger

XML Writers

XML Outputs

Persistence

Persistence
Handlers

Feature
Extractor
Facade

Configuration
Loaders

Business Logic

Feature Extractors

Weave-D Facade

XML Parsers

Data Models

Config files
XML

User
Interfaces

3D
Visualization
Interface

Presentation
Knowledge Representation
Layer 1 (Day 1)

Day
Input

1

Layer 2 (Day 2)

Layer 3 (Day 3)

2

3
C3

C1

Child (4-8 years old)

Child (8-12 years old)

Child (1-4 years old)

C4

Forest (Autumn)

Forest (Spring)

Forest (Winter)

C2

City (Day view)

C5 City (Night view)
(None)

Sunset view

Dataset 1

Dataset 2

Sunset view

Dataset 3
Demonstration - Scenario
 Description
 Sam is a sports enthusiast. He has a set of
images belonging to following sports; Croquet,
Polo, Rock-climbing, Sailing, Rowing,
Badminton. Also he has a small description of
the sport for each image. He needs to cluster
these images and text by the sports category.

 Constraints
 All the photos are not available to him at once.
He gets sets of images each day. (Incremental
learning)
User’s Point of View


Input
 Query image



Expected outcomes
 Set of related images and documents explaining the sport



Tasks
 Setting up Weave-D
 Training Weave-D
 Querying from Weave-D
 Sam doesn’t know what sport this is (Query image)
 Meaningless file names!
 Get documents explaining the sport denoted by image
Images

What happens inside?
Query
Image

Result Images

Text

Day 1

Day 2

Day 3

Result Text

Time Series Links
Associative Links
Bigger Picture!!!
 Medical domain
 Forensic domain
Methodology Standards
 Agile development – Scrum
 Documentation
 Architecture documents
 Class diagrams

 Git version controlling
 Tests
Class Diagrams

Milestones

Github

Website

Architecture
Document
Implementation Standards
 Rich client platform
 Object Oriented Programming
 Design patterns
 Factories
 Facades
 Command Objects

 High decoupling
 XML Configuration
Monetization Plans?


Promotions through Social Media
 Facebook
 Google+



Advertising on Data Mining websites
 KDNuggets



Discussions
 ICTA
 Private Hospitals
 Private Investigation Agencies



National
Hospital

Investments?
 Project group
Sri Lanka
Police
Few years ahead in Money
Path
Sell 5 units
1 unit = 80K-100K

Part Time
Today

Initial
Investment
(Rs.100,000)

Full Time

January,
2014

1st Release

Advertising
campaign
(Rs. 15,000)

Sell 10 units
1 unit = 150K-200K

January,
2015

January,
2016

2nd Release

Labor cost (4
members)
(Rs. 60,000)

Break even
Other
(Rs. 25,000)

Profitable
Glimpse to the Future
 Support mining information at different
granularities
 Extend Weave-D Client-Server architecture
 Support already existing standards (e.g.
PMML)
Further Resources
 Website:
http://weave-d.com/
 Facebook Page:
https://www.facebook.com/treadlabz.weave
d
 Google+ Page:
https://plus.google.com/10278520548758371885
9
Thank you

Más contenido relacionado

Destacado

El día de los muertos document
El día de los muertos documentEl día de los muertos document
El día de los muertos documentZach Sanchez
 
Grammar book semester 2
Grammar book semester 2Grammar book semester 2
Grammar book semester 2Zach Sanchez
 
Actividad 2 (permanente)
Actividad 2 (permanente)Actividad 2 (permanente)
Actividad 2 (permanente)AlbaPelirroja
 
Grammar book #2
Grammar book #2Grammar book #2
Grammar book #2es10190
 
Collective bargaining india
Collective bargaining indiaCollective bargaining india
Collective bargaining indiasulejen
 

Destacado (7)

El día de los muertos document
El día de los muertos documentEl día de los muertos document
El día de los muertos document
 
Grammar book semester 2
Grammar book semester 2Grammar book semester 2
Grammar book semester 2
 
Actividad 2 (permanente)
Actividad 2 (permanente)Actividad 2 (permanente)
Actividad 2 (permanente)
 
Grammar book #2
Grammar book #2Grammar book #2
Grammar book #2
 
Grammarhandbook
GrammarhandbookGrammarhandbook
Grammarhandbook
 
Grammar handbook
Grammar handbookGrammar handbook
Grammar handbook
 
Collective bargaining india
Collective bargaining indiaCollective bargaining india
Collective bargaining india
 

Similar a NBQSA 2nd round Presentation

Questions On The And Football
Questions On The And FootballQuestions On The And Football
Questions On The And FootballAmanda Gray
 
Data Science in the Real World: Making a Difference
Data Science in the Real World: Making a Difference Data Science in the Real World: Making a Difference
Data Science in the Real World: Making a Difference Srinath Perera
 
ICPSR - Complex Systems Models in the Social Sciences - Lecture 6 - Professor...
ICPSR - Complex Systems Models in the Social Sciences - Lecture 6 - Professor...ICPSR - Complex Systems Models in the Social Sciences - Lecture 6 - Professor...
ICPSR - Complex Systems Models in the Social Sciences - Lecture 6 - Professor...Daniel Katz
 
Developing a Federal Vision for Identity Management
Developing a Federal Vision for Identity ManagementDeveloping a Federal Vision for Identity Management
Developing a Federal Vision for Identity ManagementDuane Blackburn
 
IGSS Corporate Briefing
IGSS Corporate BriefingIGSS Corporate Briefing
IGSS Corporate Briefingmrsjennbrown
 
computer projecttttttttttttttttttttttttttttttttttttttttt
computer projectttttttttttttttttttttttttttttttttttttttttcomputer projecttttttttttttttttttttttttttttttttttttttttt
computer projectttttttttttttttttttttttttttttttttttttttttSugatShakya5
 
Introduction To Data Science
Introduction To Data Science Introduction To Data Science
Introduction To Data Science PriyaMaurya52
 
Big Data Analytics_Unit1.pptx
Big Data Analytics_Unit1.pptxBig Data Analytics_Unit1.pptx
Big Data Analytics_Unit1.pptxPrabhaJoshi4
 
data-science-pdf-16588.pdf
data-science-pdf-16588.pdfdata-science-pdf-16588.pdf
data-science-pdf-16588.pdfvkharish18
 
STARTTS IT Strategy (Sanitised)
STARTTS IT Strategy (Sanitised)STARTTS IT Strategy (Sanitised)
STARTTS IT Strategy (Sanitised)Alex van Vucht
 
Lifesaving AI and Javascript (JSConf Korea 2019)
Lifesaving AI and Javascript (JSConf Korea 2019)Lifesaving AI and Javascript (JSConf Korea 2019)
Lifesaving AI and Javascript (JSConf Korea 2019)Jaeman An
 
Mass declassification sept 23 2010v2.1
Mass declassification sept 23 2010v2.1Mass declassification sept 23 2010v2.1
Mass declassification sept 23 2010v2.1Jeff Jonas
 
Enterprise Grade Data Labeling - Design Your Ground Truth to Scale in Produ...
Enterprise Grade Data Labeling - Design Your Ground Truth to Scale in Produ...Enterprise Grade Data Labeling - Design Your Ground Truth to Scale in Produ...
Enterprise Grade Data Labeling - Design Your Ground Truth to Scale in Produ...Jai Natarajan
 
Data Analytics Course In Surat.pdf
Data Analytics Course In Surat.pdfData Analytics Course In Surat.pdf
Data Analytics Course In Surat.pdfSujata Gupta
 
AI in Healthcare: How to Implement Medical Imaging Using Machine Learning?
AI in Healthcare: How to Implement Medical Imaging Using Machine Learning?AI in Healthcare: How to Implement Medical Imaging Using Machine Learning?
AI in Healthcare: How to Implement Medical Imaging Using Machine Learning?Skyl.ai
 
Sci agile development qualifications 10072014
Sci agile development qualifications 10072014Sci agile development qualifications 10072014
Sci agile development qualifications 10072014Iqbal Tareen
 
DataOps: Nine steps to transform your data science impact Strata London May 18
DataOps: Nine steps to transform your data science impact  Strata London May 18DataOps: Nine steps to transform your data science impact  Strata London May 18
DataOps: Nine steps to transform your data science impact Strata London May 18Harvinder Atwal
 

Similar a NBQSA 2nd round Presentation (20)

Questions On The And Football
Questions On The And FootballQuestions On The And Football
Questions On The And Football
 
Data Science in the Real World: Making a Difference
Data Science in the Real World: Making a Difference Data Science in the Real World: Making a Difference
Data Science in the Real World: Making a Difference
 
ICPSR - Complex Systems Models in the Social Sciences - Lecture 6 - Professor...
ICPSR - Complex Systems Models in the Social Sciences - Lecture 6 - Professor...ICPSR - Complex Systems Models in the Social Sciences - Lecture 6 - Professor...
ICPSR - Complex Systems Models in the Social Sciences - Lecture 6 - Professor...
 
Developing a Federal Vision for Identity Management
Developing a Federal Vision for Identity ManagementDeveloping a Federal Vision for Identity Management
Developing a Federal Vision for Identity Management
 
IGSS Corporate Briefing
IGSS Corporate BriefingIGSS Corporate Briefing
IGSS Corporate Briefing
 
computer projecttttttttttttttttttttttttttttttttttttttttt
computer projectttttttttttttttttttttttttttttttttttttttttcomputer projecttttttttttttttttttttttttttttttttttttttttt
computer projecttttttttttttttttttttttttttttttttttttttttt
 
On Big Data
On Big DataOn Big Data
On Big Data
 
Introduction To Data Science
Introduction To Data Science Introduction To Data Science
Introduction To Data Science
 
Big Data Analytics_Unit1.pptx
Big Data Analytics_Unit1.pptxBig Data Analytics_Unit1.pptx
Big Data Analytics_Unit1.pptx
 
data-science-pdf-16588.pdf
data-science-pdf-16588.pdfdata-science-pdf-16588.pdf
data-science-pdf-16588.pdf
 
STARTTS IT Strategy (Sanitised)
STARTTS IT Strategy (Sanitised)STARTTS IT Strategy (Sanitised)
STARTTS IT Strategy (Sanitised)
 
Lifesaving AI and Javascript (JSConf Korea 2019)
Lifesaving AI and Javascript (JSConf Korea 2019)Lifesaving AI and Javascript (JSConf Korea 2019)
Lifesaving AI and Javascript (JSConf Korea 2019)
 
Mass declassification sept 23 2010v2.1
Mass declassification sept 23 2010v2.1Mass declassification sept 23 2010v2.1
Mass declassification sept 23 2010v2.1
 
Data science - An Introduction
Data science - An IntroductionData science - An Introduction
Data science - An Introduction
 
Enterprise Grade Data Labeling - Design Your Ground Truth to Scale in Produ...
Enterprise Grade Data Labeling - Design Your Ground Truth to Scale in Produ...Enterprise Grade Data Labeling - Design Your Ground Truth to Scale in Produ...
Enterprise Grade Data Labeling - Design Your Ground Truth to Scale in Produ...
 
Data Analytics Course In Surat.pdf
Data Analytics Course In Surat.pdfData Analytics Course In Surat.pdf
Data Analytics Course In Surat.pdf
 
AI in Healthcare: How to Implement Medical Imaging Using Machine Learning?
AI in Healthcare: How to Implement Medical Imaging Using Machine Learning?AI in Healthcare: How to Implement Medical Imaging Using Machine Learning?
AI in Healthcare: How to Implement Medical Imaging Using Machine Learning?
 
Sci agile development qualifications 10072014
Sci agile development qualifications 10072014Sci agile development qualifications 10072014
Sci agile development qualifications 10072014
 
Bounding.Ai
Bounding.AiBounding.Ai
Bounding.Ai
 
DataOps: Nine steps to transform your data science impact Strata London May 18
DataOps: Nine steps to transform your data science impact  Strata London May 18DataOps: Nine steps to transform your data science impact  Strata London May 18
DataOps: Nine steps to transform your data science impact Strata London May 18
 

Último

IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024Results
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)wesley chun
 

Último (20)

IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 

NBQSA 2nd round Presentation

  • 1.
  • 2. Few Statistics… (Source: http://www.cbsl.gov.lk/pics_n_docs/10_pub/_doc s/statistics) Time and Savings Deposits held by the Public 2010 1,405,808 2011 1,753,896 2012 2,143,136 Crime Rate in Sri Lanka (Source: http://www.police.lk/index.php/crime-trends) Health Expenditure in Sri Lanka (Source: http://www.who.int/gho/countries/lka.pdf)
  • 3. Introduction  What is Weave-D?  Inspired by human brain  Data Accumulating, Learning and Fusing System Supports Multimodal data  Video Incremental learning Inspiration source
  • 4. Why Weave-D? Apply previous knowledge to acquire new knowledge Heterogeneous ? Handle data Come as chunks Prevent catastrophic forgetting Incremental learning ? Growth of information Intuitive Visualizing information Simple Generalization of acquired knowledge ? Conceptualization ?
  • 5. Business Value  Medical  What we can mine?  New patient has a cancer or not?  Effective medicine for certain diseases  Diseases distribution in the country  E.g. Anuradhapura – more kidney diseases
  • 6. Business Value  Finance  Predict customers’ transactional behaviors, so banks can plan their strategies ahead  Forensics or Police  Predict criminal behavior  Identify crimes with similar evidence  And many more…
  • 7. Similar Products  IBM Watson  Developed by IBM to compete in Jeopardy  A Question answering system  Consumes “millions” of Wikipedia pages and try to find answers from the knowledge acquired  Finance and health care domains
  • 8. Uniqueness RapidMiner IBM Watson Weave-D Support heterogeneous data x x  Learn without forgetting past data x x  Support analyzing at different granularities x x  Visualization    Fast response x  x
  • 10. Weave-D architecture Raw Data Learning Component Link Generators Perception Model Logger XML Writers XML Outputs Persistence Persistence Handlers Feature Extractor Facade Configuration Loaders Business Logic Feature Extractors Weave-D Facade XML Parsers Data Models Config files XML User Interfaces 3D Visualization Interface Presentation
  • 11. Knowledge Representation Layer 1 (Day 1) Day Input 1 Layer 2 (Day 2) Layer 3 (Day 3) 2 3
  • 12. C3 C1 Child (4-8 years old) Child (8-12 years old) Child (1-4 years old) C4 Forest (Autumn) Forest (Spring) Forest (Winter) C2 City (Day view) C5 City (Night view) (None) Sunset view Dataset 1 Dataset 2 Sunset view Dataset 3
  • 13. Demonstration - Scenario  Description  Sam is a sports enthusiast. He has a set of images belonging to following sports; Croquet, Polo, Rock-climbing, Sailing, Rowing, Badminton. Also he has a small description of the sport for each image. He needs to cluster these images and text by the sports category.  Constraints  All the photos are not available to him at once. He gets sets of images each day. (Incremental learning)
  • 14. User’s Point of View  Input  Query image  Expected outcomes  Set of related images and documents explaining the sport  Tasks  Setting up Weave-D  Training Weave-D  Querying from Weave-D  Sam doesn’t know what sport this is (Query image)  Meaningless file names!  Get documents explaining the sport denoted by image
  • 15. Images What happens inside? Query Image Result Images Text Day 1 Day 2 Day 3 Result Text Time Series Links Associative Links
  • 16. Bigger Picture!!!  Medical domain  Forensic domain
  • 17. Methodology Standards  Agile development – Scrum  Documentation  Architecture documents  Class diagrams  Git version controlling  Tests
  • 19. Implementation Standards  Rich client platform  Object Oriented Programming  Design patterns  Factories  Facades  Command Objects  High decoupling  XML Configuration
  • 20. Monetization Plans?  Promotions through Social Media  Facebook  Google+  Advertising on Data Mining websites  KDNuggets  Discussions  ICTA  Private Hospitals  Private Investigation Agencies  National Hospital Investments?  Project group Sri Lanka Police
  • 21. Few years ahead in Money Path Sell 5 units 1 unit = 80K-100K Part Time Today Initial Investment (Rs.100,000) Full Time January, 2014 1st Release Advertising campaign (Rs. 15,000) Sell 10 units 1 unit = 150K-200K January, 2015 January, 2016 2nd Release Labor cost (4 members) (Rs. 60,000) Break even Other (Rs. 25,000) Profitable
  • 22. Glimpse to the Future  Support mining information at different granularities  Extend Weave-D Client-Server architecture  Support already existing standards (e.g. PMML)
  • 23. Further Resources  Website: http://weave-d.com/  Facebook Page: https://www.facebook.com/treadlabz.weave d  Google+ Page: https://plus.google.com/10278520548758371885 9

Notas del editor

  1. Data accmulation and fusion system. Seems like an already achieved thing and straightforwardLet me tell you how this is special from other tools out thereAppear Heterogenous (describe)Appear Incremental learning (describe)
  2. Data is no longer homogeneous (it is a combination of images, text, audio)Weave-D supports heterogeneous dataData is no longer available at once, data arrives as streams, at different timesWeave-D can learn incrementallyNot all information is important, user should be able to select which features are importantWeave-D allows user to select important features of data
  3. Would this be better if we present as a 2d flow chart?
  4. Show config filesShow componentsShow as a diagram
  5. Few points about what is the experiment what we’re trying to achieveExploratory mining techniqueVery difficult to measure the qualityBy InspectionCluster PurityShow horizontal not vertical
  6. Sam has an image and he doesn’t know what sport this is. And the images and text files does not have very meaningful filenames. (otherwise he could have guessed the name and found the sport). What Sam can do is, he can query this image from Weave-D and find related images and text both. Then by reading the returned documents, he can figure out the sport.Rename data to have meaningless names!
  7. Few examples explaning the same task Sam querying image and getting text in other domainsEx. Radiologist input and image of a cancer and get the full detailed reports relatedEx. Forensic investigators input an audio clip of a criminal and getting picture of a person as the resultFlexible architectureAllow user to form the architecture!Intuitive UI (Drag & Drop)
  8. Potential Customers