SlideShare ist ein Scribd-Unternehmen logo
1 von 17
A Cloud-Based Bayesian Smart 
Agent Architecture 
for Internet-of-Things Applications 
Authors: Veselin Pizurica, Piet Vandaele @waylay 
Rome, 27/10/2014
IoT early years (technology) view 
• IoT was about devices, protocols and data flows 
• “gateway centric” 
• “Liner logic”: left devices, right services…
IoT today: business point of view 
• You see marketing departments taking over  
• Picture more fuzzy, devices and services all over the 
place
Connecting dots 
“Swarm Intelligence” 
Logic in a gateway 
“Fog” computing 
Logic in the cloud 
Conway's Game of Life, 
Nash gaming theory 
TIT for TAT …
Why NOT intelligence in the cloud? 
• Latency 
• Failure (in)tolerance (lack of redundancy) – general issue 
in internet, adding more blocks system even less stable 
• Cost of pushing data in the cloud 
– Energy (battery) 
– Data storage (data can be of a huge volume) 
– SW cost of integration 
– Lack of standardization 
• Security concerns: Authentication/Authorization 
• Privacy concerns
Why intelligence in the cloud? 
• Device-agnostic and decouples logic from the 
presentation layer 
• Combination of the sensor data with API “economy” 
• Integrating multiple IoT vertical solutions 
• Cloud-capacity scales horizontally, while distributed HW 
often needs to be swapped when HW resources are no 
longer sufficient 
• Cloud intelligence also allows easy generation of analytics 
regarding the usage of the logic itself. Which rules fired 
and why? How often? 
• An architectural model arises where logic is built once 
together with a REST API
A Cloud-Based Smart Agent 
Artificial Intelligence provides us the framework and tools to 
go beyond trivial real-time decision and automation use 
cases for IoT. 
In this presentation, we present a cloud-based smart agent 
architecture for real-time decision taking in IoT applications 
Sense 
Transmit 
Store 
Analyze offline 
Act 
Reason Present
Rational Agent 
Rational Agent Architecture * 
* Russell S., Norvig P.: Artificial Intelligence A Modern Approach, Third Edition, Pearson (2014)
Agent architecture choices 
• The choice for a particular type of agent logic is 
influenced by the characteristics of the environment in 
which an agent needs to operate 
• Type of agents (using software language to express the 
logic): 
– ‘if-then-else’ constructs that are available in any programming 
language or rules engine 
– flowchart models 
– CEP (complex event processing) engines 
– Graph models (Markov, Bayesian nets)
Why Bayesian Networks in IOT? 
• Environments that cannot be completely observed, i.e. 
when not all aspects that could impact a choice of action 
are observable. 
• Unreliable, noisy or incomplete data or when domain 
knowledge is incomplete such that probabilistic reasoning 
is required 
• Use cases where the number of causes for a particular 
observation is so large, that it is nearly impossible to 
enumerate them explicitly 
• Well suited to model expert-knowledge together with 
knowledge that is retrieved from accumulated data 
• Use cases where there are asynchronous information flows
Belief propagation 
• Belief propagation algorithm was introduced by Judea Pearl, 1982 
• Pearl was inspired by the paper of cognitive psychologist Rumelhart on how 
children comprehend text 
• Generalization of the Kalman’s algorithm 
• Became very popular after it was shown that the same computations are in 
turbo codes and the same principles in the Viterbi algorithm 
• Main idea: inference by local message passing among neighboring nodes 
The message can loosely be interpreted as “I (node i ) think that you 
(node j) are that much likely to be in a given state”.
Example: Car diagnosis 
• Initial evidence: car won't start 
• Testable variables (green), “broken, so fix it” variables 
(orange) 
• Hidden variables (gray) ensure sparse structure, reduce 
parameters
Let’s focus on battery->lights
Power of casual modelling 
Lights are on 
Lights are off
Compactness (and correctness) 
Decision trees 
Flow charts 
X Y Z
SW-defined 
Sensors 
Graph 
Modeling 
SW-defined 
Actuators 
Percepts 
Actions 
IoT platforms 
Physical Sensors 
Social media 
Location 
Open Data 
Big Data 
API economy 
Cloud Smart 
Agent Platform Environment 
REST 
API 
LOB apps 
Proposed architecture 
Vertical 
Specific 
End-user 
Interface
Example: waylay platform

Weitere ähnliche Inhalte

Was ist angesagt?

Deploying ML models in the enterprise
Deploying ML models in the enterpriseDeploying ML models in the enterprise
Deploying ML models in the enterprise
doppenhe
 
Augmented Reality: On a new powerful mobile computing platforms
Augmented Reality: On a new powerful mobile computing platformsAugmented Reality: On a new powerful mobile computing platforms
Augmented Reality: On a new powerful mobile computing platforms
Chetan Kumar S
 

Was ist angesagt? (20)

Apache Spark and future of advanced analytics
Apache Spark and future of advanced analyticsApache Spark and future of advanced analytics
Apache Spark and future of advanced analytics
 
Big Data in an modern Enterprise
Big Data in an modern EnterpriseBig Data in an modern Enterprise
Big Data in an modern Enterprise
 
"Data Annotation at Scale: Pitfalls and Solutions," a Presentation from Intel
"Data Annotation at Scale: Pitfalls and Solutions," a Presentation from Intel"Data Annotation at Scale: Pitfalls and Solutions," a Presentation from Intel
"Data Annotation at Scale: Pitfalls and Solutions," a Presentation from Intel
 
Machine Learning for the Sensored IoT
Machine Learning for the Sensored IoTMachine Learning for the Sensored IoT
Machine Learning for the Sensored IoT
 
A practical look at how to build & run IoT business logic
A practical look at how to build & run IoT business logicA practical look at how to build & run IoT business logic
A practical look at how to build & run IoT business logic
 
International Journal of Computer Science, Engineering and Information Techn...
International Journal of Computer Science, Engineering and  Information Techn...International Journal of Computer Science, Engineering and  Information Techn...
International Journal of Computer Science, Engineering and Information Techn...
 
Deploying ML models in the enterprise
Deploying ML models in the enterpriseDeploying ML models in the enterprise
Deploying ML models in the enterprise
 
Operational information processing: lightning-fast, delightfully simple
Operational information processing: lightning-fast, delightfully simpleOperational information processing: lightning-fast, delightfully simple
Operational information processing: lightning-fast, delightfully simple
 
Stephen Cantrell, kdb+ Developer at Kx Systems “Kdb+: How Wall Street Tech c...
Stephen Cantrell, kdb+ Developer at Kx Systems  “Kdb+: How Wall Street Tech c...Stephen Cantrell, kdb+ Developer at Kx Systems  “Kdb+: How Wall Street Tech c...
Stephen Cantrell, kdb+ Developer at Kx Systems “Kdb+: How Wall Street Tech c...
 
What's next in edge computing?
What's next in edge computing?What's next in edge computing?
What's next in edge computing?
 
Hot tech 20160922-ep0015-dell statistica - edge analytics - the io_t economy ...
Hot tech 20160922-ep0015-dell statistica - edge analytics - the io_t economy ...Hot tech 20160922-ep0015-dell statistica - edge analytics - the io_t economy ...
Hot tech 20160922-ep0015-dell statistica - edge analytics - the io_t economy ...
 
Demystify Edge Computing Vs. Cloud Computing
Demystify Edge Computing Vs. Cloud ComputingDemystify Edge Computing Vs. Cloud Computing
Demystify Edge Computing Vs. Cloud Computing
 
Vertex perspectives artificial intelligence
Vertex perspectives   artificial intelligenceVertex perspectives   artificial intelligence
Vertex perspectives artificial intelligence
 
FIWARE Global Summit - International Data Spaces - A New Idea for Data Sharing
FIWARE Global Summit - International Data Spaces - A New Idea for Data SharingFIWARE Global Summit - International Data Spaces - A New Idea for Data Sharing
FIWARE Global Summit - International Data Spaces - A New Idea for Data Sharing
 
Google Cloud IoT Core
Google Cloud IoT CoreGoogle Cloud IoT Core
Google Cloud IoT Core
 
Augmented Reality: On a new powerful mobile computing platforms
Augmented Reality: On a new powerful mobile computing platformsAugmented Reality: On a new powerful mobile computing platforms
Augmented Reality: On a new powerful mobile computing platforms
 
IoT Meets the Cloud: The Origins of Edge Computing
IoT Meets the Cloud:  The Origins of Edge ComputingIoT Meets the Cloud:  The Origins of Edge Computing
IoT Meets the Cloud: The Origins of Edge Computing
 
Edge Computing
Edge ComputingEdge Computing
Edge Computing
 
Azure iot suite
Azure iot suiteAzure iot suite
Azure iot suite
 
FIWARE Global Summit - IoT Virtualization for Platform Interoperability
FIWARE Global Summit - IoT Virtualization for Platform InteroperabilityFIWARE Global Summit - IoT Virtualization for Platform Interoperability
FIWARE Global Summit - IoT Virtualization for Platform Interoperability
 

Ähnlich wie A Cloud-Based Bayesian Smart Agent Architecture for Internet-of-Things Applications

Week 8 - Module 19 - PPT- Internet of Things for Libraries.pdf
Week 8 - Module 19 - PPT- Internet of Things for Libraries.pdfWeek 8 - Module 19 - PPT- Internet of Things for Libraries.pdf
Week 8 - Module 19 - PPT- Internet of Things for Libraries.pdf
MohamedAli899919
 
How to make data more usable on the Internet of Things
How to make data more usable on the Internet of ThingsHow to make data more usable on the Internet of Things
How to make data more usable on the Internet of Things
PayamBarnaghi
 
BsidesLVPresso2016_JZeditsv6
BsidesLVPresso2016_JZeditsv6BsidesLVPresso2016_JZeditsv6
BsidesLVPresso2016_JZeditsv6
Rod Soto
 

Ähnlich wie A Cloud-Based Bayesian Smart Agent Architecture for Internet-of-Things Applications (20)

A Cloud-Based Bayesian Smart Agent Architecture for Internet-of-Things Applic...
A Cloud-Based Bayesian Smart Agent Architecture for Internet-of-Things Applic...A Cloud-Based Bayesian Smart Agent Architecture for Internet-of-Things Applic...
A Cloud-Based Bayesian Smart Agent Architecture for Internet-of-Things Applic...
 
Dynamic Semantics for Semantics for Dynamic IoT Environments
Dynamic Semantics for Semantics for Dynamic IoT EnvironmentsDynamic Semantics for Semantics for Dynamic IoT Environments
Dynamic Semantics for Semantics for Dynamic IoT Environments
 
Internet of Things IoT Guido Schmutz
Internet of Things IoT Guido SchmutzInternet of Things IoT Guido Schmutz
Internet of Things IoT Guido Schmutz
 
Internet of Things - Are traditional architectures good enough?
Internet of Things - Are traditional architectures good enough?Internet of Things - Are traditional architectures good enough?
Internet of Things - Are traditional architectures good enough?
 
Internet of Things (IoT)
Internet of Things (IoT)Internet of Things (IoT)
Internet of Things (IoT)
 
Presentation v3
Presentation v3Presentation v3
Presentation v3
 
Internet of Things
Internet of ThingsInternet of Things
Internet of Things
 
Semantic Technologies for the Internet of Things: Challenges and Opportunities
Semantic Technologies for the Internet of Things: Challenges and Opportunities Semantic Technologies for the Internet of Things: Challenges and Opportunities
Semantic Technologies for the Internet of Things: Challenges and Opportunities
 
Week 8 - Module 19 - PPT- Internet of Things for Libraries.pdf
Week 8 - Module 19 - PPT- Internet of Things for Libraries.pdfWeek 8 - Module 19 - PPT- Internet of Things for Libraries.pdf
Week 8 - Module 19 - PPT- Internet of Things for Libraries.pdf
 
Novi sad ai event 1-2018
Novi sad ai event 1-2018Novi sad ai event 1-2018
Novi sad ai event 1-2018
 
System Support for Internet of Things
System Support for Internet of ThingsSystem Support for Internet of Things
System Support for Internet of Things
 
I learning lot
I learning lotI learning lot
I learning lot
 
How to make data more usable on the Internet of Things
How to make data more usable on the Internet of ThingsHow to make data more usable on the Internet of Things
How to make data more usable on the Internet of Things
 
8_iot.pdf
8_iot.pdf8_iot.pdf
8_iot.pdf
 
Applicability of Machine learning in computer networks
Applicability of Machine learning in computer networksApplicability of Machine learning in computer networks
Applicability of Machine learning in computer networks
 
FIWARE Global Summit - Advanced ML/AI Techniques with FIWARE and Connected Io...
FIWARE Global Summit - Advanced ML/AI Techniques with FIWARE and Connected Io...FIWARE Global Summit - Advanced ML/AI Techniques with FIWARE and Connected Io...
FIWARE Global Summit - Advanced ML/AI Techniques with FIWARE and Connected Io...
 
Big Data on The Cloud
Big Data on The CloudBig Data on The Cloud
Big Data on The Cloud
 
20131031 giis 2013 keynote r.giaffreda
20131031 giis 2013 keynote r.giaffreda20131031 giis 2013 keynote r.giaffreda
20131031 giis 2013 keynote r.giaffreda
 
Azure Digital Twins
Azure Digital TwinsAzure Digital Twins
Azure Digital Twins
 
BsidesLVPresso2016_JZeditsv6
BsidesLVPresso2016_JZeditsv6BsidesLVPresso2016_JZeditsv6
BsidesLVPresso2016_JZeditsv6
 

Mehr von Veselin Pizurica

Mehr von Veselin Pizurica (14)

Has serverless adoption hit a roadblock?
Has serverless adoption hit a roadblock?Has serverless adoption hit a roadblock?
Has serverless adoption hit a roadblock?
 
Remote Patient & Elderly Care Monitoring
Remote Patient & Elderly Care MonitoringRemote Patient & Elderly Care Monitoring
Remote Patient & Elderly Care Monitoring
 
How to use probabilistic inference programming for application orchestration ...
How to use probabilistic inference programming for application orchestration ...How to use probabilistic inference programming for application orchestration ...
How to use probabilistic inference programming for application orchestration ...
 
Waylay - We are hiring
Waylay - We are hiringWaylay - We are hiring
Waylay - We are hiring
 
Waylay building smart city solution: IoT convention Antwerp
Waylay building smart city solution: IoT convention AntwerpWaylay building smart city solution: IoT convention Antwerp
Waylay building smart city solution: IoT convention Antwerp
 
Artificial intelligence by Aleksandra Pizurica
Artificial intelligence by Aleksandra PizuricaArtificial intelligence by Aleksandra Pizurica
Artificial intelligence by Aleksandra Pizurica
 
Automation is eating the world
Automation is eating the worldAutomation is eating the world
Automation is eating the world
 
LPWAN - IoT (Platform) Killer Application
LPWAN - IoT (Platform) Killer ApplicationLPWAN - IoT (Platform) Killer Application
LPWAN - IoT (Platform) Killer Application
 
Automation, intelligence and knowledge modelling
Automation, intelligence and knowledge modellingAutomation, intelligence and knowledge modelling
Automation, intelligence and knowledge modelling
 
When IoT Meets Artificial Intelligence
 When IoT Meets Artificial Intelligence When IoT Meets Artificial Intelligence
When IoT Meets Artificial Intelligence
 
Internet of Things introduction
Internet of Things introductionInternet of Things introduction
Internet of Things introduction
 
My life in one picture
My life in one pictureMy life in one picture
My life in one picture
 
WebRTC presentation
WebRTC presentationWebRTC presentation
WebRTC presentation
 
Artificial intelligence and IoT
Artificial intelligence and IoTArtificial intelligence and IoT
Artificial intelligence and IoT
 

Kürzlich hochgeladen

一比一原版奥兹学院毕业证如何办理
一比一原版奥兹学院毕业证如何办理一比一原版奥兹学院毕业证如何办理
一比一原版奥兹学院毕业证如何办理
F
 
在线制作约克大学毕业证(yu毕业证)在读证明认证可查
在线制作约克大学毕业证(yu毕业证)在读证明认证可查在线制作约克大学毕业证(yu毕业证)在读证明认证可查
在线制作约克大学毕业证(yu毕业证)在读证明认证可查
ydyuyu
 
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
ydyuyu
 
Russian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girls
Russian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girlsRussian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girls
Russian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girls
Monica Sydney
 
call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7
call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7
call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Abu Dhabi Escorts Service 0508644382 Escorts in Abu Dhabi
Abu Dhabi Escorts Service 0508644382 Escorts in Abu DhabiAbu Dhabi Escorts Service 0508644382 Escorts in Abu Dhabi
Abu Dhabi Escorts Service 0508644382 Escorts in Abu Dhabi
Monica Sydney
 
Russian Escort Abu Dhabi 0503464457 Abu DHabi Escorts
Russian Escort Abu Dhabi 0503464457 Abu DHabi EscortsRussian Escort Abu Dhabi 0503464457 Abu DHabi Escorts
Russian Escort Abu Dhabi 0503464457 Abu DHabi Escorts
Monica Sydney
 
Indian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
Indian Escort in Abu DHabi 0508644382 Abu Dhabi EscortsIndian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
Indian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
Monica Sydney
 

Kürzlich hochgeladen (20)

Nagercoil Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nagercoil
Nagercoil Escorts Service Girl ^ 9332606886, WhatsApp Anytime NagercoilNagercoil Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nagercoil
Nagercoil Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nagercoil
 
Real Men Wear Diapers T Shirts sweatshirt
Real Men Wear Diapers T Shirts sweatshirtReal Men Wear Diapers T Shirts sweatshirt
Real Men Wear Diapers T Shirts sweatshirt
 
一比一原版奥兹学院毕业证如何办理
一比一原版奥兹学院毕业证如何办理一比一原版奥兹学院毕业证如何办理
一比一原版奥兹学院毕业证如何办理
 
20240507 QFM013 Machine Intelligence Reading List April 2024.pdf
20240507 QFM013 Machine Intelligence Reading List April 2024.pdf20240507 QFM013 Machine Intelligence Reading List April 2024.pdf
20240507 QFM013 Machine Intelligence Reading List April 2024.pdf
 
20240509 QFM015 Engineering Leadership Reading List April 2024.pdf
20240509 QFM015 Engineering Leadership Reading List April 2024.pdf20240509 QFM015 Engineering Leadership Reading List April 2024.pdf
20240509 QFM015 Engineering Leadership Reading List April 2024.pdf
 
Call girls Service in Ajman 0505086370 Ajman call girls
Call girls Service in Ajman 0505086370 Ajman call girlsCall girls Service in Ajman 0505086370 Ajman call girls
Call girls Service in Ajman 0505086370 Ajman call girls
 
Meaning of On page SEO & its process in detail.
Meaning of On page SEO & its process in detail.Meaning of On page SEO & its process in detail.
Meaning of On page SEO & its process in detail.
 
20240510 QFM016 Irresponsible AI Reading List April 2024.pdf
20240510 QFM016 Irresponsible AI Reading List April 2024.pdf20240510 QFM016 Irresponsible AI Reading List April 2024.pdf
20240510 QFM016 Irresponsible AI Reading List April 2024.pdf
 
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
 
在线制作约克大学毕业证(yu毕业证)在读证明认证可查
在线制作约克大学毕业证(yu毕业证)在读证明认证可查在线制作约克大学毕业证(yu毕业证)在读证明认证可查
在线制作约克大学毕业证(yu毕业证)在读证明认证可查
 
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
 
Russian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girls
Russian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girlsRussian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girls
Russian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girls
 
Trump Diapers Over Dems t shirts Sweatshirt
Trump Diapers Over Dems t shirts SweatshirtTrump Diapers Over Dems t shirts Sweatshirt
Trump Diapers Over Dems t shirts Sweatshirt
 
20240508 QFM014 Elixir Reading List April 2024.pdf
20240508 QFM014 Elixir Reading List April 2024.pdf20240508 QFM014 Elixir Reading List April 2024.pdf
20240508 QFM014 Elixir Reading List April 2024.pdf
 
call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7
call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7
call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7
 
Abu Dhabi Escorts Service 0508644382 Escorts in Abu Dhabi
Abu Dhabi Escorts Service 0508644382 Escorts in Abu DhabiAbu Dhabi Escorts Service 0508644382 Escorts in Abu Dhabi
Abu Dhabi Escorts Service 0508644382 Escorts in Abu Dhabi
 
Vip Firozabad Phone 8250092165 Escorts Service At 6k To 30k Along With Ac Room
Vip Firozabad Phone 8250092165 Escorts Service At 6k To 30k Along With Ac RoomVip Firozabad Phone 8250092165 Escorts Service At 6k To 30k Along With Ac Room
Vip Firozabad Phone 8250092165 Escorts Service At 6k To 30k Along With Ac Room
 
Russian Escort Abu Dhabi 0503464457 Abu DHabi Escorts
Russian Escort Abu Dhabi 0503464457 Abu DHabi EscortsRussian Escort Abu Dhabi 0503464457 Abu DHabi Escorts
Russian Escort Abu Dhabi 0503464457 Abu DHabi Escorts
 
Story Board.pptxrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr
Story Board.pptxrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrStory Board.pptxrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr
Story Board.pptxrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr
 
Indian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
Indian Escort in Abu DHabi 0508644382 Abu Dhabi EscortsIndian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
Indian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
 

A Cloud-Based Bayesian Smart Agent Architecture for Internet-of-Things Applications

  • 1. A Cloud-Based Bayesian Smart Agent Architecture for Internet-of-Things Applications Authors: Veselin Pizurica, Piet Vandaele @waylay Rome, 27/10/2014
  • 2. IoT early years (technology) view • IoT was about devices, protocols and data flows • “gateway centric” • “Liner logic”: left devices, right services…
  • 3. IoT today: business point of view • You see marketing departments taking over  • Picture more fuzzy, devices and services all over the place
  • 4. Connecting dots “Swarm Intelligence” Logic in a gateway “Fog” computing Logic in the cloud Conway's Game of Life, Nash gaming theory TIT for TAT …
  • 5. Why NOT intelligence in the cloud? • Latency • Failure (in)tolerance (lack of redundancy) – general issue in internet, adding more blocks system even less stable • Cost of pushing data in the cloud – Energy (battery) – Data storage (data can be of a huge volume) – SW cost of integration – Lack of standardization • Security concerns: Authentication/Authorization • Privacy concerns
  • 6. Why intelligence in the cloud? • Device-agnostic and decouples logic from the presentation layer • Combination of the sensor data with API “economy” • Integrating multiple IoT vertical solutions • Cloud-capacity scales horizontally, while distributed HW often needs to be swapped when HW resources are no longer sufficient • Cloud intelligence also allows easy generation of analytics regarding the usage of the logic itself. Which rules fired and why? How often? • An architectural model arises where logic is built once together with a REST API
  • 7. A Cloud-Based Smart Agent Artificial Intelligence provides us the framework and tools to go beyond trivial real-time decision and automation use cases for IoT. In this presentation, we present a cloud-based smart agent architecture for real-time decision taking in IoT applications Sense Transmit Store Analyze offline Act Reason Present
  • 8. Rational Agent Rational Agent Architecture * * Russell S., Norvig P.: Artificial Intelligence A Modern Approach, Third Edition, Pearson (2014)
  • 9. Agent architecture choices • The choice for a particular type of agent logic is influenced by the characteristics of the environment in which an agent needs to operate • Type of agents (using software language to express the logic): – ‘if-then-else’ constructs that are available in any programming language or rules engine – flowchart models – CEP (complex event processing) engines – Graph models (Markov, Bayesian nets)
  • 10. Why Bayesian Networks in IOT? • Environments that cannot be completely observed, i.e. when not all aspects that could impact a choice of action are observable. • Unreliable, noisy or incomplete data or when domain knowledge is incomplete such that probabilistic reasoning is required • Use cases where the number of causes for a particular observation is so large, that it is nearly impossible to enumerate them explicitly • Well suited to model expert-knowledge together with knowledge that is retrieved from accumulated data • Use cases where there are asynchronous information flows
  • 11. Belief propagation • Belief propagation algorithm was introduced by Judea Pearl, 1982 • Pearl was inspired by the paper of cognitive psychologist Rumelhart on how children comprehend text • Generalization of the Kalman’s algorithm • Became very popular after it was shown that the same computations are in turbo codes and the same principles in the Viterbi algorithm • Main idea: inference by local message passing among neighboring nodes The message can loosely be interpreted as “I (node i ) think that you (node j) are that much likely to be in a given state”.
  • 12. Example: Car diagnosis • Initial evidence: car won't start • Testable variables (green), “broken, so fix it” variables (orange) • Hidden variables (gray) ensure sparse structure, reduce parameters
  • 13. Let’s focus on battery->lights
  • 14. Power of casual modelling Lights are on Lights are off
  • 15. Compactness (and correctness) Decision trees Flow charts X Y Z
  • 16. SW-defined Sensors Graph Modeling SW-defined Actuators Percepts Actions IoT platforms Physical Sensors Social media Location Open Data Big Data API economy Cloud Smart Agent Platform Environment REST API LOB apps Proposed architecture Vertical Specific End-user Interface