SlideShare a Scribd company logo
1 of 25
Context Reasoning and Prediction
in Smart Environments:
the Home Manager case
IIMSS 2017
Algarve - Portugal, 23 June 2017
Roberta Calegari, Enrico Denti
Outline
ā€¢ Scope & Goals
ā€¢ Smart Environments in the Butlers perspective
o The Butlers Vision
o The Home Manager Platform
o The Home Manager Architecture
ā€¢ Smart Environment in HM
ā€¢ The Smart Kitchen Case Study
o The Smart Kitchen: Scenario
o The Smart Kitchen: Prototype
ā€¢ Conclusions & Future Work
Scope & Goals (1/2)
Smart Environments socio-technical nature calls for
from diverse fields ļƒ  multi-paradigm perspective
REQUIREMENTS
ā€¢ availability of an effective coordination middleware
ā€¢ effective support to situatedness
ā€¢ guidelines and enabling techniques exploiting concepts,
methodologies, technologies from the most diverse fields,
in a multi-paradigm perspective
ā€¢ skills
ā€¢ concepts
ā€¢ methodologies
ā€¢ technologies
Framework for the design & development
of Smart Environments
ā€¢ accounting for technological and human / organisational aspects
ā€¢ combining different dimensions and behaviour from
pervasive, distributed, situated and intelligent computing
Scope & Goals (2/2)
Butlers for Smart Spaces
ā€¢ technology-neutral
ā€¢ reference framework
ā€¢ focused on usersā€™ situated-
ness and interaction aspects
Home Manager
ā€¢ platform for Smart Home &
Smart Living contexts
ā€¢ focused on reasoning aspects
ā€¢ multi-paradigm, agent-based
The Butlers Vision
ā€¢ Butlers for Smart Spaces specialises the Butlers framework
to the Smart Spaces context
ā€¢ Home Manager leads to concretise it as a multi-agent system
on the TuCSoN infrastructure
Butlers for Smart Spacesā€¦
Specialisation of the Butlers framework to the Smart
Spaces context
The Monitoring layer groups together the
Butlers information and control layers
The Services layer embeds
the coordination referring to
the pre-processing of raw
information into exploitable
knowledge
Goals & Policies side-by-
side take into account user-
awareness (user-related,
higher-level coordination)
The Reasoning & Situated
Reasoning layers split the
Butlers Intelligence layer
ā€¦on Home Manager as a MAS
Home Manager (apice.unibo.it/xwiki/bin/view/Products/HomeManager)
concretises it as a MAS on the TuCSoN infrastructure
The TuCSoN infrastructure conceptually
surrounds all layers, enabling and govern-
ing agent coordination & interaction
ā€¢ All layers are re-shaped
based on TuCSoN concepts
& metaphors
ā€¢ Agents & Policies sub-
layers appear side-by-side,
following the TuCSoN
approach
The Home Manager platform
ā€¢ Open source platform for Smart Spaces, built on top of the
TuCSoN multi-agent infrastructure
o deployable also on a Raspberry PI 2
o Java-based
(~interoperable with Win10-IoT core)
ā€¢ Smart House immersed in the surrounding environment
ļƒ  Smart Living context
o Devices (air conditioners, lights, etc.)
o Users of different categories + RBAC
ā€¢ Focus on Context Reasoning & Context Prediction
o Satisfy users desires while respecting global constraints
ļƒ  suitable coordination laws to govern interaction
o Anticipate needs by exploiting the userā€™s situation in time and space
Intuitive architecture
Main features:
o Autonomous ā€œsituatedā€ decisions by exploiting the userā€™s location
o Exploration of the environment around the userā€™s location
o Information about the surrounding environment (e.g. weather)
o Interaction with selected social networks (e.g. Twitter)
o Tracking of the human presence
Smart Environments in HM
ā€¢ Designing a Smart Environment in Home Manager amounts to:
o identify relevant device and service categories
o define a tuple-based representation of the relevant knowledge
o define the agent interaction
o develop an agent for each device category & service to interact with
Clear separation between
ā€¢ social / individual intelligence
ā€¢ mechanisms / policies
Features
ā€¢ independent testing and debug
of agents and policies
ā€¢ effective exploitation of the
data-driven, multi-paradigm
development approach
The Smart Kitchen Case Study
ā€¢ Smart Fridge & Smart Pantry
o food monitoring
o collecting historical data on userā€™s habits
o generate the corresponding buy tuple if necessary (policies)
ā€¢ Smart Oven
o support the userā€™s food cooking (e.g. dietary,ā€¦)
ā€¢ Smart Mixer
o recipe instructions interacting with Smart Fridge & Smart Oven to
check food availability ļƒ  context adaptation
ā€¢ Smart Shopper
o predict the userā€™s needs ļƒ  make contextualised suggestions
o shopping list based on the above data
o contact the ā€œproperā€ vendor based on context- aware policies
The Smart Kitchen: scenario
The Smart Kitchen: prototype
Middleware ļƒ  coordination laws ļƒ  interoperability & integration
ā€¢ Declarative approach
o bridge among different forms of heterogeneity
o support agent uncoupling
o support & promote separation between policies & mechanisms
o supports context reasoning
Future (current) work
Context prediction & adaptation: prediction agent
WEKA Classifier (Ilaria Bertoletti Master's thesis, 15 June 2017)
Tempera-
ture prefs
Device
usage
policies
Action plan on
air conditioners
Learning &
prediction of
user habits
Future (current) work
Context prediction & adaptation: prediction agent
WEKA Classifier (Ilaria Bertoletti Master's thesis, 15 June 2017)
CONTEXT
PREDICTION
ā€¢ Grab user habits
info from multiple
sources
ā€¢ Select relevant
data
ā€¢ Anticipate user's
routine & desires
CONTEXT
REASONING
ā€¢ Compute
heterogeneous
context info
ā€¢ Enable HM to make
suggestions
ā€¢ Increase HM
decision autonomy
PROACTIVE
ADAPTATION
ā€¢ Autonomously appy
action plan on house
devices
ā€¢ Enable HM to adapt
to new needs
ā€¢ Reduce user's
interventions
Future (current) work
Context prediction & adaptation: prediction agent
WEKA Classifier (Ilaria Bertoletti Master's thesis, 15 June 2017)
ā€¢ Get daily routine
ā€¢ Weather + policies + routine
= decision
Future (current) work
Context prediction & adaptation: prediction agent
WEKA Classifier (Ilaria Bertoletti Master's thesis, 15 June 2017)
Home Manager lays the foundations to support
context reasoning and context prediction
ā€¢ Yet, just a starting point..
ā€¢ A lot of work remains to be done
Conclusions (1)
Butlers for Smart Spaces
ā€¢ technology-neutral
ā€¢ reference framework for
pervasive IoT contexts
ā€¢ focused on usersā€™ situated-
ness and interaction aspects
Home Manager
ā€¢ concretise the BSS approach
ā€¢ the infrastructure bridges among
the agentsā€™ ontologies, APIs,
knowledge representations,
interaction protocols
Conclusions (2)
Future work
ā€¢ Deeper exploration of the context reasoning aspect
(machine learning,ā€¦)
ā€¢ Cross-platform interoperability
ā€¢ Java/Windows 10 on the Raspberry
ā€¢ Emerging standards
ā€¢ Developing more complex policies and implementing other
advanced situated services
Home Manager URLs
ā€¢ Home page
http://apice.unibo.it/xwiki/bin/view/Products/HomeManager
ā€¢ Bitbucket repository
https://bitbucket.org/tuprologteam/homemanager
Roberta Calegari roberta.calegari@unibo.it
Enrico Denti enrico.denti@unibo.it
http://www.unibo.it
http://www.cse.unibo.it/en
http://apice.unibo.it/xwiki/bin/view/Main/?language=en
Prototype screenshots
Smart kitchen
simulated device vs physical device
Mixer agent
Prototype screenshots
Smart kitchen
cooking requests
missing ingredients
Prototype screenshots
Smart oven
demo implementation
Prototype screenshots
Smart fridge
demo implementation

More Related Content

What's hot

Smart home Environment using iot
Smart home Environment using iotSmart home Environment using iot
Smart home Environment using iotparvathy s m
Ā 
2015 State of the Smart Home Report | Icontrol Networks
2015 State of the Smart Home Report | Icontrol Networks2015 State of the Smart Home Report | Icontrol Networks
2015 State of the Smart Home Report | Icontrol NetworksIan Gertler
Ā 
Wulian Smart Home Products Catalog
Wulian Smart Home Products CatalogWulian Smart Home Products Catalog
Wulian Smart Home Products CatalogWulian Smart Home
Ā 
Presentation on IoT Based Home Automation using android & NodeMCU
Presentation on IoT Based Home Automation using android & NodeMCUPresentation on IoT Based Home Automation using android & NodeMCU
Presentation on IoT Based Home Automation using android & NodeMCUSouvik Kundu
Ā 
Smart Home Automation - An Overview
Smart Home Automation - An OverviewSmart Home Automation - An Overview
Smart Home Automation - An OverviewSmart Automation
Ā 
Smart Home Evolution
Smart Home EvolutionSmart Home Evolution
Smart Home EvolutionLuca Lamera
Ā 
Life going beyond the smart home
Life going beyond the smart homeLife going beyond the smart home
Life going beyond the smart homeCOMPUTEX TAIPEI
Ā 
Srr automation smart home presentation
Srr automation smart home presentationSrr automation smart home presentation
Srr automation smart home presentationVijaykumar swaminathan
Ā 
My smart homes
My smart homesMy smart homes
My smart homesroandua
Ā 
Making the Smart Home More Insightful
Making the Smart Home More InsightfulMaking the Smart Home More Insightful
Making the Smart Home More InsightfulVectorform
Ā 
Internet of things for Smart Home
Internet of things for Smart Home Internet of things for Smart Home
Internet of things for Smart Home Khwaja Aamer
Ā 
Smartify Home Automation - Client Presentation
Smartify Home Automation - Client PresentationSmartify Home Automation - Client Presentation
Smartify Home Automation - Client PresentationAbhi Bavishi
Ā 
Home automation - SMART HOME
Home automation - SMART HOME Home automation - SMART HOME
Home automation - SMART HOME Ankur Mehra
Ā 
Wulian smart home catalog 2014
Wulian smart home catalog 2014Wulian smart home catalog 2014
Wulian smart home catalog 2014Wulian Smart Home
Ā 
IoT BASED SMART HOME USING ARDUINO
IoT BASED SMART HOME USING ARDUINOIoT BASED SMART HOME USING ARDUINO
IoT BASED SMART HOME USING ARDUINOAYSHA S KABEER
Ā 
Home automation in kerala ,home automation in calicut , home automation
Home automation in kerala ,home automation in calicut , home automation  Home automation in kerala ,home automation in calicut , home automation
Home automation in kerala ,home automation in calicut , home automation Arun Kumar
Ā 

What's hot (20)

Smart home Environment using iot
Smart home Environment using iotSmart home Environment using iot
Smart home Environment using iot
Ā 
2015 State of the Smart Home Report | Icontrol Networks
2015 State of the Smart Home Report | Icontrol Networks2015 State of the Smart Home Report | Icontrol Networks
2015 State of the Smart Home Report | Icontrol Networks
Ā 
Wulian Smart Home Products Catalog
Wulian Smart Home Products CatalogWulian Smart Home Products Catalog
Wulian Smart Home Products Catalog
Ā 
Smart home
Smart homeSmart home
Smart home
Ā 
Presentation on IoT Based Home Automation using android & NodeMCU
Presentation on IoT Based Home Automation using android & NodeMCUPresentation on IoT Based Home Automation using android & NodeMCU
Presentation on IoT Based Home Automation using android & NodeMCU
Ā 
Smart Home Automation - An Overview
Smart Home Automation - An OverviewSmart Home Automation - An Overview
Smart Home Automation - An Overview
Ā 
Smart Home Evolution
Smart Home EvolutionSmart Home Evolution
Smart Home Evolution
Ā 
Life going beyond the smart home
Life going beyond the smart homeLife going beyond the smart home
Life going beyond the smart home
Ā 
Srr automation smart home presentation
Srr automation smart home presentationSrr automation smart home presentation
Srr automation smart home presentation
Ā 
My smart homes
My smart homesMy smart homes
My smart homes
Ā 
Making the Smart Home More Insightful
Making the Smart Home More InsightfulMaking the Smart Home More Insightful
Making the Smart Home More Insightful
Ā 
Internet of things for Smart Home
Internet of things for Smart Home Internet of things for Smart Home
Internet of things for Smart Home
Ā 
Smartify Home Automation - Client Presentation
Smartify Home Automation - Client PresentationSmartify Home Automation - Client Presentation
Smartify Home Automation - Client Presentation
Ā 
Smart home
Smart homeSmart home
Smart home
Ā 
Home automation - SMART HOME
Home automation - SMART HOME Home automation - SMART HOME
Home automation - SMART HOME
Ā 
Wulian smart home catalog 2014
Wulian smart home catalog 2014Wulian smart home catalog 2014
Wulian smart home catalog 2014
Ā 
IoT BASED SMART HOME USING ARDUINO
IoT BASED SMART HOME USING ARDUINOIoT BASED SMART HOME USING ARDUINO
IoT BASED SMART HOME USING ARDUINO
Ā 
Home automation in kerala ,home automation in calicut , home automation
Home automation in kerala ,home automation in calicut , home automation  Home automation in kerala ,home automation in calicut , home automation
Home automation in kerala ,home automation in calicut , home automation
Ā 
Business Models for Smart Homes
Business Models for Smart HomesBusiness Models for Smart Homes
Business Models for Smart Homes
Ā 
Io t
Io tIo t
Io t
Ā 

Similar to Context Reasoning and Prediction in Smart Environments: the Home Manager case

Sapere project-introduction-dec-2010
Sapere project-introduction-dec-2010Sapere project-introduction-dec-2010
Sapere project-introduction-dec-2010awarenessproject
Ā 
Context-aware recommender system for multi-user smart home
Context-aware recommender system for multi-user smart homeContext-aware recommender system for multi-user smart home
Context-aware recommender system for multi-user smart homeIJECEIAES
Ā 
Meetup 11 here&now_megatriscomp design methodpartii_v0.2
Meetup 11 here&now_megatriscomp design methodpartii_v0.2Meetup 11 here&now_megatriscomp design methodpartii_v0.2
Meetup 11 here&now_megatriscomp design methodpartii_v0.2Francesco Rago
Ā 
Ted talk April 20
Ted talk April 20Ted talk April 20
Ted talk April 20Bala Iyer
Ā 
Unlocking Smart Building Potential with the RealEstateCore Ontology
Unlocking Smart Building Potential with the RealEstateCore OntologyUnlocking Smart Building Potential with the RealEstateCore Ontology
Unlocking Smart Building Potential with the RealEstateCore OntologyMemoori
Ā 
Meetup 10 here&now_megatriscomp_design_methodparti_v1
Meetup 10 here&now_megatriscomp_design_methodparti_v1Meetup 10 here&now_megatriscomp_design_methodparti_v1
Meetup 10 here&now_megatriscomp_design_methodparti_v1Francesco Rago
Ā 
Meetup 10 here&now: Megatris Comp design method (Part 1)
Meetup 10 here&now: Megatris Comp design method (Part 1)Meetup 10 here&now: Megatris Comp design method (Part 1)
Meetup 10 here&now: Megatris Comp design method (Part 1)Megatris Comp
Ā 
Smart cities no ai without ia
Smart cities   no ai without iaSmart cities   no ai without ia
Smart cities no ai without iaFredric Landqvist
Ā 
Perception.JS - A Framework for Context Acquisition Processing and Presentation
Perception.JS - A Framework for Context Acquisition Processing and PresentationPerception.JS - A Framework for Context Acquisition Processing and Presentation
Perception.JS - A Framework for Context Acquisition Processing and PresentationSupun Dissanayake
Ā 
Navigating the twilight zone - pathways towards digital transformation of foo...
Navigating the twilight zone - pathways towards digital transformation of foo...Navigating the twilight zone - pathways towards digital transformation of foo...
Navigating the twilight zone - pathways towards digital transformation of foo...Sjaak Wolfert
Ā 
A Personalized Software Assistant Framework To Achieve User Goals
A Personalized Software Assistant Framework To Achieve User GoalsA Personalized Software Assistant Framework To Achieve User Goals
A Personalized Software Assistant Framework To Achieve User GoalsPradeep K. Venkatesh
Ā 
PERICLES Policy management & ontology supported preservation - Acting on Chan...
PERICLES Policy management & ontology supported preservation - Acting on Chan...PERICLES Policy management & ontology supported preservation - Acting on Chan...
PERICLES Policy management & ontology supported preservation - Acting on Chan...PERICLES_FP7
Ā 
A Space X Industry Day Briefing 7 Jul08 Jgm R4
A Space X Industry Day Briefing 7 Jul08 Jgm R4A Space X Industry Day Briefing 7 Jul08 Jgm R4
A Space X Industry Day Briefing 7 Jul08 Jgm R4jmorriso
Ā 
INFORMATION SYSTEMS PROJECT MANAGEMENT(COLLEN AND THE GROUP)
INFORMATION SYSTEMS PROJECT MANAGEMENT(COLLEN AND THE GROUP)INFORMATION SYSTEMS PROJECT MANAGEMENT(COLLEN AND THE GROUP)
INFORMATION SYSTEMS PROJECT MANAGEMENT(COLLEN AND THE GROUP)Collen Tshebo
Ā 
UX (User Experience) Process, May 2017
UX (User Experience) Process, May 2017UX (User Experience) Process, May 2017
UX (User Experience) Process, May 2017Gary Coker
Ā 
IRJET- Smart Recipe-An Innovative Way to Cook
IRJET-  	  Smart Recipe-An Innovative Way to CookIRJET-  	  Smart Recipe-An Innovative Way to Cook
IRJET- Smart Recipe-An Innovative Way to CookIRJET Journal
Ā 

Similar to Context Reasoning and Prediction in Smart Environments: the Home Manager case (20)

Sapere project-introduction-dec-2010
Sapere project-introduction-dec-2010Sapere project-introduction-dec-2010
Sapere project-introduction-dec-2010
Ā 
Context-aware recommender system for multi-user smart home
Context-aware recommender system for multi-user smart homeContext-aware recommender system for multi-user smart home
Context-aware recommender system for multi-user smart home
Ā 
Meetup 11 here&now_megatriscomp design methodpartii_v0.2
Meetup 11 here&now_megatriscomp design methodpartii_v0.2Meetup 11 here&now_megatriscomp design methodpartii_v0.2
Meetup 11 here&now_megatriscomp design methodpartii_v0.2
Ā 
Ted talk April 20
Ted talk April 20Ted talk April 20
Ted talk April 20
Ā 
Unlocking Smart Building Potential with the RealEstateCore Ontology
Unlocking Smart Building Potential with the RealEstateCore OntologyUnlocking Smart Building Potential with the RealEstateCore Ontology
Unlocking Smart Building Potential with the RealEstateCore Ontology
Ā 
Meetup 10 here&now_megatriscomp_design_methodparti_v1
Meetup 10 here&now_megatriscomp_design_methodparti_v1Meetup 10 here&now_megatriscomp_design_methodparti_v1
Meetup 10 here&now_megatriscomp_design_methodparti_v1
Ā 
Meetup 10 here&now: Megatris Comp design method (Part 1)
Meetup 10 here&now: Megatris Comp design method (Part 1)Meetup 10 here&now: Megatris Comp design method (Part 1)
Meetup 10 here&now: Megatris Comp design method (Part 1)
Ā 
ARI2132 lecture4
ARI2132 lecture4ARI2132 lecture4
ARI2132 lecture4
Ā 
semana1.pptx
semana1.pptxsemana1.pptx
semana1.pptx
Ā 
ICS2208 lecture4
ICS2208 lecture4ICS2208 lecture4
ICS2208 lecture4
Ā 
Smart cities no ai without ia
Smart cities   no ai without iaSmart cities   no ai without ia
Smart cities no ai without ia
Ā 
Perception.JS - A Framework for Context Acquisition Processing and Presentation
Perception.JS - A Framework for Context Acquisition Processing and PresentationPerception.JS - A Framework for Context Acquisition Processing and Presentation
Perception.JS - A Framework for Context Acquisition Processing and Presentation
Ā 
Navigating the twilight zone - pathways towards digital transformation of foo...
Navigating the twilight zone - pathways towards digital transformation of foo...Navigating the twilight zone - pathways towards digital transformation of foo...
Navigating the twilight zone - pathways towards digital transformation of foo...
Ā 
A Personalized Software Assistant Framework To Achieve User Goals
A Personalized Software Assistant Framework To Achieve User GoalsA Personalized Software Assistant Framework To Achieve User Goals
A Personalized Software Assistant Framework To Achieve User Goals
Ā 
PERICLES Policy management & ontology supported preservation - Acting on Chan...
PERICLES Policy management & ontology supported preservation - Acting on Chan...PERICLES Policy management & ontology supported preservation - Acting on Chan...
PERICLES Policy management & ontology supported preservation - Acting on Chan...
Ā 
A Space X Industry Day Briefing 7 Jul08 Jgm R4
A Space X Industry Day Briefing 7 Jul08 Jgm R4A Space X Industry Day Briefing 7 Jul08 Jgm R4
A Space X Industry Day Briefing 7 Jul08 Jgm R4
Ā 
INFORMATION SYSTEMS PROJECT MANAGEMENT(COLLEN AND THE GROUP)
INFORMATION SYSTEMS PROJECT MANAGEMENT(COLLEN AND THE GROUP)INFORMATION SYSTEMS PROJECT MANAGEMENT(COLLEN AND THE GROUP)
INFORMATION SYSTEMS PROJECT MANAGEMENT(COLLEN AND THE GROUP)
Ā 
UX (User Experience) Process, May 2017
UX (User Experience) Process, May 2017UX (User Experience) Process, May 2017
UX (User Experience) Process, May 2017
Ā 
Sirris presentation
Sirris presentationSirris presentation
Sirris presentation
Ā 
IRJET- Smart Recipe-An Innovative Way to Cook
IRJET-  	  Smart Recipe-An Innovative Way to CookIRJET-  	  Smart Recipe-An Innovative Way to Cook
IRJET- Smart Recipe-An Innovative Way to Cook
Ā 

Recently uploaded

Risk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdfRisk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdfROCENODodongVILLACER
Ā 
Arduino_CSE ece ppt for working and principal of arduino.ppt
Arduino_CSE ece ppt for working and principal of arduino.pptArduino_CSE ece ppt for working and principal of arduino.ppt
Arduino_CSE ece ppt for working and principal of arduino.pptSAURABHKUMAR892774
Ā 
National Level Hackathon Participation Certificate.pdf
National Level Hackathon Participation Certificate.pdfNational Level Hackathon Participation Certificate.pdf
National Level Hackathon Participation Certificate.pdfRajuKanojiya4
Ā 
Industrial Safety Unit-IV workplace health and safety.ppt
Industrial Safety Unit-IV workplace health and safety.pptIndustrial Safety Unit-IV workplace health and safety.ppt
Industrial Safety Unit-IV workplace health and safety.pptNarmatha D
Ā 
Work Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvWork Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvLewisJB
Ā 
Instrumentation, measurement and control of bio process parameters ( Temperat...
Instrumentation, measurement and control of bio process parameters ( Temperat...Instrumentation, measurement and control of bio process parameters ( Temperat...
Instrumentation, measurement and control of bio process parameters ( Temperat...121011101441
Ā 
Main Memory Management in Operating System
Main Memory Management in Operating SystemMain Memory Management in Operating System
Main Memory Management in Operating SystemRashmi Bhat
Ā 
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsyncWhy does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsyncssuser2ae721
Ā 
Energy Awareness training ppt for manufacturing process.pptx
Energy Awareness training ppt for manufacturing process.pptxEnergy Awareness training ppt for manufacturing process.pptx
Energy Awareness training ppt for manufacturing process.pptxsiddharthjain2303
Ā 
Past, Present and Future of Generative AI
Past, Present and Future of Generative AIPast, Present and Future of Generative AI
Past, Present and Future of Generative AIabhishek36461
Ā 
welding defects observed during the welding
welding defects observed during the weldingwelding defects observed during the welding
welding defects observed during the weldingMuhammadUzairLiaqat
Ā 
Vishratwadi & Ghorpadi Bridge Tender documents
Vishratwadi & Ghorpadi Bridge Tender documentsVishratwadi & Ghorpadi Bridge Tender documents
Vishratwadi & Ghorpadi Bridge Tender documentsSachinPawar510423
Ā 
Introduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxIntroduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxk795866
Ā 
Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...VICTOR MAESTRE RAMIREZ
Ā 
šŸ”9953056974šŸ”!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
šŸ”9953056974šŸ”!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...šŸ”9953056974šŸ”!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
šŸ”9953056974šŸ”!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...9953056974 Low Rate Call Girls In Saket, Delhi NCR
Ā 
Mine Environment II Lab_MI10448MI__________.pptx
Mine Environment II Lab_MI10448MI__________.pptxMine Environment II Lab_MI10448MI__________.pptx
Mine Environment II Lab_MI10448MI__________.pptxRomil Mishra
Ā 
Correctly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleCorrectly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleAlluxio, Inc.
Ā 
Indian Dairy Industry Present Status and.ppt
Indian Dairy Industry Present Status and.pptIndian Dairy Industry Present Status and.ppt
Indian Dairy Industry Present Status and.pptMadan Karki
Ā 
Industrial Safety Unit-I SAFETY TERMINOLOGIES
Industrial Safety Unit-I SAFETY TERMINOLOGIESIndustrial Safety Unit-I SAFETY TERMINOLOGIES
Industrial Safety Unit-I SAFETY TERMINOLOGIESNarmatha D
Ā 
Research Methodology for Engineering pdf
Research Methodology for Engineering pdfResearch Methodology for Engineering pdf
Research Methodology for Engineering pdfCaalaaAbdulkerim
Ā 

Recently uploaded (20)

Risk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdfRisk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdf
Ā 
Arduino_CSE ece ppt for working and principal of arduino.ppt
Arduino_CSE ece ppt for working and principal of arduino.pptArduino_CSE ece ppt for working and principal of arduino.ppt
Arduino_CSE ece ppt for working and principal of arduino.ppt
Ā 
National Level Hackathon Participation Certificate.pdf
National Level Hackathon Participation Certificate.pdfNational Level Hackathon Participation Certificate.pdf
National Level Hackathon Participation Certificate.pdf
Ā 
Industrial Safety Unit-IV workplace health and safety.ppt
Industrial Safety Unit-IV workplace health and safety.pptIndustrial Safety Unit-IV workplace health and safety.ppt
Industrial Safety Unit-IV workplace health and safety.ppt
Ā 
Work Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvWork Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvv
Ā 
Instrumentation, measurement and control of bio process parameters ( Temperat...
Instrumentation, measurement and control of bio process parameters ( Temperat...Instrumentation, measurement and control of bio process parameters ( Temperat...
Instrumentation, measurement and control of bio process parameters ( Temperat...
Ā 
Main Memory Management in Operating System
Main Memory Management in Operating SystemMain Memory Management in Operating System
Main Memory Management in Operating System
Ā 
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsyncWhy does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
Ā 
Energy Awareness training ppt for manufacturing process.pptx
Energy Awareness training ppt for manufacturing process.pptxEnergy Awareness training ppt for manufacturing process.pptx
Energy Awareness training ppt for manufacturing process.pptx
Ā 
Past, Present and Future of Generative AI
Past, Present and Future of Generative AIPast, Present and Future of Generative AI
Past, Present and Future of Generative AI
Ā 
welding defects observed during the welding
welding defects observed during the weldingwelding defects observed during the welding
welding defects observed during the welding
Ā 
Vishratwadi & Ghorpadi Bridge Tender documents
Vishratwadi & Ghorpadi Bridge Tender documentsVishratwadi & Ghorpadi Bridge Tender documents
Vishratwadi & Ghorpadi Bridge Tender documents
Ā 
Introduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxIntroduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptx
Ā 
Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...
Ā 
šŸ”9953056974šŸ”!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
šŸ”9953056974šŸ”!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...šŸ”9953056974šŸ”!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
šŸ”9953056974šŸ”!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
Ā 
Mine Environment II Lab_MI10448MI__________.pptx
Mine Environment II Lab_MI10448MI__________.pptxMine Environment II Lab_MI10448MI__________.pptx
Mine Environment II Lab_MI10448MI__________.pptx
Ā 
Correctly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleCorrectly Loading Incremental Data at Scale
Correctly Loading Incremental Data at Scale
Ā 
Indian Dairy Industry Present Status and.ppt
Indian Dairy Industry Present Status and.pptIndian Dairy Industry Present Status and.ppt
Indian Dairy Industry Present Status and.ppt
Ā 
Industrial Safety Unit-I SAFETY TERMINOLOGIES
Industrial Safety Unit-I SAFETY TERMINOLOGIESIndustrial Safety Unit-I SAFETY TERMINOLOGIES
Industrial Safety Unit-I SAFETY TERMINOLOGIES
Ā 
Research Methodology for Engineering pdf
Research Methodology for Engineering pdfResearch Methodology for Engineering pdf
Research Methodology for Engineering pdf
Ā 

Context Reasoning and Prediction in Smart Environments: the Home Manager case

  • 1. Context Reasoning and Prediction in Smart Environments: the Home Manager case IIMSS 2017 Algarve - Portugal, 23 June 2017 Roberta Calegari, Enrico Denti
  • 2. Outline ā€¢ Scope & Goals ā€¢ Smart Environments in the Butlers perspective o The Butlers Vision o The Home Manager Platform o The Home Manager Architecture ā€¢ Smart Environment in HM ā€¢ The Smart Kitchen Case Study o The Smart Kitchen: Scenario o The Smart Kitchen: Prototype ā€¢ Conclusions & Future Work
  • 3. Scope & Goals (1/2) Smart Environments socio-technical nature calls for from diverse fields ļƒ  multi-paradigm perspective REQUIREMENTS ā€¢ availability of an effective coordination middleware ā€¢ effective support to situatedness ā€¢ guidelines and enabling techniques exploiting concepts, methodologies, technologies from the most diverse fields, in a multi-paradigm perspective ā€¢ skills ā€¢ concepts ā€¢ methodologies ā€¢ technologies
  • 4. Framework for the design & development of Smart Environments ā€¢ accounting for technological and human / organisational aspects ā€¢ combining different dimensions and behaviour from pervasive, distributed, situated and intelligent computing Scope & Goals (2/2) Butlers for Smart Spaces ā€¢ technology-neutral ā€¢ reference framework ā€¢ focused on usersā€™ situated- ness and interaction aspects Home Manager ā€¢ platform for Smart Home & Smart Living contexts ā€¢ focused on reasoning aspects ā€¢ multi-paradigm, agent-based
  • 5. The Butlers Vision ā€¢ Butlers for Smart Spaces specialises the Butlers framework to the Smart Spaces context ā€¢ Home Manager leads to concretise it as a multi-agent system on the TuCSoN infrastructure
  • 6. Butlers for Smart Spacesā€¦ Specialisation of the Butlers framework to the Smart Spaces context The Monitoring layer groups together the Butlers information and control layers The Services layer embeds the coordination referring to the pre-processing of raw information into exploitable knowledge Goals & Policies side-by- side take into account user- awareness (user-related, higher-level coordination) The Reasoning & Situated Reasoning layers split the Butlers Intelligence layer
  • 7. ā€¦on Home Manager as a MAS Home Manager (apice.unibo.it/xwiki/bin/view/Products/HomeManager) concretises it as a MAS on the TuCSoN infrastructure The TuCSoN infrastructure conceptually surrounds all layers, enabling and govern- ing agent coordination & interaction ā€¢ All layers are re-shaped based on TuCSoN concepts & metaphors ā€¢ Agents & Policies sub- layers appear side-by-side, following the TuCSoN approach
  • 8. The Home Manager platform ā€¢ Open source platform for Smart Spaces, built on top of the TuCSoN multi-agent infrastructure o deployable also on a Raspberry PI 2 o Java-based (~interoperable with Win10-IoT core) ā€¢ Smart House immersed in the surrounding environment ļƒ  Smart Living context o Devices (air conditioners, lights, etc.) o Users of different categories + RBAC ā€¢ Focus on Context Reasoning & Context Prediction o Satisfy users desires while respecting global constraints ļƒ  suitable coordination laws to govern interaction o Anticipate needs by exploiting the userā€™s situation in time and space
  • 9. Intuitive architecture Main features: o Autonomous ā€œsituatedā€ decisions by exploiting the userā€™s location o Exploration of the environment around the userā€™s location o Information about the surrounding environment (e.g. weather) o Interaction with selected social networks (e.g. Twitter) o Tracking of the human presence
  • 10. Smart Environments in HM ā€¢ Designing a Smart Environment in Home Manager amounts to: o identify relevant device and service categories o define a tuple-based representation of the relevant knowledge o define the agent interaction o develop an agent for each device category & service to interact with Clear separation between ā€¢ social / individual intelligence ā€¢ mechanisms / policies Features ā€¢ independent testing and debug of agents and policies ā€¢ effective exploitation of the data-driven, multi-paradigm development approach
  • 11. The Smart Kitchen Case Study
  • 12. ā€¢ Smart Fridge & Smart Pantry o food monitoring o collecting historical data on userā€™s habits o generate the corresponding buy tuple if necessary (policies) ā€¢ Smart Oven o support the userā€™s food cooking (e.g. dietary,ā€¦) ā€¢ Smart Mixer o recipe instructions interacting with Smart Fridge & Smart Oven to check food availability ļƒ  context adaptation ā€¢ Smart Shopper o predict the userā€™s needs ļƒ  make contextualised suggestions o shopping list based on the above data o contact the ā€œproperā€ vendor based on context- aware policies The Smart Kitchen: scenario
  • 13. The Smart Kitchen: prototype Middleware ļƒ  coordination laws ļƒ  interoperability & integration ā€¢ Declarative approach o bridge among different forms of heterogeneity o support agent uncoupling o support & promote separation between policies & mechanisms o supports context reasoning
  • 14. Future (current) work Context prediction & adaptation: prediction agent WEKA Classifier (Ilaria Bertoletti Master's thesis, 15 June 2017) Tempera- ture prefs Device usage policies Action plan on air conditioners Learning & prediction of user habits
  • 15. Future (current) work Context prediction & adaptation: prediction agent WEKA Classifier (Ilaria Bertoletti Master's thesis, 15 June 2017) CONTEXT PREDICTION ā€¢ Grab user habits info from multiple sources ā€¢ Select relevant data ā€¢ Anticipate user's routine & desires CONTEXT REASONING ā€¢ Compute heterogeneous context info ā€¢ Enable HM to make suggestions ā€¢ Increase HM decision autonomy PROACTIVE ADAPTATION ā€¢ Autonomously appy action plan on house devices ā€¢ Enable HM to adapt to new needs ā€¢ Reduce user's interventions
  • 16. Future (current) work Context prediction & adaptation: prediction agent WEKA Classifier (Ilaria Bertoletti Master's thesis, 15 June 2017) ā€¢ Get daily routine ā€¢ Weather + policies + routine = decision
  • 17. Future (current) work Context prediction & adaptation: prediction agent WEKA Classifier (Ilaria Bertoletti Master's thesis, 15 June 2017)
  • 18. Home Manager lays the foundations to support context reasoning and context prediction ā€¢ Yet, just a starting point.. ā€¢ A lot of work remains to be done Conclusions (1) Butlers for Smart Spaces ā€¢ technology-neutral ā€¢ reference framework for pervasive IoT contexts ā€¢ focused on usersā€™ situated- ness and interaction aspects Home Manager ā€¢ concretise the BSS approach ā€¢ the infrastructure bridges among the agentsā€™ ontologies, APIs, knowledge representations, interaction protocols
  • 19. Conclusions (2) Future work ā€¢ Deeper exploration of the context reasoning aspect (machine learning,ā€¦) ā€¢ Cross-platform interoperability ā€¢ Java/Windows 10 on the Raspberry ā€¢ Emerging standards ā€¢ Developing more complex policies and implementing other advanced situated services
  • 20. Home Manager URLs ā€¢ Home page http://apice.unibo.it/xwiki/bin/view/Products/HomeManager ā€¢ Bitbucket repository https://bitbucket.org/tuprologteam/homemanager
  • 21. Roberta Calegari roberta.calegari@unibo.it Enrico Denti enrico.denti@unibo.it http://www.unibo.it http://www.cse.unibo.it/en http://apice.unibo.it/xwiki/bin/view/Main/?language=en
  • 22. Prototype screenshots Smart kitchen simulated device vs physical device Mixer agent
  • 23. Prototype screenshots Smart kitchen cooking requests missing ingredients