SlideShare a Scribd company logo
Context awareness &
Contextual Computing
Occupancy Monitoring of Mary Idema Pew
Library
Advisor Professor Engelsma
Sam Serpoosh
https://github.com/Sam-Serpoosh
https://linkedin.com/in/samserpoosh
http://masihjesus.wordpress.com
@masihjesus
Device sensors more
information
We collect big data
• What do we do with it?
• Recommendation Engines
• More relevant and useful content for each individual
• Better user experience and more value
What is missing?
Human-human VS
human-computer
Current Context & Situational Information
Context can be different
Hang out suggestion
WHERE???
PREVIOUS ACTS???
WHO???
What you’re looking at
Context depends on domain
• Based on the application
• Problem it is solving
• The Domain
“Any information that can be used in order to
describe the situation of an entity relevant to
interaction between user and the application is
considered Context.”
What can be improved on
campus?
• Looking for a book?
• Campus Tour Guide?
Campus tour app  kills social
Interaction
Meeting with library staff
• new books notification
while they’re passing by
different sections
• Traffic and
Occupancy Monitoring
In certain areas
Occupancy monitoring wins
• Library staff are more interested in occupancy
monitoring
• That’s an actual problem
• Students can get help on where is less crowded to
study/work
How to solve it
• Install Beacon devices in 3rd Floor Innovation Zone
& 4th Floor Study Room
• Add a traffic/occupancy monitoring feature to a
popular application which is used by majority of
students
• Collect and process traffic data and get real-time
information for those areas
Overall architecture
Client application
• Laker Mobile
• Used by Majority of Students
• Has a Library Section
• Need to make it more useful
• Add a context-aware background
service for monitoring traffic
activities (e.g. Enter, Exit)
ibeacon
• Wireless devices transmitting radio signals to smart
devices
• Devices can hear these signals (via BLE scanning)
• Communicate with beacons
• Estimate their proximity from them
Ibeacon (cont.)
• Introduced by Apple in iOS 7
• Core Location Library
• Works with Bluetooth Low Energy (BLE)
• Proximity Calculation and Context Awareness
Main functionalities
• Region Monitoring
• Can detect Enter/Exit for a monitored region/area
• Region Change detection
• Beacon Ranging
• Can calculate the proximity to a certain beacon device
in a given region
• Proximity levels  Far, Near, Immediate, Unknown
• Identifiable through UUID, Major and Minor numbers
We used estimote beacons
Ruby on rails web server
• Receiving traffic data
• Returns traffic information in a given period in
conventional format: JSON, CSV
• Gives real-time information on population of
monitored areas
• Shows a heat map associated with monitored areas
• All the other BORING parts of a web service
Sample data
Submitted data from a client device looks like this
Sample data (cont.)
Areas population
Heat map
Overall workflow
Pretty Straightforward and Simple
Quick peak on Implementation
• CLBeaconManager From Core Location Library
• When a device enters a monitored area
• Certain callback gets invoked by beacon manager
• (void)beaconManager:(ESTBeaconManager*)didEnterRegion:(ESTBea
conRegion)
• Context-Aware logic of the application is here or
triggered here
Did enter region
Region monitoring &
beacon ranging
• Region Monitoring can happen both in background
and foreground
• Beacon Ranging can only happen when the
application is in foreground
• Proximity calculation
• Signal Strength calculation
• Solving the problem of overlapping areas
Frequency of ble scan
• Ranging happens quite frequently when application
is in foreground
• Almost every few seconds
• Region Monitoring depends on few things
Condition Max time to detect Range
Change
notifyEntryStateOnDisplay = YES
& Phone Awakened
1 second
notifyEntryStateOnDisplay = NO
& Phone Awakened
NEVER
Application is just running in
background
From few seconds up to 15
minutes
Subtleties on server
• Device is On border of a region
• Two subsequent traffic data can be submitted with
EXACT same time
• Which one do you consider in Area Population
calculation?
What we can find out?
• How long a users occupy a given area
• Enter at 9:00 AM
• Exit at 13 PM
• Taking a break or temporarily leaving the area
• Exit at 18:35
• Enter at 18:44
• Taking a break, Finding a book, meeting someone, etc.
• Just walking by a monitored area closely
• Enter at 17:35:07
• Exit at 17:35:40
Hourly population report
Closer look
Devices per day
Lessons learned
Apple users upgrade FAST
Lessons learned (CONT.)
• Dealing with new and unfamiliar technology
• Technical Side = Advertisement and Promoting
• ??A lot of unknowns, unfamiliar obstacles??
• Building a infrastructure, platform, framework
• Core logic is interchangeable
Lessons learned (cont.)
• Dealing with other organizations
• IT was worried about WiFi interference
• Bluetooth & WiFi  2.4 GHz frequency
• Students will face Internet connection problems
Wifi disconnects
• Could not connect to WiFi through my laptop???!!!
• Everything else was connected (iPhone, iPad, etc.)
• The conversation with IT hit me
• we have an Estimote beacon in our lab
• Stackoverflow to the rescue
Context matters
• Human-Human interaction is very effective at this
• We want the human-computer interaction to be
efficient and valuable
• recommending appropriate things, showing relevant
content
• Why not better? We know one more missing
piece of the puzzle
• Context is a Caved in Stone
Special thanks to
• Professor Jonathan Engelsma
• Carlos Rodriguez
• Kyle Felker
• Kristin Meyer
• Ehsan Valizadeh
• Davoud Qorashi
• All the students who used the application and
collaborated in this work
References
• Dey AK, Abowd GD. Towards a better understanding of context
and context-awareness. CHI’2000 Workshop on the
What, Who, Where, When, and How of Context-Awareness.
• Yin, Chuantao, Bertrand David, and Rene Chalon. "Use
your mobile computing devices to learn-Contextual mobile
learning system design and case studies."Computer
Science and Information Technology, 2009. ICCSIT 2009.
2nd IEEE International Conference on. IEEE, 2009.
• Prophet Kitchen application for Rubens House in Antwerp
Belgium. http://vimeo.com/84760383
• Estimote official website. http://estimote.com/
• API documentation of Estimote.
http://estimote.com/api/index.html
References (cont.)
• Estimote iOS SDK. https://github.com/Estimote/iOS-
SDK
• Apple documentation on CLBeaconManager.
https://developer.apple.com/library/ios/documentatio
n/CoreLocation/Reference/CLLocationManagerDele
gate_Protocol/CLLocationManagerDelegate/CLLoca
tionManagerDelegate.html -
//apple_ref/occ/intfm/CLLocationManagerDelegate/l
ocationManager:didEnterRegion:
References (cont.)
• Frequency of region monitoring and beacon ranging.
http://developer.radiusnetworks.com/2013/11/13/ibe
acon-monitoring-in-the-background-and-
foreground.html
• Estimote on coexistence of WiFi and Beacon
devices. https://community.estimote.com/hc/en-
us/articles/201186046-Do-Wi-Fi-Networks-Interfere-
with-Beacons-

More Related Content

Similar to Context-Awareness & Occupancy/Traffic Monitoring

Future Mobile Learning (29 August 2011)
Future Mobile Learning (29 August 2011)Future Mobile Learning (29 August 2011)
Future Mobile Learning (29 August 2011)
Judy Brown
 
Internet of things (IoT)
Internet of things (IoT)Internet of things (IoT)
Internet of things (IoT)
Prakash Honnur
 
Big Data with IOT approach and trends with case study
Big Data with IOT approach and trends with case studyBig Data with IOT approach and trends with case study
Big Data with IOT approach and trends with case study
Sharjeel Imtiaz
 
Designing and deploying mobile user studies in the wild: a practical guide
Designing and deploying mobile user studies in the wild: a practical guideDesigning and deploying mobile user studies in the wild: a practical guide
Designing and deploying mobile user studies in the wild: a practical guide
Karen Church
 
Engaging Your Audience Through Online Technologies: Session 2
Engaging Your Audience Through Online Technologies: Session 2Engaging Your Audience Through Online Technologies: Session 2
Engaging Your Audience Through Online Technologies: Session 2
HRMM
 
Geeks bearing gifts september2012
Geeks bearing gifts september2012Geeks bearing gifts september2012
Geeks bearing gifts september2012ayoungkin
 
From Context-awareness to Human Behavior Patterns
From Context-awareness to Human Behavior PatternsFrom Context-awareness to Human Behavior Patterns
From Context-awareness to Human Behavior Patterns
Ville Antila
 
introduction-to_mobile_computing 1
 introduction-to_mobile_computing 1 introduction-to_mobile_computing 1
introduction-to_mobile_computing 1
Shahid Riaz
 
Internet of things
Internet of thingsInternet of things
Internet of things
AJITHKUMAR RAVI
 
Howison si2 keynote
Howison si2 keynoteHowison si2 keynote
Howison si2 keynote
James Howison
 
Bringing Data to the Edge
Bringing Data to the EdgeBringing Data to the Edge
Bringing Data to the Edge
greenrobot
 
Savova Canuel & Crichton - Mobile technology and information literacy instruc...
Savova Canuel & Crichton - Mobile technology and information literacy instruc...Savova Canuel & Crichton - Mobile technology and information literacy instruc...
Savova Canuel & Crichton - Mobile technology and information literacy instruc...IL Group (CILIP Information Literacy Group)
 
Intelligent Conversational Agents for Ambient Computing SIGIR 2022 Ruhi Sarik...
Intelligent Conversational Agents for Ambient Computing SIGIR 2022 Ruhi Sarik...Intelligent Conversational Agents for Ambient Computing SIGIR 2022 Ruhi Sarik...
Intelligent Conversational Agents for Ambient Computing SIGIR 2022 Ruhi Sarik...
Amazon Science
 
Libraries Next Big Thing
Libraries Next Big ThingLibraries Next Big Thing
Libraries Next Big Thing
Wajdi Tahmoush
 
Intranet and extranet
Intranet and extranet Intranet and extranet
Intranet and extranet
Mahmoud Shaqria
 
AMcNab_Mobilising E-Content_AGI/LIR
AMcNab_Mobilising E-Content_AGI/LIRAMcNab_Mobilising E-Content_AGI/LIR
AMcNab_Mobilising E-Content_AGI/LIR
Alison McNab
 
Everybody’s surfin’ now: Teaching and learning with mobile technology
Everybody’s surfin’ now: Teaching and learning with mobile technology Everybody’s surfin’ now: Teaching and learning with mobile technology
Everybody’s surfin’ now: Teaching and learning with mobile technology robincanuel
 
Quality of Experience in Smart Environments
Quality of Experience in Smart EnvironmentsQuality of Experience in Smart Environments
Quality of Experience in Smart Environments
Pedro Costa
 
Making sense
Making senseMaking sense
Making sense
Jared Sheehan
 
Models and Methods for Global User Research
Models and Methods for Global User ResearchModels and Methods for Global User Research
Models and Methods for Global User Research
GfK User Centric
 

Similar to Context-Awareness & Occupancy/Traffic Monitoring (20)

Future Mobile Learning (29 August 2011)
Future Mobile Learning (29 August 2011)Future Mobile Learning (29 August 2011)
Future Mobile Learning (29 August 2011)
 
Internet of things (IoT)
Internet of things (IoT)Internet of things (IoT)
Internet of things (IoT)
 
Big Data with IOT approach and trends with case study
Big Data with IOT approach and trends with case studyBig Data with IOT approach and trends with case study
Big Data with IOT approach and trends with case study
 
Designing and deploying mobile user studies in the wild: a practical guide
Designing and deploying mobile user studies in the wild: a practical guideDesigning and deploying mobile user studies in the wild: a practical guide
Designing and deploying mobile user studies in the wild: a practical guide
 
Engaging Your Audience Through Online Technologies: Session 2
Engaging Your Audience Through Online Technologies: Session 2Engaging Your Audience Through Online Technologies: Session 2
Engaging Your Audience Through Online Technologies: Session 2
 
Geeks bearing gifts september2012
Geeks bearing gifts september2012Geeks bearing gifts september2012
Geeks bearing gifts september2012
 
From Context-awareness to Human Behavior Patterns
From Context-awareness to Human Behavior PatternsFrom Context-awareness to Human Behavior Patterns
From Context-awareness to Human Behavior Patterns
 
introduction-to_mobile_computing 1
 introduction-to_mobile_computing 1 introduction-to_mobile_computing 1
introduction-to_mobile_computing 1
 
Internet of things
Internet of thingsInternet of things
Internet of things
 
Howison si2 keynote
Howison si2 keynoteHowison si2 keynote
Howison si2 keynote
 
Bringing Data to the Edge
Bringing Data to the EdgeBringing Data to the Edge
Bringing Data to the Edge
 
Savova Canuel & Crichton - Mobile technology and information literacy instruc...
Savova Canuel & Crichton - Mobile technology and information literacy instruc...Savova Canuel & Crichton - Mobile technology and information literacy instruc...
Savova Canuel & Crichton - Mobile technology and information literacy instruc...
 
Intelligent Conversational Agents for Ambient Computing SIGIR 2022 Ruhi Sarik...
Intelligent Conversational Agents for Ambient Computing SIGIR 2022 Ruhi Sarik...Intelligent Conversational Agents for Ambient Computing SIGIR 2022 Ruhi Sarik...
Intelligent Conversational Agents for Ambient Computing SIGIR 2022 Ruhi Sarik...
 
Libraries Next Big Thing
Libraries Next Big ThingLibraries Next Big Thing
Libraries Next Big Thing
 
Intranet and extranet
Intranet and extranet Intranet and extranet
Intranet and extranet
 
AMcNab_Mobilising E-Content_AGI/LIR
AMcNab_Mobilising E-Content_AGI/LIRAMcNab_Mobilising E-Content_AGI/LIR
AMcNab_Mobilising E-Content_AGI/LIR
 
Everybody’s surfin’ now: Teaching and learning with mobile technology
Everybody’s surfin’ now: Teaching and learning with mobile technology Everybody’s surfin’ now: Teaching and learning with mobile technology
Everybody’s surfin’ now: Teaching and learning with mobile technology
 
Quality of Experience in Smart Environments
Quality of Experience in Smart EnvironmentsQuality of Experience in Smart Environments
Quality of Experience in Smart Environments
 
Making sense
Making senseMaking sense
Making sense
 
Models and Methods for Global User Research
Models and Methods for Global User ResearchModels and Methods for Global User Research
Models and Methods for Global User Research
 

Recently uploaded

Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.
ViralQR
 
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
UiPathCommunity
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
James Anderson
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
Cheryl Hung
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
ControlCase
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
nkrafacyberclub
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
Pierluigi Pugliese
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Nexer Digital
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
Ralf Eggert
 
Quantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIsQuantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIs
Vlad Stirbu
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
DanBrown980551
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
Guy Korland
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
Dorra BARTAGUIZ
 
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Product School
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
OnBoard
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
UiPathCommunity
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
Safe Software
 

Recently uploaded (20)

Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.
 
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
 
Quantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIsQuantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIs
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
 
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
 

Context-Awareness & Occupancy/Traffic Monitoring

  • 1. Context awareness & Contextual Computing Occupancy Monitoring of Mary Idema Pew Library Advisor Professor Engelsma Sam Serpoosh https://github.com/Sam-Serpoosh https://linkedin.com/in/samserpoosh http://masihjesus.wordpress.com @masihjesus
  • 3. We collect big data • What do we do with it? • Recommendation Engines • More relevant and useful content for each individual • Better user experience and more value
  • 6. Context can be different
  • 9. Context depends on domain • Based on the application • Problem it is solving • The Domain “Any information that can be used in order to describe the situation of an entity relevant to interaction between user and the application is considered Context.”
  • 10. What can be improved on campus? • Looking for a book? • Campus Tour Guide?
  • 11. Campus tour app  kills social Interaction
  • 12. Meeting with library staff • new books notification while they’re passing by different sections • Traffic and Occupancy Monitoring In certain areas
  • 13. Occupancy monitoring wins • Library staff are more interested in occupancy monitoring • That’s an actual problem • Students can get help on where is less crowded to study/work
  • 14. How to solve it • Install Beacon devices in 3rd Floor Innovation Zone & 4th Floor Study Room • Add a traffic/occupancy monitoring feature to a popular application which is used by majority of students • Collect and process traffic data and get real-time information for those areas
  • 16. Client application • Laker Mobile • Used by Majority of Students • Has a Library Section • Need to make it more useful • Add a context-aware background service for monitoring traffic activities (e.g. Enter, Exit)
  • 17. ibeacon • Wireless devices transmitting radio signals to smart devices • Devices can hear these signals (via BLE scanning) • Communicate with beacons • Estimate their proximity from them
  • 18. Ibeacon (cont.) • Introduced by Apple in iOS 7 • Core Location Library • Works with Bluetooth Low Energy (BLE) • Proximity Calculation and Context Awareness
  • 19. Main functionalities • Region Monitoring • Can detect Enter/Exit for a monitored region/area • Region Change detection • Beacon Ranging • Can calculate the proximity to a certain beacon device in a given region • Proximity levels  Far, Near, Immediate, Unknown • Identifiable through UUID, Major and Minor numbers
  • 20. We used estimote beacons
  • 21. Ruby on rails web server • Receiving traffic data • Returns traffic information in a given period in conventional format: JSON, CSV • Gives real-time information on population of monitored areas • Shows a heat map associated with monitored areas • All the other BORING parts of a web service
  • 22. Sample data Submitted data from a client device looks like this
  • 26. Quick peak on Implementation • CLBeaconManager From Core Location Library • When a device enters a monitored area • Certain callback gets invoked by beacon manager • (void)beaconManager:(ESTBeaconManager*)didEnterRegion:(ESTBea conRegion) • Context-Aware logic of the application is here or triggered here
  • 28. Region monitoring & beacon ranging • Region Monitoring can happen both in background and foreground • Beacon Ranging can only happen when the application is in foreground • Proximity calculation • Signal Strength calculation • Solving the problem of overlapping areas
  • 29. Frequency of ble scan • Ranging happens quite frequently when application is in foreground • Almost every few seconds • Region Monitoring depends on few things Condition Max time to detect Range Change notifyEntryStateOnDisplay = YES & Phone Awakened 1 second notifyEntryStateOnDisplay = NO & Phone Awakened NEVER Application is just running in background From few seconds up to 15 minutes
  • 30. Subtleties on server • Device is On border of a region • Two subsequent traffic data can be submitted with EXACT same time • Which one do you consider in Area Population calculation?
  • 31. What we can find out? • How long a users occupy a given area • Enter at 9:00 AM • Exit at 13 PM • Taking a break or temporarily leaving the area • Exit at 18:35 • Enter at 18:44 • Taking a break, Finding a book, meeting someone, etc. • Just walking by a monitored area closely • Enter at 17:35:07 • Exit at 17:35:40
  • 36. Lessons learned (CONT.) • Dealing with new and unfamiliar technology • Technical Side = Advertisement and Promoting • ??A lot of unknowns, unfamiliar obstacles?? • Building a infrastructure, platform, framework • Core logic is interchangeable
  • 37. Lessons learned (cont.) • Dealing with other organizations • IT was worried about WiFi interference • Bluetooth & WiFi  2.4 GHz frequency • Students will face Internet connection problems
  • 38. Wifi disconnects • Could not connect to WiFi through my laptop???!!! • Everything else was connected (iPhone, iPad, etc.) • The conversation with IT hit me • we have an Estimote beacon in our lab • Stackoverflow to the rescue
  • 39. Context matters • Human-Human interaction is very effective at this • We want the human-computer interaction to be efficient and valuable • recommending appropriate things, showing relevant content • Why not better? We know one more missing piece of the puzzle • Context is a Caved in Stone
  • 40. Special thanks to • Professor Jonathan Engelsma • Carlos Rodriguez • Kyle Felker • Kristin Meyer • Ehsan Valizadeh • Davoud Qorashi • All the students who used the application and collaborated in this work
  • 41.
  • 42. References • Dey AK, Abowd GD. Towards a better understanding of context and context-awareness. CHI’2000 Workshop on the What, Who, Where, When, and How of Context-Awareness. • Yin, Chuantao, Bertrand David, and Rene Chalon. "Use your mobile computing devices to learn-Contextual mobile learning system design and case studies."Computer Science and Information Technology, 2009. ICCSIT 2009. 2nd IEEE International Conference on. IEEE, 2009. • Prophet Kitchen application for Rubens House in Antwerp Belgium. http://vimeo.com/84760383 • Estimote official website. http://estimote.com/ • API documentation of Estimote. http://estimote.com/api/index.html
  • 43. References (cont.) • Estimote iOS SDK. https://github.com/Estimote/iOS- SDK • Apple documentation on CLBeaconManager. https://developer.apple.com/library/ios/documentatio n/CoreLocation/Reference/CLLocationManagerDele gate_Protocol/CLLocationManagerDelegate/CLLoca tionManagerDelegate.html - //apple_ref/occ/intfm/CLLocationManagerDelegate/l ocationManager:didEnterRegion:
  • 44. References (cont.) • Frequency of region monitoring and beacon ranging. http://developer.radiusnetworks.com/2013/11/13/ibe acon-monitoring-in-the-background-and- foreground.html • Estimote on coexistence of WiFi and Beacon devices. https://community.estimote.com/hc/en- us/articles/201186046-Do-Wi-Fi-Networks-Interfere- with-Beacons-

Editor's Notes

  1. Our devices have different sensors in order to provide more and more information. How are we using this information in our applications?
  2. Context, current context and situational information (And context is not necessarily the location of the user! That is big part of it but it’s not ALL)
  3. You have an app that suggests good restaurants, close by! When humans are talking about the same thing they consider the contextIt is raining but the app is suggesting a restaurant, which ONLY has sitting area outside! BUT humans never do that.
  4. It is a relative concept and can be completely different based on different domains and situations
  5. Most of apps in this category consider user interests, previous activities and where they are BUT not who they are hanging Out with at the time!
  6. Getting appropriate information based on what art piece you’re looking at! That is the context here (kind of an indoor GPS and the fact that You are near which art piece)
  7. Looking around for finding a book and jumping aroundCampus tour is happening all the time and can be automated as well for people (not a huge fan of this one myself)
  8. One of those moments that you come up with an idea and then realize it’sAgainst what you believe and get consider it a No-Go option!
  9. We thought of meeting with library staff and see what kinds of problems they have which Are good candidate for a context-aware application or feature to solve them.
  10. Consist of the following items: * Client device (iOS device in this project) * Estimote beacons * Ruby on Rails web server * PaaS which is Heroku in this project(joke about area is higher than Cloud [internet] and airplane cabin monitoring) :D
  11. To make it more useful we changed its content to the computer availability of Library which according to library staff is a very popular feature Also we allow users to turn on/off the feature if they wish. Everything else is happening in Background and no UI involved in this feature (mostly a background service)
  12. In the case of Estimote, UUID is representing the manufacturer, major an minor number specify each Individual beacon device
  13. Exit can only come once since the device left the area and is not in the range/region at allBut enter can come again within few minutes and population will be wrong in that moment But after that will be accurate but if we consider Enter only and the reality was Exit, until the End of the day that population would have wrong information in it (Also the scenario that phone dies after Enter)
  14. Y axis is the population of the monitored areas and X axis is the last two weeks of monitoring on an hourly basis from 9:00 AM until 2:00 AMAs we get closer to exam week the population grows until it drops again at the end of it since a lot of students are done with the semester at this point And say bye to the library until the next semester 
  15. Around lunch time population drops suddenlyAlso the same thing happens close to 6 since a lot of students have class at that timeThe population grows from morning till noon and then again after lunch until before classes
  16. In total it was about 80 devices that we collected traffic data for. Again the result of not advertising and promoting The application shows how it can affect the usage of it and users not knowing about what’s going on
  17. Green shows the users running the latest versionImpact of simplicity and ease of installation and updating handled by Apple
  18. Example of advertisement in last year project and its impactThis year we did a very small amount of advertisement and promoting the app but Even that small advertisement made N (extract out of DB) number of users turn on their bluetoothAnd use this feature and help the library. So better advertisement better results. Specially when it is dealing with some sensitive areas: Bluetooth Unique IdentifierNo stackoverflow questions, or the few ones are answered by developers of companies Manufacturing beacons and their SDK developers * Mostly source code * Mailing lists * Issue trackersThe interface of interacting with technology, is stable and reusableIn order to solve a new problem in a new domain use the building blocks Related to the context-awareness technology and change the core logic to solve things
  19. And a bunch of other devices work with 2.4 GHz frequency Since WiFi is everywhere, so are Bluetooth devices Bluetooth Smart is using Adapting Frequency Hopping approach which is solving interference problem and it’s not on a fixed frequency. They can coexist in in peace with no problem.