Network Driven Behaviour Modelling for Designing User Centred IoT Services
3 likes4,583 views
The document discusses the potential of using existing wireless networks, particularly Wi-Fi, as a sensing modality for understanding human interactions and environments in the context of the Internet of Things (IoT). It explores models for energy-efficient push notifications, personal object analytics, and human behavior assessment in workplaces using Wi-Fi signals. The findings suggest that leveraging these technologies can transform how we quantify and enhance human experiences in connected ecosystems.
Network Driven Behaviour Modelling for Designing User Centred IoT Services
- 1. Fahim Kawsar Internet of Things Research Network Driven Behaviour Modelling for Connected Living
- 3. 2 Questions
- 4. Internet is all about Human Experience not Bits and Bytes!
- 5. What Human Experience will be defined by an IoT enabled World?
- 7. If everything is connected why would you need a device?
- 8. Sense Learn Act Zero Interaction and Zero UI and Ubiquitous Awareness
- 9. WiFi is the most Pervasive Sensor Network. Its available literally everywhere.
- 10. To what extent can we leverage existing wireless network as a sensing modality to understand human context? To what extent can we leverage existing wireless network as a platform for connected objects? Sensorless Sensing with Wireless Network
- 11. People-People Interaction Wireless network is the key fabric for designing connected human experiences People-Object Interaction People-Content Interaction
- 12. People-People Interaction People-Object Interaction People-Content Interaction ”Energy Efficient Scheduling for Mobile Push Notifications”. MobiQuitous 2015
- 17. Push Notification and RRC State Machine A mobile device is in the CELL_DCH state for a specific time period (which is called tail time) without any or small data transmission after a data session, and this tail time corresponds to 60%of the total energy consumed by UE.
- 18. Bringing the Network into the Story
- 19. 1 1 1 0 1 0 1 0 1 0 1 0 0 0 0 0 0 0 1 0 1 1 1 0 Day j-4 Day j-3 Day j-2 Day j-1 Look up day, Nl=4 T 12:00 12:01 12:02 . . . . 23: 59 2 Selected Candidate Days 1 1 1 ? ? ? Day jc Lookupwindow(Lk) DSj-4=0.6 DSj-4=0.7 Over 75% of network activity can be predicted with accuracy of over 80% Discovering the Human Routine
- 20. Average latency is 157 seconds. ±15% energy can be saved by buffering notifications. ô RNC UE UTRAN GGSN SGSN CN Internet Burst Detector Deep Packet Inspector Notification Detector Notification Scheduler Prediction Model NS Request TTL TTL Push to Model For Update Request Scheduler
- 21. People-People Interaction People-Object Interaction People-Content Interaction ”Sensing WiFi Network for Personal IoT Analytics”. IoT 2015
- 22. Waste Pollution Traffic Quantified Self Quantified Home Quantified City Search for physical objects’ location and state is one of the basic services that provides foundation for many applications. 22
- 23. What we learnt in the past Dedicated Sensing Infrastructure (ZigBee, RFID, Mote, etc.) High deployment and management costs Search range is limited to the smart phones’ proximity Bluetooth Discovery with Smart Phone 23
- 24. Can WiFi network be used as a platform for personal IoT analytics? Research Objective Premise Connected objects’ movement data extracted from WiFi network signals carries vital information to model their spatio-temporal usage pattern 24
- 25. ôMobile Object Tags Static Object Tags Home Node - Proximity Ranging Service - Data Storage Service EF5 Personal Object AnalyticsQuery Server Anchor Points Query Service Index Service System Architecture System Components Object Tags Attached to physical objects and emit the location and state-of-use of the physical objects. Home Node Hosted in the residential home gateways, provide proximity ranging service, and stores objects data. Query Server Hosted in the cloud, maintains persistent connection with home node and provides query interface to personal analytics applications. 25
- 26. Prototype Personal IoT Analytics Application “Quantify the Spatio-Temporal Usage of Personal Object” IoT Analytics G 26
- 27. Things Dashboard Dashboard • Shows realtime usage status (pointer up or down) • Offers search capability 27
- 28. Locate and Query Physical Objects Timeline View • Offers recent spatio-temporal usage information 28
- 29. Realtime Insights on Spatio-Temporal Usage Insight View • Offers aggregated spatio- temporal usage information 29
- 30. Gerd Kortuem and Fahim Kawsar "Market-based User Innovation for the Internet of Things"; Internet of Things 2010 Conference Afra Mashhadi, Fahim Kawsar, and Utku Acer “Human Data Interaction in IoT: The Ownership Aspect;". The IEEE World Forum on Internet of Things 2014 You Own Your Data, You Sell Your Data • Our cloudlet based design scheme coupled with WiFi management frame based data transport offer implicit privacy and data protection as Data remains in the home gateway and this provides users with the control of their own data to do whatever they want to do with them – delete, sell or share. • An advantage of these design schemes is that, it opens up opportunity for wilful monetisation of personal data 30
- 31. People-People Interaction People-Object Interaction People-Content Interaction ”Tiny Habits in the Giant Enterprise: Understanding the Dynamics of a Quantified Workplace”. UbiComp 2015 ”Detecting Human Encounters from WiFi Radio Signals”. MUM 2015
- 33. Active Badge - Xerox | Cambridge U
- 36. Happiness Badge - Hitachi
- 37. Sociometer Badge - MIT
- 38. Spontaneous Interactions Key to Flow of Ideas A third of team performance can be predicted merely by the number of Face to Face exchanges among team members. The “data signature” of natural leaders can be discovered. Daily Productivity and Creativity can be rightly assessed.
- 40. “Only of large companies can make meaningful predictions about their workforces, while can accurately predict business metrics such as budgets, financial results, and expenses” 4% 90% - Bersin Research Employee Survey
- 41. Quantified Self Quantified Team Quantified Enterprise People Analytics Productivity Management Space Management People á n Places 7 Activity Quantified Enterprise Understand and quantify how people interact and work together in the real enterprise for personal, group and larger organisation efficiency.
- 42. • Personal Interaction Reflection • Personal Network Scale and Diversity • Personal Time and Activity Management • Personal Connection Extension For Employees • Quantifying Collaboration • Discover Emerging Leaders • Build High Performance Team • Develop Empathic Relationship For Employers • Predictive Maintenance • Better Space Arrangement & Management • Personalised Space Recommendation • Better Resource Management For Building Managers Implications
- 43. A Network and Small Data Driven Solution Smart Badge Maps and Sensors EF5 Enterprise Applications ôQuantified Enterprise Platform Advanced Models and Algorithms API Real time, network-based indoor localisation 50x reduction in deployment and management cost 30x reduction in energy expenditure of mobile devices
- 44. Radio Signal Capturing Copresence Detection Interaction Inference A network-centric architecture that captures existing radio signals (WiFi probes) from the user’s device. Co-location detection based on similarity of wireless channel propagation characteristics. An empirically defined model grounded upon sociology theories, by leveraging the size and duration of the encounter. Accuracy (Precision) 60%of Encounters Detected 90% Location to Face to Face Interaction
- 45. Behaviour Modelling Extracting high order behavioural traits Location -> Face to Face Interaction Location -> Personality F2F Encounter Diversity, Number, Frequency, regularity and Spatial Behaviour are used to extract Big Five Personality Traits Location -> Happiness Spatial Behaviour and Movement Trajectory are used to estimate Physical Activeness and then map to mental wellbeing (baseline Happiness Index Survey) This has been used to build connectivity graph and show collaboration intensity in the application.
- 47. Self Quantification @ Workspace
- 48. Timeline of Face to Face Interactions
- 49. Realtime Recommendation to New Contacts
- 50. Locating Colleagues and Empty Rooms at Realtime
- 51. Happiness Map of the Workspace
- 52. Playful Visualisation of the Workplace Mood
- 53. Collaboration Uncovered Insights from Quantified Bell Labs (Dublin and Antwerp) Workplaces 3Secrets Revealed Its all about Relationship Key to Engagement is the visualisation of the relationship structure Subtle Hints Users awareness of their collaboration nature is crucial, however presentation needs to subtle but meaningful Recommend Opportunities Users are willing to compromise their privacy when the value is higher. Recommendations of right opportunities are key to create that value 53
- 54. 54 By 2018, two million employees will be required to wear health and fitness tracking devices as a condition of employment. - Gartner’s Prediction
- 57. Designing Experience for Future Conferences 30 Billion Market Size
- 58. Monitoring Children’s Interaction and Detecting Early Signs of Autism
- 59. Monitoring Elderly People’s Interaction, Detecting Early Depression
- 60. Monitoring Depression and Bi-Polar Patients
- 61. People-People Interaction Wireless network is the key fabric for designing connected human experiences People-Object Interaction People-Content Interaction
- 62. Claudio Forlivesi Utku Acer Afra Mashhadi Fahim Kawsar Akhil Mathur Marc Van Den BroeckGeert Vanderhulst Marc Godon Nic Lane Sourav Bhattacharaya Aidan Boran Credit goes to …
- 63. Thank You Fahim Kawsar @raswak eMail: fahim.kawsar@bell-labs.com