When Service-oriented Computing Meets the IoT: A Use-case in the - - PowerPoint PPT Presentation

▶
when service oriented
SMART_READER_LITE
LIVE PREVIEW

When Service-oriented Computing Meets the IoT: A Use-case in the - - PowerPoint PPT Presentation

Nov 20, 2022 577 likes •974 views

When Service-oriented Computing Meets the IoT: A Use-case in the Context of Urban Mobile Crowdsensing Valrie Issarny, Inria Joint work with G. Bouloukakis, N. Georgantas, F. Sailhan, G. Texier, B. Lefvre & others 1 - 28/11/2019

slide-1
SLIDE 1

When Service-oriented Computing Meets the IoT: A Use-case in the Context of Urban Mobile Crowdsensing

28/11/2019

  • 1

Valérie Issarny, Inria

Joint work with G. Bouloukakis, N. Georgantas, F. Sailhan, G. Texier, B. Lefèvre &

  • thers…
slide-2
SLIDE 2

Agenda

28/11/2019

  • 2
  • 01. The promise of mobile crowdsensing but...
  • 02. System architecture for the urban IOT
  • 02. The challenge of sensor accuracy
  • 03. Crowdsensing & The urban IoT networks
  • 04. About the users participation
  • 05. Conclusion
slide-3
SLIDE 3

01

28/11/2019

  • 3

The promise of mobile crowdsensing... But

slide-4
SLIDE 4

28/11/2019

  • 4

The power of the crowd

slide-5
SLIDE 5

28/11/2019

  • 5

The pollution monitoring use case

Fixed sensing Mobile crowdsensing Social sensing High cost but accurate Many but low accuracy & diverse Qualitative but subjective

slide-6
SLIDE 6

28/11/2019

  • 6

Our initial research question

Is mobile phone sensing an effective solution to the aggregation of urban knowledge?

slide-7
SLIDE 7

28/11/2019

  • 7

Our approach: Learning from an urban-scale experiment

Ambiciti App informing about individual and collective exposure to urban pollution

slide-8
SLIDE 8

28/11/2019

  • 8

The many facets of Ambiciti

ambiciti.io

slide-9
SLIDE 9

28/11/2019

  • 9

The many challenges of Ambiciti

Accuracy of the measurements

Low cost & heterogeneous sensors Context of observations

Leveraging the diverse data sources

Data assimilation Integrating with the urban IoT networks

Gathering measurements from a large crowd

Matching Technological and societal innovations

And many more….

slide-10
SLIDE 10

02

28/11/2019

  • 10

System architecture for the urban IoT

slide-11
SLIDE 11

28/11/2019

  • 11

A SOC-based fixed & mobile IoT

slide-12
SLIDE 12

28/11/2019

  • 12

Overcoming the scale

slide-13
SLIDE 13

28/11/2019

  • 13

Enabling multi-domain/region interactions

slide-14
SLIDE 14

03

28/11/2019

  • 14

The challenge of sensor accuracy

slide-15
SLIDE 15

28/11/2019

  • 15

Inaccuracy as the norm

2 calibrated sensors Non-calibrated sensor

slide-16
SLIDE 16

28/11/2019

  • 16

Assessing the sensors performance

[R. Ventura et al. JASA 142(5), 2017]

slide-17
SLIDE 17

28/11/2019

  • 17

Phone SPL vs Reference SPL

[R. Ventura et al. JASA 142(5), 2017]

slide-18
SLIDE 18

28/11/2019

  • 18

User-initiated calibration

[R. Ventura et al. JASA 142(5), 2017]

slide-19
SLIDE 19

[F. Sailhan, V. Issarny & O Tavares Nascimento, MASS’17]

28/11/2019

  • 19

Automated collaborative calibration

Calibrate Y through collaboration with X as they meet

  • The measurements by Y & calibrated X, at time t, can be related

as: y(t) = B0 + B1x(t)

slide-20
SLIDE 20

[F. Sailhan, V. Issarny & O Tavares Nascimento, MASS’17]

28/11/2019

  • 20

Multi-party regression

slide-21
SLIDE 21

[F. Sailhan, V. Issarny & O Tavares Nascimento, MASS’17]

28/11/2019

  • 21

Robust regression filtering outliers

slide-22
SLIDE 22

[F. Sailhan, V. Issarny & O Tavares Nascimento, MASS’17]

28/11/2019

  • 22

Collaborative calibration

Communication System Service Discovery Calibration Parameters Reachable Sensing Devices Register Unregister Calibration Parameter Estimator Measurements Spatialised Measurements Graph Connectivity Connectivity Graph Calibration parameters Storage Manager Configuring Sensor Manager GPS Microphone

slide-23
SLIDE 23

[F. Sailhan, V. Issarny & O Tavares Nascimento, MASS’17]

28/11/2019

  • 23

Assessing the relevance of a rendez- vous

23 W W Reference W Reference W 5 2 3 32 6 Meeting 76 7 Meeting W W52 25 W W65 67 W56 26 Meeting

slide-24
SLIDE 24

[F. Sailhan, V. Issarny & O Tavares Nascimento, MASS’17]

28/11/2019

  • 24

Evaluation

slide-25
SLIDE 25

[F. Sailhan, V. Issarny & O Tavares Nascimento, MASS’17]

28/11/2019

  • 25

Evaluation

Encouraging results in a controlled environment. Ongoing work focused

  • n use in the wild

Context-aware collaborative sensing

slide-26
SLIDE 26

04

28/11/2019

  • 26

Crowdsensing & The urban IoT networks

slide-27
SLIDE 27

28/11/2019

  • 27

Combining the IoT infrastructure and crowdsensing to extend the WSN lifetime

[G. Texier & V. Issarny, LANMAN’18]

slide-28
SLIDE 28

28/11/2019

  • 28

The WSN

[G. Texier & V. Issarny, LANMAN’18]

27 sensors & 1 sink

slide-29
SLIDE 29

28/11/2019

  • 29

The WSN leveraging mobile sinks

[G. Texier & V. Issarny, LANMAN’18]

SPF: Shortest path tree LB: Load balancing mn5S/N: 5 mobile sinks

Sensor Sink North path South path Sink

slide-30
SLIDE 30

28/11/2019

  • 30

The LP formulation

[G. Texier & V. Issarny, LANMAN’18]

Flow conservation Exit at a sink Energy cost

  • incl. routing
slide-31
SLIDE 31

28/11/2019

  • 31

The network lifetime

[G. Texier & V. Issarny, LANMAN’18]

Sensor Sink North path South path Sink

slide-32
SLIDE 32

28/11/2019

  • 32

Sensor lifetime analysis

[G. Texier & V. Issarny, LANMAN’18]

SPF mn5N

slide-33
SLIDE 33

05

28/11/2019

  • 33

About the users participation

slide-34
SLIDE 34

28/11/2019

  • 34

A look at contributed observations (10 months)

[V. Issarny et al., Middleware’16]

Filtering Observations Known Bias Criteria Value # %

  • 18,047,413

1279.0 Paris Loc accuracy < 100 meters 1,411,174 100.0 Location acc. <30 meters 896,917 63.5 293,253 Noise level <25 & >95 555,377 39.3 260,221 Outdoor Clustering 73,841 5.2 34,351 Speed < 7km/h 62,290 4.4 26,830 Proximity No 36,768 2.6 14,503

slide-35
SLIDE 35

28/11/2019

  • 35

The diverse user perspectives

[B Lefevre & V. Issarny, Smartcomp’18]

slide-36
SLIDE 36

28/11/2019

  • 36

Take away & next step

[B Lefevre & V. Issarny, Smartcomp’18]

User-centered plastic interfaces

Must allow the adaptation of the user interface by and for the user

Effective usage environment & subjective aims Privacy

Guaranteeing privacy remains an open research question

slide-37
SLIDE 37

06

28/11/2019

  • 37

Conclusion

slide-38
SLIDE 38

28/11/2019

  • 38

Back to our initial research question

Is mobile phone sensing an effective solution to the aggregation of urban knowledge? Yes but…

slide-39
SLIDE 39

Thank you!!

28/11/2019

  • 39

To know more valerie-issarny.me project.inria.fr/siliconvalley mimove.inria.fr ambiciti.io