dynamic deployment of sensing experiments in the wild u sing smartphones
DESCRIPTION
Dynamic Deployment of Sensing Experiments in the Wild U sing Smartphones. Nicolas Haderer , Christophe Ribeiro , Romain Rouvoy , Lionel Seintuier University Lille 1 – LIFL, Inria Lille – Nord Europe. Agenda. CrowdSensing Problematic & Limitation The APISENSE platform - PowerPoint PPT PresentationTRANSCRIPT
Dynamic Deployment of Sensing Experiments in the Wild Using Smartphones
Nicolas Haderer, Christophe Ribeiro, Romain Rouvoy, Lionel Seintuier
University Lille 1 – LIFL,Inria Lille – Nord Europe
1
2
Agenda
• CrowdSensing• Problematic & Limitation• The APISENSE platform• Preliminary results• Demo
3
Why do we collect data?
• Better understanding of crowd behavior and its environment– E.g., optimizing public transport services
Paths of Chigago TwitteresRoad map of Chicago
4
Mobile|Phone Sensing
• Revolution driven by smart devices to collect of crowd activity traces
4
Increasing popularityApp distribution channels
GPSWIFI/3G/4G
AccelerometerCompas
CameraMicrophone
Rich suites of sensors
5
CrowdSensing
• Capability of lifting a (large) diffuse group of participants to delegate the task of retrieving trustable data from the field
GPSWIFI/3G/4G
AccelerometerCompas
CameraMicrophone
Crowd Sensing
6
CrowdSensing Data collection can take different forms
Participatory sensing involves the user in the sensing task (eg. surveys)
Opportunistic sensing uses mobile sensors carried by the user (eg. smartphones)
And can be effective across multiple scalesIndividual Group Community
7
CrowdSensing : opportunities
• A lot of research interests – Building Noise Map Urban area– Obtain human crowd density – Earthquakes Monitoring – …
8
Agenda
• CrowdSensing• Problematic & Limitation• The APISENSE platform• Preliminary results• Demo
9
Problematic
• Real world deployment is labor-intensive process
Taskdescription
Taskexecution
Workerrecruitment
Taskdeployment
Data uploadWorker rewarding
Crosscutting challenges
Privacy Energy
10
Existing tools
• Funf in a box
11
• Pogo : Middleware for Mobile Phone Sensing
Existing tools
12
Limitation of the SotA
• Multi-tenant architectures are limited– Constrained infrastructures (database, resources)– Tenants side effects (availability)– Legal issues (data ownership)– Security leaks (data isolation)
• Application-specific solutions– Lack of flexibility to be reused in another context
13
• Community sensing problem
Limitation of the SotA
High energy consumption
Data redundancy
14
Challenges summary
Taskdescription
Taskexecution
Workerrecruitment
Taskdeployment
Data uploadWorker rewarding
Crosscutting challenges
Privacy Energy
Softwarechallenges Scalability SecurityFlexibility
Development cost
15
Agenda
• CrowdSensing• Problematic & Limitation• The APISENSE platform• Preliminary results• Demo
16
APISENSE®
• Open crowd-sensing platform– Flexible and customizable architecture– Supporting various research communities– Leveraging the deployment of CrowdSensing tasks
http://www.apisense.fr 17
APISENSE® – The platform
18
Central Node
• A trustable central server– Intermediary between collector node & workers– Guarantees workers anonymity (generated ids)– Checks the task scripts and rewards workers– Deploy and generate sensing node
19
Sensing Node
• A cloud-oriented storage• Support for data authentication + encryption• Configurable infrastructure (SPL + components)
• XML | NoSQL database, processing services, visualization
20
APISENSE Mobile Application
• Mobile application– Downloads & executes scripts (sandbox)– Uploads datasets when plugged– Controls sensor privileges & privacy filters
Time filter Sensors privileges Location filter
21
CrowdSensing Javascript API
22
CrowdSensing Javascript API
23
APISENSE®
24
Agenda
• CrowdSensing• Problematic & Limitation• The APISENSE platform• Preliminary results• Demo
25
Application Example
• Collecting exceptions in the wild (CoffeeScript)
logcat.onLog {filter: [’*:W’,’*:E’]}, (log) -> trace.add message: log.message, time: log.timestamp, application: apps.process(log.pid).applicationName, topTask: apps.topTask().applicationName
Error log Taxonomy
Warning log Taxonomy
26
Application Example
• Assessing Machine Learning Models– User context recognition implementation : ~ 30 lines
…accelerometer.onChange(function(acc) { buffer.push(acc) });// Learning phasedialog.display({ message: "Select movement", spinner: classes },function(pattern){ accelerometer.onChange(function(acc) { buffer.push(acc) }); sleep(‘5s’) model.record(attributes(buffer), pattern); buffer = new Array(); return;});…// Exploitation phasetime.schedule({ period: '5s' }, function() { trace.add({ position: model.evaluate(attributes(buffer)), stats: model.statistics() }); buffer = new Array();} } });
Representative Confusion Matrix
27
Agenda
• CrowdSensing• Problematic & Limitation• The APISENSE platform• Preliminary results• Demo
28
Nicolas HADERERCHRISTOPHE RIBEIRORomain ROUVOYLionel SEINTURIER
Questions ?
http://apisense.fr