Mobile Data Mashups per applicazioni di Urban Computing Emanuele Della Valle  Irene Celino  . [email_address]   [email_add...
Agenda <ul><li>Introduction </li></ul><ul><ul><li>Cities are alive </li></ul></ul><ul><ul><li>Mobile users’ questions </li...
Cities Are Alive <ul><li>Cities born, grow, evolve like living beings. </li></ul><ul><li>The state of a city changes conti...
Some Mobile Users’ Question <ul><li>“ Is public transportation where I am?”  </li></ul><ul><li>“ Is the event where I am t...
Urban Computing as an Answer to Them GHOSTWAY Event, Vimercate, Milano 27-5-2009  Emanuele Della Valle and Irene Celino [s...
Urban Computing <ul><li>The integration of computing, sensing, and actuation technologies  into everyday urban settings an...
Example of Urban Computing Application GHOSTWAY Event, Vimercate, Milano 27-5-2009  Emanuele Della Valle and Irene Celino ...
Data Availability <ul><li>Some years ago, due to the lack of data, Urban Computing looked like a Sci-Fi idea.  </li></ul><...
Are Data Mashups the Solution? GHOSTWAY Event, Vimercate, Milano 27-5-2009  Emanuele Della Valle and Irene Celino [source:...
Data Mashups Offers Powerful Visualizations GHOSTWAY Event, Vimercate, Milano 27-5-2009  Emanuele Della Valle and Irene Ce...
Data Mashups Offers Simple Programming Abstractions GHOSTWAY Event, Vimercate, Milano 27-5-2009  Emanuele Della Valle and ...
Not Everything Boils Down to Plumbing GHOSTWAY Event, Vimercate, Milano 27-5-2009  Emanuele Della Valle and Irene Celino
Can Citysense Be Implemented with Pipes? Citysense was built to show you where the action is, right now. Using a billion p...
Coping with reasoning heterogeneity <ul><li>precise and consistent   inference  for telling that at a given junction all v...
Coping with defaults heterogeneity 1/2 <ul><li>Open World Assumption vs. Close World Assumption </li></ul><ul><li>While fo...
Coping with defaults heterogeneity 2/2 <ul><li>Unique Name Assumption </li></ul><ul><li>A square with several station for ...
Coping with scale <ul><li>Although we encounter large scale data  which are not manageable , it does not necessary mean th...
Coping with changing data <ul><li>Periodically changing data  change according to a temporal law that can be </li></ul><ul...
Coping with Noisy, uncertain and inconsistent data <ul><li>Traffic  data are a  very good example  of such data.  </li></u...
The LarKC Project GHOSTWAY Event, Vimercate, Milano 27-5-2009  Emanuele Della Valle and Irene Celino The Large Knowledge C...
LarKC at work for Urban Computing 1/2  GHOSTWAY Event, Vimercate, Milano 27-5-2009  Emanuele Della Valle and Irene Celino ...
LarKC at work for Urban Computing 2/2 <ul><li>We are combining  route planning  techniques with </li></ul><ul><ul><li>reas...
Conclusions and Outlooks <ul><li>LarKC aims at becoming an experimentation infrastructures for the development of advance ...
Thank you for paying attention GHOSTWAY Event, Vimercate, Milano 27-5-2009  Emanuele Della Valle and Irene Celino Any Ques...
Mobile Data Mashups  for Urban Computing Applications Emanuele Della Valle  Irene Celino  . [email_address]   [email_addre...
Identifier strategy for Pipeline 2B <ul><li>Strategy based on common sense behavior: </li></ul><ul><ul><li>Detailed graph ...
Towards Urban Baby LarKC Pipeline 3 GHOSTWAY Event, Vimercate, Milano 27-5-2009  Emanuele Della Valle and Irene Celino Urb...
Adding Traffic Predictions <ul><li>Goal: Short and Mid-Term Traffic Flow and Speed Forecast  </li></ul><ul><li>Neural Netw...
Dealing with Streaming Data <ul><li>To deal with streams in the Semantic Web context we defined C-SPARQL an extension of S...
Upcoming SlideShare
Loading in …5
×

Mobile Data Mashups for Urban Computing Applications

979 views
910 views

Published on

Published in: Technology
0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
979
On SlideShare
0
From Embeds
0
Number of Embeds
5
Actions
Shares
0
Downloads
38
Comments
0
Likes
1
Embeds 0
No embeds

No notes for slide
  • Service-Finder
  • Mobile Data Mashups for Urban Computing Applications

    1. 1. Mobile Data Mashups per applicazioni di Urban Computing Emanuele Della Valle Irene Celino . [email_address] [email_address] . http://emanueledellavalle.org http://swa.cefriel.it . Joint work with: Daniele Dell’Aglio, Kono Kim, Zhisheng Huang, Volker Tresp, Werner Hauptmann, and Yi Huang
    2. 2. Agenda <ul><li>Introduction </li></ul><ul><ul><li>Cities are alive </li></ul></ul><ul><ul><li>Mobile users’ questions </li></ul></ul><ul><ul><li>Urban Computing </li></ul></ul><ul><ul><li>Data Mashups </li></ul></ul><ul><li>Are Data Mashups up to address Mobile users’ needs? </li></ul><ul><ul><li>Powerful visualization </li></ul></ul><ul><ul><li>Simple programming abstractions </li></ul></ul><ul><ul><li>Does everything boil down to plumbing? </li></ul></ul><ul><li>Requirements for a Mobile Data Mashup Environment </li></ul><ul><li>LarKC as a backbone for a Mobile Data Mashup Environment </li></ul><ul><ul><li>What’s LarKC? </li></ul></ul><ul><ul><li>Asking LarKC </li></ul></ul><ul><ul><li>Plugging components in LarKC </li></ul></ul><ul><ul><li>Configuring a LarKC pipeline </li></ul></ul><ul><ul><li>Demo of current state of development of Urban Baby LarKC </li></ul></ul><ul><ul><li>What’s next? </li></ul></ul><ul><li>Conclusions and outlooks </li></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino
    3. 3. Cities Are Alive <ul><li>Cities born, grow, evolve like living beings. </li></ul><ul><li>The state of a city changes continuously, influenced by a lot of factors, </li></ul><ul><ul><li>human ones: people moving in the city or extending it </li></ul></ul><ul><ul><li>natural ones: precipitations or climate changes </li></ul></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino [source http://www.citysense.com ]
    4. 4. Some Mobile Users’ Question <ul><li>“ Is public transportation where I am?” </li></ul><ul><li>“ Is the event where I am the one that attract more people right now?” </li></ul><ul><li>“ Where are all my friends meeting?” </li></ul><ul><li>“ Is the traffic moving where I’m going?” </li></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino
    5. 5. Urban Computing as an Answer to Them GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino [source IEEE Pervasive Computing,July-September 2007 (Vol. 6, No. 3) ]
    6. 6. Urban Computing <ul><li>The integration of computing, sensing, and actuation technologies into everyday urban settings and lifestyles. </li></ul>[source IEEE Pervasive Computing,July-September 2007 (Vol. 6, No. 3) ] GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino
    7. 7. Example of Urban Computing Application GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino 5th cycle ASP Multidisciplinary Projects, Torino 24.1.2009
    8. 8. Data Availability <ul><li>Some years ago, due to the lack of data, Urban Computing looked like a Sci-Fi idea. </li></ul><ul><li>Nowadays , a large amount of the required information are available on the Internet at almost no cost, e.g., </li></ul><ul><ul><li>Maps (Google,Yahoo!, Wikimapia, OpenStreetMap ), </li></ul></ul><ul><ul><li>events scheduled (Eventful, Upcoming…), </li></ul></ul><ul><ul><li>voluntarily provided users location (Google Latitude), </li></ul></ul><ul><ul><li>mass presence and movements ( </li></ul></ul><ul><ul><li>multimedia data with information about location (Flickr…) </li></ul></ul><ul><ul><li>relevant places (schools, bus stops, airports...) </li></ul></ul><ul><ul><li>traffic information (accidents, problems of public transportation...) </li></ul></ul><ul><ul><li>city life (job ads, pollution, health care...) </li></ul></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino
    9. 9. Are Data Mashups the Solution? GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino [source: http://www-01.ibm.com/software/lotus/products/mashups/ ] IBM Lotus Mashups [source: http://editor.googlemashups.com ] [source: http://pipes.yahoo.com/pipes/ ] [source: http://www.popfly.com/ ] [source: http://openkapow.com/ ]
    10. 10. Data Mashups Offers Powerful Visualizations GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino Google Charts API http://code.google.com/apis/chart/ http://maps.google.it/ http://maps.yahoo.com/ MIT Simile Timeline & Timeplot http://simile.mit.edu/timeline/ http://simile.mit.edu/timeplot/
    11. 11. Data Mashups Offers Simple Programming Abstractions GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino
    12. 12. Not Everything Boils Down to Plumbing GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino
    13. 13. Can Citysense Be Implemented with Pipes? Citysense was built to show you where the action is, right now. Using a billion points of GPS and WiFi positioning data from the last few years – plus real-time feeds – Citysense sees S.F. from above and puts the top live hotspots in your hand. You don't even need to sign up, just go to citysense.com on your BlackBerry, download, and open. GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino <ul><li>Live overall activity & top hotspots First of all see if it's a good night to go out. The city is 21% busier than normal for right now? Let's go. But where to? Check out the top hotspots in real-time and head out. </li></ul><ul><li>What's at hotspot #1? Click over to Yelp or Google and find out what's going on at the #1 hotspot: Bars? Clubs? Restaurants? Then check out what's at #2 </li></ul><ul><li>Show me where the unusually high activity is Even if you're a local, Citysense can give you the live details you need. When the Mission or Soma is busier than normal – you'll know immediately. </li></ul><ul><li>Find out where everyone is going After dinner, drinks or a great night at a club, do you ever wonder where the afterparty is? Just press the &quot;Locate Me&quot; icon and see the top 5 places people go to from where you are now. </li></ul>[Source: http://www.citysense.com/moreinfo.php ]
    14. 14. Coping with reasoning heterogeneity <ul><li>precise and consistent inference for telling that at a given junction all vehicles, but public transportation ones, must go straight </li></ul><ul><ul><li>approximate reasoning when calculating the probability of a traffic jam given the current traffic conditions and the past history. </li></ul></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino It means the systems allow for multiple reasoning paradigms ; e.g. [ source http://senseable.mit.edu/ ]
    15. 15. Coping with defaults heterogeneity 1/2 <ul><li>Open World Assumption vs. Close World Assumption </li></ul><ul><li>While for the an entire city we cannot assume complete knowledge, for a time table of a bus station we can </li></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino [source: http://gizmodo.com/photogallery/trafficsky/1003143552 ]
    16. 16. Coping with defaults heterogeneity 2/2 <ul><li>Unique Name Assumption </li></ul><ul><li>A square with several station for buses and subway can be considered a unique point for multimodal travel planning, but not when the problem is giving direction in that square to a pedestrian </li></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino 1 2 29 30 L3 L3
    17. 17. Coping with scale <ul><li>Although we encounter large scale data which are not manageable , it does not necessary mean that we have to deal with all of the data simultaneously. </li></ul><ul><li>Usually, only very limited amount data are relevant for a single query/processing at a specific application. </li></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino [source: http://gizmodo.com/photogallery/trafficsky/1003143552 ]
    18. 18. Coping with changing data <ul><li>Periodically changing data change according to a temporal law that can be </li></ul><ul><ul><li>Pure periodic law , e.g. every night at 10pm Milano overpasses close. </li></ul></ul><ul><ul><li>Probabilistic law , e.g. traffic jam appear in the west side of Milano due to bad weather or when San Siro stadium hosts a soccer match. </li></ul></ul><ul><li>Event driven changing data are updated as a consequence of some external event. They can be further characterized by the mean time between changes : </li></ul><ul><ul><li>Slow , e.g. roads closed for scheduled works </li></ul></ul><ul><ul><li>Medium , e.g. roads closed for accidents or congestion due to traffic </li></ul></ul><ul><ul><li>Fast , e.g. the intensity of traffic for each street in a city </li></ul></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino
    19. 19. Coping with Noisy, uncertain and inconsistent data <ul><li>Traffic data are a very good example of such data. </li></ul><ul><li>Different sensors observing the same road area give apparently inconsistent information . </li></ul><ul><ul><li>a traffic camera may say that the road is empty </li></ul></ul><ul><ul><li>whereas an inductive loop traffic detector may tell 100 vehicles went over it </li></ul></ul><ul><ul><li>The two information may be coherent if one consider that a traffic camera transmits an image per second with a delay of 15-30 seconds, whereas a traffic detector tells the number of vehicles that went over it in 5 minutes and the information may arrive 5-10 minutes later. </li></ul></ul><ul><li>Moreover, a single data coming from a sensor in a given moment may have no certain meaning . </li></ul><ul><ul><li>an inductive loop traffic detector, it tells you 0 car went over </li></ul></ul><ul><ul><ul><li>Is the road empty ? </li></ul></ul></ul><ul><ul><ul><li>Is the traffic completely stuck ? </li></ul></ul></ul><ul><ul><ul><li>Did somebody park the car above the sensor ? </li></ul></ul></ul><ul><ul><ul><li>Is the sensor broken ? </li></ul></ul></ul><ul><ul><li>Combining multiple information from multiple sensors in a given time window can be the only reasonable way to reduce the uncertainty. </li></ul></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino
    20. 20. The LarKC Project GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino The Large Knowledge Collider a platform for infinitely scalable reasoning on the data-web Pipeline
    21. 21. LarKC at work for Urban Computing 1/2 GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino The Large Knowledge Collider project aims to develop a platform for massive distributed incomplete reasoning Traffic Monuments We are combining route planning techniques with reasoning on symbolic knowledge and traffic prediction produced by recurrent neural networks and continuous estimation of residual road capacity by real time analysis of data streams Inductive Loop http://www.larkc.eu PROBLEM : Which Milano monuments can I quickly visit from here?
    22. 22. LarKC at work for Urban Computing 2/2 <ul><li>We are combining route planning techniques with </li></ul><ul><ul><li>reasoning on symbolic knowledge, </li></ul></ul><ul><ul><li>traffic prediction produced by recurrent neural networks, and </li></ul></ul><ul><ul><li>continuous estimation of residual road capacity by real time analysis of data streams </li></ul></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino You are here
    23. 23. Conclusions and Outlooks <ul><li>LarKC aims at becoming an experimentation infrastructures for the development of advance semantic technologies. </li></ul><ul><li>The public launch of the first open source release of the platform will take place in June 2009 </li></ul><ul><li>We are developing our Urban Computing application as a showcase of the potentiality of the LarKC platform </li></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino The Large Knowledge Collider a platform for massive distributed incomplete reasoning http://www.larkc.eu
    24. 24. Thank you for paying attention GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino Any Questions?
    25. 25. Mobile Data Mashups for Urban Computing Applications Emanuele Della Valle Irene Celino . [email_address] [email_address] . http://emanueledellavalle.org http://swa.cefriel.it . Joint work with: Irene Celino, Daniele Dell’Aglio, Kono Kim, Zhisheng Huang, Volker Tresp, Werner Hauptmann, and Yi Huang
    26. 26. Identifier strategy for Pipeline 2B <ul><li>Strategy based on common sense behavior: </li></ul><ul><ul><li>Detailed graph around starting and destination point (circles with center in the points and radius of 250 m) </li></ul></ul><ul><ul><li>Main roads of the city </li></ul></ul><ul><li>Implemented in MixedStrategyIdentifier </li></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino
    27. 27. Towards Urban Baby LarKC Pipeline 3 GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino Urban City Decider SPARQL Result SPARQL Query Local Plug-in Manager SPARQL to GeoQuery Transformer Plug-in API Local Plug-in Manager SPARQL to GeoQuery Transformer Plug-in API Local Plug-in Manager Geo Location Identifier Plug-in API Local Plug-in Manager Geo Location Identifier Plug-in API Local Plug-in Manager Growing Data Set Selector Plug-in API Local Plug-in Manager PathFinding Reasoner Plug-in API Local Plug-in Manager SPARQL Endpoint Identifier Plug-in API
    28. 28. Adding Traffic Predictions <ul><li>Goal: Short and Mid-Term Traffic Flow and Speed Forecast </li></ul><ul><li>Neural Network Architecture: </li></ul><ul><ul><li>We use a time-delay recurrent neural network to forecast the traffic flow and speed </li></ul></ul><ul><ul><li>The neural network constructs a minimal set of indicators containing the traffic structure. </li></ul></ul><ul><li>Proceeding: </li></ul><ul><ul><li>Data: traffic data (flow and speed) and external inputs (e.g. temperature, holydays) </li></ul></ul><ul><ul><li>Perform feasibility study to work out specific (prototype) neural network forecast models </li></ul></ul><ul><ul><li>Develop demonstrator for traffic flow and speed forecasting based on prototype </li></ul></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino B 1 calendar input t , #24 external input t , #4 A B 2 B 3 calendar input t+1 , #24 external input t+1 , #4 hidden, #8 C 1 traffic t , # 32 0-8h hidden, #8 C 2 traffic t , # 32 8-16h hidden, #8 C 3 traffic t , # 32 16-24h hidden, #8 traffic t+1 , # 32 0-8h C 1 hidden, #8 traffic t+1 , # 32 8-16h C 2 hidden, #8 traffic t+1 , # 32 16-24h C 3 previous day next day A A A A B 1 B 2 B 3
    29. 29. Dealing with Streaming Data <ul><li>To deal with streams in the Semantic Web context we defined C-SPARQL an extension of SPARQL whose distinguishing feature is the support of continuous queries, i.e. queries registered over RDF data streams and then continuously executed. </li></ul><ul><li>An example of C-SPARQL query </li></ul><ul><ul><li>REGISTER STREAM CarsEnteringCityCenterPerDistrict </li></ul></ul><ul><ul><li>COMPUTED EVERY 5 MIN AS </li></ul></ul><ul><ul><li>PREFIX c: <http :// linkedurbandata . org/ city #> </li></ul></ul><ul><ul><li>PREFIX t: <http :// linkedurbandata . org/ traffic #> </li></ul></ul><ul><ul><li>CONSTRUCT {? district t:has - entering - cars ? passages } </li></ul></ul><ul><ul><li>FROM STREAM <http :// stream . org/ milantollgates .trdf > </li></ul></ul><ul><ul><li>[ RANGE 30 MIN STEP 5 MIN ] </li></ul></ul><ul><ul><li>WHERE { ? tollgate t: registers ? car . </li></ul></ul><ul><ul><li>? district c: contains ? street . </li></ul></ul><ul><ul><li>? tollgate c: placedIn ? street . } </li></ul></ul><ul><ul><li>AGGREGATE {(? passages , COUNT , {? district })} </li></ul></ul>GHOSTWAY Event, Vimercate, Milano 27-5-2009 Emanuele Della Valle and Irene Celino

    ×