My Unfunded Projects Victor de Boer WAI meeting 21-10-2013 img : Flickr / Kalexanders
Jan 26, 2015
My Unfunded Projects
Victor de BoerWAI meeting 21-10-2013
img: Flickr/Kalexanderson
My Unfunded Projects
1. LaVAIK: Linking and Visualising Aid information Kit
2. ICONS
3. Dance project
1. ICONS: Interaction design for low-literacy communities
• Integrate local community radios and mobile ICT for knowledge sharing
• Better support and integrate local languages in voice-based services– Development of appropriate speech elements (text-
to-speech and Speech recognition)
• Develop a free and open source toolbox for local developers.– Investigate self-sustainability – Develop appropriate business models – In collaboration with local communities.
Feature phones
Icon-based interaction
Icon-based interaction
NCR ATM interface for illiterate 'grammar' - ISOTYPE by Otto Neurath available at http://imaginarymuseum.org/MHV/PZImhv/NeurathPictureLanguage.html
ICONS
What happened?
• FP7-ICT-2011-9 – International partnership building and support to dialogues – April 2012– 10 partners– 104 pages
Participant
Participant organisation name Country
1 (c) GEIE ERCIM France
2 (sci.c.) World Wide Web Foundation Switzerland
3 Telecom
4 Council for Scientific and Industrial Research
5 VU University Amsterdam Neth.
6 Sahel Eco Mali
7 Université Cheikh Anta Diop de Dakar Senegal
8 Di Maquina UK
9 VU University Amsterdam Neth.
10 Nokia Finland
• Did not pass first round– Not detailed enough on
Req elicitation methodology
– Management structure / budget issues
2. LaVAIK: LINKING AND VISUALISING AID INFORMATION KIT
LaVAIK: LINKING AND VISUALISING AID INFORMATION KIT
• International Aid Transparency Initiative (IATI)
• IATI registry (190+ organisations)– http://iatiregistry.org
“IATI is a voluntary, multi-stakeholder initiative that seeks to improve the transparency of aid in order to increase its effectiveness in tackling poverty.”
“IATI Data Registry, the place to find IATI raw data in XML format.”
IATI Stakeholders
• Funders o Where is the money of my organisation spent?o Where do other organisations spend their money?
• Governmentso How much money is spent in my country?o What are the budgets or planned disbursements for my country?
• Publico Where is my tax money going?o What are the organisations doing with my donations?
• Localso What organisations are working in my area?o What projects are currently going on in my area?
Linked Data for IATI Kasper Brandt, MSc Artificial Intelligence
1. A IATI Linked Data model is created based on requirements elicited from interviews with experts.
2. Datasets are linked to the Linked Data model based on IATI experts’ needs.
3. Linked Data applications are created, showing that linking IATI data adds value to the data and is able to fulfill the needs of IATI users.
4. Our approach and requirements are reusable for converting an open dataset to a Linked Data model in general
Linked Data model - Triple store
• Triples loaded into a ClioPatria triple store:o http://semanticweb.cs.vu.nl/iati/o Sparql endpoint– Dereferenceable URIs (!) (
http://purl.org/collections/iati/codelist/Sector/11420)
• Total number of triples: 36,629,017
• Total number of named graphs: 4,790o Largest activities graph is UNOPS containing 1,231,896 triples
RDFLibPython RDF/Turtle
Linking datasets
http://iati2lod.appspot.com
1. We will convert all the IATI datasets available to Linked Data.
2. Convert related open datasets and indicators from UN-Habitat, Worldbank and OECD to Linked Data.
3. Generate contextualized links between produced datasets as well as existing datasets on the Web of Data.
– Link to Landportal– Link to local (Malian) rainfall /
market data
4. Provide a web-based toolkit for multimodal and interactive access to the enriched Linked Aid Data.
UN HAbitat
Worldbank
OECD
Inst. of Development Studies LOD
Citizen Journalism data
Sahel Pluvial data
RadioMarché Linked market data IATI data
Project goals
Web interface
What happened?
• Grand Challenges Round 11– Increasing Interoperability of Social Good Data– 3 pages– 4 partners:
• VU• DANS (Christophe)• Zimmerman & Zimmerman• Akvo
• 2700 proposals!
3. Dance project (EXMO, EM2)
Proposal: choreography assistant tool
SensingRepresentation
+Reasoning
Presentationgeneration
• Motion detection
• Floor sensors
• Move recognition
• Dance movement representation
• Dance choreography representation
• Use of background knowledge
• Pattern detection
• Choreography generation
• Visual presentation
• 3-D animation
• Auditory presentation
Sensingdata
Choreography variation
Presentation
Choreography
Sensing
• Motion capture– Marker-based– Marker-less
• Joint rotations, limb positions etc.– unintuitive
• Backup: Video annotation
img: news.stanford.edu
Representation languages of human movement: Labanotation
Labanotation
LabanXML and Laban Editor
LED Labanotation editor http://donhe.topcities.com/pubs/led.htmlNakamura & Hachimura (2006)
Dance Forms
Benesh
• 7 elementary movements: [plie (bend), etandre (stretch), releve (rise), sauter (jump), glisse (glide), tourne (turn), elancer (dart)]
• Positions: 1st, 2nd, 3rd,.. (left right croise)• Facing position (1…8)• Position in space• Direction of movement (de cote,
dessous, dessus, en avant, en arriere, devant, derriere)
• Combinations (100+) pas-de-chat, pas-de-bourre, piroutte
Cecchetti system
Based on interview with Marije Koning
XML Dance Grammar
Balakrishnan Ramadoss and Kannan Rajkumar. Modeling the Dance Video Semantics using Regular Tree Automata Fundamenta Informaticae 86 (2008) 175–189 175 IOS Press
Representation and Reasoning
• Multi-tiered model– Low-level image features– Atomic movements (Labanotation?)– Compound movements (100+ movements)– Emotional content, Socio-cultural layers etc.
• Machine Learning for classification and pattern detection– Generative module (automatic choreographer)
Presentation
What happened?1st try:
– FP-7 Future and Emerging Technologies Open Scheme (FET Open) • nov 2011
– VUA, UvA (Frank Nack), School of Interactive Arts and Technology – SFU California, Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur , Palindrome, Unige
– Not accepted (High impact?)
2nd try: More healthcare oriented (VU movement science)
3rd try: NWO Creatieve industrie (2012)– VU, UVA, Utwente (Vanessa Evers, Ronald Poppen, Dirk Heylen)– Industry partner…
4th try?
So…
• Not every project gets accepted – Re-use some components for talks
• None of these is really dead– If you’re interested in any one of these, come talk
to me