Semantic Ubiquitous Services (SUBI)

Timespan: Dec 2009 - Sept 2012

Project Description

The general research goal of the SUBI project is to support people in real-world tasks at each stage from 1) planning agendas through 2) mobile use on the road to 3) reminiscing about the experience afterwards. Our primary focus is on culture: 1) selecting and attending cultural events such as exhibitions and musical performances as well as 2) selecting and visiting points of interest such as statues, historic sites and museums. However, to widen the scope acute healthcare as well as longer term health promotion agendas are also considered.

The project aims at immediate real world relevance by working with actual stakeholder data and prototyping the system in real world scenarios. A major showcase of the project results will be Turku -- European Capital of Culture 2011. Other material comes from some 30 content producers, including museums, public libraries, event information aggregators, healthcare officials, city officials and copyleft content providers. At the start of the project, this knowledge base already contains some 85 million entities and 700 million triples of information. Of these, some 20 million entities have coordinate information.

The major components of the system visible to the user are as follows:

A web interface for searching for interesting events and places of interest. This will be used both in specifying event/POI watches as well as trip planning.
A mobile web interface to be used on the road that highlights nearby events and places of interest according to trip planning and interest profile
A web interface for reminiscing about and sharing the trip afterwards

The project bases partly on the results of the National Semantic Web Ontology Project in Finland (FinnONTO) and the EU FP7 project SmartMuseum. Particularly, the technical solution bases on the Semantic Web 2.0 portal CultureSampo.

Research Questions

Using knowledge from the Semantic Web to support real-life tasks
Discovering the interesting relations between Semantic Web content and places and events
The usefulness and particular questions of integrating to each stage of the tasks
Bettering state of the art in event watches by making use of semantic information
Semantic integration of large geospatial datasets
Combining statistical profile information with formal intent-based recommendation, and migrating information between the two (I'm going to Turku next weekend, give me an interesting agenda vs. I'm interested in all death metal concerts taking place at a reasonable distance from my living place
Intent-based search of events and places of interest
Generating optimal search constraints by matching richly semantically annotated intentions to richly annotated yet heterogeneous semantic data
Mapping out and analyzing the relations between different kinds of profile information: interests, goals, contextual constraints, abilities/disabilities and social environment
Content-spanning collaborative filtering (from library loan information to event recommendations)
Serendipidously expanding a user's field of interest using social and interest profiles
Data-mining algorithms for migrating information from visit logs to semantic profiles
Information extraction algorithms for discovering formal semantic annotations from event and POI text
Presentation functionality ("Give me a presentation on everything related to Akseli Gallen-Kallela")
Dynamic real-world routing based on contextual and interest information
Content recommendation between portals

Partnering Organizations and Funding

The consortium behind the project includes 18 public organizations and companies funding the research. The participants represent a wide area of functions of the society including museums, libraries, business, health organizations, government and media. The main funding organization is the Finnish Funding Agency for Tecnology and Innovation Tekes where the projects is part of the Tekes Ubicom programme.

Contact Persons

Researcher Eetu Mäkelä
Professor Eero Hyvönen

Publications

2011

A. Thalhammer, T. Ermilov, K. Nyberg, A Santoso and J. Domingue: MovieGoer - Semantic Social Recommendations and Personalized Location-based Offers. The 10th International Semantic Web Conference (ISWC 2011), poster papers, Bonn, Germany, Oct, 2011. bib pdf