Semantic Ubiquitous Services (SUBI)
Timespan: Dec 2009 - Sept 2012
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
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.
- 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.
Researcher Eetu Mäkelä
Professor Eero Hyvönen
Sven Buschbeck, Raphael Troncy, Anthony Jameson, Houda Khouf, Adrian Spirescu, Osma Suominen, Tanja Schneeberger and Eero Hyvönen: Parallel Faceted Browsing
. Proceedings of CHI 2013, Extended Abstracts, Paris, 2013
, Association for Computing Machinery (ACM), 2013. bib pdf
Tuukka Ruotsalo, Krister Haav, Antony Stoyanov, Sylvain Rochee, Elena Fanid, Romina Deliaic, Eetu Mäkelä, Tomi Kauppinen and Eero Hyvönen: SMARTMUSEUM: A Mobile Recommender System for the Web of Data
. Journal of Web Semantics, vol. 20, pp. 50-67, May, 2013. bib link
Semantic and context knowledge have been envisioned as an appropriate solution for addressing the content heterogeneity and information overload in mobile Web information access, but few have explored their full potential inmobile scenarios, where information objects refer to their physical counterparts, and retrieval is context-aware and personalized for users. We present SMARTMUSEUM, a mobile ubiquitous recommender system for the Web of Data, and its application to information needs of tourists in context-aware, on-site access to cultural heritage. The SMARTMUSEUM system utilizes Semantic Web languages as the form of data representation. Ontologies are used to bridge the semantic gap between heterogeneous content descriptions, sensor inputs, and user profiles. The system makes use of an information retrieval framework where in context data and search result clustering are used in recommendation of suitable content for mobileusers. Results from laboratory experiments demonstrate that ontology-based reasoning, query expansion, search result clustering, and context knowledge lead to significant improvement in recommendation performance. The results from field trials show that the usability of the system meets users’ expectations in real-world use. The results indicate that semantic content representation and retrieval can significantly improve the performance of mobile recommender systems in knowledge-rich domains.
Sven Buschbeck, Anthony Jameson, Raphael Troncy, Houda Khrouf, Osma Suominen and Adrian Spirescu: A Demonstrator for Parallel Faceted Browsing
. Proceedings of the IESD Challenge track at the International Workshop on Intelligent Exploration of Semantic Data (IESD 12)
, Galway, Ireland, October, 2012. bib pdf
Eero Hyvönen, Aleksi Lindblad and Eetu Mäkelä: TravelSampo System for Creating Mobile Audio Guide Tours Enriched with Linked Data
. Proceedings of CIDOC 2012 - Enriching Cultural Heritage, Helsinki, Finland
, CIDOC, http://www.cidoc2012.fi/en/cidoc2012/programme, June, 2012. bib pdf
TravelSampo  is a prototype system, by which museums are able to create interactively audio guide tours inside museums and outside in the open air. The system includes a web-based editor by which a curator can describe objects in an exhibition, or in the open air, using a set of shared ontologies published in the National Ontology Service ONKI (http://onki.fi/), and upload related audio descriptions, text, and images. Each exhibit object is given an identifier and a geo-location. When the end-user is near the object, either in a museum or in the open air, information related to the object can be given to her based on the object identifier or GPS location. A major novelty of TravelSampo lies in its ability to associate the object metadata automatically with millions of semantically related pieces of information available though the Linked Data cloud (http://linkedata.org/) and the CultureSampo system (http://www.kulttuurisampo.fi/). For example, a painting can be linked, based on the underlying ontologies and metadata, with the biography of the painter in Wikipedia or in the National Biography, with other paintings of the artist in the collections of other museums, with photos and books about the artist, and so on. This gives the end-user a richer experience than is possible with traditional audio guide systems. For the museums, TravelSampo offers a cost-efficient and dynamic way of creating information rich audio guide programs, and re-using and linking each others collections through linked data, leading to a win-win situation. The paper presents and discusses the underlying ideas of TravelSampo and our experiences in developing the systems especially from the content publishers’, i.e. the museums’ viewpoint.  E. Mäkelä, J. Väätäinen, R. Alitalo, O. Suominen, E. Hyvönen: Discovering Places of Interest through Direct and Indirect Associations in Heterogeneous Sources - The TravelSampo System. Terra Cognita 2011: Foundations, Technologies and Applications of the Geospatial Web, CEUR Workshop Proceedings, Vol-798, 2011. http://ceur-ws.org/Vol-798/proceedings.pdf
Eetu Mäkelä, Eero Hyvönen and Tuukka Ruotsalo: How to deal with massively heterogeneous cultural heritage data – lessons learned in CultureSampo
. Semantic Web – Interoperability, Usability, Applicability, vol. 3, no. 1, January, 2012. bib pdf link
This paper presents the CultureSampo system for publishing heterogeneous linked data as a service. Discussed are the problems of converting legacy data into linked data, as well as the challenge of making the massively heterogeneous yet interlinked cultural heritage content interoperable on a semantic level. Novel user interface concepts for then utilizing the content are also presented. In the approach described, the data is published not only for human use, but also as intelligent services for other computer systems that can then provide interfaces of their own for the linked data. As a concrete use case of using CultureSampo as a service, the BookSampo system for publishing Finnish fiction literature on the semantic web is presented.
Eetu Mäkelä, Aleksi Lindblad, Jari Väätäinen, Rami Alatalo, Osma Suominen and Eero Hyvönen: Discovering Places of Interest through Direct and Indirect Associations in Heterogeneous Sources -- The TravelSampo System
. Terra Cognita 2011: Foundations, Technologies and Applications of the Geospatial Web
, CEUR Workshop Proceedings, Vol-798, 2011. bib pdf
Linked data related to places has a potential to offer a vastly superior collection of information to base search and recommendation functionality on in eTourism visit planning as well as location-aware mobile applications. Particularly, through linked data, besided places interesting in themselves, it is possible to discover places interesting only through association, such as being the venue for a concert by an artist with an interesting genre. However, in order to harness this collective data source, challenges relating to data heterogeneity, quality, scale, and indexing and querying complexity must be resolved. In this paper, the TravelSampo visit planning and mobile application is presented, which tackles these issues. Using the system, queries describing both simple and complex interests can be run over some 17 million places of interest from over 20 vastly heterogeneous sources.
Joonas Laitio: Semantic Web Data Quality Control
. MSc Thesis, Aalto University, School of Electrical Engineering, Degree Programme of Automation and Systems Technology, October, 2011. bib pdf
Data quality is a growing concern on the Semantic Web. The amount of data available is growing faster than ever, and the emphasis thus far has been on creating and interlinking data without much regard to how good the data actually is. The trend is shifting from creating new data to refining what already exists. Data quality is a subjective concept and a formal representation for it is often troublesome. First, we must define what is meant by data quality - what are the different facets of the concept. Second, a way for representing this quality must be found. Third, actual processes to refine data and improve its quality and ways to take data quality into account on the Semantic Web must be developed. This work presents some solutions to the problem. Many ways to annotate quality metadata as RDF are first discovered, along with their pros and cons. A framework for managing RDF-based quality metadata is presented, with a set of tools for specifically managing the quality annotations. Additionally, an automatic annotation system and a schema validation system, within the restraints of the open world assumption, have been designed, implemented and integrated into the framework. The system has been tested using real life datasets with promising first results.
Osma Suominen and Eero Hyvönen: Expressing and Aggregating Rich Event Descriptions
. Proceedings of the 6th Workshop on Scripting and Development on the Semantic Web
, Heraklion, Greece, May, 2010. bib pdf
Publishing information about upcoming events such as concerts and discussion group meetings in a structured format allows the event information to be aggregated, filtered and delivered to potential participants. Making automatic personalized recommendations about events requires structured metadata such as machine-understandable locations and semantic descriptions about the topic and audience of the event. We present a survey of the state of current semantic representation formats for events, including iCalendar and its RDFa and microformat representations, and show that their support for expressing rich structured metadata is limited. We have also tested how well different tools support and understand the formats. Based on the surveys we have implemented a rich event information schema for a health-oriented activity portal and developed an aggregation and validation tool for gathering and processing event information.