Sunday, October 28, 2012

Intelligent Data Analysis 2012

The Eleventh International Symposium on Intelligent Data Analysis (IDA 2012) was held between 25th and 27th October, 2012 in Helsinki, Finland. Jaakko Hollmén (Aalto University, Finland) served as the General Chair and Frank Klawonn (Ostfalia University of Applied Sciences, Germany) and Allan Tucker (Brunel University, UK) as the Program Chairs. The IDA conference series is closely associated with data mining and machine learning research, with a special emphasis on novel developments in methodology or in analysis of new kinds of data sets.
At the welcome reception Timo Cantell welcomed the participants on behalf of City of Helsinki. Cantell is responsible for the Urban Research Unit at City of Helsinki. The reception was held in the Bock House that is next to the historically important senate square, surrounded by Helsinki Cathedral, Finnish government building, and main building of University of Helsinki. In his opening talk, Cantell described how the city has been active in building Helsinki Region Infoshare. This open data project aims to make regional information quickly and easily accessible. The data may be used freely at no cost, for instance, by citizens, businesses, universities, or municipal administration.
Eric Malmi presented our poster and paper "Identifying Anomalous Social Contexts from Mobile Proximity Data Using Binomial Mixture Models" with Juha Raitio, Oskar Kohonen, Krista Lagus and Timo Honkela as the co-authors. Mobile proximity information provides a rich and detailed view into the social interactions of mobile phone users. In this study, we applied a statistical anomaly detection method based on multivariate binomial mixture models to mobile proximity data from 106 users.
In this single track conference, organized in the famous Finland Hall, more than 30 papers were presented during three days. The invited talks were given by Arno Siebes on "Queries for Data Analysis", Paola Sebastiani on "Intelligent data analysis of human genetic data", and Gavin Cawley on "Over-fitting in Model Selection and Its Avoidance".
Prof. Hannu Toivonen's group at University of Helsinki has conducted research on data musicalization. The paper "Sleep Musicalization: Automatic Music Composition from Sleep Measurements" by Aurora Tulilaulu, Joonas Paalasmaa, Mikko Waris and Hannu Toivonen. Examples of composed music can be found at A closely related paper in the conference is "Analysis of Noisy Biosignals for Musical Performance" by Joonas Paalasmaa, David J. Murphy and Ove Holmqvist. The sleep analysis is based on Beddit sleep measurement device, which measures sleep with a thin sensor installed under the mattress.
Conference dinner was served in restaurant Töölönranta, next to the National Opera. Jaakko Hollmén thanked warmly all invited speakers, presenters and local organizers who had ensured the success of the event.

No comments: