Frontier Prize

This Year's Frontier Prize

Winner of the IDA 2013 Frontier Prize is "On the Importance of Nonlinear Modeling in Computer Performance Prediction" by Joshua Garland and Elizabeth Bradley



Computers are nonlinear dynamical systems that exhibit complex and sometimes even chaotic behavior. The low-level performance models used in the computer systems community, however, are linear. This paper is an exploration of that disconnect: when linear models are adequate for predicting computer performance and when they are not. Specifically, we build linear and nonlinear models of the processor load of an Intel i7-based computer as it executes a range of different programs.We then use those models to predict the processor loads forward in time and compare those forecasts to the true continuations of the time series.


The paper and the poster presentation by Joshua Garland and Elizabeth Bradley present the most surprising results through non-linear dynamical modeling of computer performance. It demonstrates that non-linear models are superior to the standard approach to predict computer performance based on linear models. In addition, the poster presentation illustrated that a computer crash can actually change the dynamics of the computer. These intriguing results have a high potential to help improving computer performance by better balancing the workload for multi-core processors.

--- Jaakko Hollmén and Frank Klawonn (Frontier Prize Chairs, IDA 2013)


The IDA Frontier Prize will be awarded to the most novel and visionary contribution. All submissions are considered for this award. The winner is selected by the Frontier Prize Chairs based on the contributions in the paper and the presentation of the work during the IDA 2013 symposium.

The Frontier Prize paper must present novel and surprising approaches to intelligent data analysis. The award consists of a plaque and a prize of 1000 Euros.

We thankfully acknowledge the support from KNIME for the Frontier Prize for IDA 2013.



FRONTIER PRIZE 2012 (Sponsored by KNIME)

The winner of the IDA Frontier Prize 2012 was Sleep Musicalization: Automatic Music Composition from Sleep Measurements by Aurora Tulilaulu, Joonas Paalasmaa, Mikko Waris, and Hannu Toivonen. Sleep Logo

Abstract:We introduce data musicalization as a novel approach to aid analysis and understanding of sleep measurement data. Data musicalization is the process of automatically composing novel music, with given data used to guide the process. We present Sleep Musicalization, a methodology that reads a signal from state-of-the-art mattress sensor, uses highly non-trivial data analysis methods to measure sleep from the signal, and then composes music from the measurements. As a result, Sleep Musicalization produces music that reflects the user’s sleep during a night and complements visualizations of sleep measurements. The ultimate goal is to help users improve their sleep and well-being. For practical use and later evaluation of the methodology, we have built a public web service at for users of the
sleep sensors.

Justification: The paper by Tulilaulu, Paalasmaa, Waris, and Toivonen was the most surprising paper in this year's meeting. It epitomizes the goals of the IDA Frontier Prize by presenting creative preliminary work on a unusual and innovative application. Representing data in the form of music has potential for a lot of interesting future research. --- Liz Bradley & Joao Gama (Frontier Prize Chairs, IDA 2012)

Ericsson Logo

FRONTIER PRIZE 2011 (Sponsored by Ericsson)

The winner of the IDA Frontier Prize 2011 was Integrating Marine Species Biomass Data by Modelling Functional Knowledge by Allan Tucker and Daniel Duplisea.


Abstract: Ecosystems and their underlying foodwebs are complex. There are many pontential functions that play key roles in the delicate balance of these systems. In this paper, we explore methods for identifying species that exhibit similar functional relationships between them using fish survey data from oceans in three different geographical regions. We exploit these functionally equivalent species to integrate the datasets into a single functional model and show that the quality of prediction is improved and the identified species make ecological sense. Of course, the approach is not only limited to fish survey data. In fact, it can be applied to any domain where multiple studies are recorded of comparable systems that can exhibit similar functional relationships.

Justification: The paper by Allan Tucker and Daniel Duplisea on integration of marine species data perfectly fits the scope of the IDA Frontier Award - it presented emerging work on integration of data from different domains (here oceans) - an important direction of future data analysis - combined with sophisticated data analysis techniques. --- Niall Adams & Michael Berthold (Frontier Prize Chairs, IDA 2011)