Time filter

Source Type

Sarlin P.,Turku Center for Computer Science

This paper adopts and adapts Kohonen's standard self-organizing map (SOM) for exploratory temporal structure analysis. The self-organizing time map (SOTM) implements SOM-type learning to one-dimensional arrays for individual time units, preserves the orientation with short-term memory and arranges the arrays in an ascending order of time. The two-dimensional representation of the SOTM attempts thus twofold topology preservation, where the horizontal direction preserves time topology and the vertical direction data topology. This enables discovering the occurrence and exploring the properties of temporal structural changes in data. For representing qualities and properties of SOTMs, we adapt measures and visualizations from the standard SOM paradigm, as well as introduce a measure of temporal structural changes. The functioning of the SOTM, and its visualizations and quality and property measures, are illustrated on artificial toy data. The usefulness of the SOTM in a real-world setting is shown on poverty, welfare and development indicators. © 2012 Elsevier B.V. Source

Salomaa A.,Turku Center for Computer Science
International Journal of Foundations of Computer Science

We investigate formal properties, mainly issues connected with propositional logic, of reaction systems introduced by Ehrenfeucht and Rozenberg. We are concerned only with the most simple variant of the systems. Basic properties of propositional formulas are expressed in terms of reaction systems. This leads to NP-completeness (resp. co-NP-completeness) of many problems concerning reaction systems. Among such problems are: (i) deciding whether the function defined by the system is total, (ii) determining the inverse of the function, (iii) deciding whether state sequences always end with a loop. Propositional formulas with monotonic truth-functions yield a particularly simple representation in terms of reaction systems. © 2013 World Scientific Publishing Company. Source

Sarlin P.,Turku Center for Computer Science
Pattern Recognition Letters

A key starting point for financial stability surveillance is understanding past, current and possible future risks and vulnerabilities. Through temporal data and dimensionality reduction, or visual dynamic clustering, this paper aims to present a holistic view of cross-sectional macro-financial patterns over time. The Self-Organizing Time Map (SOTM) is a recent adaptation of the Self-Organizing Map for exploratory temporal structure analysis, which disentangles cross-sectional data structures over time. We apply the SOTM, as well as its combination with classical cluster analysis, in financial stability surveillance. Thus, this paper uses the SOTM for decomposing and identifying temporal structural changes in macro-financial data before, during and after the global financial crisis of 2007-2009. © 2013 Elsevier B.V. All rights reserved. Source

Bjorne J.,Turku Center for Computer Science
BMC bioinformatics

We present a system for extracting biomedical events (detailed descriptions of biomolecular interactions) from research articles, developed for the BioNLP'11 Shared Task. Our goal is to develop a system easily adaptable to different event schemes, following the theme of the BioNLP'11 Shared Task: generalization, the extension of event extraction to varied biomedical domains. Our system extends our BioNLP'09 Shared Task winning Turku Event Extraction System, which uses support vector machines to first detect event-defining words, followed by detection of their relationships. Our current system successfully predicts events for every domain case introduced in the BioNLP'11 Shared Task, being the only system to participate in all eight tasks and all of their subtasks, with best performance in four tasks. Following the Shared Task, we improve the system on the Infectious Diseases task from 42.57% to 53.87% F-score, bringing performance into line with the similar GENIA Event Extraction and Epigenetics and Post-translational Modifications tasks. We evaluate the machine learning performance of the system by calculating learning curves for all tasks, detecting areas where additional annotated data could be used to improve performance. Finally, we evaluate the use of system output on external articles as additional training data in a form of self-training. We show that the updated Turku Event Extraction System can easily be adapted to all presently available event extraction targets, with competitive performance in most tasks. The scope of the performance gains between the 2009 and 2011 BioNLP Shared Tasks indicates event extraction is still a new field requiring more work. We provide several analyses of event extraction methods and performance, highlighting potential future directions for continued development. Source

Salomaa A.,Turku Center for Computer Science
Theoretical Computer Science

The paper investigates formal properties of reaction systems introduced by Ehrenfeucht and Rozenberg. A reaction system defines a function from the set 2S of subsets of a finite set S into 2S itself. We investigate properties of such functions, and characterize situations when the function is total. We also introduce and characterize the property of functional completeness. Function classes defined by different types of reaction systems are compared. Comparisons are carried out also between different methods of generating long sequences and cycles. © 2012 Elsevier B.V. All rights reserved. Source

Discover hidden collaborations