DETECT

Mission statement

The loss of aquatic biodiversity and associated Ecosystem Services is one of the most pressing problems on Earth. Sophisticated biomonitoring programs have been established to understand patterns and identify drivers of biodiversity and ecosystem function loss. In DETECT we use advanced techniques in signal and image processing, computer vision, data mining, and statistics to solve issues related to human error and cost efficiency of taxa identification. Through the interdisciplinary combination of these individual research efforts we aim to renovate a classical and partly outdated process to assess a specimen’s taxonomic identity, and related data acquisition. We aim to use the novel computational advances made during this project to facilitate cost-effective biomonitoring and promote more reliable aquatic ecosystem service management on a global scale. We also aim to make all DETECT data publically available online.

Our students  and postdocs

Jenni Raitoharju, Tampere University of Technology PhD. Former student now post-doc

Johanna Ärje, University of Jyväskylä, PhD. Former student now post doc

Ekaterina Riabchenko, Former post doc at Tampere University of Technology

Senior Lecturer Ville Tirronen, University of Jyväskylä, part time post doc

Our collaborators

Professor Moncef Gabbouj, Tampere University of Technology

Assistant Professor Alekos Iosifidis, at Århus University

Associate Professor Fabio Divino, University of Molise

Associate Professor Kwok-Pui Choi,  National University of Singapore

Program manager Samuli Korpinen, Finnish Environment Institute

Senior Scientist Toke Høye, Århus University

 

DETECT Publications

S. Kiranyaz, T. Ince, A. Iosifidis and M. Gabbouj, “Progressive Operational Perceptrons”, Neurocomputing (Elsevier), vol. 224, pp. 142-154, Feb. 2017. http://dx.doi.org/10.1016/j.neucom.2016.10.044

Ärje, J. (2016). Improving statistical classification methods and ecological status assessment for river macroinvertebrates. University of Jyväskylä, Department of Mathematics and Statistics, Report 156.

Ärje, J.,  Kärkkäinen, S., Meissner, K.,  Iosifidis, A.,  Ince, T., Gabbouj, M.,  Kiranyaz, S.  (2017) The effect of automated taxa identification errors on biological indices, Expert Systems with Applications, Volume 72, 15 April 2017, Pages 108-120, ISSN 0957-4174.https://doi.org/10.1016/j.eswa.2016.12.015

Ärje, J., Divino, F., Choi, K-P, Meissner, K. and S. Kärkkäinen (2016):Understanding the Statistical Properties of the Percent Model Affinity Index Can Improve Biomonitoring Related Decision Making. Stochastic Environmental Research and Risk Assessment 2016; 30 (7): 1981-2008.

DETECT conference papers

E. Riabchenko, K. Meissner, I. Ahmad, A. Iosifidis, V. Tirronen, G. Moncef and S. Kiranyaz, "Learned vs. Engineered Features for Fine-Grained Classification of Aquatic Macroinvertebrates", International Conference on Pattern Recognition (ICPR), Cancun, Mexico, 2016

J. Raitoharju and E. Riabchenko and K. Meissner and I. Ahmad and A. Iosifidis and M. Gabbouj and S. Kiranyaz, "Data Enrichment in Fine-Grained Classification of Aquatic Macroinvertebrates," 2016 ICPR 2nd Workshop on Computer Vision for Analysis of Underwater Imagery (CVAUI), Cancun, 2016, pp. 43-48. doi: 10.1109/CVAUI.2016.020

 

Selected related research predating DETECT

Ärje, J., Kärkkäinen, S., Turpeinen, T. & Meissner, K. (2013). Breaking the curse of dimensionality in QDA models with a novel variant of a Bayes classifier enhances automated taxa identification of freshwater macroinvertebrates. Environmetrics, 24(4), 248-259.

H. Joutsijoki, K. Meissner, M. Gabbouj, S. Kiranyaz, J. Raitoharju, J. Ärje, S. Kärkkäinen, V. Tirronen, T. Turpeinen, M. Juhola, “Evaluating the performance of artificial neural networks for the classification of freshwater benthic macroinvertebrates”, Ecological Informatics, vol. 20, Mar. 2014, pp. 1-12, doi:10.1016/j.ecoinf.2014.01.004.

S. Kiranyaz, T. Ince, J. Pulkkinen, M. Gabbouj, J. Ärje, S. Kärkkäinen, V. Tirronen, M. Juhola, T. Turpeinen, K. Meissner, “Classification and retrieval on macroinvertebrate image databases”, Computers in Biology and Medicine, vol. 41, no. 7, Jul. 2011, pp. 463-472,  doi:10.1016/j.compbiomed.2011.04.008.

 

Consortia conference papers predating DETECT

 

S. Kiranyaz, M. Gabbouj, J. Pulkkinen, T. Ince and K. Meissner (2010). Classification and Retrieval on Macroinvertebrate Image Databases using Evolutionary RBF Neural Networks", Int. Workshop on Advanced Image Technology (IWAIT), Malaysia, Kuala Lumpur.

J. Ärje, S. Kärkkäinen, K. Meissner and T. Turpeinen (2010). Statistical classification and proportion estimation - an application to a macroinvertebrate image database. 2010 IEEE International Workshop on MACHINE LEARNING FOR SIGNAL PROCESSING, Finland, Kittilä.

S. Kiranyaz, M. Gabbouj, J. Pulkkinen, T. Ince and K. Meissner, "Network of evolutionary binary classifiers for classification and retrieval in macroinvertebrate databases," 2010 IEEE International Conference on Image Processing, Hong Kong, 2010, pp. 2257-2260. doi: 10.1109/ICIP.2010.5651161

 

Links to other projects

 

DETECT links to other projects such as:

DNAQUA-net

Published 2017-06-12 at 17:07, updated 2024-03-22 at 9:46