@inproceedings{f94d2b851cd94da59fc74362d3482dd1,
title = "Scalable and parallel machine learning algorithms for statistical data mining - Practice \& experience",
abstract = "Many scientific datasets (e.g. earth sciences, medical sciences, etc.) increase with respect to their volume or in terms of their dimensions due to the ever increasing quality of measurement devices. This contribution will specifically focus on how these datasets can take advantage of new 'big data' technologies and frameworks that often are based on parallelization methods. Lessons learned with medical and earth science data applications that require parallel clustering and classification techniques such as support vector machines (SVMs) and density-based spatial clustering of applications with noise (DBSCAN) are a substantial part of the contribution. In addition, selected experiences of related 'big data' approaches and concrete mining techniques (e.g. dimensionality reduction, feature selection, and extraction methods) will be addressed too. In order to overcome identified challenges, we outline an architecture framework design that we implement with open available tools in order to enable scalable and parallel machine learning applications in distributed systems.",
author = "M. Riedel and M. Goetz and M. Richerzhagen and P. Glock and C. Bodenstein and Memon, \{A. S.\} and Memon, \{M. S.\}",
note = "Funding Information: This project was supported by grants from the National Institute of Diabetes and Digestive and Kidney Diseases (Mayo Clinic O{\textquoteright}Brien Urology Research Center, DK100227 and DK83007) and made possible by the Rochester Epidemiology Project (AG034676) and the National Center for Advancing Translational Sciences (UL1 TR002377) from the National Institutes of Health, US Public Health Service. Publisher Copyright: {\textcopyright} 2015 MIPRO.; 38th International Convention on Information and Communication Technology, Electronics and Microelectronics, MIPRO 2015 ; Conference date: 25-05-2015 Through 29-05-2015",
year = "2015",
month = jul,
day = "15",
doi = "10.1109/MIPRO.2015.7160265",
language = "English",
series = "2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics, MIPRO 2015 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "204--209",
editor = "Vlado Sruk and Zeljko Butkovic and Boris Vrdoljak and Andrej Sokolic and Stjepan Gros and Petar Biljanovic and Karolj Skala and Slobodan Ribaric and Branko Mikac and Marina Cicin-Sain and Mladen Mauher",
booktitle = "2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics, MIPRO 2015 - Proceedings",
address = "United States",
}