Software-based Performance and Complexity Analysis for the Design of Embedded Classification Systems

Beitrag bei einer Tagung
(Konferenzbeitrag)


Details zur Publikation

Autor(en): Ring M, Jensen U, Kugler P, Eskofier B
Herausgeber: IEEE
Jahr der Veröffentlichung: 2012
Tagungsband: Proceedings of the 2012 21st International Conference on Pattern Recognition (ICPR)
Seitenbereich: 2266-2269
Sprache: Englisch


Abstract


Embedded microcontrollers are employed in an increasing number of applications as a target for the implementation of classification systems. This is true for example for the fields of sports, automotive and medical engineering. However, important challenges arise when implementing classification systems on embedded microcontrollers, which is mainly due to limited hardware resources. In this paper, we present a solution to the two main challenges, namely obtaining a classification system with low computational complexity and at the same time high classification accuracy. For the first challenge, we propose complexity measures on the mathematical operation and parameter level, because the abstraction level of the commonly used Landau notation is too high in the context of embedded system implementation. For the second challenge, we present a software toolbox that trains different classification systems, compares their classification rate, and finally analyzes the complexity of the trained system. To give an impression of the importance of such complexity measures when dealing with limited hardware resources, we present the example analysis of the popular Pima Indians Diabetes data set, where considerable complexity differences between classification systems were revealed.



FAU-Autoren / FAU-Herausgeber

Eskofier, Björn Prof. Dr.
Stiftungs-Juniorprofessur für Sportinformatik (Digital Sports)
Jensen, Ulf
Lehrstuhl für Informatik 5 (Mustererkennung)
Kugler, Patrick
Lehrstuhl für Informatik 5 (Mustererkennung)
Ring, Matthias
Lehrstuhl für Informatik 5 (Mustererkennung)


Zitierweisen

APA:
Ring, M., Jensen, U., Kugler, P., & Eskofier, B. (2012). Software-based Performance and Complexity Analysis for the Design of Embedded Classification Systems. In IEEE (Eds.), Proceedings of the 2012 21st International Conference on Pattern Recognition (ICPR) (pp. 2266-2269). Tsukuba, JP.

MLA:
Ring, Matthias, et al. "Software-based Performance and Complexity Analysis for the Design of Embedded Classification Systems." Proceedings of the 21st International Conference on Pattern Recognition (ICPR 2012), Tsukuba Ed. IEEE, 2012. 2266-2269.

BibTeX: 

Zuletzt aktualisiert 2018-08-08 um 18:55