Techn. Fakultät Willkommen am Institut für Informatik FAU-Logo

Embedded Classification Software Toolbox (ECST)


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.

With the Embedded Classification Software Toolbox (ECST), 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 accuracy, and finally analyzes the complexity of the trained system.


A file containing pre-computed features can be loaded, or custom features can be computed from raw sensors data.
Multiple algorithms for comparision can be selected in every step of the pattern recognition pipeline.
Example complexity analysis of the Pima Indians Diabetes data set from the UCI Machine Learning Repository.

Source Code

Visit project page at Opens external link in new windowGitHub.

Citation Request

Please cite this publication when using the ECST

Ring, Matthias; Jensen, Ulf; Kugler, Patrick; Eskofier, Bjoern M.

Software-based performance and complexity analysis for the design of embedded classification systems.

In Proceedings of the 21st International Conference of Pattern Recognition (ICPR 2012), Tsukuba, Japan, pp. 2266-2269, 2012.


More information is available in

Jensen, Ulf; Kugler, Patrick; Ring, Matthias; Eskofier, Bjoern M.

Approaching the accuracy–cost conflict in embedded classification system design.

Pattern Analysis and Applications, DOI: 10.1007/s10044-015-0503-1, 2015.