International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 185 - Issue 19 |
Published: Jun 2023 |
Authors: Umapriya Selvam, P. Muthu Subramanian, A. Rajeswari |
![]() |
Umapriya Selvam, P. Muthu Subramanian, A. Rajeswari . Machine Learning on Standard Embedded Device. International Journal of Computer Applications. 185, 19 (Jun 2023), 8-10. DOI=10.5120/ijca2023922911
@article{ 10.5120/ijca2023922911, author = { Umapriya Selvam,P. Muthu Subramanian,A. Rajeswari }, title = { Machine Learning on Standard Embedded Device }, journal = { International Journal of Computer Applications }, year = { 2023 }, volume = { 185 }, number = { 19 }, pages = { 8-10 }, doi = { 10.5120/ijca2023922911 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2023 %A Umapriya Selvam %A P. Muthu Subramanian %A A. Rajeswari %T Machine Learning on Standard Embedded Device%T %J International Journal of Computer Applications %V 185 %N 19 %P 8-10 %R 10.5120/ijca2023922911 %I Foundation of Computer Science (FCS), NY, USA
Developers of ARM microcontrollers now have access to the first neural network software development tools, making machine learning in embedded systems a possibility. This study examines the application of one such tool, the STM Cube AI, on popular ARM Cortex-M microcontrollers. It evaluates and contrasts its performance with that of two others widely employed supervised machine learning (ML) algorithms, namely Support Vector Machines (SVM) and k-Nearest Neighbors (k-NN). The outcomes of three datasets demonstrate that X-Cube-AI consistently delivers good performance despite the shortcomings of the embedded platform. Popular desktop programs like TensorFlow and Keras are seamlessly incorporated into the workflow.