Performance Analysis of an Embedded System for Target Detection in Smart Crosswalks using Machine Learning

J. M. Lozano Domínguez, J. M. Corralejo Mora, I. J. Fernández de Viana González, T. J. Mateo Sanguino, M. J. Redondo González

2022

Abstract

Embedded systems with low computing resources for artificial intelligence are being a key piece for the deployment of the Internet of Things in different areas as energy efficiency, agriculture or water monitoring, amid others. This paper carries out a study of the computational performance of a smart road detection and signalling system. To this end, the implementation methodology from Matlab® to C++ of a one-class SVM classifier with two pattern analysis strategies based on RADAR signals and RAW data is described. As a result, we found a balance between AUC, RAM consumption, processing time and power consumption for a Teensy 4.1 microcontroller with STFT and the fitcsvm2 algorithm versus other hardware options such as an I7-3770K processor, Raspberry Pi Zero and Teensy 3.6.

Paper Citation

in Harvard Style

Lozano Domínguez J., Corralejo Mora J., Fernández de Viana González I., Mateo Sanguino T. and Redondo González M. (2022). Performance Analysis of an Embedded System for Target Detection in Smart Crosswalks using Machine Learning. In Proceedings of the 17th International Conference on Software Technologies - Volume 1: ICSOFT, ISBN 978-989-758-588-3, pages 382-389. DOI: 10.5220/0011142700003266

in Bibtex Style

@conference{icsoft22,
author={J. M. Lozano Domínguez and J. M. Corralejo Mora and I. J. Fernández de Viana González and T. J. Mateo Sanguino and M. J. Redondo González},
title={Performance Analysis of an Embedded System for Target Detection in Smart Crosswalks using Machine Learning},
booktitle={Proceedings of the 17th International Conference on Software Technologies - Volume 1: ICSOFT,},
year={2022},
pages={382-389},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011142700003266},
isbn={978-989-758-588-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Software Technologies - Volume 1: ICSOFT,
TI - Performance Analysis of an Embedded System for Target Detection in Smart Crosswalks using Machine Learning
SN - 978-989-758-588-3
AU - Lozano Domínguez J.
AU - Corralejo Mora J.
AU - Fernández de Viana González I.
AU - Mateo Sanguino T.
AU - Redondo González M.
PY - 2022
SP - 382
EP - 389
DO - 10.5220/0011142700003266