Performance Evaluation of the Nvidia Jetson Nano through a Real-time Machine Learning Application

Patricio Sebastian Valladares Cabezas; Mayerly Tatiana Toscano Revelo; Paulina Adriana Morillo Alcivar; Diego Fernando Vallejo Huanga; Rodrigo Efrain Tufiño Cardenas

doi:10.1007/978-3-030-68017-6_51

Performance Evaluation of the Nvidia Jetson Nano through a Real-time Machine Learning Application

Título traducido de la contribución: Evaluación del rendimiento de Nvidia Jetson Nano a través de una aplicación de aprendizaje automático en tiempo real

Patricio Sebastian Valladares Cabezas, Mayerly Tatiana Toscano Revelo, Paulina Adriana Morillo Alcivar, Diego Fernando Vallejo Huanga, Rodrigo Efrain Tufiño Cardenas

Grupo de Investigación Infraestructura de Datos Espaciales Inteligencia Artificial Geoportales y Computación Aplicada (IDE IA GEO CA)
Universidad Politécnica Salesiana

Producción científica: Contribución a una conferencia › Documento

Resumen

El uso de aplicaciones con Machine Learning (ML) es cada vez más frecuente y su uso diario exige más capacidad de procesamiento de información en tiempo real. Muchos dispositivos despliegan su infraestructura en entornos de Cloud Computing, donde la latencia y las particiones de red son los principales retos que deben afrontar. Sin embargo, en entornos como Dew Computing, estos problemas se mitigan ya que el procesamiento de la información se realiza directamente sobre la fuente de datos, por lo que no es necesaria una conexión a Internet. Este artículo evalúa el desempeño de la plataforma Nvidia Jetson Nano, bajo un enfoque de Dew Computing, con una aplicación que utiliza ML para resolver un problema de identificación y conteo de vehículos terrestres, en tiempo real, en la ciudad de Quito, Ecuador. Se realizaron dos tipos de experimentos, el primer experimento tuvo como objetivo evaluar el uso de los recursos de procesamiento (CPU y GPU), la temperatura del dispositivo, el consumo de energía y la cantidad de RAM utilizada en la tarea de ML. El segundo experimento buscó evaluar la efectividad de la plataforma combinada con OpenDataCam.

Título traducido de la contribución	Evaluación del rendimiento de Nvidia Jetson Nano a través de una aplicación de aprendizaje automático en tiempo real
Idioma original	Inglés estadounidense
DOI	https://doi.org/10.1007/978-3-030-68017-6_51
Estado	Publicada - 26 ene. 2021
Evento	4th International Conference on Intelligent Human Systems Integration: Integrating People and Intelligent Systems (IHSI 2021) - IT Duración: 22 feb. 2021 → 24 feb. 2021

Conferencia

Conferencia	4th International Conference on Intelligent Human Systems Integration: Integrating People and Intelligent Systems (IHSI 2021)
Período	22/02/21 → 24/02/21

Areas de Conocimiento del CACES

116A Computación

Acceder al documento

10.1007/978-3-030-68017-6_51

Citar esto

Valladares Cabezas, P. S., Toscano Revelo, M. T., Morillo Alcivar, P. A., Vallejo Huanga, D. F., & Tufiño Cardenas, R. E. (2021). Performance Evaluation of the Nvidia Jetson Nano through a Real-time Machine Learning Application. Papel presentado en 4th International Conference on Intelligent Human Systems Integration: Integrating People and Intelligent Systems (IHSI 2021). https://doi.org/10.1007/978-3-030-68017-6_51

@conference{50edb48a326445f8bf27907eeff82e80,

title = "Performance Evaluation of the Nvidia Jetson Nano through a Real-time Machine Learning Application",

abstract = "he use of applications with Machine Learning (ML) is increasingly frequent and their daily use demands more capacity for processing information in real-time. Many devices deploy their infrastructure in Cloud Computing environments, where latency and network partitions are the main challenges they must face. However, in environments such as Dew Computing, these problems are mitigated since the information processing is carried out directly on the data source, so an Internet connection is not necessary. This article evaluates the performance of the Nvidia Jetson Nano platform, under a Dew Computing approach, with an application that uses ML to solve a problem of identification and counting of land vehicles, in real-time, in the city of Quito, Ecuador. Two types of experiments were conducted, the first experiment aimed to evaluate the use of processing resources (CPU and GPU), device temperature, power consumption, and the amount of RAM used in the ML task. The second experiment sought to evaluate the effectiveness of the platform combined with OpenDataCam.",

author = "{Valladares Cabezas}, {Patricio Sebastian} and {Toscano Revelo}, {Mayerly Tatiana} and {Morillo Alcivar}, {Paulina Adriana} and {Vallejo Huanga}, {Diego Fernando} and {Tufi{\~n}o Cardenas}, {Rodrigo Efrain}",

year = "2021",

month = jan,

day = "26",

doi = "10.1007/978-3-030-68017-6_51",

language = "English (US)",

note = "4th International Conference on Intelligent Human Systems Integration: Integrating People and Intelligent Systems (IHSI 2021) ; Conference date: 22-02-2021 Through 24-02-2021",

}

Valladares Cabezas, PS, Toscano Revelo, MT, Morillo Alcivar, PA , Vallejo Huanga, DF & Tufiño Cardenas, RE 2021, 'Performance Evaluation of the Nvidia Jetson Nano through a Real-time Machine Learning Application', Papel presentado en 4th International Conference on Intelligent Human Systems Integration: Integrating People and Intelligent Systems (IHSI 2021), 22/02/21 - 24/02/21. https://doi.org/10.1007/978-3-030-68017-6_51

Performance Evaluation of the Nvidia Jetson Nano through a Real-time Machine Learning Application. / Valladares Cabezas, Patricio Sebastian; Toscano Revelo, Mayerly Tatiana; Morillo Alcivar, Paulina Adriana et al.
2021. Papel presentado en 4th International Conference on Intelligent Human Systems Integration: Integrating People and Intelligent Systems (IHSI 2021).

Producción científica: Contribución a una conferencia › Documento

TY - CONF

T1 - Performance Evaluation of the Nvidia Jetson Nano through a Real-time Machine Learning Application

AU - Valladares Cabezas, Patricio Sebastian

AU - Toscano Revelo, Mayerly Tatiana

AU - Morillo Alcivar, Paulina Adriana

AU - Vallejo Huanga, Diego Fernando

AU - Tufiño Cardenas, Rodrigo Efrain

PY - 2021/1/26

Y1 - 2021/1/26

N2 - he use of applications with Machine Learning (ML) is increasingly frequent and their daily use demands more capacity for processing information in real-time. Many devices deploy their infrastructure in Cloud Computing environments, where latency and network partitions are the main challenges they must face. However, in environments such as Dew Computing, these problems are mitigated since the information processing is carried out directly on the data source, so an Internet connection is not necessary. This article evaluates the performance of the Nvidia Jetson Nano platform, under a Dew Computing approach, with an application that uses ML to solve a problem of identification and counting of land vehicles, in real-time, in the city of Quito, Ecuador. Two types of experiments were conducted, the first experiment aimed to evaluate the use of processing resources (CPU and GPU), device temperature, power consumption, and the amount of RAM used in the ML task. The second experiment sought to evaluate the effectiveness of the platform combined with OpenDataCam.

AB - he use of applications with Machine Learning (ML) is increasingly frequent and their daily use demands more capacity for processing information in real-time. Many devices deploy their infrastructure in Cloud Computing environments, where latency and network partitions are the main challenges they must face. However, in environments such as Dew Computing, these problems are mitigated since the information processing is carried out directly on the data source, so an Internet connection is not necessary. This article evaluates the performance of the Nvidia Jetson Nano platform, under a Dew Computing approach, with an application that uses ML to solve a problem of identification and counting of land vehicles, in real-time, in the city of Quito, Ecuador. Two types of experiments were conducted, the first experiment aimed to evaluate the use of processing resources (CPU and GPU), device temperature, power consumption, and the amount of RAM used in the ML task. The second experiment sought to evaluate the effectiveness of the platform combined with OpenDataCam.

U2 - 10.1007/978-3-030-68017-6_51

DO - 10.1007/978-3-030-68017-6_51

M3 - Paper

T2 - 4th International Conference on Intelligent Human Systems Integration: Integrating People and Intelligent Systems (IHSI 2021)

Y2 - 22 February 2021 through 24 February 2021

ER -

Valladares Cabezas PS, Toscano Revelo MT, Morillo Alcivar PA , Vallejo Huanga DF , Tufiño Cardenas RE. Performance Evaluation of the Nvidia Jetson Nano through a Real-time Machine Learning Application. 2021. Papel presentado en 4th International Conference on Intelligent Human Systems Integration: Integrating People and Intelligent Systems (IHSI 2021). doi: 10.1007/978-3-030-68017-6_51

Performance Evaluation of the Nvidia Jetson Nano through a Real-time Machine Learning Application

Resumen

Conferencia

Areas de Conocimiento del CACES

Acceder al documento

Huella

Citar esto