TY - GEN
T1 - Low-Cost Field Equipment Design based on High-Performance Heterogeneous Architecture
AU - Auccahuasi, Wilver
AU - Cosme, Miryan
AU - Garcia-Rodriguez, Julio
AU - Yucra-Sotomayor, Daniel
AU - Olaya-Cotera, Sandro
AU - Flores-Castaneda, Rosalynn Ornella
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - At present, high performance equipment is gaining importance due to the computational capabilities it allows to develop, they are present in workstations as well as in personal computers. In field work it is important to analyze large volumes of data, as well as the use of applications that require high computational capacity, which the high performance solutions described above cannot be used, due to the need for energy, which in field work is not always available as energy sources are not always available. In the present work we describe a design of a low cost system to work in the field, based on Nvidia portable architecture, coupled with a parallel processing system based on Neuro Stick 2, for portability is coupled to the system a touch screen, a battery system to power the system and expansion units, as a result of the design we present the results of the operation of the system, The design can be applied and scaled, depending on the needs and works, taking into account that the Linux operating system and the programs to be used must be compatible.
AB - At present, high performance equipment is gaining importance due to the computational capabilities it allows to develop, they are present in workstations as well as in personal computers. In field work it is important to analyze large volumes of data, as well as the use of applications that require high computational capacity, which the high performance solutions described above cannot be used, due to the need for energy, which in field work is not always available as energy sources are not always available. In the present work we describe a design of a low cost system to work in the field, based on Nvidia portable architecture, coupled with a parallel processing system based on Neuro Stick 2, for portability is coupled to the system a touch screen, a battery system to power the system and expansion units, as a result of the design we present the results of the operation of the system, The design can be applied and scaled, depending on the needs and works, taking into account that the Linux operating system and the programs to be used must be compatible.
KW - GPU
KW - HPC
KW - image
KW - processing
KW - video
UR - https://www.scopus.com/pages/publications/105004803813
U2 - 10.1109/ICMLAS64557.2025.10968455
DO - 10.1109/ICMLAS64557.2025.10968455
M3 - Contribución a la conferencia
AN - SCOPUS:105004803813
T3 - 2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings
SP - 1362
EP - 1367
BT - 2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025
Y2 - 10 March 2025 through 12 March 2025
ER -