Please use this identifier to cite or link to this item:
http://www.repositorio.ufop.br/jspui/handle/123456789/15312
Title: | Enhancing performance of Gabriel graph-based classifiers by a hardware co-processor for embedded system applications. |
Authors: | Arias Garcia, Janier Mafra, Augusto Amaral Gade, Liliane dos Reis Coelho, Frederico Gualberto Ferreira Castro, Cristiano Leite de Torres, Luiz Carlos Bambirra Braga, Antônio de Pádua |
Keywords: | Machine learning System on a chip Large margin Latency sensitive IoT |
Issue Date: | 2020 |
Citation: | ARIAS GARCIA, J. et al. Enhancing performance of Gabriel graph-based classifiers by a hardware co-processor for embedded system applications. IEEE Transactions on Industrial Informatics, v. 17, p. 1186-1196, 2021. Disponível em: <https://ieeexplore.ieee.org/document/9072429>. Acesso em: 29 abr. 2022. |
Abstract: | It is well known that there is an increasing interest in edge computing to reduce the distance between cloud and end devices, especially for Machine Learning (ML) methods. However, when related to latency-sensitive applications, little work can be found in ML literature on suitable embedded systems implementations. This paper presents new ways to implement the decision rule of a large margin classifier based on Gabriel graphs as well as an efficient implementation of this on an embedded system. The proposed approach uses the nearest neighbor method as the decision rule, and the implementation starts from an RTL pipeline architecture developed for binary large margin classifiers and proposes the integration in a hardware/software co-design. Results showed that the proposed approach was statistically similar to the classifier and had a speedup factor of up to 8x compared to the classifier executed in software, with performance suitable for ML latency-sensitive applications. |
URI: | http://www.repositorio.ufop.br/jspui/handle/123456789/15312 |
metadata.dc.identifier.uri2: | https://ieeexplore.ieee.org/document/9072429 |
metadata.dc.identifier.doi: | https://doi.org/10.1109/TII.2020.2987329 |
ISSN: | 1941-0050 |
Appears in Collections: | DECSI - Artigos publicados em periódicos |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
ARTIGO_EnhacingPerformanceGabriel.pdf Restricted Access | 2,94 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.