Improved design for hardware implementation of graph-based large margin classifiers for embedded edge computing

Descrição

Tipo

Artigo de periódico

Título alternativo

Primeiro orientador

Membros da banca

Resumo

The number of connected embedded edge computing Internet of Things (IoT) devices has been increasing over the years, contributing to the significant growth of available data in different scenarios. Thereby, machine learning algorithms arise to enable task automation and process optimization based on those data. However, due to some learning methods’ computational complexity implementing geometric classifiers, it is a challenge to map these on embedded systems or devices with limited resources in size, processing, memory, and power, to accomplish the desired requirements. This hampers the applicability of these methods to complex industrial embedded edge applications. This work evaluates strategies to reduce classifiers’ implementation costs based on the CHIP-clas model, independent of hyperparameter tuning and optimization algorithms. The proposal aims to evaluate the tradeoff between numerical precision and model performance and analyze the hardware implementations of a distance-based classifier. Two 16-b floating-point formats were compared to the 32-b floating-point precision implementation. Also, a new hardware architecture was developed and then compared to the state-of-the-art reference. The results indicate that the model is robust to low precision computation, providing statistically equivalent results compared to the baseline model, also pointing out statistically equivalent performance and a global speed-up factor of approx 4.39 in processing time.

Abstract

Assunto

Internet das coisas

Palavras-chave

Hardware , Optimization , Embedded systems , Computational modeling , Numerical models , Internet of Things , Field programmable gate arrays, Classifiers , edge computing , embedded system , FPGA , Gabriel graph , hardware design of neural networks , Internet of Things (IoT) , large margin , latency-sensitive applications , system-on-a-chip, Edge Computing , Hardware Implementation , Classifier Implementation , Limited Resources , Learning Algorithms , Internet Of Things , Internet Of Things Devices , Hardware Architecture , Training Set , Computational Cost , Support Vector Machine , Distance Matrix , Power Consumption , Parallelization , System Architecture , Resource Consumption , Samples In Order , Time Slot , Distance Calculation , Mahalanobis Distance , Clock Cycles , Hardware Accelerators , ARM Processor , Offline Learning , Numerical Accuracy , Impact Of Reduction , Single Precision , Hardware Resources , Support Vector Machine Training , Scalable

Citação

Curso

Endereço externo

https://ieeexplore.ieee.org/document/9805692

Avaliação

Revisão

Suplementado Por

Referenciado Por