An evolving multivariate time series compression algorithm for IoT applications

The Internet of Things (IoT) is transforming how devices interact and share data, especially in areas like vehicle monitoring. However, transmitting large volumes of real-time data can result in high latency and substantial energy consumption. In this context, Tiny Machine Learning (TinyML) emerges...

Descripción completa

Detalles Bibliográficos
Autor: Costa, Hagi Jakobson Dantas da
Tipo de recurso: tesis de maestría
Estado:Versión publicada
Fecha de publicación:2024
País:Brasil
Institución:Universidade Federal do Rio Grande do Norte (UFRN)
Repositorio:Repositório Institucional da UFRN
Idioma:portugués
OAI Identifier:oai:repositorio.ufrn.br:123456789/62451
Acceso en línea:https://repositorio.ufrn.br/handle/123456789/62451
Access Level:acceso abierto
Palabra clave:Multivariate time series compression
IoT
Online algorithms
Evolving algorithms
TinyML
CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA
Descripción
Sumario:The Internet of Things (IoT) is transforming how devices interact and share data, especially in areas like vehicle monitoring. However, transmitting large volumes of real-time data can result in high latency and substantial energy consumption. In this context, Tiny Machine Learning (TinyML) emerges as a promising solution, enabling the execution of machine-learning models on resource-constrained embedded devices. This paper aims to develop two online multivariate time series compression approaches specifically designed for TinyML, utilizing the Typicality and Eccentricity Data Analytics (TEDA) framework. The proposed approaches are based on data eccentricity and do not require predefined mathematical models or assumptions about data distribution, thereby optimizing compression performance. Both approaches were applied to two case studies: one using the Freematics ONE+ device for vehicle monitoring in an embedded scenario, and another using the OBD-II dataset collected from the Freematics ONE+ in a non-embedded context. The results indicate that the proposed approaches, whether for parallel or sequential compression, present significant improvements in runtime and compression errors. These findings highlight the potential of the approaches to improve the performance of embedded IoT systems, enhancing the efficiency and sustainability of vehicular applications.