Human Activity Recognition: A Dynamic Inductive Bias Selection Perspective

In this article, we study activity recognition in the context of sensor-rich environments. In these environments, many different constraints arise at various levels during the data generation process, such as the intrinsic characteristics of the sensing devices, their energy and computational constr...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Massinissa Hamidi, Aomar Osmani
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	human activity recognition inductive bias meta-learning hyperparameter optimization sensor-rich environments sensor characteristics Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/4b5c84aed66443ad8494dd5dfe04e341
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4b5c84aed66443ad8494dd5dfe04e341
record_format	dspace
spelling	oai:doaj.org-article:4b5c84aed66443ad8494dd5dfe04e3412021-11-11T19:14:06ZHuman Activity Recognition: A Dynamic Inductive Bias Selection Perspective10.3390/s212172781424-8220https://doaj.org/article/4b5c84aed66443ad8494dd5dfe04e3412021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7278https://doaj.org/toc/1424-8220In this article, we study activity recognition in the context of sensor-rich environments. In these environments, many different constraints arise at various levels during the data generation process, such as the intrinsic characteristics of the sensing devices, their energy and computational constraints, and their collective (collaborative) dimension. These constraints have a fundamental impact on the final activity recognition models as the quality of the data, its availability, and its reliability, among other things, are not ensured during model deployment in real-world configurations. Current approaches for activity recognition rely on the activity recognition chain which defines several steps that the sensed data undergo: This is an inductive process that involves exploring a hypothesis space to find a theory able to explain the observations. For activity recognition to be effective and robust, this inductive process must consider the constraints at all levels and model them explicitly. Whether it is a bias related to sensor measurement, transmission protocol, sensor deployment topology, heterogeneity, dynamicity, or stochastic effects, it is essential to understand their substantial impact on the quality of the data and ultimately on activity recognition models. This study highlights the need to exhibit the different types of biases arising in real situations so that machine learning models, e.g., can adapt to the dynamicity of these environments, resist sensor failures, and follow the evolution of the sensors’ topology. We propose a metamodeling approach in which these biases are specified as hyperparameters that can control the structure of the activity recognition models. Via these hyperparameters, it becomes easier to optimize the inductive processes, reason about them, and incorporate additional knowledge. It also provides a principled strategy to adapt the models to the evolutions of the environment. We illustrate our approach on the SHL dataset, which features motion sensor data for a set of human activities collected in real conditions. The obtained results make a case for the proposed metamodeling approach; noticeably, the robustness gains achieved when the deployed models are confronted with the evolution of the initial sensing configurations. The trade-offs exhibited and the broader implications of the proposed approach are discussed with alternative techniques to encode and incorporate knowledge into activity recognition models.Massinissa HamidiAomar OsmaniMDPI AGarticlehuman activity recognitioninductive biasmeta-learninghyperparameter optimizationsensor-rich environmentssensor characteristicsChemical technologyTP1-1185ENSensors, Vol 21, Iss 7278, p 7278 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	human activity recognition inductive bias meta-learning hyperparameter optimization sensor-rich environments sensor characteristics Chemical technology TP1-1185
spellingShingle	human activity recognition inductive bias meta-learning hyperparameter optimization sensor-rich environments sensor characteristics Chemical technology TP1-1185 Massinissa Hamidi Aomar Osmani Human Activity Recognition: A Dynamic Inductive Bias Selection Perspective
description	In this article, we study activity recognition in the context of sensor-rich environments. In these environments, many different constraints arise at various levels during the data generation process, such as the intrinsic characteristics of the sensing devices, their energy and computational constraints, and their collective (collaborative) dimension. These constraints have a fundamental impact on the final activity recognition models as the quality of the data, its availability, and its reliability, among other things, are not ensured during model deployment in real-world configurations. Current approaches for activity recognition rely on the activity recognition chain which defines several steps that the sensed data undergo: This is an inductive process that involves exploring a hypothesis space to find a theory able to explain the observations. For activity recognition to be effective and robust, this inductive process must consider the constraints at all levels and model them explicitly. Whether it is a bias related to sensor measurement, transmission protocol, sensor deployment topology, heterogeneity, dynamicity, or stochastic effects, it is essential to understand their substantial impact on the quality of the data and ultimately on activity recognition models. This study highlights the need to exhibit the different types of biases arising in real situations so that machine learning models, e.g., can adapt to the dynamicity of these environments, resist sensor failures, and follow the evolution of the sensors’ topology. We propose a metamodeling approach in which these biases are specified as hyperparameters that can control the structure of the activity recognition models. Via these hyperparameters, it becomes easier to optimize the inductive processes, reason about them, and incorporate additional knowledge. It also provides a principled strategy to adapt the models to the evolutions of the environment. We illustrate our approach on the SHL dataset, which features motion sensor data for a set of human activities collected in real conditions. The obtained results make a case for the proposed metamodeling approach; noticeably, the robustness gains achieved when the deployed models are confronted with the evolution of the initial sensing configurations. The trade-offs exhibited and the broader implications of the proposed approach are discussed with alternative techniques to encode and incorporate knowledge into activity recognition models.
format	article
author	Massinissa Hamidi Aomar Osmani
author_facet	Massinissa Hamidi Aomar Osmani
author_sort	Massinissa Hamidi
title	Human Activity Recognition: A Dynamic Inductive Bias Selection Perspective
title_short	Human Activity Recognition: A Dynamic Inductive Bias Selection Perspective
title_full	Human Activity Recognition: A Dynamic Inductive Bias Selection Perspective
title_fullStr	Human Activity Recognition: A Dynamic Inductive Bias Selection Perspective
title_full_unstemmed	Human Activity Recognition: A Dynamic Inductive Bias Selection Perspective
title_sort	human activity recognition: a dynamic inductive bias selection perspective
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/4b5c84aed66443ad8494dd5dfe04e341
work_keys_str_mv	AT massinissahamidi humanactivityrecognitionadynamicinductivebiasselectionperspective AT aomarosmani humanactivityrecognitionadynamicinductivebiasselectionperspective
_version_	1718431582346280960

Human Activity Recognition: A Dynamic Inductive Bias Selection Perspective

Ejemplares similares