Cargando…

A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors

The sliding window technique is widely used to segment inertial sensor signals, i.e., accelerometers and gyroscopes, for activity recognition. In this technique, the sensor signals are partitioned into fix sized time windows which can be of two types: (1) non-overlapping windows, in which time windo...

Descripción completa

Detalles Bibliográficos
Autores principales: Dehghani, Akbar, Sarbishei, Omid, Glatard, Tristan, Shihab, Emad
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6891351/
https://www.ncbi.nlm.nih.gov/pubmed/31752158
http://dx.doi.org/10.3390/s19225026
_version_ 1783475793123344384
author Dehghani, Akbar
Sarbishei, Omid
Glatard, Tristan
Shihab, Emad
author_facet Dehghani, Akbar
Sarbishei, Omid
Glatard, Tristan
Shihab, Emad
author_sort Dehghani, Akbar
collection PubMed
description The sliding window technique is widely used to segment inertial sensor signals, i.e., accelerometers and gyroscopes, for activity recognition. In this technique, the sensor signals are partitioned into fix sized time windows which can be of two types: (1) non-overlapping windows, in which time windows do not intersect, and (2) overlapping windows, in which they do. There is a generalized idea about the positive impact of using overlapping sliding windows on the performance of recognition systems in Human Activity Recognition. In this paper, we analyze the impact of overlapping sliding windows on the performance of Human Activity Recognition systems with different evaluation techniques, namely, subject-dependent cross validation and subject-independent cross validation. Our results show that the performance improvements regarding overlapping windowing reported in the literature seem to be associated with the underlying limitations of subject-dependent cross validation. Furthermore, we do not observe any performance gain from the use of such technique in conjunction with subject-independent cross validation. We conclude that when using subject-independent cross validation, non-overlapping sliding windows reach the same performance as sliding windows. This result has significant implications on the resource usage for training the human activity recognition systems.
format Online
Article
Text
id pubmed-6891351
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-68913512019-12-12 A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors Dehghani, Akbar Sarbishei, Omid Glatard, Tristan Shihab, Emad Sensors (Basel) Article The sliding window technique is widely used to segment inertial sensor signals, i.e., accelerometers and gyroscopes, for activity recognition. In this technique, the sensor signals are partitioned into fix sized time windows which can be of two types: (1) non-overlapping windows, in which time windows do not intersect, and (2) overlapping windows, in which they do. There is a generalized idea about the positive impact of using overlapping sliding windows on the performance of recognition systems in Human Activity Recognition. In this paper, we analyze the impact of overlapping sliding windows on the performance of Human Activity Recognition systems with different evaluation techniques, namely, subject-dependent cross validation and subject-independent cross validation. Our results show that the performance improvements regarding overlapping windowing reported in the literature seem to be associated with the underlying limitations of subject-dependent cross validation. Furthermore, we do not observe any performance gain from the use of such technique in conjunction with subject-independent cross validation. We conclude that when using subject-independent cross validation, non-overlapping sliding windows reach the same performance as sliding windows. This result has significant implications on the resource usage for training the human activity recognition systems. MDPI 2019-11-18 /pmc/articles/PMC6891351/ /pubmed/31752158 http://dx.doi.org/10.3390/s19225026 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Dehghani, Akbar
Sarbishei, Omid
Glatard, Tristan
Shihab, Emad
A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors
title A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors
title_full A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors
title_fullStr A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors
title_full_unstemmed A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors
title_short A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors
title_sort quantitative comparison of overlapping and non-overlapping sliding windows for human activity recognition using inertial sensors
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6891351/
https://www.ncbi.nlm.nih.gov/pubmed/31752158
http://dx.doi.org/10.3390/s19225026
work_keys_str_mv AT dehghaniakbar aquantitativecomparisonofoverlappingandnonoverlappingslidingwindowsforhumanactivityrecognitionusinginertialsensors
AT sarbisheiomid aquantitativecomparisonofoverlappingandnonoverlappingslidingwindowsforhumanactivityrecognitionusinginertialsensors
AT glatardtristan aquantitativecomparisonofoverlappingandnonoverlappingslidingwindowsforhumanactivityrecognitionusinginertialsensors
AT shihabemad aquantitativecomparisonofoverlappingandnonoverlappingslidingwindowsforhumanactivityrecognitionusinginertialsensors
AT dehghaniakbar quantitativecomparisonofoverlappingandnonoverlappingslidingwindowsforhumanactivityrecognitionusinginertialsensors
AT sarbisheiomid quantitativecomparisonofoverlappingandnonoverlappingslidingwindowsforhumanactivityrecognitionusinginertialsensors
AT glatardtristan quantitativecomparisonofoverlappingandnonoverlappingslidingwindowsforhumanactivityrecognitionusinginertialsensors
AT shihabemad quantitativecomparisonofoverlappingandnonoverlappingslidingwindowsforhumanactivityrecognitionusinginertialsensors