Next Article in Journal
Design of an Edge-Detection CMOS Image Sensor with Built-in Mask Circuits
Previous Article in Journal
UAV Positioning Mechanisms in Landing Stations: Classification and Engineering Design Review
Previous Article in Special Issue
Sensory Interactive Table (SIT)—Development of a Measurement Instrument to Support Healthy Eating in a Social Dining Setting

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Comparing Person-Specific and Independent Models on Subject-Dependent and Independent Human Activity Recognition Performance

1
Insight Centre for Data Analytics, School of Computer Science and Information Technology, University College Cork, T12 XF62 Cork, Ireland
2
Tyndall National Institute, University College Cork, T12 R5CP Cork, Ireland
3
CONNECT Centre for Future Networks and Communications, Tyndall National Institute, University College Cork, T12 R5CP Cork, Ireland
*
Authors to whom correspondence should be addressed.
This paper is an extended version of our paper published in Scheurer, S.; Tedesco, S.; Brown, K.N.; O’Flynn, B. Subject-dependent and-independent human activity recognition with person-specific and-independent models. In Proceedings of the 6th international Workshop on Sensor-based Activity Recognition and Interaction, Rostock, Germany, 16–17 September 2019; pp. 1–7
Sensors 2020, 20(13), 3647; https://doi.org/10.3390/s20133647
Received: 31 May 2020 / Revised: 23 June 2020 / Accepted: 24 June 2020 / Published: 29 June 2020
(This article belongs to the Special Issue Sensor-Based Activity Recognition and Interaction)
The distinction between subject-dependent and subject-independent performance is ubiquitous in the human activity recognition (HAR) literature. We assess whether HAR models really do achieve better subject-dependent performance than subject-independent performance, whether a model trained with data from many users achieves better subject-independent performance than one trained with data from a single person, and whether one trained with data from a single specific target user performs better for that user than one trained with data from many. To those ends, we compare four popular machine learning algorithms’ subject-dependent and subject-independent performances across eight datasets using three different personalisation–generalisation approaches, which we term person-independent models (PIMs), person-specific models (PSMs), and ensembles of PSMs (EPSMs). We further consider three different ways to construct such an ensemble: unweighted, κ -weighted, and baseline-feature-weighted. Our analysis shows that PSMs outperform PIMs by 43.5% in terms of their subject-dependent performances, whereas PIMs outperform PSMs by 55.9% and κ -weighted EPSMs—the best-performing EPSM type—by 16.4% in terms of the subject-independent performance.
Keywords: human activity recognition; machine learning; ensemble methods; boosting; bagging; inertial sensors human activity recognition; machine learning; ensemble methods; boosting; bagging; inertial sensors
MDPI and ACS Style

Scheurer, S.; Tedesco, S.; O’Flynn, B.; Brown, K.N. Comparing Person-Specific and Independent Models on Subject-Dependent and Independent Human Activity Recognition Performance. Sensors 2020, 20, 3647.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop