EUVIMEDEUVIMED entdecken
Crossref

Human Activity Recognition with Smartwatch Data by using Mahalanobis Distance-Based Outlier Detection and Ensemble Learning Methods

Ensar Arif SAĞBAŞ, Serkan BALLI

Academic Platform Journal of Engineering and Smart Systems · 2023

DOI: 10.21541/apjess.1105362 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Platform Journal of Engineering and Smart Systems, 2023. Verfasst von Ensar Arif SAĞBAŞ und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: Muğla Sıtkı Koçman Üniversitesi.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recognition of human activities is part of smart healthcare applications. In this context, the detection of human actions with high accuracy has been a field that has been working for many years. With the increase in the usage of smart devices, smartphones and smartwatches have become the constant equipment of these studies thanks to their internal sensors. Sometimes abnormal data are included in data sets due to the way the data were collected and for reasons arising from the sensors. For this reason, it becomes important to detect outlier data. In this study, step counter and heart rate sensors were used in addition to an accelerometer and gyroscope in order to detect human activities. Afterward, the outliers were detected and cleared with a Mahalanobis distance-based approach. With the aim of achieving a better classification performance, machine learning methods were used by strengthening them with ensemble learning methods. The obtained results showed that step counter, heart rate sensors, and ensemble learning methods positively affect the success of the classification. In addition, it was found that the Mahalanobis distance-based outlier detection method increased the classification accuracy significantly.

Förderung

  • Muğla Sıtkı Koçman Üniversitesi

Zitieren

APA

SAĞBAŞ, E. A., & BALLI, S. (2023). Human Activity Recognition with Smartwatch Data by using Mahalanobis Distance-Based Outlier Detection and Ensemble Learning Methods. Academic Platform Journal of Engineering and Smart Systems. https://doi.org/10.21541/apjess.1105362

Vancouver

SAĞBAŞ EA, BALLI S. Human Activity Recognition with Smartwatch Data by using Mahalanobis Distance-Based Outlier Detection and Ensemble Learning Methods. Academic Platform Journal of Engineering and Smart Systems. 2023. doi:10.21541/apjess.1105362

BibTeX
@article{SABA2023,
  author = {SAĞBAŞ, Ensar Arif and BALLI, Serkan},
  title = {Human Activity Recognition with Smartwatch Data by using Mahalanobis Distance-Based Outlier Detection and Ensemble Learning Methods},
  journal = {Academic Platform Journal of Engineering and Smart Systems},
  year = {2023},
  doi = {10.21541/apjess.1105362}
}
Kostenlos starten →