EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Emotion Recognition Using PPG Signals of Smartwatch on Purpose of Threat Detection

Gyuwon Hwang iD, Sohee Yoo iD, Jaehyun Yoo iD

Sensors · 2024

DOI: 10.3390/s25010018 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Gyuwon Hwang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of AI Convergence, Sungshin Women's University, 34 da-gil 2, Bomun-ro, Seongbuk-gu, Seoul 02844, Republic of Korea. Hauptthemen laut MEDLINE: Emotions, Photoplethysmography. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korean National Police Agency.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes a machine learning approach to detect threats using short-term PPG (photoplethysmogram) signals from a commercial smartwatch. In supervised learning, having accurately annotated training data is essential. However, a key challenge in the threat detection problem is the uncertainty regarding how accurately data labeled as ‘threat’ reflect actual threat responses since participants may react differently to the same experiments. In this paper, Gaussian Mixture Models are learned to remove ambiguously labeled training, and those models are also used to remove ambiguous test data. For the realistic test scenario, PPG measurements are collected from participants playing a horror VR (Virtual Reality) game, and the proposed method validates the superiority of our proposed approach in comparison with other methods. Also, the proposed filtering with GMM improves prediction accuracy by 23% compared to the method that does not incorporate the filtering.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EmotionsPhotoplethysmographyHumansMachine LearningAlgorithmsSignal Processing, Computer-AssistedAdultMaleFemale

Stichwörter der Autor:innen

PPG signalmachine learningsmartwatchthreat detection

Autor:innen und Institutionen

  • School of AI Convergence, Sungshin Women's University, 34 da-gil 2, Bomun-ro, Seongbuk-gu, Seoul 02844, Republic of Korea.

ORCID-Profile: Gyuwon Hwang, Sohee Yoo, Jaehyun Yoo

Förderung

  • Korean National Police Agency

Zitieren

APA

Hwang, G., Yoo, S., & Yoo, J. (2024). Emotion Recognition Using PPG Signals of Smartwatch on Purpose of Threat Detection. Sensors. https://doi.org/10.3390/s25010018

Vancouver

Hwang G, Yoo S, Yoo J. Emotion Recognition Using PPG Signals of Smartwatch on Purpose of Threat Detection. Sensors. 2024. doi:10.3390/s25010018

BibTeX
@article{Hwang2024,
  author = {Hwang, Gyuwon and Yoo, Sohee and Yoo, Jaehyun},
  title = {Emotion Recognition Using PPG Signals of Smartwatch on Purpose of Threat Detection},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s25010018}
}
Kostenlos starten →