EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Human Activity Prediction Based on Forecasted IMU Activity Signals by Sequence-to-Sequence Deep Neural Networks

Ismael Espinoza Jaramillo iD, Channabasava Chola iD, Jin-Gyun Jeong, Ji-Heon Oh, Hwanseok Jung, Jin-Hyuk Lee, Won Hee Lee, Tae-Seong Kim iD

Sensors · 18.07.2023 · 23 (14) · 6491

DOI: 10.3390/s23146491 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.07.2023. Verfasst von Ismael Espinoza Jaramillo und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics and Information Convergence Engineering, Kyung Hee University, Yongin 17104, Republic of Korea. Hauptthemen laut MEDLINE: Neural Networks, Computer, Human Activities. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute for Information and Communications Technology Promotion (IITP), National Research Foundation of Korea (NRF).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human Activity Recognition (HAR) has gained significant attention due to its broad range of applications, such as healthcare, industrial work safety, activity assistance, and driver monitoring. Most prior HAR systems are based on recorded sensor data (i.e., past information) recognizing human activities. In fact, HAR works based on future sensor data to predict human activities are rare. Human Activity Prediction (HAP) can benefit in multiple applications, such as fall detection or exercise routines, to prevent injuries. This work presents a novel HAP system based on forecasted activity data of Inertial Measurement Units (IMU). Our HAP system consists of a deep learning forecaster of IMU activity signals and a deep learning classifier to recognize future activities. Our deep learning forecaster model is based on a Sequence-to-Sequence structure with attention and positional encoding layers. Then, a pre-trained deep learning Bi-LSTM classifier is used to classify future activities based on the forecasted IMU data. We have tested our HAP system for five daily activities with two tri-axial IMU sensors. The forecasted signals show an average correlation of 91.6% to the actual measured signals of the five activities. The proposed HAP system achieves an average accuracy of 97.96% in predicting future activities.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerHuman ActivitiesHumansExerciseAccidental Falls

Stichwörter der Autor:innen

attentiondeep learning forecastinghuman activity predictioninertial measurement unitsequence-to-sequence encoding

Autor:innen und Institutionen

  • Department of Electronics and Information Convergence Engineering, Kyung Hee University, Yongin 17104, Republic of Korea.
  • Department of Software Convergence, Kyung Hee University, Yongin 17104, Republic of Korea.

ORCID-Profile: Ismael Espinoza Jaramillo, Channabasava Chola, Tae-Seong Kim

Förderung

  • Institute for Information and Communications Technology Promotion (IITP)
  • National Research Foundation of Korea (NRF)

Zitieren

APA

Jaramillo, I. E., Chola, C., Jeong, J. G., Oh, J. H., Jung, H., Lee, J. H., Lee, W. H., & Kim, T. S. (2023). Human Activity Prediction Based on Forecasted IMU Activity Signals by Sequence-to-Sequence Deep Neural Networks. Sensors, 23(14), 6491. https://doi.org/10.3390/s23146491

Vancouver

Jaramillo IE, Chola C, Jeong JG, Oh JH, Jung H, Lee JH, et al. Human Activity Prediction Based on Forecasted IMU Activity Signals by Sequence-to-Sequence Deep Neural Networks. Sensors. 2023;23(14):6491. doi:10.3390/s23146491

BibTeX
@article{Jaramillo2023,
  author = {Jaramillo, Ismael Espinoza and Chola, Channabasava and Jeong, Jin-Gyun and Oh, Ji-Heon and Jung, Hwanseok and Lee, Jin-Hyuk and Lee, Won Hee and Kim, Tae-Seong},
  title = {Human Activity Prediction Based on Forecasted IMU Activity Signals by Sequence-to-Sequence Deep Neural Networks},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {14},
  pages = {6491},
  doi = {10.3390/s23146491}
}
Kostenlos starten →