EUVIMEDEUVIMED entdecken
Crossref

DT4ECG: a subject-aware ECG monitoring framework for joint user attribution and human activity recognition

Siyu You iD, Boyuan Gu iD, Yanhui Yang iD, Shuaiqi Cheng iD, Shiyu Yu iD, Shisheng Guo iD

Biomedical Physics & Engineering Express · 01.12.2026 · 12 (6) · 065017

DOI: 10.1088/2057-1976/aebbc3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Physics & Engineering Express, online erschienen am 12.11.2026. Verfasst von Siyu You und 5 weiteren Autor:innen. Beteiligte Einrichtung: Glasgow College, University of Electronic Science and Technology of China, Chengdu 611731, People's Republic of China. Hauptthemen laut MEDLINE: Electrocardiography, Signal Processing, Computer-Assisted, Human Activities, Pattern Recognition, Automated. Die Arbeit nennt 46 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electrocardiogram (ECG) signals contain information about both user identity and physical activity, but individual physiological differences complicate activity inference. We propose DT4ECG, a subject-aware multi-task framework for joint identity recognition (IDR) and human activity recognition (HAR) among enrolled users. A multi-scale residual convolution backbone extracts complementary waveform and temporal features, while a subject adaptive fusion module (SAFM) uses learned identity-related representations to calibrate activity features. Evaluation on two public datasets and one self-built dataset achieves IDR macro F 1 of 98.59%–99.96% and HAR macro F 1 of 95.40%–96.82%. Ablation results show consistent HAR improvements from SAFM across the three datasets, and recorded-noise tests characterize sensitivity to common ECG artifacts. The two-channel model contains 0.361 million parameters. These findings demonstrate the value of treating subject-related physiology as context for activity recognition. By linking activity estimates to user attribution within a single ECG framework, this work provides a basis for integrated physiological monitoring among enrolled users in shared-device settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectrocardiographySignal Processing, Computer-AssistedHuman ActivitiesPattern Recognition, AutomatedHumansAlgorithmsMonitoring, PhysiologicFemaleArtifacts

Stichwörter der Autor:innen

ECGhuman activity recognitionmulti-task learningsubject-aware calibrationuser attributionwearable monitoring

Autor:innen und Institutionen

  • Glasgow College, University of Electronic Science and Technology of China, Chengdu 611731, People's Republic of China.
  • School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, People's Republic of China.

ORCID-Profile: Siyu You, Boyuan Gu, Yanhui Yang, Shuaiqi Cheng, Shiyu Yu, Shisheng Guo

Zitieren

APA

You, S., Gu, B., Yang, Y., Cheng, S., Yu, S., & Guo, S. (2026). DT4ECG: a subject-aware ECG monitoring framework for joint user attribution and human activity recognition. Biomedical Physics & Engineering Express, 12(6), 065017. https://doi.org/10.1088/2057-1976/aebbc3

Vancouver

You S, Gu B, Yang Y, Cheng S, Yu S, Guo S. DT4ECG: a subject-aware ECG monitoring framework for joint user attribution and human activity recognition. Biomedical Physics & Engineering Express. 2026;12(6):065017. doi:10.1088/2057-1976/aebbc3

BibTeX
@article{You2026,
  author = {You, Siyu and Gu, Boyuan and Yang, Yanhui and Cheng, Shuaiqi and Yu, Shiyu and Guo, Shisheng},
  title = {DT4ECG: a subject-aware ECG monitoring framework for joint user attribution and human activity recognition},
  journal = {Biomedical Physics & Engineering Express},
  year = {2026},
  volume = {12},
  number = {6},
  pages = {065017},
  doi = {10.1088/2057-1976/aebbc3}
}
Kostenlos starten →