EUVIMEDEUVIMED entdecken
Crossref

On-Device Deep Learning with Live Channel Attention for Real-Time ANS State Classification on Wearable Platforms

Arun C., Anandhu P, Ajay B. S

INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · 08.04.2026 · 10 (04) · 1-9

DOI: 10.55041/ijsrem59521 ↗

Kurz gefasst

Fachartikel in der Zeitschrift INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, online erschienen am 08.04.2026. Verfasst von Arun C. und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Abstract—Edge-deployed wearable systems for autonomic nervous system (ANS) monitoring predominantly rely on handcrafted statistical features and binary thresholds, yielding no real-time insight into which physiological channel drives each classification decision. A deep learning platform is presented that addresses these dual limitations directly on an ESP32 microcontroller without cloud dependency. Four physiological modalities are acquired concurrently: electrodermal activity via a galvanic skin response (GSR) sensor, peripheral oxygen saturation (SpO2) and heart rate via a photoplethysmographic pulse oximetry module, skin surface temperature via a precision analog temperature sensor, and three-axis linear acceleration via a microelectromechanical systems (MEMS) inertial sensor. Raw 10-second multimodal windows are classified by a quantized one-dimensional convolutional neural network with a bidirectional long short-term memory layer (1D-CNN + BiLSTM) into four clinically distinct ANS states: normal baseline, sympathetic arousal, parasympathetic suppression, and mixed dysregulation. A novel Physiological Autonomic Signature Token (PAST)—a 4-dimensional learned Channel Attention Vector (CAV) requiring only 256 additional parameters—is computed at every inference pass and displayed live on the device LCD, delivering the first inference-time, per-sensor attribution on a microcontroller-resident physiological classifier. A Physiological Coherence Score (PCS), computed as the cosine similarity between the BiLSTM hidden state slices of the two dominant PAST channels and requiring no additional parameters, provides a third confidence dimension that detects inter-channel physiological inconsistency and flags suspected sensor artifacts at inference time. Monte Carlo (MC) Dropout over T = 20 stochastic forward passes provides predictive uncertainty quantification; high-variance predictions trigger a 'LOW CONFIDENCE' alert. The system sustains approximately 47 hours of monitoring at 42 mA average current from a 2000 mAh cell, completing single-pass inference in 6.8 ms—advancing TinyML for interpretable, confidence-aware ANS monitoring. Index Terms—Autonomic nervous system monitoring, channel attention, edge inference, explainable AI, TinyML, wearable health monitoring.

Zitieren

APA

C., A., P, A., & S, A. B. (2026). On-Device Deep Learning with Live Channel Attention for Real-Time ANS State Classification on Wearable Platforms. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, 10(04), 1-9. https://doi.org/10.55041/ijsrem59521

Vancouver

C. A, P A, S AB. On-Device Deep Learning with Live Channel Attention for Real-Time ANS State Classification on Wearable Platforms. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT. 2026;10(04):1-9. doi:10.55041/ijsrem59521

BibTeX
@article{C2026,
  author = {C., Arun and P, Anandhu and S, Ajay B.},
  title = {On-Device Deep Learning with Live Channel Attention for Real-Time ANS State Classification on Wearable Platforms},
  journal = {INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT},
  year = {2026},
  volume = {10},
  number = {04},
  pages = {1--9},
  doi = {10.55041/ijsrem59521}
}
Kostenlos starten →