AMS-HD: Hyperdimensional Computing for Real-Time and Energy-Efficient Acute Mountain Sickness Detection

TL;DR

AMS-HD introduces the first on-device hyperdimensional computing framework for real-time acute mountain sickness detection. By encoding physiological features into high-dimensional hypervectors and using Hadamard/low-discrepancy HV generation, it delivers binary and multiclass AMS classification with low memory and energy footprint on wearables and edge platforms. The approach is validated on FPGA, ARM-based embedded devices, and smartwatch–phone systems, achieving competitive accuracy (e.g., up to $0.84$ binary and $0.69$ multiclass) while reducing hardware resources and power compared to conventional models. This work demonstrates a practical, hardware-aware path to continuous AMS monitoring in high-altitude environments, enabling always-on, low-power health surveillance.

Abstract

Altitude sickness is a potentially life-threatening condition that impacts many individuals traveling to elevated altitudes. Timely detection is critical as symptoms can escalate rapidly. Early recognition enables simple interventions such as descent, oxygen, or medication, and prompt treatment can save lives by significantly lowering the risk of severe complications. Although conventional machine learning (ML) techniques have been applied to identify altitude sickness using physiological signals, such as heart rate, oxygen saturation, respiration rate, blood pressure, and body temperature, they often struggle to balance predictive performance with low hardware demands. In contrast, hyperdimensional computing (HDC) remains under-explored for this task with limited biomedical features, where it may offer a compelling alternative to existing classification models. Its vector symbolic framework is inherently suited to hardware-efficient design, making it a strong candidate for low-power systems like wearables. Leveraging lightweight computation and efficient streamlined memory usage, HDC enables real-time detection of altitude sickness from physiological parameters collected by wearable devices, achieving accuracy comparable to that of traditional ML models. We present AMS-HD, a novel system that integrates tailored feature extraction and Hadamard HV encoding to enhance both the precision and efficiency of HDC-based detection. This framework is well-positioned for deployment in wearable health monitoring platforms, enabling continuous, on-the-go tracking of acute altitude sickness.

Figures (11)

• Figure 1: Overview of the proposed AMS-HD framework. The system provides a complete design from high-level bipolar computing ($-1$/$+1$) on mobile and embedded processors to low-level binary computing (logic $0$/$1$) on hardware platforms such as ASICs and FPGAs. By integrating physiological signals with lightweight hyperdimensional operations, the framework enables always-on, resource-efficient detection of acute mountain sickness.
• Figure 2: Overview of an HDC model: encoding, training, and classification via similarity search.
• Figure 3: Neuro-symbolic learning architectures and their corresponding encoding: (a) language text processing using n-gram encoding, and (b) image processing using record-based encoding (+1s represent logic-1s in memory, -1s represent logic-0s in memory.)
• Figure 4: Proposed AMS-HD training pipeline: MI feature selection, positional encoding, hyperdimensional projection, and ⓐ pseudo- vs. ⓑ quasi-random binarization.
• Figure 5: Feature importance scores calculated via MI, highlighting SpO$_2$ (%) as the most influential feature.