Wearable Biometric Sensors for XR Integrations


BioMojo has developed a unique computational systems biology approach, honed by years developing open source human physiology engines. We use this approach to extract and deliver relevant biomarkers from curated data that is delivered from wearable devices that we help to create with our university and commercial partners.

Our multi-disciplinary team of scientists and technologists develop disruptive solutions based on:

  • Clinically accurate sensor technology designed for use in extreme environments
  • Sensors designed to be small, lightweight, rugged, modular, multi-use, easy to use with low electronic visibility
  • The ability to integrate sensors into the heads up display (HUD) for wearable augmented reality displays
  • Analytics that drive meaningful outcomes
  • Adherence to regulatory design control processes

BioMojo creates software applications and hardware solutions that are optimized for computing at the edge, automating the organization and fusion of data collected from multiple sources with neural networks and machine learning to recognize patterns and anomalies. We focus on solutions that support our SOF medical community to optimize the performance of our SOF Operators (i.e., increase both physical and cognitive capability while mitigating the effects of stressors that degrade performance and health).

BioPod is a wrist-worn wearable platform that provides multimodal physiological and activity monitoring. It tracks temperature, blood oxygen saturation (SPO2), respiration rate, electrodermal activity (EDA) and heart rate variability (HRV) derived from time and frequency domain analysis which is related to stress and consequently human performance. The device also contains an accelerometer and gyroscope to measure linear and rotational motion and measures of subject postures, behaviors and activities. BioPOD is also equipped with a machine learning capability that includes onboard artificial neural network models. These serve to pair a novel signal quality index to measured physiological signals. Our approach ensures that data and measures collected and derived by the wearable is of high integrity and not significantly contaminated by motion artifacts or other sources of noise or interference.