Contactless Stress Monitoring using Wireless Signals
This invention discloses methods for non-invasive, continuous stress monitoring using wireless signals and signal processing techniques. The system works by transmitting wireless signals, analyzing their reflections to extract physiological features of the subject, and using machine learning to continuously assess stress-related features. This technology offers a contactless, automated solution for stress monitoring which may find applicability in the following areas:
- Driver Fatigue: Understanding driver fatigue is a critical problem, particularly for commercial drivers such as trucking fleets and ride-sharing services. Fatigue is also relevant to other transportation sectors, such as aviation, where alertness is essential to safety and operational performance.
- Education: The ability to assess cognitive stress through this technology is important for tailoring learning and education across a range of settings, including traditional classrooms, online learning, and training programs, especially within defense.
- Defense/Security: Stress monitoring has significant applications in national security, such as airport screening and border control, as well as in commercial environments such as retail.
- General Workforce Fatigue: Tracking worker fatigue in manufacturing and industrial environments can be valuable for improving workplace safety as well as for insurers assessing occupational risk.
-
Personal Health: Insight into stress levels supports individuals and healthcare providers in making informed decisions for more effective stress management.
Researchers
-
contactless stress monitoring using wireless signals
United States of America | Pending
Technology
The disclosed technology passively emits wireless signals into the environment, which reflect off the user’s body and capture subtle physiological changes such as breathing patterns, heart rate, and body movements. These reflected signals are processed through a feature extraction pipeline, which includes filtering for respiration and applying a neural network-based approach to extract heartbeat intervals and compute heart rate variability—a key biomarker for stress. A machine learning model then analyzes these stress-related features to determine the user’s stress level. This enables continuous, contactless stress monitoring without requiring any user interaction.
Problem Addressed
Stress has far‑reaching impacts across health, workplace safety and performance, education and training programs, as well as security‑related environments. In the context of personal health, chronic stress contributes to the early onset of age-related diseases such as diabetes and Alzheimer’s and increases the risk of mental health conditions like depression and anxiety. As such, there is a growing need for continuous and automated stress monitoring systems that can guide decision-making across a wide variety of settings. Existing solutions—such as saliva sampling, wearables, and camera-based methods—are often intrusive, uncomfortable, or unreliable. The disclosed technology uses RF signals to provide a non-invasive, continuous stress monitoring system across a wide range of environments and activities without interrupting user activities.
Advantages
- Seamlessly and non-intrusively monitors stress without requiring wearables, body contact, or user input, unlike prior methods which disrupt daily activities
- Supports productivity and well-being by informing interventions in medical, workplace, and academic settings
- Enables stress assessment during sleep to support better sleep quality and recovery
- Operates without requiring the user to remain static unlike prior systems
- Allows location-specific monitoring via incorporation into smart devices such as screens or kiosks, overcoming GPS-based systems' lack of sensitivity indoors
- Requires no physical contact or user effort, unlike previous systems such as wearable sensors which require daily recharging
- Maintains privacy and works in low-light conditions, unlike previous camera-based systems
Publications
Ha, Unsoo, Sohrab Madani and Fadel Adib. “WiStress: Contactless Stress Monitoring Using Wireless Signals.” Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 5, no. 3 (2021): 1-37. https://doi.org/10.1145/3478121
License this technology
Interested in this technology? Connect with our experienced licensing team to initiate the process.
Sign up for technology updates
Sign up now to receive the latest updates on cutting-edge technologies and innovations.