What should you do if you want to check someone’s pulse from the entire room, such as remotely monitoring an elderly relative? You might think this is impossible because you have to contact the body with common health monitoring devices such as fingertip pulse oximeters and smartwatches.

However, researchers are developing technologies that can monitor a person's vital signs at a distance. One of these technologies is radar.

We are electrical engineers who learn radar systems. We combine advances in radar technology and artificial intelligence to reliably monitor breathing and heart rhythm without touching the body.

Contactless health monitoring has the potential to be more comfortable and easier to use than traditional methods, especially for people who want to monitor their vital signs at home.

How radar works

Radar is known for measuring the speed of cars, making weather forecasts and detecting obstacles at sea and in the air. It senses them by sending electromagnetic waves that travel at the speed of light, waiting for objects they bounce in the path and sensing them as they return to the device.

Radars can determine how far things are, how fast they move, and how they are in shape by analyzing the characteristics of reflected waves.

Radar can also be used to monitor vital signs such as breathing and heart rate. Each breath or heartbeat will cause your chest to move slightly - it is hard to see or feel when it is exercised. But today’s radar is sensitive enough to detect these tiny movements, even through a room.

Advantages of radar

There are other technologies available for remote measurement of health. Camera-based technology can use infrared light to monitor changes in the skin surface in the same way as a pulse serum table, revealing information about your heart’s activity. Computer vision systems can also monitor breathing and other activities, such as sleep, and can detect when someone falls.

However, the camera often fails when the body is blocked by blankets or clothing, or when the lighting is insufficient. I also worry that different skin tones reflect different infrared light, which will lead to inaccurate readings for people with darker skin. In addition, high-resolution cameras based on long-term health monitoring have created serious concerns about patient privacy.

On the other hand, radar solves many problems. The wavelength of the transmitted wave is much longer than that of visible or infrared light, allowing the waves to pass through blankets, clothes and even walls. Measurements are not affected by lighting or skin tone, making them more reliable under different conditions.

Radar images are also extremely low resolution - think old game boy graphics with modern 4K TVs - so it doesn't capture enough details to identify someone, but it can still monitor important activities. While it does carry out project energy, the amount does not constitute a health hazard. The frequency and power levels of the health monitoring radar are similar to those of the mobile phone.

Radar + AI

The radar is powerful, but it has a huge challenge: it can challenge everything to move. Since it can detect tiny chest movements from the heartbeat, it also picks up bigger movements from the head, limbs or other people's head, limbs or others. This makes it difficult for traditional processing techniques to clearly extract vital signs.

To solve this problem, we created a "brain" to make the radar smarter. The brain we call it MM-MURE is a neural network - an artificial intelligence - that learns and estimates chest movement directly from the original radar signal. This approach is called end-to-end learning. This means that unlike other radar and AI technologies, the network itself ignores noise and focuses only on important signals.

We found that this AI enhancement not only gives more accurate results, but is also faster than traditional methods. It immediately deals with multiple people, such as an elderly couple, and adapts to new situations, even during training, situations that are not seen - such as when people sit at different heights, ride bikes, or stand together.

Impact on health care

Reliable remote health monitoring using radar and AI may be a major boon for healthcare. As there is no need to touch the patient's skin, the risk of rash, contamination and discomfort may be greatly reduced. This is especially useful in long-term care, where reducing wires and equipment can make life easier for patients and caregivers.

Imagine a nursing home with radar quietly watching residents and reminding the caregiver immediately if someone has difficulty breathing, falls or needs help. It can be implemented as a home system that checks breathing while sleeping - no wearables are required. Doctors can even use radar to remotely monitor patients recovering from surgery or disease.

This technology is rapidly moving towards real-world use. In the future, checking your health may be as simple as walking into a room, with invisible waves and smart AI working silently to occupy vital signs.