Surging needs

Innovations needed for an aging population.

The world is facing a change in demographic situation where a diminishing part of the population shall support a growing group of elderly. In addition to this we see rising numbers of life style related diseases such as dementia and cardiovascular diseases. This situation calls for innovations. In this context we offer a non-intrusive, autonomous supervision system for elderly based on novel radar sensor technology.

This system offers monitoring of vital signs, that is respiration pattern and respiration rate. Moreover is the sensor is able to capture and alert on, motion and presence/absence of one or more persons in a room. From the caregivers point of view this means that nightly supervision of within a nursing home for example can be done more efficiently as resources are directed towards patients in need of help rather than ambulatory fixed-time visits. From the patients point of view it means that he/she can feel safe at night without being unnecessarily disturbed.

Night supervision

RayVS1 offers comfort and security.

AI has the potential to be a gamechanger for the eHealth market. These services need reliable data. Raytelligence aims at playing a global role in this Eco-system.  With our sensors and services we can play an important role in collecting data and make decisions for the AI algorithms.


The EaZense sensor provides a high-level service to the end user. Signal processing and signal analysis is performed in the sensor itself and/or in a cloud service. Examples of such services are:


- “Patient X sleeps well with respiration rate 23 bpm”


- “Patient Y has fallen out of bed”


- “Person Z has a walking speed deviating from normal”


These services can be calculated in the sensor itself or in a cloud service. The cloud service is particularly interesting when several sensors cooperate to deliver a specific service e.g. cover an entire apartment.

All signal processing for vital sign monitoring is performed within the sensor. This means that all relevant information is sent to the caregivers IT-system for proper action e.g. alarms, alerts or pure logging. Besides of respiratory rate, sleep quality is also a specific parameters of interest.


The EaZense sensor has capability to run machine learning algorithms in the sensor it self or in a connected cloud-based service. These algorithms are used for modeling normal behavior by relying on detected trends and deviations from such. The sensor is particularly suited to monitor parameters that has been proven to be early warnings of cognitive impediment.

Our sensor enable care facilities to identify and characterize patient activities over time. By analyzing sensor data streams over a longer time perspective, caregivers can have a continuous and unubtrusive tool for measuring e.g. patients improvement after a surgery.