Nursing AI device can monitor the correct movements of elderly residents with radio waves and when help is needed to call for help
- The device bounces radio waves around a room to look at objects and movement
- When it detects motion, the signal returns to the mounted sensor
- Artificial Intelligence analyzes the data to create a constant picture of activity
- The team said this could be used in nursing homes to warn staff that a resident is falling
- It could also be used to help people with dementia keep track of their activities
A radar-like tool that can track movements throughout the day without using an invasive camera could be used in nursing homes to alert staff if a resident falls by.
A team from MIT & # 39; s Computer Science and Artificial Intelligence lab said the goal was to create a device that can track movement without physical contact.
A sensor on the wall transmits a continuous low power radio power and when the waves hit a person or object, they bounce back to the sensor.
The sensor can then analyze the wave for information about the environment and tell exactly what the person is doing in the room – continuously throughout the day.
Researchers said this could be used to keep a diary of moving staff and warn if a resident falls into a care home or no longer moves.
The radio frequency device measures very precise movements in a room, but reports back in a format that can only be understood by computers – not by human viewers.
A radar-like tool that can track movements throughout the day without using an invasive camera could be used in nursing homes to alert staff if a resident falls
A sensor on the wall transmits a continuous low power radio and when the waves hit something like a person or object, they kick back to the sensor
Researchers said this could be used to create a diary of staff and conscious staff if a resident falls into a care home or does not move for a long period of time
The team says this protects the privacy of everyone who lives in a room that has the monitor installed, because no one will be able to actually see what they & # 39; re doing.
& # 39; This can be used by the family who & # 39; s concerned about mother & # 39; s living in a parental home, & # 39; said lead author and MIT professor Dina Katabi.
& # 39; They can get a complete description of their mother & # 39 ;s daily life to make sure the facility does its job and that she has a good life. & # 39;
The device is incredibly precise and can tell when someone has read a book, taken out a coat or even just slept in an armchair.
It uses artificial intelligence around & # 39; radio waves & # 39; read back & # 39; to the sensor and a detailed floor plan of & # 39; the room to determine what happened.
Researchers say it could be used to create a & # 39; transcript & # 39; to make every day of life with a blow-by-blow account of movements from entering & # 39; the door to sleeping & # 39; the sleep.
Named RF-Diary, the tool is a & # 39; non-intrusive, privacy-saving & # 39; way to control vulnerable people in a nursing home or hospital, the MIT developers claim.
They expect the product to go on sale within two years and say one case of use is to keep people & # 39; tabs on elderly parents who & # 39; live alone & # 39 ;.
The authors say it could also be used to track dementia sufferers what they have been doing all day and function normally.
& # 39; The textual description helps her to remember what & # 39 ;s in it. the day happened, allowing them to function despite the memory lapses, & # 39; said Katabi.
& # 39; For people in later stages of Alzheimer's, it helps staff in & # 39; the assisted living community where they live to learn what they did and whether they expose themselves to some dangerous behavior. & # 39;
Researchers say it could be used to create a & # 39; transcript & # 39; to make every day of life with a blow-by-blow account of movements from the entrance to sleep & # 39;
The system was trained by recording wireless signals from volunteers performing a variety of activities labeled by short-term human annotators.
After that training process, the system is able to generalize to new people and homes that it has never been seen before – but that needs to be set up every time.
Privacy was a key feature of its development, according to Katabi, who says that everyone who is controlled should agree to perform a range of moves to & # 39; train the system & # 39; and make sure they agree to have it installed.
Experiments showed that RF-Diary could generate accurate title names for a person's activities, even in a dark room where video control would not work.
The system can achieve more than 90 percent classification accuracy on more than 30 different actions for households, the team said.
The research can be seen in more detail on the project & # 39 ;s website.
WHAT IS RADAR? HIGH FREQUENCY RADIO WAVES DEVELOPED DURING WW2 BY FEEDING PILOTS
Radar is an acronym, which stands for & # 39; Radio detection innd ranging.
It uses high frequency radio frequencies and was first developed in World War II to help fighter pilots.
It works in a simple way, a machine sends out a wave and then a separate sensor detects it when it jumps back.
This is about the same way that sight works, light is detached from an object and in the eye, where it is detected and processed.
Instead of using visible light, which has a small wavelength, radar uses radio waves that have a much larger wavelength.
By detecting the range of & # 39; rebound waves, a computer can create an image of what lies ahead that is invisible to the human eye.
This can be used to see through different materials, in darkness, fog and a variety of different weather conditions.
Scientists often use this method to detect terrain and also study archeological and valuable finds.
As a non-invasive technique, it can be used to gain insight without degrading or damaging precious finds and monuments.