Hello Everyone ,
With variety of motion sensors on Thingy:52 , can it be used to detect if a person has fallen ? If 'yes' then how accurate the results will be ?
If someone has tried it then please share your experience.
Thanks
Hello Everyone ,
With variety of motion sensors on Thingy:52 , can it be used to detect if a person has fallen ? If 'yes' then how accurate the results will be ?
If someone has tried it then please share your experience.
Thanks
Hi,
We don't have any example demo that you can work on but there is some options to explore. To best detect a fall using the sensor date from the Thingy52 you could maybe use something like this example form Edge impulse on the device.
it can in theory be very accurate and might even be able to detect different types of fall, but that would require a huge set of sample data and training a couple models. Exactly how and what is the best solution is hard to say. Maybe a simple accelerometer check is enough.
Regards,
Jonathan
Hi,
We don't have any example demo that you can work on but there is some options to explore. To best detect a fall using the sensor date from the Thingy52 you could maybe use something like this example form Edge impulse on the device.
it can in theory be very accurate and might even be able to detect different types of fall, but that would require a huge set of sample data and training a couple models. Exactly how and what is the best solution is hard to say. Maybe a simple accelerometer check is enough.
Regards,
Jonathan