Place recognition with WiFi fingerprints using Autoencoders and Neural Networks

Posted by floydsoft on Wednesday November 16, 2016 @10:31PM
from the github.com dept.

https://github.com/aqibsaeed/Place-Recognition-using-Autoencoders-and-NN

( 4 comments | 55 points | on HN )

Re:Place recognition with WiFi fingerprints using Autoencode... by mrcabada on Thursday November 17, 2016 @12:49AM (#12974716)

I've worked on a similar approach for Indoor Locationing, I had 5 APs with OpenWRT reading the RSSI of my phone and some Neural Nets implementation, which eventually learned where I am in the house.

Video: https://youtu.be/eY0BQJJPdX4

[ Parent | on HN ]

Re:Place recognition with WiFi fingerprints using Autoencode... by tonmoy on Thursday November 17, 2016 @09:03AM (#12977489)

If something simple like the location of a AP changes, would this system have to train from scratch with the entire dataset?

[ Parent | on HN ]

Re:Place recognition with WiFi fingerprints using Autoencode... by floydsoft on Thursday November 17, 2016 @09:13AM (#12977571)

NN can be trained online.

[ Parent | on HN ]

Re:Place recognition with WiFi fingerprints using Autoencode... by f00_ on Thursday November 17, 2016 @12:31AM (#12974635)

this is really interesting, company I work for has recently started working on "location analytics" using signal strength (rssi) of the signal sent when your phone scans for wifi

[ Parent | on HN ]