Changes between Version 14 and Version 15 of other/summer/2019/fitness-assist


Ignore:
Timestamp:
Aug 15, 2019, 3:56:27 PM (16 months ago)
Author:
JustinEsposito
Comment:

Legend:

Unmodified
Added
Removed
Modified
  • other/summer/2019/fitness-assist

    v14 v15  
    1313== Solution in Depth ==
    1414
    15 Our solution uses the channel state information (CSI) that is embedded in !WiFi signals to determine what exercise a user is performing. !WiFi is the best candidate because it is ubiquitous in a most settings, meaning users would not have to buy dedicated devices for exercise monitoring. Additionally, individual features can be derived from CSI, allowing the detection of different exercises. To extract these features, we implemented a
    16 
    17 ADD TYPE OF DEEP LEARNING MODEL HERE
    18 
    19 that searches for repetitive patterns in the CSI data using autocorrelation, which compares a signal to a copy of itself at a different point in time.
     15Our solution uses the channel state information (CSI) that is embedded in !WiFi signals to determine what exercise a user is performing. !WiFi is the best candidate because it is ubiquitous in a most settings, meaning users would not have to buy dedicated devices for exercise monitoring. Additionally, individual features can be derived from CSI, allowing the detection of different exercises. To extract these features, we implemented a Deep Neural Network that searches for repetitive patterns in the CSI data using autocorrelation, which compares a signal to a copy of itself at a different point in time.
    2016
    2117== Tools ==