Skip to content

Instantly share code, notes, and snippets.

@Micrified
Created May 20, 2020 11:37
Show Gist options
  • Save Micrified/4d4d153b480ff5e0badd9c9cce9bd3be to your computer and use it in GitHub Desktop.
Save Micrified/4d4d153b480ff5e0badd9c9cce9bd3be to your computer and use it in GitHub Desktop.
Requirements SMS

Introduction

  • The application developed for the second assignment of Smart Phone Sensing delivers indoor (and outdoor) localization using RSS signals from WiFi access points using Bayes filters names
  • load distribution
  • phones used
  • version of android

Data Collection

...

Map Layout

  • Needs dimensions

Data Processing

  • how many APs typically?
  • how many samples in total?
  • how many samples for training, how many for testing?

Online

  • everything online

Filters

  • in short? automatic and manual
  • filters also online

Sample Radio Maps

  • pmf for two cells
  • gaussian distribution vs. histogram
  • aka PDF vs. PMF
  • I believe we use PDF

Evaluation

Bayes Iteration Approach

  • number of tries? steady state? parallel/serial?
  • convergence conditions??

App design

  • short explanation on how the app works

Confusion Matrix

  • figure
  • how many total training samples, how many testing samples
  • how many iterations

Discussion

Filtering Methods

  • Manual
  • Automatic
  • any other interesting things we've noticed
  • what was hard to do?
  • how do we handle APs that don't exist in certain cells??
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment