fingerprinting for outdoor Geolocation using LoRa 1 HumanTech | - - PowerPoint PPT Presentation

▶
fingerprinting for outdoor geolocation
SMART_READER_LITE
LIVE PREVIEW

fingerprinting for outdoor Geolocation using LoRa 1 HumanTech | - - PowerPoint PPT Presentation

Oct 23, 2023 31 likes •223 views

Francesco Carrino Ales Janka Omar Abou Khaled Elena Mugellini Simon Ruffieux LoRaLoc: machine learning-based fingerprinting for outdoor Geolocation using LoRa 1 HumanTech | 14.06.2019 | SDS 2019 Outline Context and goals

slide-1
SLIDE 1

LoRaLoc: machine learning-based fingerprinting for outdoor Geolocation using LoRa

HumanTech | 14.06.2019 | SDS 2019

Francesco Carrino Ales Janka Omar Abou Khaled Elena Mugellini Simon Ruffieux

1

slide-2
SLIDE 2

Outline

  • Context and goals
  • Methodology
  • Results and discussion
  • Conclusion and perspectives

2

slide-3
SLIDE 3

Context and goals

3

slide-4
SLIDE 4

Context

  • IoT and Geolocation  opportunities!
  • GPS

– High power consumption – Only outdoor

  • LoRa

– Long Range – Low power consumption – Can be used also indoor

4

LoRaWAN Architecture

(source: https://www.thethingsnetwork.org/docs/lorawan/)

slide-5
SLIDE 5

Context – Geolocation using LoRa

  • LoRa for geolocation

– Time of Arrival (TOA) Vs. Time Difference of Arrival/Flight (TDOA/TDOF) – Line-of-sight

5

Gateway (precisely synchronized time references) End-device (clock not synchronized) Gateway (precisely synchronized time references) Gateway (precisely synchronized time references)

slide-6
SLIDE 6

Challenges - Non-line-of-sight

  • Challenge 1: In urban environments: Non-line-of-sight

conditions

  • Challenge 2: Real data not (yet) available, costly to

collect, small dataset…

6

End-device Gateway Gateway

X

Gateway

slide-7
SLIDE 7
  • GPS & LoRa  reference map

Idea: fingerprinting & machine learning & simulator

7

Latitude Longitude

slide-8
SLIDE 8

Algorithm idea

TDOA 0.5 Nan 0.2 0.05 NaN NaN 0.1 …

8

Input vector Gateway Model Corrected geolocation

slide-9
SLIDE 9

Methodology

9

slide-10
SLIDE 10

Simulator

  • No real data –> Simulator
  • Goals:

– Testing algorithms – Transfer learning

  • Data generation

– Ground Truth – GPS dataset – LoRa dataset

  • Sensors’ systematic error + “Local” noise (i.e., geolocated

circular masks)

  • Different masks affect differently each gateway
  • Missing values (NaN) related to masks and gateways

10

slide-11
SLIDE 11

Data processing

  • Preprocessing – Handling NaN

– Remove – Impute mean – Impute median – Impute K-NN

  • Regression

– Random Forest (RFR) – Neural Networks (NN)

  • Wider (i.e., more neurons per layer)
  • Deeper (i.e., more hidden layers)

– LSTM (Long short-term memory)

11

slide-12
SLIDE 12

Results and discussion

12

slide-13
SLIDE 13

Test #1 - Number of gateways

  • Impact of # of gateways on RMSE of the

prediction (N = 10’000)

  • Take home message: at least 7 gateways visible

to have an error under 50 m… but the more the better

13

Models n_gw = 5 n_gw = 7 n_gw = 10 n_gw = 20 rem. kNN rem. kNN rem. kNN rem. kNN Wider

55.35 65.01 49.61 49.72 20.02 22.54 13.44 14.21

Deeper

58.92 71.94 50.17 49.35 21.48 26.85 15.67 15.15

LSTM

56.93 63.87 41.68 48.40 17.71 19.01 13.86 12.81

RFRa

49.05 62.01 34.72 40.01 20.85 24.90 25.92 24.95

slide-14
SLIDE 14

Test #2 – Loss function & NaN handling

  • Regression results (RMSE) obtained comparing loss

functions and methods to handle NaN (N = 10’000)

  • Take home messages:

– mse seems better for Neural Networks (NN) – mae seems better for Random Forest Regressor (RFR) – “Remove” and “K-nn” approaches achieve similar results – LSTM usually achieve the best performance

14

Loss: mse Loss: mae rem.

mean

med. kNN rem.

mean

med. kNN Wider

19.66 43.52 42.68 20.03 20.05 54.09 52.77 20.03

Deeper

18.49 41.07 39.97 17.31 22.28 51.08 52.15 17.13

LSTM

13.03 28.96 28.20 12.82 13.89 32.53 31.78 12.83

RFR

21.35

  • 31.05

31.04 22.06

slide-15
SLIDE 15

Test #3 – Dataset size

15

N=2’000 N=10’000 N=100’000 Remove k-NN Remove k-NN Remove k-NN Wider

23.12 25.74 19.66 20.03 13.85 15.54

Deeper

22.12 26.25 18.49 17.31 11.16 13.10

LSTM

18.51 21.32 13.03 12.82 8.95 8.78

RFR

36.68 39.64 24.90 22.66 10.09 11.21

  • Regression results (RMSE) obtained comparing different

dataset size

  • Take home messages:

– The more the better – With a bigger dataset Random Forest get relatively similar performance to Neural Network

slide-16
SLIDE 16

Conclusion & perspectives

16

slide-17
SLIDE 17

Conclusion & perspectives

17

  • Regression not directly “aware” of gateway position

– Advantage: no need to know the position of gateways – Drawback: training data very specific to training setting (common problem for fingerprinting techniques)

  • Open questions

– Validation of the simulator – Why does LSTM perform better? – Transfer learning?

  • Real data

– The impute methods that performed better (i.e., remove and kNN) cannot be used with real data – Much more missing values (NaN) than expected!

slide-18
SLIDE 18

Real data - preview

18

  • Additional challenge: also small changes in the end-node location (red

dot) implies different gateways (blue crosses) if any detecting the signal (cyan circles)

slide-19
SLIDE 19

Thanks! Question?

  • Francesco Carrino

– Web page: http://francesc.carrino.home.hefr.ch/#/ – e-mail: francesco.carrino@hefr.ch

19