-
Build feature matrix
-
Build ground truth
-
Plot error cumulative probability
-
Compute prediction criterion : error @ 80%
-
Extract prediction for the test set
- Save result in .csv file
-
Cross validation: Build a « leave 1 device out » strategy
olivier.isson@gmail.com before 28/02/2020
- Python code used to generate previous goals
- Predicted position for test set in .csv format:
pred_pos_test_list.csv - Short explanation of your approach and your choices : ~ 1 2 pages, can be included into the notebook or a separate document
En plus des données de capteurs, les appareils transmettent des informations relatives au fonctionnement du système
Aernouts, M., Berkvens, R., Van Vlaenderen, K., Weyn, M., 2018. SigFox and LoRaWAN datasets for fingerprint localization in large urban and rural areas. Data, 3, 13.
Anagnostopoulos, G. and Kalousis, A., 2019. A reproducible comparison of RSSI fingerprinting localization methods using LoRaWAN. arXiv:1908.05085v1.
Choi, W., Chang, Y.-S., Jung, Y. and Song, J., 2018. Low-power LoRa signal-based outdoor positioning using fingerprint algorithm. ISPRS Int. J. Geo-Inf, 7, 440.