Indoor locationing using Wi-Fi fingerprints, machine learning, and deep learning.

Evaluated data and trained and tuned three models (random forest, k-NN, and neural network) in Python (Sci-kitlearn, Keras) to predict smartphone user locations in the UJIIndoorLoc indoor locationing dataset, achieving comparable results on the test set to those reported by teams who participated in the 2015 EvAAL-ETRI competition. The competition was a part of the 6th International Conference on Indoor Positioning and Indoor Navigation.

Link to dataset: https://archive.ics.uci.edu/ml/datasets/ujiindoorloc

The dataset is described in Torres-Sospedra et al. (2014) and the competition in Torres-Sospedrea et al. (2017).

Note: I did not attend the competition, but compared my results to theirs.

References

Torres-Sospedra, J., Montoliu, R., Martínez-Usó, A., Avariento, J. P., Arnau, T. J., Benedito-Bordonau, M., & Huerta, J. (2014). UJIIndoorLoc: A new multi-building and multi-floor database for WLAN fingerprint-based indoor localization problems. 2014 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

Torres-Sospedra, J., Moreira, A., Knauth, S., Berkvens, R., Montoliu, R., Belmonte, O., . . . Peremans, H. (2017). A realistic evaluation of indoor positioning systems based on Wi-Fi fingerprinting: the 2015 EvAAL-ETRI competition. Journal of Ambient Intelligence and Smart Environments, 9(2), 263-279.