No Description

Matthieu PUIGT 45c97327f1 Mettre à jour '' 5 years ago
functions 8443e89dc0 Mettre à jour 'functions/OMP.m' 5 years ago 45c97327f1 Mettre à jour '' 5 years ago
script_demo.m ee25aee1ff Mettre à jour 'script_demo.m' 5 years ago

Informed Nonnegative Matrix Factorization Methods for Mobile Sensor Network Calibration

by Clément Dorffer, Matthieu Puigt, Gilles Delmaire, and Gilles Roussel

In this paper, we consider the problem of blindly calibrating a mobile sensor network—i.e., determining the gain and the offset of each sensor—from heterogeneous observations on a defined spatial area over time. For that purpose, we propose to revisit blind sensor calibration as an informed Nonnegative Matrix Factorization (NMF) problem with missing entries. In the considered framework, one matrix factor contains the calibration structure of the sensors—and especially the values of the sensed phenomenon—while the other one contains the calibration parameters of the whole sensor network. The available information is taken into account by using a specific parameterization of the NMF problem. Moreover, we also consider additional NMF constraints which can be independently taken into account, i.e., an approximate constraint over the mean calibration parameters and a sparse approximation of the sensed phenomenon over a known dictionary. The enhancement of our proposed approaches is investigated through more than 5000 simulations and is shown to be accurate for the considered application and to outperform a multi-hop micro-calibration technique as well as a method based on low-rank matrix completion and nonnegative least squares.


Download the Matlab codes of the mobile sensor calibration techniques. The codes were written by Clément DORFFER and are maintained by Clément DORFFER, Matthieu PUIGT, Gilles DELMAIRE, and Gilles ROUSSEL (clement.dorffer [at] and {matthieu.puigt, gilles.delmaire, gilles.roussel} [at]

It contains several functions and folders:

  • README.m
  • script_demo.m
  • functions
    • ACIN_Cal.m
    • IN_Cal.m
    • OMP.m
    • SpAIN_Cal.m
    • SpIN_Cal.m

Tuning the parameters of the methods

If you plan to apply the proposed methods to your mobile crowdsensing data, please be aware that several parameters must be set, i.e., the size of the cells to define the rendez-vous must be appropriately chosen, the dictionary is not applicable as is, the number of NMF iterations must be carrefully fixed. In case of doubts, do not give up! Please contact us: we will do our best to help you (see the Support section for contact information).


If you use this code for research or educational purpose, please cite:

C. Dorffer, M. Puigt, G. Delmaire, G. Roussel, "Informed Nonnegative Matrix Factorization Methods for Mobile Sensor Network Calibration", IEEE Transactions on Signal and Information Processing over Networks, Volume 4, Issue 4, pp. 667-682, December 2018.


For any suggestions or questions about this code, please contact: clement.dorffer [at] and matthieu.puigt [at]