Deep Learning and Matrix Completion-aided IoT Network Localization in the Outlier Scenarios
This work addresses IoT network localization in outlier scenarios, presenting an incremental improvement by integrating deep learning with matrix completion for enhanced robustness.
The paper tackled the problem of recovering outlier-contaminated Euclidean distance matrices in IoT network localization by proposing a deep learning and matrix completion approach that jointly recovers distance and coordinate matrices while modeling outliers as sparse. Numerical experiments showed the technique accurately recovers sensor locations even with outliers.
In this paper, we propose a deep learning and matrix completion aided approach for recovering an outlier contaminated Euclidean distance matrix D in IoT network localization. Unlike conventional localization techniques that search the solution over a whole set of matrices, the proposed technique restricts the search to the set of Euclidean distance matrices. Specifically, we express D as a function of the sensor coordinate matrix X that inherently satisfies the unique properties of D, and then jointly recover D and X using a deep neural network. To handle outliers effectively, we model them as a sparse matrix L and add a regularization term of L into the optimization problem. We then solve the problem by alternately updating X, D, and L. Numerical experiments demonstrate that the proposed technique can recover the location information of sensors accurately even in the presence of outliers.