Toolboxes & Code Repositories

DASF

A library implementing the DASF algorithmic framework for solving linear signal or feature fusion optimization problems in a distributed setting, where different signal- or feature dimensions of each sample are spread across the nodes of a network.

 

Description:

The DASF algorithm is a general algorithmic framework for solving linear signal or feature fusion optimization problems in a distributed setting, where different signal- or feature dimensions of each sample are spread across the nodes of a network. These problems require linearly combining the observed signals or features collected at the various nodes to satisfy a pre-defined optimization criterion. The proposed distributed adaptive signal fusion (DASF) algorithm is an iterative method that solves these types of problems by allowing each node to share a linearly compressed version of the local sensor signal observations with its neighbors to reduce the communication requirements of the network. The general DASF algorithm is shown to have several existing distributed algorithms from the literature as a special case (including principal component analysis, canonical correlation analysis, (generalized) eigenvalue problems, minimum variance beamformers, multichannel Wiener filters, etc.), while at the same time allowing to solve new distributed problems as well with guaranteed convergence and optimality.

More Information:

  • Related research challenge: AI-Driven Data Science

  • Responsible Research Lead:Alexander Bertrand

  • Authors: Cem Musluoglu, Charles Hovine, Alexander Bertrand

  • Programming Language: Matlab and Python

  • Link to the repository

  • Categories: Networks and graphs, Time series, Embedded systems, Optimization, Distributed intelligence

Publications:

  • C. A. Musluoglu and A. Bertrand, "A Unified Algorithmic Framework for Distributed Adaptive Signal and Feature Fusion Problems - Part I: Algorithm Derivation", IEEE Transactions on Signal Processing, 2023, doi: https://doi.org/10.1109/TSP.2023.3275272.

  •  C. A. Musluoglu, C. Hovine and A. Bertrand, "A Unified Algorithmic Framework for Distributed Adaptive Signal and Feature Fusion Problems - Part II: Convergence Properties", IEEE Transactions on Signal Processing, 2023, doi: https://doi.org/10.1109/TSP.2023.3275273.

  • C. Hovine and A. Bertrand, "A Distributed Adaptive Algorithm for Non-Smooth Spatial Filtering Problems in Wireless Sensor Networks", IEEE Transactions on Signal Processing, vol. 72, pp. 4682-4697, 2024, doi: 10.1109/TSP.2024.3474168

  • C. Hovine and A. Bertrand, "Distributed Adaptive Spatial Filtering with Inexact Local Solvers", arXiv:2405.03277, 2024