Physics-Motivated Machine Learning with multi-scale sensing and distributed sensor networks
This proposal will establish an international research laboratory at DTU focusing on machine learning and signal processing for physical applications lead by Distinguished Professor Peter Gerstoft from University of California San Diego. _x000D_ _x000D_ A sensor network is a collection of spatially located sensors used to extract physical information. The proposal develops the fundamental algorithms for processing sensor networks using machine learning and array processing from a statistical point of view. This research holds significant potential for fields underpinned by physical structures, such as acoustics, electromagnetics, biophysics, and extending to complex organic systems like natural habitats. By combining machine learning, multiscale sensing, sensor networks and spatio-temporal signal processing, we envision a transformative impact on the ability to understand, predict, and interact with complex physical phenomena across different scales in disciplines that are normally treated separately.
3/6 complete
Imported from OpenAIRE | Grant NNF24OC0089302.
Open sourceOverview
Grant agreement NNF24OC0089302
Open sourceThis proposal will establish an international research laboratory at DTU focusing on machine learning and signal processing for physical applications lead by Distinguished Professor Peter Gerstoft from University of California San Diego. _x000D_ _x000D_ A sensor network is a collection of spatially located sensors used to extract physical information. The proposal develops the fundamental algorithms for processing sensor networks using machine learning and array processing from a statistical point of view. This research holds significant potential for fields underpinned by physical structures, such as acoustics, electromagnetics, biophysics, and extending to complex organic systems like natural habitats. By combining machine learning, multiscale sensing, sensor networks and spatio-temporal signal processing, we envision a transformative impact on the ability to understand, predict, and interact with complex physical phenomena across different scales in disciplines that are normally treated separately.