Title :
Combining signal processing and machine learning techniques for real time measurement of raindrops
Author :
Denby, Bruce ; Prévotet, Jean-Christophe ; Garda, Patrick ; Granado, Bertrand ; Barthes, Laurent ; Golé, Peter ; Lavergnat, Jacques ; Delahaye, Jean-Yves
Author_Institution :
Lab. des Instruments et Systemes, Universitd de Versailles St. Quentin en Yvelines, Paris, France
fDate :
12/1/2001 12:00:00 AM
Abstract :
The data acquisition system for a new type of optical disdrometer is presented. As the device must measure sizes and velocities of raindrops as small as 0.1 mm diameter in real time in the presence of high noise and a variable baseline, algorithm design has been a challenge. The combining of standard signal processing techniques and machine learning methods (in this case, a neural network) has been essential to obtaining good performance
Keywords :
data acquisition; geophysical signal processing; learning (artificial intelligence); meteorological instruments; meteorology; multilayer perceptrons; rain; data acquisition system; dual beam disdrometer; high noise; machine learning methods; meteorology; multilayer perceptions; optical disdrometer; photodiode current variations; power spectral density; raindrop sizes; raindrop velocities; real time instrumentation; real time raindrop measurement; signal processing techniques; slope algorithm; variable baseline; Data acquisition; Machine learning; Machine learning algorithms; Noise measurement; Optical noise; Optical signal processing; Signal processing; Signal processing algorithms; Size measurement; Velocity measurement;
Journal_Title :
Instrumentation and Measurement, IEEE Transactions on
