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

Volume

50

Issue

6

fYear

2001

fDate

12/1/2001 12:00:00 AM

Firstpage

1717

Lastpage

1724

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;

fLanguage

English

Journal_Title

Instrumentation and Measurement, IEEE Transactions on

Publisher

ieee

ISSN

0018-9456

Type

jour

DOI

10.1109/19.982973

Filename

982973