Publication Date:
2017-04-04
Description:
The classical approach used to solve the underwater
port protection problem is the acoustic based technique (sonar
sensors). It has been shown that integrating a sonar system with an
auxiliary array of magnetic sensors can improve the overall
effectiveness of the intruder detection system. One of the major
problems that arise from the use of magnetic systems is the
interpretation of the magnetic signals coming from the sensors. In
this paper a machine learning approach is explored for the detection
of divers or, in general, of underwater magnetic sources that should
ultimately support an automatic detection system. Currently this
task requires a human online monitoring or an offline signal
processing procedure. The proposed research, by windowing the
sensed signals, uses Linear Support Vector Machines for
classification, as tool for the detection problem. Preliminary
empirical results show the viability of the method.
Description:
Published
Description:
401-408
Description:
1.6. Osservazioni di geomagnetismo
Description:
2.5. Laboratorio per lo sviluppo di sistemi di rilevamento sottomarini
Description:
3.4. Geomagnetismo
Description:
N/A or not JCR
Description:
restricted
Keywords:
underwater detection systems
;
port protection
;
magnetic signal processing
;
Support Vector Machine
;
04. Solid Earth::04.05. Geomagnetism::04.05.04. Magnetic anomalies
;
04. Solid Earth::04.05. Geomagnetism::04.05.08. Instruments and techniques
;
05. General::05.01. Computational geophysics::05.01.01. Data processing
;
05. General::05.01. Computational geophysics::05.01.05. Algorithms and implementation
Repository Name:
Istituto Nazionale di Geofisica e Vulcanologia (INGV)
Type:
article
