Gastaldo, P.
Preferred name
Gastaldo, P.
4 results
Filters
Settings
The search returned 4 results
Now showing 1 - 4 of 4
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Open Access , Computational Intelligence Methods for Underwater Magnetic-based Protection Systems
(2011-07-31); ; ; ; Magnetic-based detection technologies for undersea protection systems are very effective in monitoring critical areas where weak signal sources are difficult to identify (e.g. diver intrusion in proximity of the seafloor). The complexity of the involved geomagnetic phenomena and the nature of the target detection strategy require the use of adaptive methods for signal processing. The paper shows that Computational Intelligence (CI) models can be integrated with those magnetic-based technologies, and presents an effective, reliable system for adaptive undersea protection. Two different CI paradigms are successfully tested for the specific application task: Circular BackPropagation (CBP) and Support Vector Machines (SVMs). Experimental results on real data prove the advantage of the integrated approach over existing conventional methods. Individual CI components and the overall detection system have been verified in real experiments.222 438 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Restricted , Linear SVM for Underwater Magnetic Signals Based Port Protection
(2010); ; ; ; 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.251 33 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Open Access , Harbour Sea-floor Clearance: “HD” High Definition Magnetic Survey Performance
(2009-10-21); ; ; ; Seafloor clearance methods based on acoustic, direct-inspection, and single-sensor magnetic approaches suffer from limitations in controlling the target-sensor distance, and may prove ineffective when the small size or the dangerous nature of targets requires high accuracy in localization. Moreover, random magnetic variations over time bring about spatial decorrelation phenomena, and hinder the application of double-sensor methods in noisy harbour environments. The new High Definition (HD) magnetic survey protocol tackles the measurement-distance problem in two ways: first, by varying the sensor depth dynamically, and secondly by backprojecting the measured field according to seafloor data and vertical incremental factors associated with the bandwidth characteristics of targets. The method to make up for timeinduced loss in spatial localization ability exploits the local behaviour of a coherence function, which correlates local observations to a set of spatially-stabilized reference stations. The consequent normalization of measured magnetic signals allows one to assign the monitored areas with a specific level of confidence in the detection results, ranging from 100% (certainty) to 0% (random events). The principles of HD detection have been fully applied in the seafloor clearance of the firing test site located south of Cape Teulada (Sardinia, Italy), where very weak signal sources such as cartridge cases, mines, and small objects down to 1 Kg mass values (lobster pots) have been successfully localized, even when covered by extensive colonies of Posidonia.230 544 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Open Access , A Preliminary Study on SVM based Analysis of Underwater Magnetic Signals for Port Protection
(2009-09); ; ; ; People who attend to the problem of underwater port protection usually use sonar based systems. Recently it has been shown that integrating a sonar system with an auxiliary array of magnetic sensors can improve the effectiveness of the intruder detection system. One of the major issues that arise from the integrated magnetic and acoustic system is the interpretation of the magnetic signals coming from the sensors. In this paper a machine learning approach is proposed for the detection of divers or, in general, of underwater magnetic sources. The research proposed here, by means of a windowing of the signals, uses Support Vector Machines for classification, as tool for the detection problem. Empirical results show the effectiveness of the method.177 463
