Research On Target Recognition Based With Networks Of Underwork Sensor

With the development of science and technology,with the needs for national security,ithas become more and more important for us to identify the underwater target. Underwatertarget recognition is one of the three key technical （exploration，orientation，recognition）in the development of acoustic equipment. It is an important symbol of the intelligentizedexploration system and is always one of the difficult problems，which are urgent to beresolved in the sonar information processing theory. Developing the research in this fieldhas the most important practical meaning and martial value.The recognition of underwater targets include active and passive identification.Thepassive recognition is our work.Firstly,we extract the feature of the radiated noise formunderwater targets.secondly designed a classifier，finally，in order to identify the underwatertarget，we sent the eigenvectors which can reflect the characteristics of the underwatertarget to the classifier.In the stage of feature extraction,in order to get the power spectrum of the signal,people FFT(Fast Fourier transform)the signal form underwater targets.In the process offeature extraction of power spectral, the main methods we used are included continuousspectrum、line spectrum、modulated continuous spectrum、modulated line spectrum featureextraction.In this case,we can get eigenvectors based on different methods of featureextraction.After getting the feature vectors of the targets，in order to identify the target，wedesigned a classifier based on genetic and BP neural network.After the simulation，it canbe seen that the classifier identify the underwater target effectively,whose recognitionaccuracy is85%or more. In order to show the target identification based on underwatersensor networks,we use a method based on D-S evidence theory to recognize the targets.The process is：firstly，the BP neural network must been trained.secondly，putting thefeature vector which is described above into the trained BP neural network，in this way, theoutput form BP neural network is the basic probability assignment which is needed for D-Sevidence theory.Finally,we recognized the target with the method of D-S theory. After thesimulation, it can be seen that this method can improve the recognition accuracySignificantly, whose recognition accuracy is90%or more.Under the existing conditions of the laboratory,we simulated the underwater sensornetworks by arranging in a number of sensor nodes. Firstly,the ensor nodes sent the collected dates to the gateway，the gateway transfer the data to the datebase of the networkcontrol system with the serial port. Secondly,the target is identified in the database bycalling matlab program,Finally，achieving the remote monitoring of recognition results withthe embedded web.