Passive Sonar Signal Detection and Classification Based on Independent Component Analysis

Moura, Natanael Nunes de; Seixas, J.; Ramos, Ricardo R.

doi:10.5772/18286

Cited by 35 publications

(41 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…barges), the second one is average speed vessels (including cart) and third includes large vessels with low speed. Figure 20 show ROC curve compares the result of the proposed algorithm and method expressed in [15], [9] and [5] applied on same database. It is seen in Figure 20 that result of proposed method (adaptive fusion) is obviously better than other methods.…”

Section: Discussionmentioning

confidence: 99%

“…Table 4 shows the values of parameters of sonar equation in the Persian Gulf. In [9], for target detection, DEMON analysis is applied. DEMON algorithm is a narrow-band filter that reduces the ambient noises.…”

Section: Discussionmentioning

confidence: 99%

“…In order to compare, the results of this method are compared with three general and practical passive sonar detection methods as sonar equation [15], detection based on the DEMON and independent component analyze (ICA) [9] and target detection based on TPSW and neural networks [5] TL is the transmission loss, NL is the noise level, DI is the directivity index of the array (an approximation to the array gain) and DT is the detection threshold. In this paper optimum DT is selected by receiving operating characteristics (ROC) curve.…”

Section: Discussionmentioning

confidence: 99%

“…Wakayama et al describes the forecasting of probability of target presence in a search area [8] (also referred to as the PT map) considering both detection and nondetection conditions. Moura et al in [9] performed independent component analysis for detect and classify signals against background noise. Kil Woo et al describes DEMON algorithm for detecting target in passive sonar [10].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Passive Sonar Target Detection Using Statistical Classifier and Adaptive Threshold

Alaie¹,

Farsi²

2017

Preprint

View full text Add to dashboard Cite

This paper presents the results of an experimental investigation about target detecting with passive sonar in Persian Gulf. Detecting propagated sounds in the water is one of the basic challenges of the researchers in sonar field. This challenge will be complex in shallow water (like Persian Gulf) and noise less vessels. Generally, in passive sonar the targets are detected by sonar equation (with constant threshold) which increase the detection error in shallow water. Purpose of this study is proposed a new method for detecting targets in passive sonars using adaptive threshold. In this method, target signal (sound) is processed in time and frequency domain. For classifying, Bayesian classification is used and prior distribution is estimated by Maximum Likelihood algorithm. Finally, target was detected by combining the detection points in both domains using LMS adaptive filter. Results of this paper has showed that proposed method has improved true detection rate about 27% compare other the best detection method.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Passive Sonar Target Detection Using Statistical Classifier and Adaptive Threshold

Alaie¹,

Farsi²

2017

Preprint

View full text Add to dashboard Cite

show abstract

“…After filtering, the signal is demodulated to obtain the contact propulsion. As the sampling frequency of the signal is so high with respect to the propulsion band, a resampling is performed so that the signal is transposed to the propulsion range where the propeller characteristics are more evident [10]. Then, a fast Fourier transform (STFFT -Short Time Fourier Transform) [11] is implemented to reach the spectrum.…”

Section: Propulsion Identificationmentioning

confidence: 99%

Improving the DEMON analysis using Independent Component Analysis

Moura¹,

Seixas²,

Fernandes³

2016

Anais Do 11. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

Abstract-Passive sonar systems used in submarines, performs the direction of arrival (DOA), the detection and classification of targets signals that are impinging on the hydrophones from a particular direction of interest. In some situations, depending on the resolution of the beamformer (hydrophones array) and when the signals are at too close bearings, a cross interference may bring difficult on the target identification by the operator of sonar. This paper aims at using independent component analysis (ICA) as preprocessing on DEMON analysis to improve the targets identification.The FastICA algorithm was used, which was applied to the simulated data, and performance was measured both, qualitatively and quantitatively.

show abstract

Deep Convolutional Neural Network Architectures for Tonal Frequency Identification in a Lofargram

Park

Jung

2020

Int. J. Control Autom. Syst.

View full text Add to dashboard Cite

Passive Sonar Signal Detection and Classification Based on Independent Component Analysis

Cited by 35 publications

References 21 publications

Passive Sonar Target Detection Using Statistical Classifier and Adaptive Threshold

Passive Sonar Target Detection Using Statistical Classifier and Adaptive Threshold

Improving the DEMON analysis using Independent Component Analysis

Deep Convolutional Neural Network Architectures for Tonal Frequency Identification in a Lofargram

Contact Info

Product

Resources

About