Class‐modular multi‐layer perceptron networks for supporting passive sonar signal classification

Filho, João B. O. Souza; Seixas, J. M.

doi:10.1049/iet-rsn.2015.0179

Cited by 13 publications

(10 citation statements)

References 20 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the present work, the passive sonar signal classification was developed in the context of the Brazilian Navy, which provided the classified experimental data. A variety of works has been developed with similar data, such as [14,19]. In [19], several preprocessing strategies were tested to improve the classification performance of a multi-layer perceptron multi-layer perceptron (MLP) operating on the ship's irradiated noise power spectrum.…”

Section: Related Workmentioning

confidence: 99%

“…Here, we employed different strategies for probing deeper on how the synthetic data generated by the GAN models might be included in the classifier training phase. The research hypothesis we follow refers to a design evaluation focused on class-expert GAN models, motivated by the results from [14], which showed that the class-expert solution was efficient in PSS context. Signal classification from the developed models takes into consideration the error bars coming from the data sample available.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Models for Passive Sonar Signal Classification of Military Data

Fernandes¹,

Moura²,

Seixas³

2022

Remote Sensing

View full text Add to dashboard Cite

The noise radiated from ships can be used for their identification and classification using passive sonar systems. Several techniques have been proposed for military ship classification based on acoustic signatures, which can be acquired through controlled experiments performed in an acoustic lane. The cost for such data acquisition is a significant issue since the ship and crew have to be dislocated from the fleet. In addition, the experiments have to be repeated for different operational conditions, taking a considerable amount of time. Even with this massive effort, the scarce amount of data produced by these controlled experiments may limit further detailed analyses. In this paper, deep learning models are used for full exploitation of such acquired data, envisaging passive sonar signal classification. A drawback of such models is the large number of parameters, which requires extensive data volumes for parameter tuning along the training phase. Thus, generative adversarial networks (GANs) are used to synthesize data so that a larger data volume can be produced for training convolutional neural networks (CNNs), which are used for the classification task. Different GAN design approaches were evaluated and both maximum probability and class-expert strategies were exploited for signal classification. Special attention was paid to how the expert knowledge might give a handle on analyzing the performance of the various deep learning models through tests that mirrored actual deployment. An accuracy as high as 99.0±0.4% was achieved using experimental data, which improves upon previous machine learning designs in the field.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Learning Models for Passive Sonar Signal Classification of Military Data

Fernandes¹,

Moura²,

Seixas³

2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…First, this method utilizes the deep neural network (DNN), a purely data-driven approach, to extract features from acoustic data for automatic depth estimation. Recently, many studies present applications of neural networks (NNs) to the underwater acoustic field, such as target localization [16][17][18] , classification [19][20][21][22] etc. According to the simulation and experimental results of the preceding literature, a well-trained NN has a competitive performance in comparison to conventional methods.…”

Section: Introductionmentioning

confidence: 99%

Target depth estimation by deep neural network based on acoustic interference structure in deep water

Guo

Duan

Yang

2022

IET Radar Sonar & Navi

View full text Add to dashboard Cite

Automatic and robust target depth estimation is an important issue of an active detection system working in the reliable acoustic path (RAP) environment. In this paper, the target depth-sensitive acoustic interference structure is used as input, and a deep neural network (DNN) method is proposed to realize automatic depth estimation. Furthermore, to improve the robustness of the network, both the sound speed profile (SSP) uncertainty and the target trajectory uncertainty are considered in the training dataset. The former is modelled as a random weighted sum of the empirical orthogonal function (EOF), and the latter is modelled by the partial-data-lacking of the network input. The method was evaluated through simulated data and compared with the conventional method of matching the measured interference structure with the replicas. The presented method exhibits a higher accuracy of depth estimate in uncertain environments when the signalto-noise ratio (SNR) is higher than −6 dB, but its performance deteriorates rapidly as the SNR decreases further. The method is also verified by semi-simulation with experimental data in deep water.

show abstract

“…Estas ferramentas podem auxiliar o trabalho do operador, aliviando o esforço de vigilância exigido, bem como permitir que sua atuação se concentre em situações de maior risco. Dentre elas, resultados promissores foram obtidos com as redes convolucionais [1], as redes neurais especialistas [2] e a técnica de curvas principais [3] na identificação de classes de contato.…”

Section: Introductionunclassified

Classificação Hierárquica de Navios em Sinais de Sonar Passivo

Muniz¹,

Filho²,

Oliveira³

2020

Anais Do 14. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

Resumo-A classificação de possíveis ameaças a submarinoś e realizada por operadores de sonar, que analisam as características tonais e espectrais dos ruídos adquiridos no ambiente aquático. Automatizar esta tarefa através da construção de sistemas automáticos de reconhecimento de classes e navios reduziria o desgaste físico e psíquico deste profissional. Este artigo discute a classificação de navios propondo um modelo de classificação hierárquica. Duas técnicas são avaliadas para a construção deste classificador: Random Forest e k-nearest neighbors. Resultados envolvendo sinais reais adquiridos de 28 navios apontam um melhor desempenho da técnica k-nearest neighbors.Keywords-sonar passivo; random forest; k-nearest neighbors; sistemas de apoioà decisão; aprendizagem de máquina

show abstract

Class‐modular multi‐layer perceptron networks for supporting passive sonar signal classification

Cited by 13 publications

References 20 publications

Deep Learning Models for Passive Sonar Signal Classification of Military Data

Deep Learning Models for Passive Sonar Signal Classification of Military Data

Target depth estimation by deep neural network based on acoustic interference structure in deep water

Classificação Hierárquica de Navios em Sinais de Sonar Passivo

Contact Info

Product

Resources

About