This series of papers deals with vessel recognition. The project is conducted by using fuzzy neural networks and basing on the spectra of vessel radiated-noise. This paper is the last in the series. It deals with the ...This series of papers deals with vessel recognition. The project is conducted by using fuzzy neural networks and basing on the spectra of vessel radiated-noise. This paper is the last in the series. It deals with the application of fuzzy neural network to the recognition of targets. The neural network is a multi-layered forward network and the learning algorithm is BP (error Back Propagation). In the paper, the adust formula of parameter of fuzzier is given. The paper provides a recognition result which is drawn from 1049 samples gathered from 41 vessels in 63 operating conditions, with an original recording time of about 3.5 hours. The identifications are more than 92% correct.展开更多
This series of papers deal with vessels-target recognition. The project is conducted by using fuzzy neuraI networks and basing recognition on the spectra of vessel radiated-noise. Paper (Ⅰ) describes the characterist...This series of papers deal with vessels-target recognition. The project is conducted by using fuzzy neuraI networks and basing recognition on the spectra of vessel radiated-noise. Paper (Ⅰ) describes the characteristics of vessel radiated-noise spectra, which are composed of two distinctive categories: the stationary and the non-stationary. The project framework is introduced in the paper. It includes two steps. One is to extract effectively recognizable features (those common in one category and those distinguish categories). The other is to memorize the characteristics of specific vessel targets. The memorization is realized with characteristics pattern plate library of specific vessels (including line spectrum, double-frequency spectrum and average power spectrum pattern plate library). Detailed discussions on theories, models, parameter analysis, line-spectrum extraction methods, as well as gaps between reality and theory concerning vessels radiated-noise are also included in Paper (Ⅰ). Paper (Ⅰ) finally proposes a method of automatic extraction of line spectrum by using machines. Paper (Ⅱ) will discuss the stability, uniqueness of line spectrum and its pattern plate. Paper (Ⅲ) will focus on the extraction of features from double-frequency spectrum and average power spectrum, and the establishment of their pattern plates. Paper (Ⅳ) will discuss fuzzy neural networks and recognition approaches展开更多
This series of papers deal with vessel recoghtion. This paper is the second of the paper series. It focuses on how to memorize the stable features of line spectrum of specific vessels by using line spectrum pattern p...This series of papers deal with vessel recoghtion. This paper is the second of the paper series. It focuses on how to memorize the stable features of line spectrum of specific vessels by using line spectrum pattern plate and on related problems. This paper examines the analyzing parameters of line spectrum: average times, time length and their impact on the occurrence of stable lines. It compares the impact of two dtherellt average times on the occurrence of stable lines (occurrence ratio > 70%) and unstable lines, and shows that it takes longer time span for average when stable lines for recoghtion are used. Moreover, the paper discusses the statistic methods of establishing line spectrum pattern plate usihg stable lines,including the definition of stability and related para-meters. The stability of line spectrum and the uniqueness of stable lines are investigated in over 1000 samples gathered from 43 vessels in 65 operating conditions (with an original recording time of 3.5 hours). The results demonstrate the statistical implication of such uniqueness. The average overlapping ratio is 5 %; the proportion of vessels without stable lines is 8 %. Studies also show that the richness of line spectrums is not an identifying feature, distinguishing type A vessels from type B vessels展开更多
This series of papers deal with vessel recognition. The project is conducted by using fuzzy neural networks and basing on the spectra of vessel radiated-noise. Based on the studies of a large amount of ship radiat...This series of papers deal with vessel recognition. The project is conducted by using fuzzy neural networks and basing on the spectra of vessel radiated-noise. Based on the studies of a large amount of ship radiated-noise data, which has been collected from actual ships on the sea, effectively recognizable features are extracted. Such features include line-spectrum features, stationary and nonstationary spectrum features as well as rhythm features. Finally the categorization are tested by unknown samples on the sea, including 33 surface vessels, 8 underwater vessels in 30 operating conditions. Methods for memorization and classilication are also explored in the project. Paper (Ⅲ) is the thirird in the series. It deals with the extraction method of modulation information in double-frequency power spectrum and the establishment of pattern plate of double-frequency spectrum as well as average power spectrum. To extract features from double-frequency spectrum, the tendency of wave is subtracted from the wave of each channel and the modulation of high frequency is compensated. The modulation degree of lines is shown by relative Value and converted to fuzzy value by fuzzy function. The pattern-plate of double-frequency spectrum memorises stable line and its respective modulation strength. The pattern-plate of average power spectrum memorizes the spectra mean of typical samples and the standard variance展开更多
A new algorithm based on a Supervised Self-Organizing neural network for the pas sive sonar target recognition was proposed. Because of the incompleteness of the passive sonar exemplar set, the algorithm introduced a ...A new algorithm based on a Supervised Self-Organizing neural network for the pas sive sonar target recognition was proposed. Because of the incompleteness of the passive sonar exemplar set, the algorithm introduced a Multi-Activation-function structure and Supervised Self-Organizing competitive learning algorithm into the classic feed-forward neural networks,and obviously improved the generalization ability in target recognition. Besides, it can effi ciently reduce the learning time and avoid the local optimum. The recognition experiments of realistic passive sonar signals show that this new algorithm has good generalization ability and high recognition rate展开更多
Traditional direction of arrival(DOA)estimation methods based on sparse reconstruction commonly use convex or smooth functions to approximate non-convex and non-smooth sparse representation problems.This approach ofte...Traditional direction of arrival(DOA)estimation methods based on sparse reconstruction commonly use convex or smooth functions to approximate non-convex and non-smooth sparse representation problems.This approach often introduces errors into the sparse representation model,necessitating the development of improved DOA estimation algorithms.Moreover,conventional DOA estimation methods typically assume that the signal coincides with a predetermined grid.However,in reality,this assumption often does not hold true.The likelihood of a signal not aligning precisely with the predefined grid is high,resulting in potential grid mismatch issues for the algorithm.To address the challenges associated with grid mismatch and errors in sparse representation models,this article proposes a novel high-performance off-grid DOA estimation approach based on iterative proximal projection(IPP).In the proposed method,we employ an alternating optimization strategy to jointly estimate sparse signals and grid offset parameters.A proximal function optimization model is utilized to address non-convex and non-smooth sparse representation problems in DOA estimation.Subsequently,we leverage the smoothly clipped absolute deviation penalty(SCAD)function to compute the proximal operator for solving the model.Simulation and sea trial experiments have validated the superiority of the proposed method in terms of higher resolution and more accurate DOA estimation performance when compared to both traditional sparse reconstruction methods and advanced off-grid techniques.展开更多
文摘This series of papers deals with vessel recognition. The project is conducted by using fuzzy neural networks and basing on the spectra of vessel radiated-noise. This paper is the last in the series. It deals with the application of fuzzy neural network to the recognition of targets. The neural network is a multi-layered forward network and the learning algorithm is BP (error Back Propagation). In the paper, the adust formula of parameter of fuzzier is given. The paper provides a recognition result which is drawn from 1049 samples gathered from 41 vessels in 63 operating conditions, with an original recording time of about 3.5 hours. The identifications are more than 92% correct.
文摘This series of papers deal with vessels-target recognition. The project is conducted by using fuzzy neuraI networks and basing recognition on the spectra of vessel radiated-noise. Paper (Ⅰ) describes the characteristics of vessel radiated-noise spectra, which are composed of two distinctive categories: the stationary and the non-stationary. The project framework is introduced in the paper. It includes two steps. One is to extract effectively recognizable features (those common in one category and those distinguish categories). The other is to memorize the characteristics of specific vessel targets. The memorization is realized with characteristics pattern plate library of specific vessels (including line spectrum, double-frequency spectrum and average power spectrum pattern plate library). Detailed discussions on theories, models, parameter analysis, line-spectrum extraction methods, as well as gaps between reality and theory concerning vessels radiated-noise are also included in Paper (Ⅰ). Paper (Ⅰ) finally proposes a method of automatic extraction of line spectrum by using machines. Paper (Ⅱ) will discuss the stability, uniqueness of line spectrum and its pattern plate. Paper (Ⅲ) will focus on the extraction of features from double-frequency spectrum and average power spectrum, and the establishment of their pattern plates. Paper (Ⅳ) will discuss fuzzy neural networks and recognition approaches
文摘This series of papers deal with vessel recoghtion. This paper is the second of the paper series. It focuses on how to memorize the stable features of line spectrum of specific vessels by using line spectrum pattern plate and on related problems. This paper examines the analyzing parameters of line spectrum: average times, time length and their impact on the occurrence of stable lines. It compares the impact of two dtherellt average times on the occurrence of stable lines (occurrence ratio > 70%) and unstable lines, and shows that it takes longer time span for average when stable lines for recoghtion are used. Moreover, the paper discusses the statistic methods of establishing line spectrum pattern plate usihg stable lines,including the definition of stability and related para-meters. The stability of line spectrum and the uniqueness of stable lines are investigated in over 1000 samples gathered from 43 vessels in 65 operating conditions (with an original recording time of 3.5 hours). The results demonstrate the statistical implication of such uniqueness. The average overlapping ratio is 5 %; the proportion of vessels without stable lines is 8 %. Studies also show that the richness of line spectrums is not an identifying feature, distinguishing type A vessels from type B vessels
文摘This series of papers deal with vessel recognition. The project is conducted by using fuzzy neural networks and basing on the spectra of vessel radiated-noise. Based on the studies of a large amount of ship radiated-noise data, which has been collected from actual ships on the sea, effectively recognizable features are extracted. Such features include line-spectrum features, stationary and nonstationary spectrum features as well as rhythm features. Finally the categorization are tested by unknown samples on the sea, including 33 surface vessels, 8 underwater vessels in 30 operating conditions. Methods for memorization and classilication are also explored in the project. Paper (Ⅲ) is the thirird in the series. It deals with the extraction method of modulation information in double-frequency power spectrum and the establishment of pattern plate of double-frequency spectrum as well as average power spectrum. To extract features from double-frequency spectrum, the tendency of wave is subtracted from the wave of each channel and the modulation of high frequency is compensated. The modulation degree of lines is shown by relative Value and converted to fuzzy value by fuzzy function. The pattern-plate of double-frequency spectrum memorises stable line and its respective modulation strength. The pattern-plate of average power spectrum memorizes the spectra mean of typical samples and the standard variance
文摘A new algorithm based on a Supervised Self-Organizing neural network for the pas sive sonar target recognition was proposed. Because of the incompleteness of the passive sonar exemplar set, the algorithm introduced a Multi-Activation-function structure and Supervised Self-Organizing competitive learning algorithm into the classic feed-forward neural networks,and obviously improved the generalization ability in target recognition. Besides, it can effi ciently reduce the learning time and avoid the local optimum. The recognition experiments of realistic passive sonar signals show that this new algorithm has good generalization ability and high recognition rate
基金supported by the National Science Foundation for Distinguished Young Scholars(Grant No.62125104)the National Natural Science Foundation of China(Grant No.52071111).
文摘Traditional direction of arrival(DOA)estimation methods based on sparse reconstruction commonly use convex or smooth functions to approximate non-convex and non-smooth sparse representation problems.This approach often introduces errors into the sparse representation model,necessitating the development of improved DOA estimation algorithms.Moreover,conventional DOA estimation methods typically assume that the signal coincides with a predetermined grid.However,in reality,this assumption often does not hold true.The likelihood of a signal not aligning precisely with the predefined grid is high,resulting in potential grid mismatch issues for the algorithm.To address the challenges associated with grid mismatch and errors in sparse representation models,this article proposes a novel high-performance off-grid DOA estimation approach based on iterative proximal projection(IPP).In the proposed method,we employ an alternating optimization strategy to jointly estimate sparse signals and grid offset parameters.A proximal function optimization model is utilized to address non-convex and non-smooth sparse representation problems in DOA estimation.Subsequently,we leverage the smoothly clipped absolute deviation penalty(SCAD)function to compute the proximal operator for solving the model.Simulation and sea trial experiments have validated the superiority of the proposed method in terms of higher resolution and more accurate DOA estimation performance when compared to both traditional sparse reconstruction methods and advanced off-grid techniques.
