Resonance-Based Time-Frequency Manifold for Feature Extraction of Ship-Radiated Noise

Self Cite

For the purpose of improving the accuracy of underwater acoustic target recognition with only a small number of labeled data, we proposed a novel recognition method, including 4 steps: pre-processing, pre-training, fine-tuning and recognition. The 4 steps can be explained as follows: (1) Pre-processing with Resonance-based Sparsity Signal Decomposition (RSSD): RSSD was firstly utilized to extract high-resonance components from ship-radiated noise. The high-resonance components contain the major information for target recognition. (2) Pre-training with unsupervised feature-extraction: we proposed a one-dimensional convolution autoencoder-decoder model and then we pre-trained the model to extract features from the high-resonance components. (3) Fine-tuning with supervised feature-separation: a supervised feature-separation algorithm was proposed to fine-tune the model and separate the extracted features. (4) Recognition: classifiers were trained to recognize the separated features and complete the recognition mission. The unsupervised pre-training autoencoder-decoder can make good use of a large number of unlabeled data, so that only a small number of labeled data are required in the following supervised fine-tuning and recognition, which is quite effective when it is difficult to collect enough labeled data. The recognition experiments were all conducted on ship-radiated noise data recorded using a sensory hydrophone. By combining the 4 steps above, the proposed recognition method can achieve recognition accuracy of 93.28%, which sufficiently surpasses other traditional state-of-art feature-extraction methods.

Section: Resonance-based Sparsity Signal Decomposition For Pre-promentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Underwater Acoustic Target Recognition Based on Supervised Feature-Separation Algorithm

Yuan

Cheng

2018

Self Cite

“…It can improve the effectiveness and efficiency of the similarity measure by maintaining the characteristics of the original signal in a smaller dimensionality. Compared with principal component analysis (PCA) [27], linear discriminant analysis (LDA) [28] and other linear feature extraction methods, manifold learning [29], restricted Boltzmann machine (RBM) [30], autoencoder (AE) [31], as typical representatives of non-linear feature extraction methods, can retain much richer sample features of high-dimensional vibration signals. High computational complexity is the bottleneck of manifold learning based on local domain classification and its feature extraction process is sensitive to noise [32].…”

Section: Introductionmentioning

confidence: 99%

Combining SDAE Network with Improved DTW Algorithm for Similarity Measure of Ultra-Weak FBG Vibration Responses in Underground Structures

Zuo

et al. 2020

Quantifying structural status and locating structural anomalies are critical to tracking and safeguarding the safety of long-distance underground structures. Given the dynamic and distributed monitoring capabilities of an ultra-weak fiber Bragg grating (FBG) array, this paper proposes a method combining the stacked denoising autoencoder (SDAE) network and the improved dynamic time wrapping (DTW) algorithm to quantify the similarity of vibration responses. To obtain the dimensionality reduction features that were conducive to distance measurement, the silhouette coefficient was adopted to evaluate the training efficacy of the SDAE network under different hyperparameter settings. To measure the distance based on the improved DTW algorithm, the one nearest neighbor (1-NN) classifier was utilized to search the best constraint bandwidth. Moreover, the study proposed that the performance of different distance metrics used to quantify similarity can be evaluated through the 1-NN classifier. Based on two one-dimensional time-series datasets from the University of California, Riverside (UCR) archives, the detailed implementation process for similarity measure was illustrated. In terms of feature extraction and distance measure of UCR datasets, the proposed integrated approach of similarity measure showed improved performance over other existing algorithms. Finally, the field-vibration responses of the track bed in the subway detected by the ultra-weak FBG array were collected to determine the similarity characteristics of structural vibration among different monitoring zones. The quantitative results indicated that the proposed method can effectively quantify and distinguish the vibration similarity related to the physical location of structures.

“…For non-stationary signal processing, time-frequency analysis [7,8] is widely used to provide the joint distribution information of the time and frequency domains, and describe the relationship between signal frequency and time. In addition, based on the assumption that the signal is stationary in a short time duration, high-resolution spectral estimation methods can be used to obtain the spectrum with high frequency resolution using a short time series.…”

Section: Introductionmentioning

confidence: 99%

Passive Detection of Ship-Radiated Acoustic Signal Using Coherent Integration of Cross-Power Spectrum with Doppler and Time Delay Compensations

Guo

Piao

Guo

et al. 2020

Passive sonar is widely used for target detection, identification and classification based on the target radiated acoustic signal. Under the influence of Doppler, generated by relative motion between the moving target and the sonar array, the received ship-radiated acoustic signals are non-stationary and time-varying, which has a negative effect on target detection and other fields. In order to reduce the influence of Doppler and improve the performance of target detection, a coherent integration method based on cross-power spectrum is proposed in this paper. It can be concluded that the frequency shift and phase change in the cross-power spectrum obtained by each pair of data segments can be corrected with the compensations of time scale (Doppler) factor and time delay. Moreover, the time scale factor and time delay can be estimated from the amplitude and phase of the original cross-power spectrum, respectively. Therefore, coherent integration can be implemented with the compensated cross-power spectra. Simulation and experimental data processing results show that the proposed method can provide sufficient processing gains and effectively extract the discrete spectra for the detection of moving targets.