arXiv subjects

Longyu Jiang

Publications and source records attributed to Longyu Jiang.

6 recordsLinked to original sources

arXiv2025

Passive Underwater Acoustic Signal Separation based on Feature Decoupling Dual-path Network

Signal separation in the passive underwater acoustic domain has heavily relied on deep learning techniques to isolate ship radiated noise. However, the separation networks commonly used in this domain stem from speech separation applications and may not fully consider the unique aspects of underwater acoustics beforehand, such as the influence of different propagation media, signal frequencies and modulation characteristics. This oversight highlights the need for tailored approaches that account for the specific characteristics of underwater sound propagation. This study introduces a novel temporal network designed to separate ship radiated noise by employing a dual-path model and a feature decoupling approach. The mixed signals' features are transformed into a space where they exhibit greater independence, with each dimension's significance decoupled. Subsequently, a fusion of local and global attention mechanisms is employed in the separation layer. Extensive comparisons showcase the effectiveness of this method when compared to other prevalent network models, as evidenced by its performance in the ShipsEar and DeepShip datasets.

cs.SD↗

arXiv2021

Subspace-based compressive sensing algorithm for raypath separation in a shallow-water waveguide

Compressive sensing (CS) has been applied to estimate the direction of arrival (DOA) in underwater acoustics. However, the key problem needed to be resolved in a {multipath} propagation environment is to suppress the interferences between the raypaths. Thus, in this paper, {a subspace-based compressive sensing algorithm that formulates the statistic information of the signal subspace in a CS framework is proposed.} The experiment results show that (1) the proposed algorithm enables the separation of raypaths that arrive closely at the {receiver} array and (2) the existing algorithms fail, especially in a low signal-to-noise ratio (SNR) environment.

cs.SD↗

arXiv2020

The $X(2239)$ and $η(2225)$ as hidden-strange molecular states from $Λ\barΛ$ interaction

In this work, we propose a possible assignment of the newly observed $X(2239)$, as well as the $η(2225)$, as a molecular state from the interaction of a baryon $Λ$ and an antibaryon $\barΛ$. With the help of effective Lagrangians, the $Λ\barΛ$ interaction is described within the one-boson-exchange model with $η$, $η'$, $ω$, $ϕ$, and $σ$ exchanges considered. After inserting the potential kernel into the quasipotential Bethe-Salpeter equation, the bound states from the $Λ\barΛ$ interaction can be studied by searching for the pole of the scattering amplitude. Two loosely bound states with spin parities $I^G(J^{PC})=0^+(0^{-+})$ and $0^-(1^{--})$ appear near the threshold almost with the same parameter. The $0^-(1^{--})$ state can be assigned to the $X(2239)$ observed at BESIII, which is very close to the $Λ\barΛ$ threshold. The scalar meson $η(2225)$ can be interpreted as a $0^+(0^{-+})$ state from the $Λ\barΛ$ interaction. The annihilation effect is also discussed through a coupled-channel calculation plus a phenomenological optical potential. It provides large widths to two bound states produced from the $Λ\barΛ$ interaction. The mass of the $1^-$ state is a little larger than the mass of the $0^-$ state after including the annihilation effect, which is consistent with our assignment of these two states as $X(2239)$ and $η(2225)$, respectively. The results suggest that further investigation is expected to understand the structures near the $Λ\barΛ$ threshold, such as $X(2239)$, $η(2225)$, and $X(2175)$.

hep-ph↗

arXiv2016

PCANet: An energy perspective

The principal component analysis network (PCANet), which is one of the recently proposed deep learning architectures, achieves the state-of-the-art classification accuracy in various databases. However, the explanation of the PCANet is lacked. In this paper, we try to explain why PCANet works well from energy perspective point of view based on a set of experiments. The impact of various parameters on the error rate of PCANet is analyzed in depth. It was found that this error rate is correlated with the logarithm of energy of image. The proposed energy explanation approach can be used as a testing method for checking if every step of the constructed networks is necessary.

cs.CV↗

arXiv2015

Kernel principal component analysis network for image classification

In order to classify the nonlinear feature with linear classifier and improve the classification accuracy, a deep learning network named kernel principal component analysis network (KPCANet) is proposed. First, mapping the data into higher space with kernel principal component analysis to make the data linearly separable. Then building a two-layer KPCANet to obtain the principal components of image. Finally, classifying the principal components with linearly classifier. Experimental results show that the proposed KPCANet is effective in face recognition, object recognition and hand-writing digits recognition, it also outperforms principal component analysis network (PCANet) generally as well. Besides, KPCANet is invariant to illumination and stable to occlusion and slight deformation.

cs.LG↗

arXiv2014

Performance evaluation of wavelet scattering network in image texture classification in various color spaces

Texture plays an important role in many image analysis applications. In this paper, we give a performance evaluation of color texture classification by performing wavelet scattering network in various color spaces. Experimental results on the KTH_TIPS_COL database show that opponent RGB based wavelet scattering network outperforms other color spaces. Therefore, when dealing with the problem of color texture classification, opponent RGB based wavelet scattering network is recommended.

cs.CV↗