arXiv subjects

Yadong Liu

Publications and source records attributed to Yadong Liu.

29 records · Page 2Linked to original sources

arXiv2023

Algorithms for Object Detection in Substations

Inspection of high-voltage power equipment is an effective way to ensure power supply reliability. Object recognition, one of the key technologies in automatic power equipment inspection, attracts attention of many researchers and engineers. Although quite a few existing models have some their own advantages, object relationship between equipment which is very important in this task is scarcely considered. This paper combining object relationship modeling and Transformer Model proposes a Relation Transformer Model. It has four parts -- backbone, encoder, decoder and prediction heads. With this structure, the proposed method shows in experiments a much better performance than other three commonly used models in object recognition in substation, largely promoting the development of automatic power equipment inspection.

cs.CV↗

arXiv2022

Asymptotic behavior for 2D stochastic Navier-Stokes equations with memory in unbounded domains

We consider a stochastic model which describes the motion of a 2D incompressible fluid in a unbounded domain with viscosity and memory effects. This model is different from the classical stochastic Navier-Stokes-Voigt equations due to the absence of the Voigt term $ -αΔu_{t}$, and has a much weaker dissipation than the usual Navier-Stokes-Voigt model since only the memory viscoelasticity is present. We are interested in the global well-posedness and long-time behaviors of this model. We first investigate the well-posedness by using the classical Faedo-Galerkin method. Unlike the general method of energy estimate, we then split the solution into two parts and get the low-order and high-order uniform estimates, respectively. Based on the uniform estimates of far-field values of solutions, we further prove the existence and uniqueness of random attractors in unbounded domains with a constructed compact subspace corresponding to memory. Finally, we give the upper semicontinuity of the attractors when stochastic perturbation approaches to zero.

math.AP↗

arXiv2022

Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings

Inducing semantic representations directly from speech signals is a highly challenging task but has many useful applications in speech mining and spoken language understanding. This study tackles the unsupervised learning of semantic representations for spoken utterances. Through converting speech signals into hidden units generated from acoustic unit discovery, we propose WavEmbed, a multimodal sequential autoencoder that predicts hidden units from a dense representation of speech. Secondly, we also propose S-HuBERT to induce meaning through knowledge distillation, in which a sentence embedding model is first trained on hidden units and passes its knowledge to a speech encoder through contrastive learning. The best performing model achieves a moderate correlation (0.5~0.6) with human judgments, without relying on any labels or transcriptions. Furthermore, these models can also be easily extended to leverage textual transcriptions of speech to learn much better speech embeddings that are strongly correlated with human annotations. Our proposed methods are applicable to the development of purely data-driven systems for speech mining, indexing and search.

cs.CL↗

arXiv2022

Convolutional Neural Networks with A Topographic Representation Module for EEG-Based Brain-Computer Interfaces

Objective: Convolutional Neural Networks (CNNs) have shown great potential in the field of Brain-Computer Interfaces (BCIs). The raw Electroencephalogram (EEG) signal is usually represented as 2-Dimensional (2-D) matrix composed of channels and time points, which ignores the spatial topological information. Our goal is to make the CNN with the raw EEG signal as input have the ability to learn EEG spatial topological features, and improve its performance while essentially maintaining its original structure. Methods:We propose an EEG Topographic Representation Module (TRM). This module consists of (1) a mapping block from the raw EEG signal to a 3-D topographic map and (2) a convolution block from the topographic map to an output of the same size as input. According to the size of the kernel used in the convolution block, we design 2 types of TRMs, namely TRM-(5,5) and TRM-(3,3). We embed the TRM into 3 widely used CNNs, and tested them on 2 publicly available datasets (Emergency Braking During Simulated Driving Dataset (EBDSDD), and High Gamma Dataset (HGD)). Results: The results show that the classification accuracies of all 3 CNNs are improved on both datasets after using the TRM. With TRM-(5,5), the average accuracies of DeepConvNet, EEGNet and ShallowConvNet are improved by 6.54%, 1.72% and 2.07% on EBDSDD, and by 6.05%, 3.02% and 5.14% on HGD, respectively; with TRM-(3,3), they are improved by 7.76%, 1.71% and 2.17% on EBDSDD, and by 7.61%, 5.06% and 6.28% on HGD, respectively. Significance: We improve the classification performance of 3 CNNs on 2 datasets by the use of TRM, indicating that it has the capability to mine the EEG spatial topological information. In addition, since the output of TRM has the same size as the input, CNNs with the raw EEG signal as input can use this module without changing their original structures.

eess.SP↗

arXiv2022

EEG-Based Detection of Braking Intention During Simulated Driving

Accurately detecting and identifying drivers' braking intention is the basis of man-machine driving. In this paper, we proposed an electroencephalographic (EEG)-based braking intention measurement strategy. We used the Car Learning to Act (Carla) platform to build the simulated driving environment. 11 subjects participated in our study, and each subject drove a simulated vehicle to complete emergency braking and normal braking tasks. We compared the EEG topographic maps in different braking situations and used three different classifiers to predict the subjects' braking intention through EEG signals. The experimental results showed that the average response time of subjects in emergency braking was 762 ms; emergency braking and no braking can be well distinguished, while normal braking and no braking were not easy to be classified; for the two different types of braking, emergency braking and normal braking had obvious differences in EEG topographic maps, and the classification results also showed that the two were highly distinguishable. This study provides a user-centered driver-assistance system and a good framework to combine with advanced shared control algorithms, which has the potential to be applied to achieve a more friendly interaction between the driver and vehicle in real driving environment.

cs.HC↗

arXiv2022

Short time existence of a quasi-stationary fluid-structure interaction problem for plaque growth

We address a quasi-stationary fluid-structure interaction problem coupled with cell reactions and growth, which comes from the plaque formation during the stage of the atherosclerotic lesion in human arteries. The blood is modeled by the incompressible Navier--Stokes equation, while the motion of vessels is captured by a quasi-stationary equation of nonlinear elasticity. The growth happens when both cells in fluid and solid react, diffuse and transport across the interface, resulting in the accumulation of foam cells, which are exactly seen as the plaques. Via a fixed-point argument, we derive the local well-posedness of the nonlinear system, which is sustained by the analysis of decoupled linear systems.

math.AP↗

arXiv2021

On a fluid-structure interaction problem for plaque growth: cylindrical domain

This paper concerns a free-boundary fluid-structure interaction problem for plaque growth proposed by Yang et al. [J. Math. Biol., 72(4):973--996, 2016] with additional viscoelastic effects, which was also investigated by the authors [arXiv preprint: 2110.00042, 2021]. Compared to it, the problem is posed in a cylindrical domain with ninety-degree contact angles, which brings additional difficulties when we deal with the linearization of the system By a reflection argument, we obtain the existence and uniqueness of strong solutions to the model problems for the linear systems, which are then shown to be well-posed in a cylindrical (annular) domain via a localization procedure. Finally, we prove that the full nonlinear system admits a unique strong solution locally with the aid of the contraction mapping principle.

math.AP↗

arXiv2021

On a fluid-structure interaction problem for plaque growth

We study a free-boundary fluid-structure interaction problem with growth, which arises from the plaque formation in blood vessels. The fluid is described by the incompressible Navier-Stokes equation, while the structure is considered as a viscoelastic incompressible neo-Hookean material. Moreover, the growth due to the biochemical process is taken into account. Applying the maximal regularity theory to a linearization of the equations, along with a deformation mapping, we prove the well-posedness of the full nonlinear problem via the contraction mapping principle.

math.AP↗

arXiv2021

Existence of weak solutions to a generalized nonlinear multi-layered fluid-structure interaction problem with the Navier-slip boundary conditions

We consider a fluid-structure interaction problem with Navier-slip boundary conditions in which the fluid is considered as a non-Newtonian fluid and the structure is described by a nonlinear multi-layered model. The fluid domain is driven by a nonlinear elastic shell and thus is not fixed. To simplify the problem, we map the moving fluid domain into a fixed domain by applying an arbitrary Lagrange Euler mapping. Unlike the classical method by which we can consider the problem as its entirety, we utilize the time-discretization and split the problem into a fluid subproblem and a structure subproblem by an operator splitting scheme. Since the structure subproblem is nonlinear, Lax-Milgram lemma does not hold. Here we prove the existence and uniqueness by means of the traditional semigroup theory. Noticing that the Non-Newtonian fluid possesses a $ p- $Laplacian structure, we show the existence and uniqueness of solutions to the fluid subproblem by considering the Browder-Minty theorem. With the uniform energy estimates, we deduce the weak and weak* convergence respectively. By a generalized Aubin-Lions-Simon Lemma proposed by Muha and Canić [J. Differential Equations {\bf 266} (2019), 8370--8418], we obtain the strong convergence. Finally, we construct the test functions and pass the approximate weak formulation to the limit as time step goes to zero with the convergence results.

math.AP↗

arXiv2020

Ultra2Speech -- A Deep Learning Framework for Formant Frequency Estimation and Tracking from Ultrasound Tongue Images

Thousands of individuals need surgical removal of their larynx due to critical diseases every year and therefore, require an alternative form of communication to articulate speech sounds after the loss of their voice box. This work addresses the articulatory-to-acoustic mapping problem based on ultrasound (US) tongue images for the development of a silent-speech interface (SSI) that can provide them with an assistance in their daily interactions. Our approach targets automatically extracting tongue movement information by selecting an optimal feature set from US images and mapping these features to the acoustic space. We use a novel deep learning architecture to map US tongue images from the US probe placed beneath a subject's chin to formants that we call, Ultrasound2Formant (U2F) Net. It uses hybrid spatio-temporal 3D convolutions followed by feature shuffling, for the estimation and tracking of vowel formants from US images. The formant values are then utilized to synthesize continuous time-varying vowel trajectories, via Klatt Synthesizer. Our best model achieves R-squared (R^2) measure of 99.96% for the regression task. Our network lays the foundation for an SSI as it successfully tracks the tongue contour automatically as an internal representation without any explicit annotation.

eess.IV↗

arXiv2017

Massive Streaming PMU Data Modeling and Analytics in Smart Grid State Evaluation Based on Multiple High-Dimensional Covariance Tests

The analogous deployment of phase measurement units (PMUs), the increase of data quantum and the deregulation of energy market, all call for the robust state evaluation in large scale power systems. Implementing model based estimators is impractical because of the complexity scale of solving the high dimension power flow equations. In this paper, we first represent massive streaming PMU data as big random matrix flow. By exploiting the variations in the covariance matrix of the massive streaming PMU data, a novel power state evaluation algorithm is then developed based on the multiple high dimensional covariance matrix tests. The proposed test statistic is flexible and nonparametric, which assumes no specific parameter distribution or dimension structure for the PMU data. Besides, it can jointly reveal the relative magnitude, duration and location of a system event. For the sake of practical application, we reduce the computation of the proposed test statistic from $O(\varepsilon n_g^4)$ to $O(ηn_g^2)$ by principal component calculation and redundant computation elimination. The novel algorithm is numerically evaluated utilizing the IEEE 30-, 118-bus system, a Polish 2383-bus system, and a real 34-PMU system. The case studies illustrate and verify the superiority of proposed state evaluation indicator.

stat.AP↗