arXiv subjects

Juan Liu

Publications and source records attributed to Juan Liu.

At least 73 records · Page 4Linked to original sources

arXiv2020

An Early Study on Intelligent Analysis of Speech under COVID-19: Severity, Sleep Quality, Fatigue, and Anxiety

The COVID-19 outbreak was announced as a global pandemic by the World Health Organisation in March 2020 and has affected a growing number of people in the past few weeks. In this context, advanced artificial intelligence techniques are brought to the fore in responding to fight against and reduce the impact of this global health crisis. In this study, we focus on developing some potential use-cases of intelligent speech analysis for COVID-19 diagnosed patients. In particular, by analysing speech recordings from these patients, we construct audio-only-based models to automatically categorise the health state of patients from four aspects, including the severity of illness, sleep quality, fatigue, and anxiety. For this purpose, two established acoustic feature sets and support vector machines are utilised. Our experiments show that an average accuracy of .69 obtained estimating the severity of illness, which is derived from the number of days in hospitalisation. We hope that this study can foster an extremely fast, low-cost, and convenient way to automatically detect the COVID-19 disease.

eess.AS↗

arXiv2020

COVID-19 and Computer Audition: An Overview on What Speech & Sound Analysis Could Contribute in the SARS-CoV-2 Corona Crisis

At the time of writing, the world population is suffering from more than 10,000 registered COVID-19 disease epidemic induced deaths since the outbreak of the Corona virus more than three months ago now officially known as SARS-CoV-2. Since, tremendous efforts have been made worldwide to counter-steer and control the epidemic by now labelled as pandemic. In this contribution, we provide an overview on the potential for computer audition (CA), i.e., the usage of speech and sound analysis by artificial intelligence to help in this scenario. We first survey which types of related or contextually significant phenomena can be automatically assessed from speech or sound. These include the automatic recognition and monitoring of breathing, dry and wet coughing or sneezing sounds, speech under cold, eating behaviour, sleepiness, or pain to name but a few. Then, we consider potential use-cases for exploitation. These include risk assessment and diagnosis based on symptom histograms and their development over time, as well as monitoring of spread, social distancing and its effects, treatment and recovery, and patient wellbeing. We quickly guide further through challenges that need to be faced for real-life usage. We come to the conclusion that CA appears ready for implementation of (pre-)diagnosis and monitoring tools, and more generally provides rich and significant, yet so far untapped potential in the fight against COVID-19 spread.

cs.SD↗

arXiv2020

Deep Reinforcement Learning for Fresh Data Collection in UAV-assisted IoT Networks

Due to the flexibility and low operational cost, dispatching unmanned aerial vehicles (UAVs) to collect information from distributed sensors is expected to be a promising solution in Internet of Things (IoT), especially for time-critical applications. How to maintain the information freshness is a challenging issue. In this paper, we investigate the fresh data collection problem in UAV-assisted IoT networks. Particularly, the UAV flies towards the sensors to collect status update packets within a given duration while maintaining a non-negative residual energy. We formulate a Markov Decision Process (MDP) to find the optimal flight trajectory of the UAV and transmission scheduling of the sensors that minimizes the weighted sum of the age of information (AoI). A UAV-assisted data collection algorithm based on deep reinforcement learning (DRL) is further proposed to overcome the curse of dimensionality. Extensive simulation results demonstrate that the proposed DRL-based algorithm can significantly reduce the weighted sum of the AoI compared to other baseline algorithms.

cs.IT↗

arXiv2019

Meta-QSM: An Image-Resolution-Arbitrary Network for QSM Reconstruction

Quantitative Susceptibility Mapping (QSM) can estimate the underlying tissue magnetic susceptibility and reveal pathology. Current deep-learning-based approaches to solve the QSM inverse problem are restricted on fixed image resolution. They trained a specific model for each image resolution which is inefficient in computing. In this work, we proposed a novel method called Meta-QSM to firstly solve QSM reconstruction of arbitrary image resolution with a single model. In Meta-QSM, weight prediction was used to predict the weights of kernels by taking the image resolution as input. The proposed method was evaluated on synthetic data and clinical data with comparison to existing QSM reconstruction methods. The experimental results showed the Meta-QSM can effectively reconstruct susceptibility maps with different image resolution using one neural network training.

physics.med-ph↗

arXiv2019

Deep Quantitative Susceptibility Mapping for Background Field Removal and Total Field Inversion

Quantitative susceptibility mapping (QSM) utilizes MRI signal phase to estimate local tissue susceptibility, which has been shown useful to provide novel image contrast and as biomarkers of abnormal tissue. QSM requires addressing a challenging post-processing problem: filtering of image phase estimates and inversion of the phase to susceptibility relationship. A wide variety of quantification errors, robustness limitations, and artifacts constraints QSM clinical translation. To overcome these limitations, a robust deep-learning-based QSM reconstruction approach is proposed to perform background field removal and susceptibility inversion simultaneously from input MRI phase images. Synthetic training data based on in-vivo data sources and physics simulations were used for training. The network was quantitatively tested using gold-standard in-silico labeled dataset against established background field removal and QSM inversion approaches. In addition, the algorithm was applied to a QSM challenge data and clinical susceptibility-weighted imaging (SWI) data. When quantitatively compared against gold-standard in-silico labels, the proposed algorithm outperformed the existing comparable background field removal approaches and QSM reconstruction algorithms. The QSM challenge data and clinical SWI data demonstrated that the proposed approach was able to robustly generate high quality local field and QSM with improved accuracy.

physics.med-ph↗

arXiv2019

Non-locally Encoder-Decoder Convolutional Network for Whole Brain QSM Inversion

Quantitative Susceptibility Mapping (QSM) reconstruction is a challenging inverse problem driven by ill conditioning of its field-to -susceptibility transformation. State-of-art QSM reconstruction methods either suffer from image artifacts or long computation times, which limits QSM clinical translation efforts. To overcome these limitations, a non-locally encoder-decoder gated convolutional neural network is trained to infer whole brain susceptibility map, using the local field and brain mask as the inputs. The performance of the proposed method is evaluated relative to synthetic data, a publicly available challenge dataset, and clinical datasets. The proposed approach can outperform existing methods on quantitative metrics and visual assessment of image sharpness and streaking artifacts. The estimated susceptibility maps can preserve conspicuity of fine features and suppress streaking artifacts. The demonstrated methods have potential value in advancing QSM clinical research and aiding in the translation of QSM to clinical operations.

cs.AI↗

arXiv2019

MRI Tissue Magnetism Quantification through Total Field Inversion with Deep Neural Networks

Quantitative susceptibility mapping (QSM) utilizes MRI signal phase to infer estimates of local tissue magnetism (magnetic susceptibility), which has been shown useful to provide novel image contrast and as biomarkers of abnormal tissue. QSM requires addressing a challenging post-processing problem: filtering of image phase estimates and inversion of the phase to susceptibility relationship. A wide variety of quantification errors, robustness limitations, and artifacts plague QSM algorithms. To overcome these limitations, a robust deep-learning-based single-step QSM reconstruction approach is proposed and demonstrated. This neural network was trained using magnetostatic physics simulations based on in-vivo data sources. Random perturbations were added to the physics simulations to provide sufficient input-label pairs for the training purposes. The network was quantitatively tested using gold-standard in-silico labeled datasets against established QSM total field inversion approaches. In addition, the algorithm was applied to susceptibility-weighted imaging (SWI) data collected on a cohort of clinical subjects with brain hemmhorage. When quantitatively compared against gold-standard in-silico labels, the proposed algorithm outperformed the existing comparable approaches. High quality QSM were consistently estimated from clinical susceptibility-weighted data on 100 subjects without any noticeable inversion failures. The proposed approach was able to robustly generate high quality QSM with improved accuracy in in-silico gold-standard experiments. QSM produced by the proposed method can be generated in real-time on existing MRI scanner platforms and provide enhanced visualization and quantification of magnetism-based tissue contrasts.

physics.med-ph↗

arXiv2019

Selective Diffraction with Complex Amplitude Modulation by Dielectric Metasurfaces

Metasurfaces have attracted extensive interests due to their ability to locally manipulate optical parameters of light and easy integration to complex optical systems. Particularly, metasurfaces can provide a novel platform for splitting and diffracting light into several beams with desired profile, which is in contrast to traditional gratings. Here, we propose and experimentally demonstrate a novel method for generating independently selective diffraction orders. Our method is based on complex amplitude modulation with ultrathin dielectric metasurfaces. By tailoring the geometric parameters of silicon nanofin structures, we can spatially control the geometric and dynamic phase as well as the amplitude simultaneously. We compare the results with a metasurface that uses a phase-only modulation, to verify such selective diffraction can be solely efficiently achieved with complex amplitude modulation. Besides, the diffraction angles of each order have been measured, which are consistent with standard grating theory. Our developed method for achieving selective diffraction with metasurfaces has potential applications in beam shaping, parallel laser fabrication, and nanoscale optical detection.

physics.optics↗

arXiv2019

An inverse medium problem using Stekloff eigenvalues and a Bayesian approach

This paper studies the reconstruction of Stekloff eigenvalues and the index of refraction of an inhomogeneous medium from Cauchy data. The inverse spectrum problem to reconstruct Stekloff eigenvalues is investigated using a new integral equation for the reciprocity gap method. Given reconstructed eigenvalues, a Bayesian approach is proposed to estimate the index of refraction. Moreover, since it is impossible to know the multiplicities of the reconstructed eigenvalues and since the eigenvalues can be complex, we employ the recently developed spectral indicator method to compute Stekloff eigenvalues. Numerical experiments validate the effectiveness of the proposed methods.

math-ph↗

arXiv2019

Quantitative Susceptibility Inversion Through Parcellated Multiresolution Neural Networks and K-Space Substitution

Purpose: Quantitative Susceptibility Mapping (QSM) reconstruction is a challenging inverse problem driven by poor conditioning of the field to susceptibility transformation. State-of-art QSM reconstruction methods either suffer from image artifacts or long computation times, which limits QSM clinical translation efforts. To overcome these limitations, a deep-learning-based approach is proposed and demonstrated. Methods: An encoder-decoder neural network was trained to infer susceptibility maps on volume parcellated regions. The training data consisted of fabricated susceptibility distributions modeled to mimic the spatial frequency patterns of in-vivo brain susceptibility distributions. Inferred volume parcels were recombined to form composite QSM. This approach is denoted as ASPEN, standing for Approximated Susceptibility through Parcellated Encoder-decoder Networks. ASPEN performance was evaluated relative to several well-established approaches on a gold-standard challenge dataset and on cohort of 200 study subjects. Results: ASPEN provided similar levels of quantitative accuracy compared to the evaluated established approaches on the gold standard ISMRM Challenge dataset, but qualitatively showed marked reductions in streaking artifacts and map blurring. On the large-cohort dataset, ASPEN achieved the highest score compared with other methods in a multi-rater evaluation of streaking artifacts and map resolution. Conclusion: The proposed ASPEN approach can robustly infer susceptibility maps in near real-time on routine computational hardware. This preliminary study establishes ASPEN's parity with existing approaches for quantitative accuracy on a well-curated gold standard dataset and further demonstrates its robustness to streaking artifacts across a large cohort of subjects.

physics.med-ph↗

arXiv2018

Group-sparse SVD Models and Their Applications in Biological Data

Sparse Singular Value Decomposition (SVD) models have been proposed for biclustering high dimensional gene expression data to identify block patterns with similar expressions. However, these models do not take into account prior group effects upon variable selection. To this end, we first propose group-sparse SVD models with group Lasso (GL1-SVD) and group L0-norm penalty (GL0-SVD) for non-overlapping group structure of variables. However, such group-sparse SVD models limit their applicability in some problems with overlapping structure. Thus, we also propose two group-sparse SVD models with overlapping group Lasso (OGL1-SVD) and overlapping group L0-norm penalty (OGL0-SVD). We first adopt an alternating iterative strategy to solve GL1-SVD based on a block coordinate descent method, and GL0-SVD based on a projection method. The key of solving OGL1-SVD is a proximal operator with overlapping group Lasso penalty. We employ an alternating direction method of multipliers (ADMM) to solve the proximal operator. Similarly, we develop an approximate method to solve OGL0-SVD. Applications of these methods and comparison with competing ones using simulated data demonstrate their effectiveness. Extensive applications of them onto several real gene expression data with gene prior group knowledge identify some biologically interpretable gene modules.

stat.ML↗

arXiv2018

Joint Queue-Aware and Channel-Aware Delay Optimal Scheduling of Arbitrarily Bursty Traffic over Multi-State Time-Varying Channels

This paper is motivated by the observation that the average queueing delay can be decreased by sacrificing power efficiency in wireless communications. In this sense, we naturally wonder what is the minimum queueing delay when the available power is limited and how to achieve the minimum queueing delay. To answer these two questions in the scenario where randomly arriving packets are transmitted over multi-state wireless fading channel, a probabilistic cross-layer scheduling policy is proposed in this paper, and characterized by a constrained Markov Decision Process (MDP). Using the steady-state probability of the underlying Markov chain, we are able to derive the mathematical expressions of the concerned metrics, namely, the average queueing delay and the average power consumption. To describe the delay-power tradeoff, we formulate a non-linear programming problem, which, however, is very challenging to solve. By analyzing its structure, this optimization problem can be converted into an equivalent Linear Programming (LP) problem via variable substitution, which allows us to derive the optimal delay-power tradeoff as well as the optimal scheduling policy. The optimal scheduling policy turns out to be dual-threshold-based, which means transmission decisions should be made based on the optimal thresholds imposed on the queue length and the channel state.

cs.IT↗

arXiv2018

Extended Sampling Method in Inverse Scattering

A new sampling method for inverse scattering problems is proposed to process far field data of one incident wave. As the linear sampling method, the method sets up ill-posed integral equations and uses the (approximate) solutions to reconstruct the target. In contrast, the kernels of the associated integral operators are the far field patterns of sound soft balls. The measured data is moved to right hand sides of the equations, which gives the method the ability to process limit aperture data. Furthermore, a multilevel technique is employed to improve the reconstruction. Numerical examples show that the method can effectively determine the location and approximate the support with little a priori information of the unknown target.

math.AP↗

arXiv2018

Age-Optimal Trajectory Planning for UAV-Assisted Data Collection

Unmanned aerial vehicle (UAV)-aided data collection is a new and promising application in many practical scenarios. In this work, we study the age-optimal trajectory planning problem in UAV-enabled wireless sensor networks, where a UAV is dispatched to collect data from the ground sensor nodes (SNs). The age of information (AoI) collected from each SN is characterized by the data uploading time and the time elapsed since the UAV leaves this SN. We attempt to design two age-optimal trajectories, referred to as the Max-AoI-optimal and Ave-AoI-optimal trajectories, respectively. The Max-AoI-optimal trajectory planning is to minimize the age of the `oldest' sensed information among the SNs. The Ave-AoI-optimal trajectory planning is to minimize the average AoI of all the SNs. Then, we show that each age-optimal flight trajectory corresponds to a shortest Hamiltonian path in the wireless sensor network where the distance between any two SNs represents the amount of inter-visit time. The dynamic programming (DP) method and genetic algorithm (GA) are adopted to find the two different age-optimal trajectories. Simulation results validate the effectiveness of the proposed methods, and show how the UAV's trajectory is affected by the two AoI metrics.

cs.IT↗

arXiv2018

Spectral Indicator Method for A Non-selfadjoint Steklov Eigenvalue Problem

We propose an efficient numerical method for a non-selfadjoint Steklov eigenvalue problem. The Lagrange finite element is used for discretization. The convergence is proved using the spectral perturbation theory for compact operators. The non-sefadjointness of the problem leads to non-Hermitian matrix eigenvalue problem. Due to the existence of complex eigenvalues and lack of a priori spectral information, we propose a modified version of the recently developed spectral indicator method to compute (complex) eigenvalues in a given region on the complex plane. In particular, to reduce computational cost, the problem is transformed into a much smaller matrix eigenvalue problem involving the unknowns only on the boundary of the domain. Numerical examples are presented to validate the effectiveness of the proposed method.

math.NA↗

arXiv2018

Concave/convex switchable lens using active phase-change material Ge3Sb2Te6

Normally, the focal length of a conventional lens is fixed. Scientists have made much effort in modulating it into bifocal, which is very important for virtual reality (VR) and argument reality (AR) 3D display. It is even much more difficult for a lens to realize both convex and concave functions with one geometric structure, that is, a concave/convex switchable lens, which can tune 3D real-images and virtual-images in AR and VR, corresponding to long depth of view in 3D display. Based on the tunable refractive indexes of phase-change materials, here we propose a series of concave/convex switchable lenses. When the phase-change material is in different states, one switchable lens is able to perform a negative or positive focal length, or perform negative and positive focal lengths simultaneously. The lenses can be either cylindrical, spherical or other types. For the superior characteristics, these switchable lenses can be employed in various optical fields.

physics.optics↗

arXiv2018

Multi Phase in Cold Dense Quark Matter

In this article, we study dynamic chiral symmetry breaking at zero temperature, finite chemical potential and external magnetic field with massless NJL model. We have proposed a mathematical method to classify phases in phase diagram of cold dense quark matter, and use mathematical analysis to identify the multi phase phenomenon among solutions for gap equation which means with fixed chemical potential and magnetic field, there could be two phases coexisting.

hep-ph↗

arXiv2017

Sparse Weighted Canonical Correlation Analysis

Given two data matrices $X$ and $Y$, sparse canonical correlation analysis (SCCA) is to seek two sparse canonical vectors $u$ and $v$ to maximize the correlation between $Xu$ and $Yv$. However, classical and sparse CCA models consider the contribution of all the samples of data matrices and thus cannot identify an underlying specific subset of samples. To this end, we propose a novel sparse weighted canonical correlation analysis (SWCCA), where weights are used for regularizing different samples. We solve the $L_0$-regularized SWCCA ($L_0$-SWCCA) using an alternating iterative algorithm. We apply $L_0$-SWCCA to synthetic data and real-world data to demonstrate its effectiveness and superiority compared to related methods. Lastly, we consider also SWCCA with different penalties like LASSO (Least absolute shrinkage and selection operator) and Group LASSO, and extend it for integrating more than three data matrices.

cs.LG↗