arXiv subjects

Yun Zhao

Publications and source records attributed to Yun Zhao.

At least 73 records · Page 4Linked to original sources

arXiv2021

Empirical Analysis of Machine Learning Configurations for Prediction of Multiple Organ Failure in Trauma Patients

Multiple organ failure (MOF) is a life-threatening condition. Due to its urgency and high mortality rate, early detection is critical for clinicians to provide appropriate treatment. In this paper, we perform quantitative analysis on early MOF prediction with comprehensive machine learning (ML) configurations, including data preprocessing (missing value treatment, label balancing, feature scaling), feature selection, classifier choice, and hyperparameter tuning. Results show that classifier choice impacts both the performance improvement and variation most among all the configurations. In general, complex classifiers including ensemble methods can provide better performance than simple classifiers. However, blindly pursuing complex classifiers is unwise as it also brings the risk of greater performance variation.

cs.LG↗

arXiv2021

BART based semantic correction for Mandarin automatic speech recognition system

Although automatic speech recognition (ASR) systems achieved significantly improvements in recent years, spoken language recognition error occurs which can be easily spotted by human beings. Various language modeling techniques have been developed on post recognition tasks like semantic correction. In this paper, we propose a Transformer based semantic correction method with pretrained BART initialization, Experiments on 10000 hours Mandarin speech dataset show that character error rate (CER) can be effectively reduced by 21.7% relatively compared to our baseline ASR system. Expert evaluation demonstrates that actual improvement of our model surpasses what CER indicates.

cs.CL↗

arXiv2021

BERTSurv: BERT-Based Survival Models for Predicting Outcomes of Trauma Patients

Survival analysis is a technique to predict the times of specific outcomes, and is widely used in predicting the outcomes for intensive care unit (ICU) trauma patients. Recently, deep learning models have drawn increasing attention in healthcare. However, there is a lack of deep learning methods that can model the relationship between measurements, clinical notes and mortality outcomes. In this paper we introduce BERTSurv, a deep learning survival framework which applies Bidirectional Encoder Representations from Transformers (BERT) as a language representation model on unstructured clinical notes, for mortality prediction and survival analysis. We also incorporate clinical measurements in BERTSurv. With binary cross-entropy (BCE) loss, BERTSurv can predict mortality as a binary outcome (mortality prediction). With partial log-likelihood (PLL) loss, BERTSurv predicts the probability of mortality as a time-to-event outcome (survival analysis). We apply BERTSurv on Medical Information Mart for Intensive Care III (MIMIC III) trauma patient data. For mortality prediction, BERTSurv obtained an area under the curve of receiver operating characteristic curve (AUC-ROC) of 0.86, which is an improvement of 3.6% over baseline of multilayer perceptron (MLP) without notes. For survival analysis, BERTSurv achieved a concordance index (C-index) of 0.7. In addition, visualizations of BERT's attention heads help to extract patterns in clinical notes and improve model interpretability by showing how the model assigns weights to different inputs.

cs.AI↗

arXiv2020

How Much Does It Hurt: A Deep Learning Framework for Chronic Pain Score Assessment

Chronic pain is defined as pain that lasts or recurs for more than 3 to 6 months, often long after the injury or illness that initially caused the pain has healed. The "gold standard" for chronic pain assessment remains self report and clinical assessment via a biopsychosocial interview, since there has been no device that can measure it. A device to measure pain would be useful not only for clinical assessment, but potentially also as a biofeedback device leading to pain reduction. In this paper we propose an end-to-end deep learning framework for chronic pain score assessment. Our deep learning framework splits the long time-course data samples into shorter sequences, and uses Consensus Prediction to classify the results. We evaluate the performance of our framework on two chronic pain score datasets collected from two iterations of prototype Pain Meters that we have developed to help chronic pain subjects better understand their health condition.

eess.SP↗

arXiv2020

Near-degenerate quadrature-squeezed vacuum generation on a silicon-nitride chip

Squeezed states are a primary resource for continuous-variable (CV) quantum information processing. To implement CV protocols in a scalable and robust way, it is desirable to generate and manipulate squeezed states using an integrated photonics platform. In this Letter, we demonstrate the generation of quadrature-phase squeezed states in the radio-frequency carrier sideband using a small-footprint silicon-nitride microresonator with a dual-pumped four-wave-mixing process. We record a squeezed noise level of 1.34 dB ($\pm$0.16 dB) below the photocurrent shot noise, which corresponds to 3.09 dB ($\pm$0.49 dB) of quadrature squeezing on chip. We also show that it is critical to account for the nonlinear behavior of the pump fields to properly predict the squeezing that can be generated in this system. This technology represents a significant step toward creating and manipulating large-scale CV cluster states that can be used for quantum information applications including universal quantum computing.

physics.optics↗

arXiv2020

Scalable Bayesian Functional Connectivity Inference for Multi-Electrode Array Recordings

Multi-electrode arrays (MEAs) can record extracellular action potentials (also known as 'spikes') from hundreds or thousands of neurons simultaneously. Inference of a functional network from a spike train is a fundamental and formidable computational task in neuroscience. With the advancement of MEA technology, it has become increasingly crucial to develop statistical tools for analyzing multiple neuronal activity as a network. In this paper, we propose a scalable Bayesian framework for inference of functional networks from MEA data. Our framework makes use of the hierarchical structure of networks of neurons. We split the large scale recordings into smaller local networks for network inference, which not only eases the computational burden from Bayesian sampling but also provides useful insights on regional connections in organoids and brains. We speed up the expensive Bayesian sampling process by using parallel computing. Experiments on both synthetic datasets and large-scale real-world MEA recordings show the effectiveness and efficiency of the scalable Bayesian framework. Inference of networks from controlled experiments exposing neural cultures to cadmium presents distinguishable results and further confirms the utility of our framework.

cs.CE↗

arXiv2020

Nanophotonic spin-glass for realization of a coherent Ising machine

The need for solving optimization problems is prevalent in a wide range of physical applications, including neuroscience, network design, biological systems, socio-economics, and chemical reactions. Many of these are classified as non-deterministic polynomial-time (NP) hard and thus become intractable to solve as the system scales to a large number of elements. Recent research advances in photonics have sparked interest in using a network of coupled degenerate optical parametric oscillators (DOPO's) to effectively find the ground state of the Ising Hamiltonian, which can be used to solve other combinatorial optimization problems through polynomial-time mapping. Here, using the nanophotonic silicon-nitride platform, we propose a network of on-chip spatial-multiplexed DOPO's for the realization of a photonic coherent Ising machine. We demonstrate the generation and coupling of two microresonator-based DOPO's on a single chip. Through a reconfigurable phase link, we achieve both in-phase and out-of-phase operation, which can be deterministically achieved at a fast regeneration speed of 400 kHz with a large phase tolerance. Our work provides the critical building blocks towards the realization of a chip-scale photonic Ising machine.

physics.optics↗

arXiv2020

Frequency-Domain Quantum Interference with Correlated Photons from an Integrated Microresonator

Frequency encoding of quantum information together with fiber and integrated photonic technologies can significantly reduce the complexity and resource requirements for realizing all-photonic quantum networks. The key challenge for such frequency domain processing of single photons is to realize coherent and selective interactions between quantum optical fields of different frequencies over a range of bandwidths. Here, we report frequency-domain Hong-Ou-Mandel interference with spectrally distinct photons generated from a chip-based microresonator. We use four-wave mixing to implement an active frequency beam-splitter and achieve interference visibilities of $0.95 \pm 0.02$. Our work establishes four-wave mixing as a tool for selective high-fidelity two-photon operations in the frequency domain which, combined with integrated single-photon sources, provides a building block for frequency-multiplexed photonic quantum networks.

quant-ph↗

arXiv2020

Visible nonlinear photonics via high-order-mode dispersion engineering

Over the past decade, remarkable advances have been realized in chip-based nonlinear photonic devices for classical and quantum applications in the near- and mid-infrared regimes. However, few demonstrations have been realized in the visible and near-visible regimes, primarily due to the large normal material group-velocity dispersion (GVD) that makes it challenging to phase match third-order parametric processes. In this paper, we show that exploiting dispersion engineering of higher-order waveguide modes provides waveguide dispersion that allows for small or anomalous GVD in the visible and near-visible regimes and phase matching of four-wave mixing processes. We illustrate the power of this concept by demonstrating in silicon nitride microresonators a near-visible modelocked Kerr frequency comb and a narrow-band photon-pair source compatible with Rb transitions. These realizations extend applications of nonlinear photonics towards the visible and near-visible regimes for applications in time and frequency metrology, spectral calibration, quantum information, and biomedical applications.

physics.optics↗

arXiv2019

Core-Shell Nanofiber Containing Large Amount of Flame Retardants via Coaxial Dual-Nozzle Electrospinning as Battery Separators

Lithium-ion batteries have attracted enormous interests recently as promising power sources. However, the safety issue associated with the employment of highly flammable liquid electrolyte impedes the further development of next-generation lithium-ion batteries. Recently, researchers reported the use of electrospun core-shell fiber as the battery separator consisting of polymer layer as protective shell and flame retardants loaded inside as core. In case of a typical battery shorting, the protective polymer shell melts during thermal-runaway and the flame retardants inside would be released to suppress the combustion of the electrolyte. Due to the use of a single precursor solution for electrospinning containing both polymer and flame retardants, the weight ratio of flame retardants is limited and dependent. Herein, we developed a dual-nozzle, coaxial electrospinning approach to fabricate the core-shell nanofiber with a greatly enhanced flame retardants weight percentage in the final fibers. The weight ratio of flame retardants of triphenyl phosphate in the final composite reaches over 60 wt.%. The LiFePO4-based cell using this composite nanofiber as battery separator exhibits excellent flame-retardant property without compromising the cycling stability or rate performances. In addition, this functional nanofiber can also be coated onto commercial separators instead of being used directly as separators.

physics.app-ph↗

arXiv2019

An Auxiliary Classifier Generative Adversarial Framework for Relation Extraction

Relation extraction models suffer from limited qualified training data. Using human annotators to label sentences is too expensive and does not scale well especially when dealing with large datasets. In this paper, we use Auxiliary Classifier Generative Adversarial Networks (AC-GANs) to generate high-quality relational sentences and to improve the performance of relation classifier in end-to-end models. In AC-GAN, the discriminator gives not only a probability distribution over the real source, but also a probability distribution over the relation labels. This helps to generate meaningful relational sentences. Experimental results show that our proposed data augmentation method significantly improves the performance of relation extraction compared to state-of-the-art methods

cs.CL↗

arXiv2019

Turn-key, high-efficiency Kerr comb source

We demonstrate an approach for automated Kerr comb generation in the normal group-velocity dispersion (GVD) regime. Using a coupled-ring geometry in silicon nitride, we precisely control the wavelength location and splitting strength of avoided mode crossings to generate low-noise frequency combs with pump-to-comb conversion efficiencies of up to 41%, which is the highest reported to date for normal-GVD Kerr combs. Our technique enables on-demand generation of a high-power comb source for applications such as wavelength-division multiplexing in optical communications.

physics.optics↗

arXiv2019

Dimension Estimates for Non-conformal Repellers and Continuity of Sub-additive Topological Pressure

Given a non-conformal repeller $Λ$ of a $C^{1+γ}$ map, we study the Hausdorff dimension of the repeller and continuity of the sub-additive topological pressure for the sub-additive singular valued potentials. Such a potential always possesses an equilibrium state. We then use a substantially modified version of Katok's approximating argument, to construct a compact invariant set on which the corresponding dynamical quantities (such as Lyapunov exponents and metric entropy) are close to that of the equilibrium measure. This allows us to establish continuity of the sub-additive topological pressure and obtain a sharp lower bound of the Hausdorff dimension of the repeller. The latter is given by the zero of the super-additive topological pressure

math.DS↗

arXiv2019

A Deep Learning Framework for Classification of in vitro Multi-Electrode Array Recordings

Multi-Electrode Arrays (MEAs) have been widely used to record neuronal activities, which could be used in the diagnosis of gene defects and drug effects. In this paper, we address the problem of classifying in vitro MEA recordings of mouse and human neuronal cultures from different genotypes, where there is no easy way to directly utilize raw sequences as inputs to train an end-to-end classification model. While carefully extracting some features by hand could partially solve the problem, this approach suffers from obvious drawbacks such as difficulty of generalizing. We propose a deep learning framework to address this challenge. Our approach correctly classifies neuronal culture data prepared from two different genotypes -- a mouse Knockout of the delta-catenin gene and human induced Pluripotent Stem Cell-derived neurons from Williams syndrome. By splitting the long recordings into short slices for training, and applying Consensus Prediction during testing, our deep learning approach improves the prediction accuracy by 16.69% compared with feature based Logistic Regression for mouse MEA recordings. We further achieve an accuracy of 95.91% using Consensus Prediction in one subset of mouse MEA recording data, which were all recorded at six days in vitro. As high-density MEA recordings become more widely available, this approach could be generalized for classification of neurons carrying different mutations and classification of drug responses.

q-bio.NC↗

arXiv2019

Measure theoretic pressure and dimension formula for non-ergodic measures

This paper first studies the measure theoretic pressure of measures that are not necessarily ergodic. We define the measure theoretic pressure of an invariant measure (not necessarily ergodic) via the Carathéodory-Pesin structure described in \cite{Pes97}, and show that this quantity is equal to the essential supremum of the free energy of the measures in an ergodic decomposition. To the best of our knowledge, this formula is new even for entropy. Meanwhile, we define the measure theoretic pressure in another way by using separated sets, it is showed that this quantity is exactly the free energy if the measure is ergodic. Particularly, if the dynamical system satisfies the uniform separation condition and the ergodic measures are entropy dense, this quantity is still equal to the the free energy even if the measure is non-ergodic. As an application of the main result, we find that the Hausdorff dimension of an invariant measure supported on an average conformal repeller is given by the zero of the measure theoretic pressure of this measure. Furthermore, if a hyperbolic diffeomorphism is average conformal and volume-preserving, the Hausdorff dimension of any invariant measure on the hyperbolic set is equal to the sum of the zeros of measure theoretic pressure restricted to stable and unstable directions.

math.DS↗

arXiv2018

Dimensions of C1-average conformal hyperbolic sets

This paper introduces the concept of average conformal hyperbolic sets, which admit only one positive and one negative Lyapunov exponents for any ergodic measure. For an average conformal hyperbolic set of a C1 diffeomorphism, utilizing the techniques in sub-additive thermodynamics formalism and some geometric arguments with unstable/stable manifolds, a formula of the Hausdorff dimension and lower (upper) box dimension is given in this paper, which are exactly the sum of the dimensions of the restriction of the hyperbolic set to a stable and unstable manifolds. Furthermore, the dimensions of an average conformal hyperbolic set varies continuously with respect to the dynamics.

math.DS↗

arXiv2017

Two-dimensional structure reconstruction with expectation and maximization algorithm

In this report, we applied expectation and maximization (EM) method described by Philips et al [1] to recover two-dimensional (2D) structure from multiple sparse signal images in random orientation. The detailed derivation of EM algorithm for 2D image reconstruction was evaluated. Data sets with average 40 photons per frame were successfully classified by orientation. And the 2D mask structure is reconstructed by merging all frames with the appropriate rotations applied to each one. It provides us an alternative approach in data set classification and structural information recovery from extremely weak signal with incomplete information.

physics.data-an↗

arXiv2017

Extracting single crystal diffraction pattern from powder diffraction by intensity correlation functions

We applied the analysis of x-ray intensity angular correlation function to dilute ensembles of identical spinel crystals. Firstly, we show that the angular correlation from measured diffraction patterns with many crystals per shot converges to the correlation for single crystal. Secondly, we determined the diffraction pattern from single crystal from diffraction patterns of many crystals. Finally, we discussed the full 3D reciprocal space retrieval and its potential application in solving structure with dilute powder diffraction data, where the intensity fluctuation could be observed on each ring.

cond-mat.mtrl-sci↗