arXiv subjects

Yi Li

Publications and source records attributed to Yi Li.

At least 451 records · Page 25Linked to original sources

arXiv2021

Deep-learning-based Hyperspectral imaging through a RGB camera

Hyperspectral image (HSI) contains both spatial pattern and spectral information which has been widely used in food safety, remote sensing, and medical detection. However, the acquisition of hyperspectral images is usually costly due to the complicated apparatus for the acquisition of optical spectrum. Recently, it has been reported that HSI can be reconstructed from single RGB image using convolution neural network (CNN) algorithms. Compared with the traditional hyperspectral cameras, the method based on CNN algorithms is simple, portable and low cost. In this study, we focused on the influence of the RGB camera spectral sensitivity (CSS) on the HSI. A Xenon lamp incorporated with a monochromator were used as the standard light source to calibrate the CSS. And the experimental results show that the CSS plays a significant role in the reconstruction accuracy of an HSI. In addition, we proposed a new HSI reconstruction network where the dimensional structure of the original hyperspectral datacube was modified by 3D matrix transpose to improve the reconstruction accuracy.

eess.IV↗

arXiv2021

Blending search queries with social media data to improve forecasts of economic indicators

The forecasting of political, economic, and public health indicators using internet activity has demonstrated mixed results. For example, while some measures of explicitly surveyed public opinion correlate well with social media proxies, the opportunity for profitable investment strategies to be driven solely by sentiment extracted from social media appears to have expired. Nevertheless, the internet's space of potentially predictive input signals is combinatorially vast and will continue to invite careful exploration. Here, we combine unemployment related search data from Google Trends with economic language on Twitter to attempt to nowcast and forecast: 1. State and national unemployment claims for the US, and 2. Consumer confidence in G7 countries. Building off of a recently developed search-query-based model, we show that incorporating Twitter data improves forecasting of unemployment claims, while the original method remains marginally better at nowcasting. Enriching the input signal with temporal statistical features (e.g., moving average and rate of change) further reduces errors, and improves the predictive utility of the proposed method when applied to other economic indices, such as consumer confidence.

cs.SI↗

arXiv2021

Vulnerability Detection with Fine-grained Interpretations

Despite the successes of machine learning (ML) and deep learning (DL) based vulnerability detectors (VD), they are limited to providing only the decision on whether a given code is vulnerable or not, without details on what part of the code is relevant to the detected vulnerability. We present IVDetect an interpretable vulnerability detector with the philosophy of using Artificial Intelligence (AI) to detect vulnerabilities, while using Intelligence Assistant (IA) via providing VD interpretations in terms of vulnerable statements. For vulnerability detection, we separately consider the vulnerable statements and their surrounding contexts via data and control dependencies. This allows our model better discriminate vulnerable statements than using the mixture of vulnerable code and~contextual code as in existing approaches. In addition to the coarse-grained vulnerability detection result, we leverage interpretable AI to provide users with fine-grained interpretations that include the sub-graph in the Program Dependency Graph (PDG) with the crucial statements that are relevant to the detected vulnerability. Our empirical evaluation on vulnerability databases shows that IVDetect outperforms the existing DL-based approaches by 43%--84% and 105%--255% in top-10 nDCG and MAP ranking scores. IVDetect correctly points out the vulnerable statements relevant to the vulnerability via its interpretation~in 67% of the cases with a top-5 ranked list. It improves over baseline interpretation models by 12.3%--400% and 9%--400% in accuracy.

cs.CR↗

arXiv2021

Statistical Inference for Cox Proportional Hazards Models with a Diverging Number of Covariates

For statistical inference on regression models with a diverging number of covariates, the existing literature typically makes sparsity assumptions on the inverse of the Fisher information matrix. Such assumptions, however, are often violated under Cox proportion hazards models, leading to biased estimates with under-coverage confidence intervals. We propose a modified debiased lasso approach, which solves a series of quadratic programming problems to approximate the inverse information matrix without posing sparse matrix assumptions. We establish asymptotic results for the estimated regression coefficients when the dimension of covariates diverges with the sample size. As demonstrated by extensive simulations, our proposed method provides consistent estimates and confidence intervals with nominal coverage probabilities. The utility of the method is further demonstrated by assessing the effects of genetic markers on patients' overall survival with the Boston Lung Cancer Survival Cohort, a large-scale epidemiology study investigating mechanisms underlying the lung cancer.

stat.ME↗

arXiv2021

Phase-resolved electrical detection of coherently coupled magnonic devices

We demonstrate the electrical detection of magnon-magnon hybrid dynamics in yttrium iron garnet/permalloy (YIG/Py) thin film bilayer devices. Direct microwave current injection through the conductive Py layer excites the hybrid dynamics consisting of the uniform mode of Py and the first standing spin wave ($n=1$) mode of YIG, which are coupled via interfacial exchange. Both the two hybrid modes, with Py or YIG dominated excitations, can be detected via the spin rectification signals from the conductive Py layer, providing phase resolution of the coupled dynamics. The phase characterization is also applied to a nonlocally excited Py device, revealing the additional phase shift due to the perpendicular Oersted field. Our results provide a device platform for exploring hybrid magnonic dynamics and probing their phases, which are crucial for implementing coherent information processing with magnon excitations

cond-mat.mes-hall↗

arXiv2021

Advances in coherent coupling between magnons and acoustic phonons

The interaction between magnetic and acoustic excitations have recently inspired many interdisciplinary studies ranging from fundamental physics to circuit implementation. Specifically, the exploration of their coherent interconversion enabled via the magnetoelastic coupling opens a new playground combining straintronics and spintronics, and provides a unique platform for building up on-chip coherent information processing networks with miniaturized magnonic and acoustic devices. In this Perspective, we will focus on the recent progress of magnon-phonon coupled dynamic systems, including materials, circuits, imaging and new physics. In particular, we highlight the unique features such as nonreciprocal acoustic wave propagation and strong coupling between magnons and phonons in magnetic thin-film systems, which provides a unique platform for their coherent manipulation and transduction. We will also review the frontier of surface acoustic wave resonators in coherent quantum transduction and discuss how the novel acoustic circuit design can be applied in microwave spintronics.

cond-mat.mes-hall↗

arXiv2021

Ensemble machine learning approach for screening of coronary heart disease based on echocardiography and risk factors

Background: Extensive clinical evidence suggests that a preventive screening of coronary heart disease (CHD) at an earlier stage can greatly reduce the mortality rate. We use 64 two-dimensional speckle tracking echocardiography (2D-STE) features and seven clinical features to predict whether one has CHD. Methods: We develop a machine learning approach that integrates a number of popular classification methods together by model stacking, and generalize the traditional stacking method to a two-step stacking method to improve the diagnostic performance. Results: By borrowing strengths from multiple classification models through the proposed method, we improve the CHD classification accuracy from around 70% to 87.7% on the testing set. The sensitivity of the proposed method is 0.903 and the specificity is 0.843, with an AUC of 0.904, which is significantly higher than those of the individual classification models. Conclusions: Our work lays a foundation for the deployment of speckle tracking echocardiography-based screening tools for coronary heart disease.

stat.ML↗

arXiv2021

Learn an index operator by CNN for solving diffusive optical tomography: a deep direct sampling method

In this work, we investigate the diffusive optical tomography (DOT) problem in the case that limited boundary measurements are available. Motivated by the direct sampling method (DSM), we develop a deep direct sampling method (DDSM) to recover the inhomogeneous inclusions buried in a homogeneous background. In this method, we design a convolutional neural network (CNN) to approximate the index functional that mimics the underling mathematical structure. The benefits of the proposed DDSM include fast and easy implementation, capability of incorporating multiple measurements to attain high-quality reconstruction, and advanced robustness against the noise. Numerical experiments show that the reconstruction accuracy is improved without degrading the efficiency, demonstrating its potential for solving the real-world DOT problems.

math.NA↗

arXiv2021

More Separable and Easier to Segment: A Cluster Alignment Method for Cross-Domain Semantic Segmentation

Feature alignment between domains is one of the mainstream methods for Unsupervised Domain Adaptation (UDA) semantic segmentation. Existing feature alignment methods for semantic segmentation learn domain-invariant features by adversarial training to reduce domain discrepancy, but they have two limits: 1) associations among pixels are not maintained, 2) the classifier trained on the source domain couldn't adapted well to the target. In this paper, we propose a new UDA semantic segmentation approach based on domain closeness assumption to alleviate the above problems. Specifically, a prototype clustering strategy is applied to cluster pixels with the same semantic, which will better maintain associations among target domain pixels during the feature alignment. After clustering, to make the classifier more adaptive, a normalized cut loss based on the affinity graph of the target domain is utilized, which will make the decision boundary target-specific. Sufficient experiments conducted on GTA5 $\rightarrow$ Cityscapes and SYNTHIA $\rightarrow$ Cityscapes proved the effectiveness of our method, which illustrated that our results achieved the new state-of-the-art.

cs.CV↗

arXiv2021

A Survey of Smart Contract Formal Specification and Verification

A smart contract is a computer program which allows users to automate their actions on the blockchain platform. Given the significance of smart contracts in supporting important activities across industry sectors including supply chain, finance, legal and medical services, there is a strong demand for verification and validation techniques. Yet, the vast majority of smart contracts lack any kind of formal specification, which is essential for establishing their correctness. In this survey, we investigate formal models and specifications of smart contracts presented in the literature and present a systematic overview in order to understand the common trends. We also discuss the current approaches used in verifying such property specifications and identify gaps with the hope to recognize promising directions for future work.

cs.SE↗

arXiv2021

Formal Analysis of Composable DeFi Protocols

Decentralized finance (DeFi) has become one of the most successful applications of blockchain and smart contracts. The DeFi ecosystem enables a wide range of crypto-financial activities, while the underlying smart contracts often contain bugs, with many vulnerabilities arising from the unforeseen consequences of composing DeFi protocols together. In this paper, we propose a formal process-algebraic technique that models DeFi protocols in a compositional manner to allow for efficient property verification. We also conduct a case study to demonstrate the proposed approach in analyzing the composition of two interacting DeFi protocols, namely, Curve and Compound. Finally, we discuss how the proposed modeling and verification approach can be used to analyze financial and security properties of interest.

cs.CR↗

arXiv2021

Estimation and Inference for High Dimensional Generalized Linear Models: A Splitting and Smoothing Approach

The focus of modern biomedical studies has gradually shifted to explanation and estimation of joint effects of high dimensional predictors on disease risks. Quantifying uncertainty in these estimates may provide valuable insight into prevention strategies or treatment decisions for both patients and physicians. High dimensional inference, including confidence intervals and hypothesis testing, has sparked much interest. While much work has been done in the linear regression setting, there is lack of literature on inference for high dimensional generalized linear models. We propose a novel and computationally feasible method, which accommodates a variety of outcome types, including normal, binomial, and Poisson data. We use a "splitting and smoothing" approach, which splits samples into two parts, performs variable selection using one part and conducts partial regression with the other part. Averaging the estimates over multiple random splits, we obtain the smoothed estimates, which are numerically stable. We show that the estimates are consistent, asymptotically normal, and construct confidence intervals with proper coverage probabilities for all predictors. We examine the finite sample performance of our method by comparing it with the existing methods and applying it to analyze a lung cancer cohort study.

stat.ME↗

arXiv2021

A Context-based Automated Approach for Method Name Consistency Checking and Suggestion

Misleading method names in software projects can confuse developers, which may lead to software defects and affect code understandability. In this paper, we present DeepName, a context-based, deep learning approach to detect method name inconsistencies and suggest a proper name for a method. The key departure point is the philosophy of "Show Me Your Friends, I'll Tell You Who You Are". Unlike the state-of-the-art approaches, in addition to the method's body, we also consider the interactions of the current method under study with the other ones including the caller and callee methods, and the sibling methods in the same enclosing class. The sequences of sub-tokens in the program entities' names in the contexts are extracted and used as the input for an RNN-based encoder-decoder to produce the representations for the current method. We modify that RNN model to integrate the copy mechanism and our newly developed component, called the non-copy mechanism, to emphasize on the possibility of a certain sub-token not to be copied to follow the current sub-token in the currently generated method name. We conducted several experiments to evaluate DeepName on large datasets with +14M methods. For consistency checking, DeepName improves the state-of-the-art approach by 2.1%, 19.6%, and 11.9% relatively in recall, precision, and F-score, respectively. For name suggestion, DeepName improves relatively over the state-of-the-art approaches in precision (1.8%--30.5%), recall (8.8%--46.1%), and F-score (5.2%--38.2%). To assess DeepName's usefulness, we detected inconsistent methods and suggested new method names in active projects. Among 50 pull requests, 12 were merged into the main branch. In total, in 30/50 cases, the team members agree that our suggested method names are more meaningful than the current names.

cs.SE↗

arXiv2021

Fault Localization with Code Coverage Representation Learning

In this paper, we propose DeepRL4FL, a deep learning fault localization (FL) approach that locates the buggy code at the statement and method levels by treating FL as an image pattern recognition problem. DeepRL4FL does so via novel code coverage representation learning (RL) and data dependencies RL for program statements. Those two types of RL on the dynamic information in a code coverage matrix are also combined with the code representation learning on the static information of the usual suspicious source code. This combination is inspired by crime scene investigation in which investigators analyze the crime scene (failed test cases and statements) and related persons (statements with dependencies), and at the same time, examine the usual suspects who have committed a similar crime in the past (similar buggy code in the training data). For the code coverage information, DeepRL4FL first orders the test cases and marks error-exhibiting code statements, expecting that a model can recognize the patterns discriminating between faulty and non-faulty statements/methods. For dependencies among statements, the suspiciousness of a statement is seen taking into account the data dependencies to other statements in execution and data flows, in addition to the statement by itself. Finally, the vector representations for code coverage matrix, data dependencies among statements, and source code are combined and used as the input of a classifier built from a Convolution Neural Network to detect buggy statements/methods. Our empirical evaluation shows that DeepRL4FL improves the top-1 results over the state-of-the-art statement-level FL baselines from 173.1% to 491.7%. It also improves the top-1 results over the existing method-level FL baselines from 15.0% to 206.3%.

cs.SE↗

arXiv2021

Comments on large central charge $T\bar{T}$ deformed conformal field theory and cutoff AdS holography

In this article we study large central charge partition function and entanglement entropy of $T\bar{T}$ deformed two dimensional conformal field theory, following the approach to $T\bar{T}$ deformation as integrated infinitesimal double trace deformation used by Guica et al.. For sphere partition function and entanglement entropy of half great circle with antipodal points being the entangling surface, we obtain different results compared to previous works, with more reasonable CFT limits and qualitatively different behaviour as the deformation parameter $μ$ goes to infinity, which contradicts the simple version of the cutoff AdS holography proposal. For a modified version of cutoff AdS holography which is supposed to work only in the sector of classical pure gravity, we show that the flow equation of the metric and one point function of energy-momentum tensor in $T\bar{T}$ deformation corresponds to the flow equation of the boundary metric and Brown-York tensor on a cutoff surface in AdS space as the cutoff surface moves in the direction of normal geodesics. In addition the flow equation of gravity on-shell action takes the form of $T\bar{T}$ deformation, with straightforward generalization to higher dimensions. As an example we give a holographic computation of the sphere partition function of $T\bar{T}$ CFT.

hep-th↗

arXiv2021

Growth and site-specific organization of micron-scale biomolecular devices on living mammalian cells

Mesoscale molecular assemblies on the cell surface, such as cilia and filopodia, integrate information, control transport and amplify signals. Synthetic devices mimicking these structures could sensitively monitor these cellular functions and direct new ones. The challenges in creating such devices, however are that they must be integrated with cells in a precise kinetically controlled process and a device's structure and its precisely structured cell interface must then be maintained during active cellular function. Here we report the ability to integrate synthetic micro-scale filaments, DNA nanotubes, into a cell's architecture by anchoring them by their ends to specific receptors on the surfaces of mammalian cells. These filaments can act as shear stress meters: how anchored nanotubes bend at the cell surface quantitatively indicates the magnitude of shear stresses between 0-2 dyn per cm2, a regime important for cell signaling. Nanotubes can also grow while anchored to cells, thus acting as dynamic components of cells. This approach to cell surface engineering, in which synthetic biomolecular assemblies are organized within existing cellular architecture, could make it possible to build new types of sensors, machines and scaffolds that can interface with, control and measure properties of cells.

q-bio.BM↗

arXiv2020

Modified Gaussian Process Regression Models for Cyclic Capacity Prediction of Lithium-ion Batteries

This paper presents the development of machine learning-enabled data-driven models for effective capacity predictions for lithium-ion batteries under different cyclic conditions. To achieve this, a model structure is first proposed with the considerations of battery ageing tendency and the corresponding operational temperature and depth-of-discharge. Then based on a systematic understanding of covariance functions within the Gaussian process regression, two related data-driven models are developed. Specifically, by modifying the isotropic squared exponential kernel with an automatic relevance determination structure, 'Model A' could extract the highly relevant input features for capacity predictions. Through coupling the Arrhenius law and a polynomial equation into a compositional kernel, 'Model B' is capable of considering the electrochemical and empirical knowledge of battery degradation. The developed models are validated and compared on the Nickel Manganese Cobalt Oxide (NMC) lithium-ion batteries with various cycling patterns. Experimental results demonstrate that the modified Gaussian process regression model considering the battery electrochemical and empirical ageing signature outperforms other counterparts and is able to achieve satisfactory results for both one-step and multi-step predictions. The proposed technique is promising for battery capacity predictions under various cycling cases.

cs.LG↗

arXiv2020

Anomalous Hall and Nernst Effects in FeRh

Antiferromagnets with tunable phase transitions are promising for future spintronics applications. We investigated spin-dependent transport properties of FeRh thin films, which show a temperature driven antiferromagnetic-to-ferromagnetic phase transition. Epitaxial FeRh films grown on MgO (001) substrates exhibit a clear magnetic and electronic phase transition. By performing anomalous Hall and anomalous Nernst effect measurements over a wide range of temperatures, we demonstrate that the thermally driven transition shows distinctly different transverse transport on both side of the phase transition. Particularly, a sign change of both anomalous Hall and Nernst signals is observed.

cond-mat.mtrl-sci↗