arXiv subjects

Xuan Zhang

Publications and source records attributed to Xuan Zhang.

At least 217 records · Page 12Linked to original sources

arXiv2020

OralCam: Enabling Self-Examination and Awareness of Oral Health Using a Smartphone Camera

Due to a lack of medical resources or oral health awareness, oral diseases are often left unexamined and untreated, affecting a large population worldwide. With the advent of low-cost, sensor-equipped smartphones, mobile apps offer a promising possibility for promoting oral health. However, to the best of our knowledge, no mobile health (mHealth) solutions can directly support a user to self-examine their oral health condition. This paper presents OralCam, the first interactive app that enables end-users' self-examination of five common oral conditions (diseases or early disease signals) by taking smartphone photos of one's oral cavity. OralCam allows a user to annotate additional information (e.g. living habits, pain, and bleeding) to augment the input image, and presents the output hierarchically, probabilistically and with visual explanations to help a laymen user understand examination results. Developed on our in-house dataset that consists of 3,182 oral photos annotated by dental experts, our deep learning based framework achieved an average detection sensitivity of 0.787 over five conditions with high localization accuracy. In a week-long in-the-wild user study (N=18), most participants had no trouble using OralCam and interpreting the examination results. Two expert interviews further validate the feasibility of OralCam for promoting users' awareness of oral health.

cs.HC↗

arXiv2019

RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing

Personalized recommendation systems leverage deep learning models and account for the majority of data center AI cycles. Their performance is dominated by memory-bound sparse embedding operations with unique irregular memory access patterns that pose a fundamental challenge to accelerate. This paper proposes a lightweight, commodity DRAM compliant, near-memory processing solution to accelerate personalized recommendation inference. The in-depth characterization of production-grade recommendation models shows that embedding operations with high model-, operator- and data-level parallelism lead to memory bandwidth saturation, limiting recommendation inference performance. We propose RecNMP which provides a scalable solution to improve system throughput, supporting a broad range of sparse embedding models. RecNMP is specifically tailored to production environments with heavy co-location of operators on a single server. Several hardware/software co-optimization techniques such as memory-side caching, table-aware packet scheduling, and hot entry profiling are studied, resulting in up to 9.8x memory latency speedup over a highly-optimized baseline. Overall, RecNMP offers 4.2x throughput improvement and 45.8% memory energy savings.

cs.DC↗

arXiv2019

Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices

Recent works propose neural network- (NN-) inspired analog-to-digital converters (NNADCs) and demonstrate their great potentials in many emerging applications. These NNADCs often rely on resistive random-access memory (RRAM) devices to realize the NN operations and require high-precision RRAM cells (6~12-bit) to achieve a moderate quantization resolution (4~8-bit). Such optimistic assumption of RRAM resolution, however, is not supported by fabrication data of RRAM arrays in large-scale production process. In this paper, we propose an NN-inspired super-resolution ADC based on low-precision RRAM devices by taking the advantage of a co-design methodology that combines a pipelined hardware architecture with a custom NN training framework. Results obtained from SPICE simulations demonstrate that our method leads to robust design of a 14-bit super-resolution ADC using 3-bit RRAM devices with improved power and speed performance and competitive figure-of-merits (FoMs). In addition to the linear uniform quantization, the proposed ADC can also support configurable high-resolution nonlinear quantization with high conversion speed and low conversion energy, enabling future intelligent analog-to-information interfaces for near-sensor analytics and processing.

cs.LG↗

arXiv2019

Distributed Optimal Frequency Control for Integrated Energy Systems with Electricity and Heat

With more and more distributed energy resources (DERs) deployed in Integrated Energy Systems (IESs), frequency stability challenges the pursuit of reliability and efficiency. This paper proposes a fully-distributed frequency control method for load-side DERs, in which the optimality can be guaranteed in an IES where electricity and heat are coupled. Moreover, the global asymptotic stability of the closed-loop system is proved and the robustness with respect to inaccurate coefficients is shown. Case studies demonstrate the effectiveness of proposed method.

eess.SY↗

arXiv2019

Boundary Zonal Flow in Rotating Turbulent Rayleigh-Bénard Convection

For rapidly rotating turbulent Rayleigh--Bénard convection in a slender cylindrical cell, experiments and direct numerical simulations reveal a boundary zonal flow (BZF) that replaces the classical large-scale circulation. The BZF is located near the vertical side wall and enables enhanced heat transport there. Although the azimuthal velocity of the BZF is cyclonic (in the rotating frame), the temperature is an anticyclonic traveling wave of mode one whose signature is a bimodal temperature distribution near the radial boundary. The BZF width is found to scale like $Ra^{1/4}Ek^{2/3}$ where the Ekman number $Ek$ decreases with increasing rotation rate.

physics.flu-dyn↗

arXiv2019

Attacking Vision-based Perception in End-to-End Autonomous Driving Models

Recent advances in machine learning, especially techniques such as deep neural networks, are enabling a range of emerging applications. One such example is autonomous driving, which often relies on deep learning for perception. However, deep learning-based perception has been shown to be vulnerable to a host of subtle adversarial manipulations of images. Nevertheless, the vast majority of such demonstrations focus on perception that is disembodied from end-to-end control. We present novel end-to-end attacks on autonomous driving in simulation, using simple physically realizable attacks: the painting of black lines on the road. These attacks target deep neural network models for end-to-end autonomous driving control. A systematic investigation shows that such attacks are easy to engineer, and we describe scenarios (e.g., right turns) in which they are highly effective. We define several objective functions that quantify the success of an attack and develop techniques based on Bayesian Optimization to efficiently traverse the search space of higher dimensional attacks. Additionally, we define a novel class of hijacking attacks, where painted lines on the road cause the driver-less car to follow a target path. Through the use of network deconvolution, we provide insights into the successful attacks, which appear to work by mimicking activations of entirely different scenarios. Our code is available at https://github.com/xz-group/AdverseDrive

cs.LG↗

arXiv2019

Evaluating Ordering Strategies of Star Glyph Axes

Star glyphs are a well-researched visualization technique to represent multi-dimensional data. They are often used in small multiple settings for a visual comparison of many data points. However, their overall visual appearance is strongly influenced by the ordering of dimensions. To this end, two orthogonal categories of layout strategies are proposed in the literature: order dimensions by similarity to get homogeneously shaped glyphs vs. order by dissimilarity to emphasize spikes and salient shapes. While there is evidence that salient shapes support clustering tasks, evaluation, and direct comparison of data-driven ordering strategies has not received much research attention. We contribute an empirical user study to evaluate the efficiency, effectiveness, and user confidence in visual clustering tasks using star glyphs. In comparison to similarity-based ordering, our results indicate that dissimilarity-based star glyph layouts support users better in clustering tasks, especially when clutter is present.

cs.GR↗

arXiv2019

A Scheme for Continuous Input to the Tsetlin Machine with Applications to Forecasting Disease Outbreaks

In this paper, we apply a new promising tool for pattern classification, namely, the Tsetlin Machine (TM), to the field of disease forecasting. The TM is interpretable because it is based on manipulating expressions in propositional logic, leveraging a large team of Tsetlin Automata (TA). Apart from being interpretable, this approach is attractive due to its low computational cost and its capacity to handle noise. To attack the problem of forecasting, we introduce a preprocessing method that extends the TM so that it can handle continuous input. Briefly stated, we convert continuous input into a binary representation based on thresholding. The resulting extended TM is evaluated and analyzed using an artificial dataset. The TM is further applied to forecast dengue outbreaks of all the seventeen regions in the Philippines using the spatio-temporal properties of the data. Experimental results show that dengue outbreak forecasts made by the TM are more accurate than those obtained by a Support Vector Machine (SVM), Decision Trees (DTs), and several multi-layered Artificial Neural Networks (ANNs), both in terms of forecasting precision and F1-score.

cs.LG↗

arXiv2019

Curriculum Learning for Domain Adaptation in Neural Machine Translation

We introduce a curriculum learning approach to adapt generic neural machine translation models to a specific domain. Samples are grouped by their similarities to the domain of interest and each group is fed to the training algorithm with a particular schedule. This approach is simple to implement on top of any neural framework or architecture, and consistently outperforms both unadapted and adapted baselines in experiments with two distinct domains and two language pairs.

cs.CL↗

arXiv2019

Simple Physical Adversarial Examples against End-to-End Autonomous Driving Models

Recent advances in machine learning, especially techniques such as deep neural networks, are promoting a range of high-stakes applications, including autonomous driving, which often relies on deep learning for perception. While deep learning for perception has been shown to be vulnerable to a host of subtle adversarial manipulations of images, end-to-end demonstrations of successful attacks, which manipulate the physical environment and result in physical consequences, are scarce. Moreover, attacks typically involve carefully constructed adversarial examples at the level of pixels. We demonstrate the first end-to-end attacks on autonomous driving in simulation, using simple physically realizable attacks: the painting of black lines on the road. These attacks target deep neural network models for end-to-end autonomous driving control. A systematic investigation shows that such attacks are surprisingly easy to engineer, and we describe scenarios (e.g., right turns) in which they are highly effective, and others that are less vulnerable (e.g., driving straight). Further, we use network deconvolution to demonstrate that the attacks succeed by inducing activation patterns similar to entirely different scenarios used in training.

cs.RO↗

arXiv2019

Polarization sensitive laser intensity inside femtosecond filament in air

Polarization dependence on clamping intensity inside femtosecond filament was experimentally measured in air. By tuning the laser pulse ellipse from linear polarization to circular polarization, the measured clamping intensity inside laser filament is gradually increased up to 1.7 times. The experimental results are in good agreement with the simulation results by solving the extended nonlinear Schrodinger equation (NLSE). The polarization sensitive clamping intensity inside filaments offers an important factor towards fully understanding the polarization related phenomenon observed so far.

physics.optics↗

arXiv2018

Sparse Bayesian Learning-Based Direction Finding Method With Unknown Mutual Coupling Effect

The imperfect array degrades the direction finding performance. In this paper, we investigate the direction finding problem in uniform linear array (ULA) system with unknown mutual coupling effect between antennas. By exploiting the target sparsity in the spatial domain, sparse Bayesian learning (SBL)-based model is proposed and converts the direction finding problem into a sparse reconstruction problem. In the sparse-based model, the \emph{off-grid} errors are introduced by discretizing the direction area into grids. Therefore, an off-grid SBL model with mutual coupling vector is proposed to overcome both the mutual coupling and the off-grid effect. With the distribution assumptions of unknown parameters including the noise variance, the off-grid vector, the received signals and the mutual coupling vector, a novel direction finding method based on SBL with unknown mutual coupling effect named DFSMC is proposed, where an expectation-maximum (EM)-based step is adopted by deriving the estimation expressions for all the unknown parameters theoretically. Simulation results show that the proposed DFSMC method can outperform state-of-the-art direction finding methods significantly in the array system with unknown mutual coupling effect.

eess.SP↗

arXiv2018

A Hybrid Model for Role-related User Classification on Twitter

To aid a variety of research studies, we propose TWIROLE, a hybrid model for role-related user classification on Twitter, which detects male-related, female-related, and brand-related (i.e., organization or institution) users. TWIROLE leverages features from tweet contents, user profiles, and profile images, and then applies our hybrid model to identify a user's role. To evaluate it, we used two existing large datasets about Twitter users, and conducted both intra- and inter-comparison experiments. TWIROLE outperforms existing methods and obtains more balanced results over the several roles. We also confirm that user names and profile images are good indicators for this task. Our research extends prior work that does not consider brand-related users, and is an aid to future evaluation efforts relative to investigations that rely upon self-labeled datasets.

cs.SI↗

arXiv2018

An Empirical Exploration of Curriculum Learning for Neural Machine Translation

Machine translation systems based on deep neural networks are expensive to train. Curriculum learning aims to address this issue by choosing the order in which samples are presented during training to help train better models faster. We adopt a probabilistic view of curriculum learning, which lets us flexibly evaluate the impact of curricula design, and perform an extensive exploration on a German-English translation task. Results show that it is possible to improve convergence time at no loss in translation quality. However, results are highly sensitive to the choice of sample difficulty criteria, curriculum schedule and other hyperparameters.

cs.CL↗

arXiv2018

SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification

Holistic person re-identification (ReID) has received extensive study in the past few years and achieves impressive progress. However, persons are often occluded by obstacles or other persons in practical scenarios, which makes partial person re-identification non-trivial. In this paper, we propose a spatial-channel parallelism network (SCPNet) in which each channel in the ReID feature pays attention to a given spatial part of the body. The spatial-channel corresponding relationship supervises the network to learn discriminative feature for both holistic and partial person re-identification. The single model trained on four holistic ReID datasets achieves competitive accuracy on these four datasets, as well as outperforms the state-of-the-art methods on two partial ReID datasets without training.

cs.CV↗

arXiv2018

Unusual evolution of B_{c2} and T_c with inclined fields in restacked TaS_2 nanosheets

Recently we reported an enhanced superconductivity in restacked monolayer TaS_2 nanosheets compared with the bulk TaS_2, pointing to the exotic physical properties of low dimensional systems. Here we tune the superconducting properties of this system with magnetic field along different directions, where a strong Pauli paramagnetic spin-splitting effect is found in this system. Importantly, an unusual enhancement as high as 3.8 times of the upper critical field B_{c2}, as compered with the Ginzburg-Landau (GL) model and Tinkham model, is observed under the inclined external magnetic field. Moreover, with the out-of-plane field fixed, we find that the superconducting transition temperature T_c can be enhanced by increasing the in-plane field and forms a dome-shaped phase diagram. An extended GL model considering the special microstructure with wrinkles was proposed to describe the results. The restacked crystal structure without inversion center along with the strong spin-orbit coupling may also play an important role for our observations.

cond-mat.supr-con↗

arXiv2018

Robust Distributed Compression of Symmetrically Correlated Gaussian Sources

Consider a lossy compression system with $\ell$ distributed encoders and a centralized decoder. Each encoder compresses its observed source and forwards the compressed data to the decoder for joint reconstruction of the target signals under the mean squared error distortion constraint. It is assumed that the observed sources can be expressed as the sum of the target signals and the corruptive noises, which are generated independently from two symmetric multivariate Gaussian distributions. Depending on the parameters of such distributions, the rate-distortion limit of this system is characterized either completely or at least for sufficiently low distortions. The results are further extended to the robust distributed compression setting, where the outputs of a subset of encoders may also be used to produce a non-trivial reconstruction of the corresponding target signals. In particular, we obtain in the high-resolution regime a precise characterization of the minimum achievable reconstruction distortion based on the outputs of $k+1$ or more encoders when every $k$ out of all $\ell$ encoders are operated collectively in the same mode that is greedy in the sense of minimizing the distortion incurred by the reconstruction of the corresponding $k$ target signals with respect to the average rate of these $k$ encoders.

cs.IT↗

arXiv2018

AxTrain: Hardware-Oriented Neural Network Training for Approximate Inference

The intrinsic error tolerance of neural network (NN) makes approximate computing a promising technique to improve the energy efficiency of NN inference. Conventional approximate computing focuses on balancing the efficiency-accuracy trade-off for existing pre-trained networks, which can lead to suboptimal solutions. In this paper, we propose AxTrain, a hardware-oriented training framework to facilitate approximate computing for NN inference. Specifically, AxTrain leverages the synergy between two orthogonal methods---one actively searches for a network parameters distribution with high error tolerance, and the other passively learns resilient weights by numerically incorporating the noise distributions of the approximate hardware in the forward pass during the training phase. Experimental results from various datasets with near-threshold computing and approximation multiplication strategies demonstrate AxTrain's ability to obtain resilient neural network parameters and system energy efficiency improvement.

cs.LG↗