arXiv subjects

Xiaoyu Zhang

Publications and source records attributed to Xiaoyu Zhang.

At least 217 records · Page 12Linked to original sources

arXiv2021

Flow-Sensory Contact Electrification of Graphene

All-electronic interrogation of biofluid flow velocity by sensors incorporated in ultra-low-power or self-sustained systems offers the promise of enabling multifarious emerging research and applications. Electrical sensors based on nanomaterials are of high spatiotemporal resolution and exceptional sensitivity to external flow stimulus and easily integrated and fabricated using scalable techniques. But existing nano-based electrical flow-sensing technologies remain lacking in precision and stability and are typically only applicable to simple aqueous solutions or liquid/gas dual-phase mixtures, making them unsuitable for monitoring low-flow (~micrometer/second) yet important characteristics of continuous biofluids (e.g., hemorheological behaviors in microcirculation). Here we show that monolayer-graphene single microelectrodes harvesting charge from continuous aqueous flow provide an ideal flow sensing strategy: Our devices deliver over six months stability and sub-micrometer/second resolution in real-time quantification of whole-blood flows with multiscale amplitude-temporal characteristics in a microfluidic chip. The flow transduction is enabled by low-noise charge transfer at graphene/water interface in response to flow-sensitive rearrangement of the interfacial electrical double layer. Our results demonstrate the feasibility of using a graphene-based self-powered strategy for monitoring biofluid flow velocity with key performance metrics orders of magnitude higher than other electrical approaches.

physics.app-ph↗

arXiv2021

Interaction-aware Kalman Neural Networks for Trajectory Prediction

Forecasting the motion of surrounding obstacles (vehicles, bicycles, pedestrians and etc.) benefits the on-road motion planning for intelligent and autonomous vehicles. Complex scenes always yield great challenges in modeling the patterns of surrounding traffic. For example, one main challenge comes from the intractable interaction effects in a complex traffic system. In this paper, we propose a multi-layer architecture Interaction-aware Kalman Neural Networks (IaKNN) which involves an interaction layer for resolving high-dimensional traffic environmental observations as interaction-aware accelerations, a motion layer for transforming the accelerations to interaction aware trajectories, and a filter layer for estimating future trajectories with a Kalman filter network. Attributed to the multiple traffic data sources, our end-to-end trainable approach technically fuses dynamic and interaction-aware trajectories boosting the prediction performance. Experiments on the NGSIM dataset demonstrate that IaKNN outperforms the state-of-the-art methods in terms of effectiveness for traffic trajectory prediction.

cs.RO↗

arXiv2020

Heterogeneous Graph Collaborative Filtering

Graph-based collaborative filtering (CF) algorithms have gained increasing attention. Existing work in this literature usually models the user-item interactions as a bipartite graph, where users and items are two isolated node sets and edges between them indicate their interactions. Then, the unobserved preference of users can be exploited by modeling high-order connectivity on the bipartite graph. In this work, we propose to model user-item interactions as a heterogeneous graph which consists of not only user-item edges indicating their interaction but also user-user edges indicating their similarity. We develop heterogeneous graph collaborative filtering (HGCF), a GCN-based framework which can explicitly capture both the interaction signal and similarity signal through embedding propagation on the heterogeneous graph. Since the heterogeneous graph is more connected than the bipartite graph, the sparsity issue can be alleviated and the demand for expensive high-order connectivity modeling can be lowered. Extensive experiments conducted on three public benchmarks demonstrate its superiority over the state-of-the-arts. Further analysis verifies the importance of user-user edges in the graph, justifying the rationality and effectiveness of HGCF.

cs.IR↗

arXiv2020

Coarse-To-Fine Visual Localization Using Semantic Compact Map

Robust visual localization for urban vehicles remains challenging and unsolved. The limitation of computation efficiency and memory size has made it harder for large-scale applications. Since semantic information serves as a stable and compact representation of the environment, we propose a coarse-to-fine localization system based on a semantic compact map. Pole-like objects are stored in the compact map, then are extracted from semantically segmented images as observations. Localization is performed by a particle filter, followed by a pose alignment module decoupling translation and rotation to achieve better accuracy. We evaluate our system both on synthetic and realistic datasets and compare it with two baselines, a state-of-art semantic feature-based system, and a traditional SIFT feature-based system. Experiments demonstrate that even with a significantly small map, such as a 10 KB map for a 3.7 km long trajectory, our system provides a comparable accuracy with the baselines.

cs.RO↗

arXiv2020

Rate-dependent bifurcation dodging in a thermoacoustic system driven by colored noise

Tipping in multistable systems occurs usually by varying the input slightly, resulting in the output switching to an often unsatisfactory state. This phenomenon is manifested in thermoacoustic systems. This thermoacoustic instability may lead to the disintegration of rocket engines, gas turbines and aeroengines, so it is necessary to design control measures for its suppression. It was speculated that such unwanted instability states may be dodged by changing quickly enough the bifurcation parameters. Thus, in this work, based on a fundamental mathematical model of thermoacoustic systems driven by colored noise, the corresponding Fokker-Planck-Kolmogorov equation of the amplitude is derived by using a stochastic averaging method. A transient dynamical behavior is identified through a probability density analysis. We find that the rate of change of parameters and the correlation time of the noise are helpful to dodge thermoacoustic instability, while a relatively large noise intensity is a disadvantageous factor. In addition, power-law relationships between the maximum amplitude and the noise parameters are explored, and the probability of successfully dodging a thermoacoustic instability is calculated. These results serve as a guide to the design of engines and to propose an effective control strategy, which is of great significance to aerospace-related fields.

nlin.AO↗

arXiv2020

Cassandra: Detecting Trojaned Networks from Adversarial Perturbations

Deep neural networks are being widely deployed for many critical tasks due to their high classification accuracy. In many cases, pre-trained models are sourced from vendors who may have disrupted the training pipeline to insert Trojan behaviors into the models. These malicious behaviors can be triggered at the adversary's will and hence, cause a serious threat to the widespread deployment of deep models. We propose a method to verify if a pre-trained model is Trojaned or benign. Our method captures fingerprints of neural networks in the form of adversarial perturbations learned from the network gradients. Inserting backdoors into a network alters its decision boundaries which are effectively encoded in their adversarial perturbations. We train a two stream network for Trojan detection from its global ($L_\infty$ and $L_2$ bounded) perturbations and the localized region of high energy within each perturbation. The former encodes decision boundaries of the network and latter encodes the unknown trigger shape. We also propose an anomaly detection method to identify the target class in a Trojaned network. Our methods are invariant to the trigger type, trigger size, training data and network architecture. We evaluate our methods on MNIST, NIST-Round0 and NIST-Round1 datasets, with up to 1,000 pre-trained models making this the largest study to date on Trojaned network detection, and achieve over 92\% detection accuracy to set the new state-of-the-art.

cs.CV↗

arXiv2020

Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction

Click-through rate (CTR) prediction is an essential task in web applications such as online advertising and recommender systems, whose features are usually in multi-field form. The key of this task is to model feature interactions among different feature fields. Recently proposed deep learning based models follow a general paradigm: raw sparse input multi-filed features are first mapped into dense field embedding vectors, and then simply concatenated together to feed into deep neural networks (DNN) or other specifically designed networks to learn high-order feature interactions. However, the simple \emph{unstructured combination} of feature fields will inevitably limit the capability to model sophisticated interactions among different fields in a sufficiently flexible and explicit fashion. In this work, we propose to represent the multi-field features in a graph structure intuitively, where each node corresponds to a feature field and different fields can interact through edges. The task of modeling feature interactions can be thus converted to modeling node interactions on the corresponding graph. To this end, we design a novel model Feature Interaction Graph Neural Networks (Fi-GNN). Taking advantage of the strong representative power of graphs, our proposed model can not only model sophisticated feature interactions in a flexible and explicit fashion, but also provide good model explanations for CTR prediction. Experimental results on two real-world datasets show its superiority over the state-of-the-arts.

cs.IR↗

arXiv2020

Object-oriented SLAM using Quadrics and Symmetry Properties for Indoor Environments

Aiming at the application environment of indoor mobile robots, this paper proposes a sparse object-level SLAM algorithm based on an RGB-D camera. A quadric representation is used as a landmark to compactly model objects, including their position, orientation, and occupied space. The state-of-art quadric-based SLAM algorithm faces the observability problem caused by the limited perspective under the plane trajectory of the mobile robot. To solve the problem, the proposed algorithm fuses both object detection and point cloud data to estimate the quadric parameters. It finishes the quadric initialization based on a single frame of RGB-D data, which significantly reduces the requirements for perspective changes. As objects are often observed locally, the proposed algorithm uses the symmetrical properties of indoor artificial objects to estimate the occluded parts to obtain more accurate quadric parameters. Experiments have shown that compared with the state-of-art algorithm, especially on the forward trajectory of mobile robots, the proposed algorithm significantly improves the accuracy and convergence speed of quadric reconstruction. Finally, we made available an opensource implementation to replicate the experiments.

cs.RO↗

arXiv2020

Rate-dependent tipping-delay phenomenon in a thermoacoustic system with colored noise

Tipping is a phenomenon in multistable systems where small changes in inputs cause huge changes in outputs. When the parameter varies within a certain time scale, the rate will affect the tipping behaviors. These behaviors are undesirable in thermoacoustic systems, which are widely used in aviation, power generation and other industries. Thus, this paper aims at considering the tipping behaviors of the thermoacoustic system with the time-varying parameters and the combined excitations of additive and multiplicative colored noises. Transient dynamical behaviors for the proposed thermoacoustic model are implemented through the reduced Fokker-Planck-Kolmogorov equation derived by a standard stochastic averaging method. Then, the tipping problems of the rate-dependent thermoacoustic systems with random fluctuations are studied by virtue of the obtained probability density functions. Our results show that the rate delays the value of the tipping parameter compared to the one with the quasi-steady assumption, which is called as a rate-dependent tipping-delay phenomenon. Besides, the influences of the initial values, the rate, the changing time of the parameters, and the correlation time of the noises on the rate-dependent tipping-delay phenomenon are analyzed in detail. These results are of great significance for research in related fields such as aviation and land gas turbines.

nlin.AO↗

arXiv2020

Dependence of the Inverse Spin Hall Effect in Sr(Nb$_x$Ti$_{1-x}$)O$_3$ on the Nb concentration

We measured the spin rectify effect and the inverse spin Hall effect in Nb-doped SrTiO$_3$ by injecting the spins from ferromagnetic thin films to SrTiO$_3$ using spin pumping. It was shown that the spin injection is increased when the doping level is increased. However, the spin Hall angle decreases when Nb occupies more than $\sim$2\% of the Ti sites, which is due to that beyond this concentration, the electron contributed the spin Hall effect is from the $d-$orbitals of Nb instead those from the Ti. Our work points to the importance of orbital occupations in the (inverse) spin Hall effect. We may explore controllable spin and charge interconversion in oxide spintronics.

cond-mat.mes-hall↗

arXiv2019

Unsupervised Visual Representation Learning with Increasing Object Shape Bias

(Very early draft)Traditional supervised learning keeps pushing convolution neural network(CNN) achieving state-of-art performance. However, lack of large-scale annotation data is always a big problem due to the high cost of it, even ImageNet dataset is over-fitted by complex models now. The success of unsupervised learning method represented by the Bert model in natural language processing(NLP) field shows its great potential. And it makes that unlimited training samples becomes possible and the great universal generalization ability changes NLP research direction directly. In this article, we purpose a novel unsupervised learning method based on contrastive predictive coding. Under that, we are able to train model with any non-annotation images and improve model's performance to reach state-of-art performance at the same level of model complexity. Beside that, since the number of training images could be unlimited amplification, an universal large-scale pre-trained computer vision model is possible in the future.

cs.CV↗

arXiv2019

Allocations of Cold Standbys to Series and Parallel Systems with Dependent Components

In the context of industrial engineering, cold-standby redundancies allocation strategy is usually adopted to improve the reliability of coherent systems. This paper investigates optimal allocation strategies of cold standbys for series and parallel systems comprised of dependent components with left/right tail weakly stochastic arrangement increasing lifetimes. For the case of heterogeneous and independent matched cold standbys, it is proved that better redundancies should be put in the nodes having weaker [better] components for series [parallel] systems. For the case of homogeneous and independent cold standbys, it is shown that more redundancies should be put in standby with weaker [better] components to enhance the reliability of series [parallel] systems. The results developed here generalize and extend those corresponding ones in the literature to the case of series and parallel systems with dependent components. Numerical examples are also presented to provide guidance for the practical use of our theoretical findings.

stat.OT↗

arXiv2019

Optimal design of shell-graded-infill structures by a hybrid MMC-MMV approach

In the present work, a hybrid MMC-MMV approach is developed for designing additive manufacturing-oriented shell-graded-infill structures. The key idea is to describe the geometry of a shell-graded-infill structure explicitly using some geometry parameters. To this end, a set of morphable voids is adopted to describe the boundary of the coating shell, while a set of morphable components combing with a coordinate perturbation technique are introduced to represent the graded infill distribution. Under such treatment, both the crisp boundary of the coating shell and the graded infill can be optimized simultaneously, with a small number of design variables. Numerical examples demonstrate the effectiveness of the proposed approach.

cs.CE↗

arXiv2019

Unsupervised Annotation of Phenotypic Abnormalities via Semantic Latent Representations on Electronic Health Records

The extraction of phenotype information which is naturally contained in electronic health records (EHRs) has been found to be useful in various clinical informatics applications such as disease diagnosis. However, due to imprecise descriptions, lack of gold standards and the demand for efficiency, annotating phenotypic abnormalities on millions of EHR narratives is still challenging. In this work, we propose a novel unsupervised deep learning framework to annotate the phenotypic abnormalities from EHRs via semantic latent representations. The proposed framework takes the advantage of Human Phenotype Ontology (HPO), which is a knowledge base of phenotypic abnormalities, to standardize the annotation results. Experiments have been conducted on 52,722 EHRs from MIMIC-III dataset. Quantitative and qualitative analysis have shown the proposed framework achieves state-of-the-art annotation performance and computational efficiency compared with other methods.

cs.CL↗

arXiv2019

Understanding Thermal Annealing of Artificial Spin Ice

We have performed a detailed study of thermal annealing of the moment configuration in artificial spin ice. Permalloy (Ni$_{80}$Fe$_{20}$) artificial spin ice samples were examined in the prototypical square ice geometry, studying annealing as a function of island thickness, island shape, and annealing temperature and duration. We also measured the Curie temperature as a function of film thickness, finding that thickness has a strong effect on the Curie temperature in regimes of relevance to many studies of the dynamics of artificial spin ice systems. Increasing the interaction energy between island moments and reducing the energy barrier to flipping the island moments allows the system to more closely approach the collective low energy state of the moments upon annealing, suggesting new channels for understanding the thermalization processes in these important model systems.

cond-mat.mes-hall↗

arXiv2019

Persistence of Delayed Complex Balanced Chemical Reaction Networks

In this paper, we derive two sufficient conditions to diagnose the persistence of two classes of delayed complex balanced chemical reaction network systems equipped with mass-action kinetics. One class is identified by $\dim Z_W=\dim\mathscr{S}-1$ ($Z_W$ is defined by \ref{eq:g} while $\mathscr{S}$ is the stoichiometric subspace of the network), the other class is identified through $\dim Z_W=0$ for any semilocking species set $W$ in the network. Then we also derive that delayed complex balanced systems with 2-d stoichiometric subspace are persistent. The results recur those proposed by Anderson et al. [D. F. Anderson, \textit{SIAM J. Appl. Math.}, 68 (2008), pp. 1464-1476; D. F. Anderson and A. Shiu, \textit{SIAM J. Appl. Math.}, 70 (2010), pp. 1840-1858] for checking the persistence of complex balanced reaction network systems without time delay. Further, we prove the above mentioned two classes of network systems are globally asymptotically stable at the corresponding positive equilibrium if the trajectory starts from a positive initial function. We illustrate the analysis by two numerical examples.

math.DS↗

arXiv2019

Integrated Multi-omics Analysis Using Variational Autoencoders: Application to Pan-cancer Classification

Different aspects of a clinical sample can be revealed by multiple types of omics data. Integrated analysis of multi-omics data provides a comprehensive view of patients, which has the potential to facilitate more accurate clinical decision making. However, omics data are normally high dimensional with large number of molecular features and relatively small number of available samples with clinical labels. The "dimensionality curse" makes it challenging to train a machine learning model using high dimensional omics data like DNA methylation and gene expression profiles. Here we propose an end-to-end deep learning model called OmiVAE to extract low dimensional features and classify samples from multi-omics data. OmiVAE combines the basic structure of variational autoencoders with a classification network to achieve task-oriented feature extraction and multi-class classification. The training procedure of OmiVAE is comprised of an unsupervised phase without the classifier and a supervised phase with the classifier. During the unsupervised phase, a hierarchical cluster structure of samples can be automatically formed without the need for labels. And in the supervised phase, OmiVAE achieved an average classification accuracy of 97.49% after 10-fold cross-validation among 33 tumour types and normal samples, which shows better performance than other existing methods. The OmiVAE model learned from multi-omics data outperformed that using only one type of omics data, which indicates that the complementary information from different omics datatypes provides useful insights for biomedical tasks like cancer classification.

cs.LG↗

arXiv2019

Semi-supervised Compatibility Learning Across Categories for Clothing Matching

Learning the compatibility between fashion items across categories is a key task in fashion analysis, which can decode the secret of clothing matching. The main idea of this task is to map items into a latent style space where compatible items stay close. Previous works try to build such a transformation by minimizing the distances between annotated compatible items, which require massive item-level supervision. However, these annotated data are expensive to obtain and hard to cover the numerous items with various styles in real applications. In such cases, these supervised methods fail to achieve satisfactory performances. In this work, we propose a semi-supervised method to learn the compatibility across categories. We observe that the distributions of different categories have intrinsic similar structures. Accordingly, the better distributions align, the closer compatible items across these categories become. To achieve the alignment, we minimize the distances between distributions with unsupervised adversarial learning, and also the distances between some annotated compatible items which play the role of anchor points to help align. Experimental results on two real-world datasets demonstrate the effectiveness of our method.

cs.IR↗