arXiv subjects

Meng Li

Publications and source records attributed to Meng Li.

At least 379 records · Page 21Linked to original sources

arXiv2018

Automated segmentaiton and classification of arterioles and venules using Cascading Dilated Convolutional Neural Networks

The change of retinal vasculature is an early sign of many vascular and systematic diseases, such as diabetes and hypertension. Different behaviors of retinal arterioles and venules form an important metric to measure the disease severity. Therefore, an accurate classification of arterioles and venules is of great necessity. In this work, we propose a novel architecture of deep convolutional neural network for segmenting and classifying arterioles and venules on retinal fundus images. This network takes the original color fundus image as inputs and multi-class labels as outputs. We adopt the encoding-decoding structure (Unet) as the backbone network of our proposed model. To improve the classification accuracy, we develop a special encoding path that couples InceptionV4 modules and Cascading Dilated Convolutions (CDCs) on top of the backbone network. The model is thus able to extract and fuse high-level semantic features from multi-scale receptive fields. The proposed method has outperformed the previous state-of-the-art method on DRIVE dataset with an accuracy of 0.955 $\pm$ 0.002.

cs.CV↗

arXiv2018

Multistep Speed Prediction on Traffic Networks: A Graph Convolutional Sequence-to-Sequence Learning Approach with Attention Mechanism

Multistep traffic forecasting on road networks is a crucial task in successful intelligent transportation system applications. To capture the complex non-stationary temporal dynamics and spatial dependency in multistep traffic-condition prediction, we propose a novel deep learning framework named attention graph convolutional sequence-to-sequence model (AGC-Seq2Seq). In the proposed deep learning framework, spatial and temporal dependencies are modeled through the Seq2Seq model and graph convolution network separately, and the attention mechanism along with a newly designed training method based on the Seq2Seq architecture is proposed to overcome the difficulty in multistep prediction and further capture the temporal heterogeneity of traffic pattern. We conduct numerical tests to compare AGC-Seq2Seq with other benchmark models using a real-world dataset. The results indicate that our model yields the best prediction performance in terms of various prediction error measures. Furthermore, the variation of spatiotemporal correlation of traffic conditions under different perdition steps and road segments is revealed through sensitivity analyses.

cs.LG↗

arXiv2018

Streaming Algorithms for Planar Convex Hulls

Many classical algorithms are known for computing the convex hull of a set of $n$ point in $\mathbb{R}^2$ using $O(n)$ space. For large point sets, whose size exceeds the size of the working space, these algorithms cannot be directly used. The current best streaming algorithm for computing the convex hull is computationally expensive, because it needs to solve a set of linear programs. In this paper, we propose simpler and faster streaming and W-stream algorithms for computing the convex hull. Our streaming algorithm has small pass complexity, which is roughly a square root of the current best bound, and it is simpler in the sense that our algorithm mainly relies on computing the convex hulls of smaller point sets. Our W-stream algorithms, one of which is deterministic and the other of which is randomized, have nearly-optimal tradeoff between the pass complexity and space usage, as we established by a new unconditional lower bound.

cs.CG↗

arXiv2018

Deep Learning for Quality Control of Subcortical Brain 3D Shape Models

We present several deep learning models for assessing the morphometric fidelity of deep grey matter region models extracted from brain MRI. We test three different convolutional neural net architectures (VGGNet, ResNet and Inception) over 2D maps of geometric features. Further, we present a novel geometry feature augmentation technique based on a parametric spherical mapping. Finally, we present an approach for model decision visualization, allowing human raters to see the areas of subcortical shapes most likely to be deemed of failing quality by the machine. Our training data is comprised of 5200 subjects from the ENIGMA Schizophrenia MRI cohorts, and our test dataset contains 1500 subjects from the ENIGMA Major Depressive Disorder cohorts. Our final models reduce human rater time by 46-70%. ResNet outperforms VGGNet and Inception for all of our predictive tasks.

q-bio.NC↗

arXiv2018

Computed Tomography Image Enhancement using 3D Convolutional Neural Network

Computed tomography (CT) is increasingly being used for cancer screening, such as early detection of lung cancer. However, CT studies have varying pixel spacing due to differences in acquisition parameters. Thick slice CTs have lower resolution, hindering tasks such as nodule characterization during computer-aided detection due to partial volume effect. In this study, we propose a novel 3D enhancement convolutional neural network (3DECNN) to improve the spatial resolution of CT studies that were acquired using lower resolution/slice thicknesses to higher resolutions. Using a subset of the LIDC dataset consisting of 20,672 CT slices from 100 scans, we simulated lower resolution/thick section scans then attempted to reconstruct the original images using our 3DECNN network. A significant improvement in PSNR (29.3087dB vs. 28.8769dB, p-value < 2.2e-16) and SSIM (0.8529dB vs. 0.8449dB, p-value < 2.2e-16) compared to other state-of-art deep learning methods is observed.

cs.CV↗

arXiv2018

Data Efficient Lithography Modeling with Transfer Learning and Active Data Selection

Lithography simulation is one of the key steps in physical verification, enabled by the substantial optical and resist models. A resist model bridges the aerial image simulation to printed patterns. While the effectiveness of learning-based solutions for resist modeling has been demonstrated, they are considerably data-demanding. Meanwhile, a set of manufactured data for a specific lithography configuration is only valid for the training of one single model, indicating low data efficiency. Due to the complexity of the manufacturing process, obtaining enough data for acceptable accuracy becomes very expensive in terms of both time and cost, especially during the evolution of technology generations when the design space is intensively explored. In this work, we propose a new resist modeling framework for contact layers, utilizing existing data from old technology nodes and active selection of data in a target technology node, to reduce the amount of data required from the target lithography configuration. Our framework based on transfer learning and active learning techniques is effective within a competitive range of accuracy, i.e., 3-10X reduction on the amount of training data with comparable accuracy to the state-of-the-art learning approach.

cs.LG↗

arXiv2018

Unconditional superconvergence analysis of a linearized Crank-Nicolson Galerkin FEM for generalized Ginzburg-Landau equation

In this paper, a linearized Crank-Nicolson Galerkin finite element method (FEM) for generalized Ginzburg-Landau equation (GLE) is considered, in which, the difference method in time and the standard Galerkin FEM are employed. Based on the linearized Crank-Nicolson difference method in time and the standard Galerkin finite element method with bilinear element in space, the time-discrete and space-time discrete systems are both constructed. We focus on a rigorous analysis and consideration of unconditional superconvergence error estimates of the discrete schemes. Firstly, by virtue of the temporal error results, the regularity for the time-discrete system is presented. Secondly, the classical Ritz projection is used to obtain the spatial error with order $O(h^2)$ in the sense of $L^2-$norm. Thanks to the relationship between the Ritz projection and the interpolated projection, the superclose estimate with order $O(τ^2 + h^2)$ in the sense of $H^1-$norm is derived. Thirdly, it follows from the interpolated postprocessing technique that the global superconvergence result is deduced. Finally, some numerical results are provided to confirm the theoretical analysis.

math.NA↗

arXiv2018

Comparing and weighting imperfect models using D-probabilities

We propose a new approach for assigning weights to models using a divergence-based method ({\em D-probabilities}), relying on evaluating parametric models relative to a nonparametric Bayesian reference using Kullback-Leibler divergence. D-probabilities are useful in goodness-of-fit assessments, in comparing imperfect models, and in providing model weights to be used in model aggregation. D-probabilities avoid some of the disadvantages of Bayesian model probabilities, such as large sensitivity to prior choice, and tend to place higher weight on a greater diversity of models. In an application to linear model selection against a Gaussian process reference, we provide simple analytic forms for routine implementation and show that D-probabilities automatically penalize model complexity. Some asymptotic properties are described, and we provide interesting probabilistic interpretations of the proposed model weights. The framework is illustrated through simulation examples and an ozone data application.

stat.ME↗

arXiv2018

Reducing over-clustering via the powered Chinese restaurant process

Dirichlet process mixture (DPM) models tend to produce many small clusters regardless of whether they are needed to accurately characterize the data - this is particularly true for large data sets. However, interpretability, parsimony, data storage and communication costs all are hampered by having overly many clusters. We propose a powered Chinese restaurant process to limit this kind of problem and penalize over clustering. The method is illustrated using some simulation examples and data with large and small sample size including MNIST and the Old Faithful Geyser data.

cs.LG↗

arXiv2018

Standardization of multivariate Gaussian mixture models and background adjustment of PET images in brain oncology

In brain oncology, it is routine to evaluate the progress or remission of the disease based on the differences between a pre-treatment and a post-treatment Positron Emission Tomography (PET) scan. Background adjustment is necessary to reduce confounding by tissue-dependent changes not related to the disease. When modeling the voxel intensities for the two scans as a bivariate Gaussian mixture, background adjustment translates into standardizing the mixture at each voxel, while tumor lesions present themselves as outliers to be detected. In this paper, we address the question of how to standardize the mixture to a standard multivariate normal distribution, so that the outliers (i.e., tumor lesions) can be detected using a statistical test. We show theoretically and numerically that the tail distribution of the standardized scores is favorably close to standard normal in a wide range of scenarios while being conservative at the tails, validating voxelwise hypothesis testing based on standardized scores. To address standardization in spatially heterogeneous image data, we propose a spatial and robust multivariate expectation-maximization (EM) algorithm, where prior class membership probabilities are provided by transformation of spatial probability template maps and the estimation of the class mean and covariances are robust to outliers. Simulations in both univariate and bivariate cases suggest that standardized scores with soft assignment have tail probabilities that are either very close to or more conservative than standard normal. The proposed methods are applied to a real data set from a PET phantom experiment, yet they are generic and can be used in other contexts.

stat.ME↗

arXiv2018

Quantum communication protocols by quantum walks with two coins

We introduce some new perfect state transfer and teleportation schemes by quantum walks with two coins. Encoding the transferred information in coin 1 state and alternatively using two coin operators, we can perfectly recover the information on coin 1 state at target position only by at most two times of flipping operation. Based on quantum walks with two coins either on the line or on the $N$-circle, we can perfectly transfer any qubit state. In addition, using quantum walks with two coins either on complete graphs or regular graphs, we can first implement perfect qudit state transfer by quantum walks. Compared with existing schemes driven by one coin, more general graph structures can be used to perfectly transfer more general state. Moreover, the external control of coin operator during the transmitting process can be decreased greatly. Selecting coin 1 as the sender and coin 2 as the receiver, we also study how to realize generalized teleportation over long steps of walks by the above quantum walk models. Because quantum walks is an universal quantum computation model, our schemes may provide an universal platform for the design of quantum network and quantum computer.

quant-ph↗

arXiv2018

PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training

Massive data exist among user local platforms that usually cannot support deep neural network (DNN) training due to computation and storage resource constraints. Cloud-based training schemes provide beneficial services but suffer from potential privacy risks due to excessive user data collection. To enable cloud-based DNN training while protecting the data privacy simultaneously, we propose to leverage the intermediate representations of the data, which is achieved by splitting the DNNs and deploying them separately onto local platforms and the cloud. The local neural network (NN) is used to generate the feature representations. To avoid local training and protect data privacy, the local NN is derived from pre-trained NNs. The cloud NN is then trained based on the extracted intermediate representations for the target learning task. We validate the idea of DNN splitting by characterizing the dependency of privacy loss and classification accuracy on the local NN topology for a convolutional NN (CNN) based image classification task. Based on the characterization, we further propose PrivyNet to determine the local NN topology, which optimizes the accuracy of the target learning task under the constraints on privacy loss, local computation, and storage. The efficiency and effectiveness of PrivyNet are demonstrated with the CIFAR-10 dataset.

cs.LG↗

arXiv2017

BayesBD: An R Package for Bayesian Inference on Image Boundaries

We present the BayesBD package providing Bayesian inference for boundaries of noisy images. The BayesBD package implements flexible Gaussian process priors indexed by the circle to recover the boundary in a binary or Gaussian noised image, with the benefits of guaranteed geometric restrictions on the estimated boundary, (nearly) minimax optimal and smoothness adaptive convergence rates, and convenient joint inferences under certain assumptions. The core sampling tasks for our model have linear complexity, and our implementation in c++ using packages Rcpp and RcppArmadillo is computationally efficient. Users can access the full functionality of the package in both Rgui and the corresponding shiny application. Additionally, the package includes numerous utility functions to aid users in data preparation and analysis of results. We compare BayesBD with selected existing packages using both simulations and real data applications, and demonstrate the excellent performance and flexibility of BayesBD even when the observation contains complicated structural information that may violate its assumptions.

stat.CO↗

arXiv2017

Machine Learning for Large-Scale Quality Control of 3D Shape Models in Neuroimaging

As very large studies of complex neuroimaging phenotypes become more common, human quality assessment of MRI-derived data remains one of the last major bottlenecks. Few attempts have so far been made to address this issue with machine learning. In this work, we optimize predictive models of quality for meshes representing deep brain structure shapes. We use standard vertex-wise and global shape features computed homologously across 19 cohorts and over 7500 human-rated subjects, training kernelized Support Vector Machine and Gradient Boosted Decision Trees classifiers to detect meshes of failing quality. Our models generalize across datasets and diseases, reducing human workload by 30-70\%, or equivalently hundreds of human rater hours for datasets of comparable size, with recall rates approaching inter-rater reliability.

q-bio.QM↗

arXiv2016

Not Call Me Cellular Any More: The Emergence of Scaling Law, Fractal Patterns and Small-World in Wireless Networks

In conventional cellular networks, for base stations (BSs) that are deployed far away from each other, it is general to assume them to be mutually independent. Nevertheless, after long-term evolution of cellular networks in various generations, this assumption no longer holds. Instead, the BSs, which seem to be gradually deployed by operators in a service-oriented manner, have embedded many fundamentally distinctive features in their locations, coverage and traffic loading. These features can be leveraged to analyze the intrinsic pattern in BSs and even human community. In this paper, according to large-scale measurement datasets, we build up a correlation model of BSs by utilizing one of the most important features, ie., spatial traffic. Coupling with the theory of complex networks, we make further analysis on the structure and characteristics of this traffic load correlation model. Numerical results show that the degree distribution follows scale-free property. Also the datasets unveil the characteristics of fractality and small-world. Furthermore, we apply collective influence (CI) algorithm to localize the influential base stations and demonstrate that some low-degree BSs may outrank BSs with larger degree.

cs.SI↗

arXiv2016

Machine-to-Machine (M2M) Communications in Software-defined and Virtualized Cellular Networks

Machine-to-machine (M2M) communications have attracted great attention from both academia and industry. In this paper, with recent advances in wireless network virtualization and software-defined networking (SDN), we propose a novel framework for M2M communications in software-defined cellular networks with wireless network virtualization. In the proposed framework, according to different functions and quality of service (QoS) requirements of machine-type communication devices (MTCDs), a hypervisor enables the virtualization of the physical M2M network, which is abstracted and sliced into multiple virtual M2M networks. In addition, we develop a decision-theoretic approach to optimize the random access process of M2M communications. Furthermore, we develop a feedback and control loop to dynamically adjust the number of resource blocks (RBs) that are used in the random access phase in a virtual M2M network by the SDN controller. Extensive simulation results with different system parameters are presented to show the performance of the proposed scheme.

cs.NI↗

arXiv2016

Software-defined and Virtualized Cellular Networks with M2M Communications

Machine-to-machine (M2M) communications have attracted great attention from both academia and industry. In this paper, with recent advances in wireless network virtualization and software-defined networking (SDN), we propose a novel framework for M2M communications in software-defined cellular networks with wireless network virtualization. In the proposed framework, according to different functions and quality of service (QoS) requirements of machine-type communication devices (MTCDs), a hypervisor enables the virtualization of the physical M2M network, which is abstracted and sliced into multiple virtual M2M networks. Moreover, we formulate a decision-theoretic approach to optimize the random access process of M2M communications. In addition, we develop a feedback and control loop to dynamically adjust the number of resource blocks (RBs) that are used in the random access phase in a virtual M2M network by the SDN controller. Extensive simulation results with different system parameters are presented to show the performance of the proposed scheme.

cs.NI↗

arXiv2016

Machine to Machine (M2M) Communications in Virtualized Vehicular Ad Hoc Networks

With the growing interest in the use of internet of things (IoT), machine-to-machine (M2M) communications have become an important networking paradigm. In this paper, with recent advances in wireless network virtualization (WNV), we propose a novel framework for M2M communications in vehicular ad-hoc networks (VANETs) with WNV. In the proposed framework, according to different applications and quality of service (QoS) requirements of vehicles, a hypervisor enables the virtualization of the physical vehicular network, which is abstracted and sliced into multiple virtual networks. Moreover, the process of resource blocks (RBs) selection and random access in each virtual vehicular network is formulated as a partially observable Markov decision process (POMDP), which can achieve the maximum reward about transmission capacity. The optimal policy for RBs selection is derived by virtue of a dynamic programming approach. Extensive simulation results with different system parameters are presented to show the performance improvement of the proposed scheme.

cs.NI↗