arXiv subjects

Wei Fan

Publications and source records attributed to Wei Fan.

At least 199 records · Page 11Linked to original sources

arXiv2019

Near-field Ultra-wideband mmWave Channel Characterization Using Successive Cancellation Beamspace UCA Algorithm

Of the wide palette of 5G features, ultra-wide bandwidth and large-scale antenna configuration are regarded as the essential enabling technology components at millimeter wave (mmWave) communication. Accurate knowledge of delay and angle information of multipath components is essential for many applications in mmWave systems. There is a strong need for a low computation-cost channel estimation algorithm for such systems, where typically adopted far-field and narrowband assumptions might be violated. In this work, a generic yet novel beamspace uniform circular array (UCA) beamforming algorithm with successive cancellation scheme is proposed to jointly detect the impinging angle and delay of the multipath components. The proposed algorithm is computationally cheap and it works for ultra-wideband (UWB) systems in the near-field conditions. Both numerical simulations and experimental validation results are provided to demonstrate the effectiveness and robustness of the proposed algorithm, compared to the state-of-art works.

eess.SP↗

arXiv2018

Multi-Task Learning with Multi-View Attention for Answer Selection and Knowledge Base Question Answering

Answer selection and knowledge base question answering (KBQA) are two important tasks of question answering (QA) systems. Existing methods solve these two tasks separately, which requires large number of repetitive work and neglects the rich correlation information between tasks. In this paper, we tackle answer selection and KBQA tasks simultaneously via multi-task learning (MTL), motivated by the following motivations. First, both answer selection and KBQA can be regarded as a ranking problem, with one at text-level while the other at knowledge-level. Second, these two tasks can benefit each other: answer selection can incorporate the external knowledge from knowledge base (KB), while KBQA can be improved by learning contextual information from answer selection. To fulfill the goal of jointly learning these two tasks, we propose a novel multi-task learning scheme that utilizes multi-view attention learned from various perspectives to enable these tasks to interact with each other as well as learn more comprehensive sentence representations. The experiments conducted on several real-world datasets demonstrate the effectiveness of the proposed method, and the performance of answer selection and KBQA is improved. Also, the multi-view attention scheme is proved to be effective in assembling attentive information from different representational perspectives.

cs.CL↗

arXiv2018

AURORA: Auditing PageRank on Large Graphs

Ranking on large-scale graphs plays a fundamental role in many high-impact application domains, ranging from information retrieval, recommender systems, sports team management, biology to neuroscience and many more. PageRank, together with many of its random walk based variants, has become one of the most well-known and widely used algorithms, due to its mathematical elegance and the superior performance across a variety of application domains. Important as it might be, state-of-the-art lacks an intuitive way to explain the ranking results by PageRank (or its variants), e.g., why it thinks the returned top-k webpages are most important ones in the entire graph; why it gives a higher rank to actor John than actor Smith in terms of their relevance w.r.t. a particular movie? In order to answer these questions, this paper proposes a paradigm shift for PageRank, from identifying which nodes are most important to understanding why the ranking algorithm gives a particular ranking result. We formally define the PageRank auditing problem, whose central idea is to identify a set of key graph elements (e.g., edges, nodes, subgraphs) with the highest influence on the ranking results. We formulate it as an optimization problem and propose a family of effective and scalable algorithms (AURORA) to solve it. Our algorithms measure the influence of graph elements and incrementally select influential elements w.r.t. their gradients over the ranking results. We perform extensive empirical evaluations on real-world datasets, which demonstrate that the proposed methods (AURORA) provide intuitive explanations with a linear scalability.

cs.SI↗

arXiv2018

AnatomyNet: Deep Learning for Fast and Fully Automated Whole-volume Segmentation of Head and Neck Anatomy

Methods: Our deep learning model, called AnatomyNet, segments OARs from head and neck CT images in an end-to-end fashion, receiving whole-volume HaN CT images as input and generating masks of all OARs of interest in one shot. AnatomyNet is built upon the popular 3D U-net architecture, but extends it in three important ways: 1) a new encoding scheme to allow auto-segmentation on whole-volume CT images instead of local patches or subsets of slices, 2) incorporating 3D squeeze-and-excitation residual blocks in encoding layers for better feature representation, and 3) a new loss function combining Dice scores and focal loss to facilitate the training of the neural model. These features are designed to address two main challenges in deep-learning-based HaN segmentation: a) segmenting small anatomies (i.e., optic chiasm and optic nerves) occupying only a few slices, and b) training with inconsistent data annotations with missing ground truth for some anatomical structures. Results: We collected 261 HaN CT images to train AnatomyNet, and used MICCAI Head and Neck Auto Segmentation Challenge 2015 as a benchmark dataset to evaluate the performance of AnatomyNet. The objective is to segment nine anatomies: brain stem, chiasm, mandible, optic nerve left, optic nerve right, parotid gland left, parotid gland right, submandibular gland left, and submandibular gland right. Compared to previous state-of-the-art results from the MICCAI 2015 competition, AnatomyNet increases Dice similarity coefficient by 3.3% on average. AnatomyNet takes about 0.12 seconds to fully segment a head and neck CT image of dimension 178 x 302 x 225, significantly faster than previous methods. In addition, the model is able to process whole-volume CT images and delineate all OARs in one pass, requiring little pre- or post-processing. https://github.com/wentaozhu/AnatomyNet-for-anatomical-segmentation.git.

cs.CV↗

arXiv2018

Finding Similar Medical Questions from Question Answering Websites

The past few years have witnessed the flourishing of crowdsourced medical question answering (Q&A) websites. Patients who have medical information demands tend to post questions about their health conditions on these crowdsourced Q&A websites and get answers from other users. However, we observe that a large portion of new medical questions cannot be answered in time or receive only few answers from these websites. On the other hand, we notice that solved questions have great potential to solve this challenge. Motivated by these, we propose an end-to-end system that can automatically find similar questions for unsolved medical questions. By learning the vector presentation of unsolved questions and their candidate similar questions, the proposed system outputs similar questions according to the similarity between vector representations. Through the vector representation, the similar questions are found at the question level, and the diversity of medical questions expression issue can be addressed. Further, we handle two more important issues, i.e., training data generation issue and efficiency issue, associated with the LSTM training procedure and the retrieval of candidate similar questions. The effectiveness of the proposed system is validated on a large-scale real-world dataset collected from a crowdsourced maternal-infant Q&A website.

cs.AI↗

arXiv2018

Wilson loop of the heterotic sigma model and the sv-map

The single-valued projection (sv) is a relation between scattering amplitudes of gauge bosons in heterotic and open superstring theories. Recently we have studied sv from the aspect of nonlinear sigma models [1], where the gauge physics of open string sigma model is under the Wilson loop representation but the gauge physics of heterotic string sigma model is under the fermionic representation since the Wilson loop representation is absent in the heterotic case. There we showed that the sv comes from a sum of six radial orderings of heterotic vertices on the complex plane. In this paper, we propose a Wilson loop representation for the heterotic case and using the Wilson loop representation to show that sv comes from a sum of two opposite-directed contours of the heterotic sigma model. We firstly prove that the Wilson loop is the exact propagator of the fermion field that carry the gauge physics of the heterotic string in the fermionic representation. Then we construct the action of the heterotic string sigma model in terms of the Wilson loop, by exploring the geometry of the Wilson loop and by generalizing the nonabelian Stokes's theorem [2], [3], [4] to the fermionic case. After that, we compute some three loop and four loop diagrams as an example, to show how the sv for $ζ_2$ and $ζ_3$ arises from a sum of the contours of the Wilson loop. Finally we conjecture that this sum of contours of the Wilson loop is the mechanism behind the sv for general cases.

hep-th↗

arXiv2018

Design and characterization of high energy micro-CT with a laser-based X-ray source

The increasingly demand for machining accuracy and product quality excites a great interest in high-resolution non-destructive testing (NDT) methods, but spatial resolution of conventional high-energy computed tomography (CT) is limited to sub-millimeter because of large X-ray spot size. Therefore, we propose a novel high-resolution high-energy CT based on laser-driven X-ray source and prove its feasibility to allow high-spatial-resolution tomographic imaging of dense objects. A numerical model is developed with a consideration of realistic factors including parameter fluctuations, statistical noise and detecting efficiency. By using modulation transfer functions, the system performance is quantitatively characterized and optimized in terms of source characteristics, detector aperture, geometrical configuration and projection parameters. As a result, the simulated tomography for a high-density object (up to 19.35g/cm3) achieves a basic spatial resolution of 64.9μm. This concept expands the prospects of laser-based compact X-ray sources and shows a great potential to achieve high-perspectivity micro-CT imaging for various industrial applications.

physics.ins-det↗

arXiv2018

DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification

In this work, we present a fully automated lung computed tomography (CT) cancer diagnosis system, DeepLung. DeepLung consists of two components, nodule detection (identifying the locations of candidate nodules) and classification (classifying candidate nodules into benign or malignant). Considering the 3D nature of lung CT data and the compactness of dual path networks (DPN), two deep 3D DPN are designed for nodule detection and classification respectively. Specifically, a 3D Faster Regions with Convolutional Neural Net (R-CNN) is designed for nodule detection with 3D dual path blocks and a U-net-like encoder-decoder structure to effectively learn nodule features. For nodule classification, gradient boosting machine (GBM) with 3D dual path network features is proposed. The nodule classification subnetwork was validated on a public dataset from LIDC-IDRI, on which it achieved better performance than state-of-the-art approaches and surpassed the performance of experienced doctors based on image modality. Within the DeepLung system, candidate nodules are detected first by the nodule detection subnetwork, and nodule diagnosis is conducted by the classification subnetwork. Extensive experimental results demonstrate that DeepLung has performance comparable to experienced doctors both for the nodule-level and patient-level diagnosis on the LIDC-IDRI dataset.\footnote{https://github.com/uci-cbcl/DeepLung.git}

cs.CV↗

arXiv2017

SV-map between Type I and Heterotic Sigma Models

The scattering amplitudes of gauge bosons in heterotic and open superstring theories are related by the single-valued projection which yields heterotic amplitudes by selecting a subset of multiple zeta value coefficients in the $α'$ (string tension parameter) expansion of open string amplitudes. In the present work, we argue that this relation holds also at the level of low-energy expansions (or individual Feynman diagrams) of the respective effective actions, by investigating the beta functions of two-dimensional sigma models describing world-sheets of open and heterotic strings. We analyze the sigma model Feynman diagrams generating identical effective action terms in both theories and show that the heterotic coefficients are given by the single-valued projection of the open ones. The single-valued projection appears as a result of summing over all radial orderings of heterotic vertices on the complex plane representing string world-sheet.

hep-th↗

arXiv2017

Bringing Semantic Structures to User Intent Detection in Online Medical Queries

The Internet has revolutionized healthcare by offering medical information ubiquitously to patients via web search. The healthcare status, complex medical information needs of patients are expressed diversely and implicitly in their medical text queries. Aiming to better capture a focused picture of user's medical-related information search and shed insights on their healthcare information access strategies, it is challenging yet rewarding to detect structured user intentions from their diversely expressed medical text queries. We introduce a graph-based formulation to explore structured concept transitions for effective user intent detection in medical queries, where each node represents a medical concept mention and each directed edge indicates a medical concept transition. A deep model based on multi-task learning is introduced to extract structured semantic transitions from user queries, where the model extracts word-level medical concept mentions as well as sentence-level concept transitions collectively. A customized graph-based mutual transfer loss function is designed to impose explicit constraints and further exploit the contribution of mentioning a medical concept word to the implication of a semantic transition. We observe an 8% relative improvement in AUC and 23% relative reduction in coverage error by comparing the proposed model with the best baseline model for the concept transition inference task on real-world medical text queries.

cs.CL↗

arXiv2017

DeepLung: 3D Deep Convolutional Nets for Automated Pulmonary Nodule Detection and Classification

In this work, we present a fully automated lung CT cancer diagnosis system, DeepLung. DeepLung contains two parts, nodule detection and classification. Considering the 3D nature of lung CT data, two 3D networks are designed for the nodule detection and classification respectively. Specifically, a 3D Faster R-CNN is designed for nodule detection with a U-net-like encoder-decoder structure to effectively learn nodule features. For nodule classification, gradient boosting machine (GBM) with 3D dual path network (DPN) features is proposed. The nodule classification subnetwork is validated on a public dataset from LIDC-IDRI, on which it achieves better performance than state-of-the-art approaches, and surpasses the average performance of four experienced doctors. For the DeepLung system, candidate nodules are detected first by the nodule detection subnetwork, and nodule diagnosis is conducted by the classification subnetwork. Extensive experimental results demonstrate the DeepLung is comparable to the experienced doctors both for the nodule-level and patient-level diagnosis on the LIDC-IDRI dataset.

cs.CV↗

arXiv2017

Lesion detection and Grading of Diabetic Retinopathy via Two-stages Deep Convolutional Neural Networks

We propose an automatic diabetic retinopathy (DR) analysis algorithm based on two-stages deep convolutional neural networks (DCNN). Compared to existing DCNN-based DR detection methods, the proposed algorithm have the following advantages: (1) Our method can point out the location and type of lesions in the fundus images, as well as giving the severity grades of DR. Moreover, since retina lesions and DR severity appear with different scales in fundus images, the integration of both local and global networks learn more complete and specific features for DR analysis. (2) By introducing imbalanced weighting map, more attentions will be given to lesion patches for DR grading, which significantly improve the performance of the proposed algorithm. In this study, we label 12,206 lesion patches and re-annotate the DR grades of 23,595 fundus images from Kaggle competition dataset. Under the guidance of clinical ophthalmologists, the experimental results show that our local lesion detection net achieve comparable performance with trained human observers, and the proposed imbalanced weighted scheme also be proved to significantly improve the capability of our DCNN-based DR grading algorithm.

cs.CV↗

arXiv2016

An Automated CNN Recommendation System for Image Classification Tasks

Nowadays the CNN is widely used in practical applications for image classification task. However the design of the CNN model is very professional work and which is very difficult for ordinary users. Besides, even for experts of CNN, to select an optimal model for specific task may still need a lot of time (to train many different models). In order to solve this problem, we proposed an automated CNN recommendation system for image classification task. Our system is able to evaluate the complexity of the classification task and the classification ability of the CNN model precisely. By using the evaluation results, the system can recommend the optimal CNN model and which can match the task perfectly. The recommendation process of the system is very fast since we don't need any model training. The experiment results proved that the evaluation methods are very accurate and reliable.

cs.CV↗

arXiv2016

Multi-source Hierarchical Prediction Consolidation

In big data applications such as healthcare data mining, due to privacy concerns, it is necessary to collect predictions from multiple information sources for the same instance, with raw features being discarded or withheld when aggregating multiple predictions. Besides, crowd-sourced labels need to be aggregated to estimate the ground truth of the data. Because of the imperfect predictive models or human crowdsourcing workers, noisy and conflicting information is ubiquitous and inevitable. Although state-of-the-art aggregation methods have been proposed to handle label spaces with flat structures, as the label space is becoming more and more complicated, aggregation under a label hierarchical structure becomes necessary but has been largely ignored. These label hierarchies can be quite informative as they are usually created by domain experts to make sense of highly complex label correlations for many real-world cases like protein functionality interactions or disease relationships. We propose a novel multi-source hierarchical prediction consolidation method to effectively exploits the complicated hierarchical label structures to resolve the noisy and conflicting information that inherently originates from multiple imperfect sources. We formulate the problem as an optimization problem with a closed-form solution. The proposed method captures the smoothness overall information sources as well as penalizing any consolidation result that violates the constraints derived from the label hierarchy. The hierarchical instance similarity, as well as the consolidation result, are inferred in a totally unsupervised, iterative fashion. Experimental results on both synthetic and real-world datasets show the effectiveness of the proposed method over existing alternatives.

cs.DB↗

arXiv2016

Temporally modulated phase retrieval method for weak temporal phase measurement of laser pulses

The measurement of weak temporal phase for picosecond and nanosecond laser pulses is important but quite difficult. We propose a simple iterative algorithm, which is based on a temporally movable phase modulation process, to retrieve the weak temporal phase of laser pulses. This unambiguous method can achieve a high accuracy and simultaneously measure the weak temporal phase and temporal profile of pulses, which are almost transform-limited. Detailed analysis shows that this iterative method has valuable potential applications in the characterization of pulses with weak temporal phase.

physics.optics↗

arXiv2016

Variational hybridization and transformation for large inaccurate noisy-or networks

Variational inference provides approximations to the computationally intractable posterior distribution in Bayesian networks. A prominent medical application of noisy-or Bayesian network is to infer potential diseases given observed symptoms. Previous studies focus on approximating a handful of complicated pathological cases using variational transformation. Our goal is to use variational transformation as part of a novel hybridized inference for serving reliable and real time diagnosis at web scale. We propose a hybridized inference that allows variational parameters to be estimated without disease posteriors or priors, making the inference faster and much of its computation recyclable. In addition, we propose a transformation ranking algorithm that is very stable to large variances in network prior probabilities, a common issue that arises in medical applications of Bayesian networks. In experiments, we perform comparative study on a large real life medical network and scalability study on a much larger (36,000x) synthesized network.

cs.LG↗

arXiv2016

On Study of the Binarized Deep Neural Network for Image Classification

Recently, the deep neural network (derived from the artificial neural network) has attracted many researchers' attention by its outstanding performance. However, since this network requires high-performance GPUs and large storage, it is very hard to use it on individual devices. In order to improve the deep neural network, many trials have been made by refining the network structure or training strategy. Unlike those trials, in this paper, we focused on the basic propagation function of the artificial neural network and proposed the binarized deep neural network. This network is a pure binary system, in which all the values and calculations are binarized. As a result, our network can save a lot of computational resource and storage. Therefore, it is possible to use it on various devices. Moreover, the experimental results proved the feasibility of the proposed network.

cs.NE↗

arXiv2016

Stochastic Gradient Made Stable: A Manifold Propagation Approach for Large-Scale Optimization

Stochastic gradient descent (SGD) holds as a classical method to build large scale machine learning models over big data. A stochastic gradient is typically calculated from a limited number of samples (known as mini-batch), so it potentially incurs a high variance and causes the estimated parameters bounce around the optimal solution. To improve the stability of stochastic gradient, recent years have witnessed the proposal of several semi-stochastic gradient descent algorithms, which distinguish themselves from standard SGD by incorporating global information into gradient computation. In this paper we contribute a novel stratified semi-stochastic gradient descent (S3GD) algorithm to this nascent research area, accelerating the optimization of a large family of composite convex functions. Though theoretically converging faster, prior semi-stochastic algorithms are found to suffer from high iteration complexity, which makes them even slower than SGD in practice on many datasets. In our proposed S3GD, the semi-stochastic gradient is calculated based on efficient manifold propagation, which can be numerically accomplished by sparse matrix multiplications. This way S3GD is able to generate a highly-accurate estimate of the exact gradient from each mini-batch with largely-reduced computational complexity. Theoretic analysis reveals that the proposed S3GD elegantly balances the geometric algorithmic convergence rate against the space and time complexities during the optimization. The efficacy of S3GD is also experimentally corroborated on several large-scale benchmark datasets.

cs.LG↗