arXiv subjects

Jie Chen

Publications and source records attributed to Jie Chen.

At least 631 records · Page 35Linked to original sources

arXiv2018

Automatic Seismic Salt Interpretation with Deep Convolutional Neural Networks

One of the most crucial tasks in seismic reflection imaging is to identify the salt bodies with high precision. Traditionally, this is accomplished by visually picking the salt/sediment boundaries, which requires a great amount of manual work and may introduce systematic bias. With recent progress of deep learning algorithm and growing computational power, a great deal of efforts have been made to replace human effort with machine power in salt body interpretation. Currently, the method of Convolutional neural networks (CNN) is revolutionizing the computer vision field and has been a hot topic in the image analysis. In this paper, the benefits of CNN-based classification are demonstrated by using a state-of-art network structure U-Net, along with the residual learning framework ResNet, to delineate salt body with high precision. Network adjustments, including the Exponential Linear Units (ELU) activation function, the Lovász-Softmax loss function, and stratified $K$-fold cross-validation, have been deployed to further improve the prediction accuracy. The preliminary result using SEG Advanced Modeling (SEAM) data shows good agreement between the predicted salt body and manually interpreted salt body, especially in areas with weak reflections. This indicates the great potential of applying CNN for salt-related interpretations.

physics.geo-ph↗

arXiv2018

Mean-square Stabilizability via Output Feedback for Non-minimum Phase Networked Feedback Systems

This work studies mean-square stabilizability via output feedback for a networked linear time invariant (LTI) feedback system with a non-minimum phase plant. In the feedback system, the control signals are transmitted to the plant over a set of parallel communication channels with possible packet dropout. Our goal is to analytically describe intrinsic constraints among channel packet dropout probabilities and the plant's characteristics, such as unstable poles, non-minimum phase zeros in the mean-square stabilizability of the system. It turns out that this is a very hard problem. Here, we focus on the case in which the plant has relative degree one and each non-minimum zero of the plant is only associated with one of control input channels. Then, the admissible region of packet dropout probabilities in the mean-square stabilizability of the system is obtained. Moreover, a set of hyper-rectangles in this region is presented in terms of the plant's non-minimum phase zeros, unstable poles and Wonham decomposition forms which is related to the structure of controllable subspace of the plant. When the non-minimum phase zeros are void, it is found that the supremum of packet dropout probabilities' product in the admissible region is determined by the product of plant's unstable poles only. A numerical example is presented to illustrate the fundamental constraints in the mean-square stabilizability of the networked system.

eess.SY↗

arXiv2018

On the algebraic Gordian distance

Using Blanchfield pairings, we show that two Alexander polynomials cannot be realized by a pair of matrices with Gordian distance one if a corresponding quadratic equation does not have an integer solution. We also give an example of how our results help in calculating the Gordian distances, algebraic Gordian distances and polynomial distances.

math.GT↗

arXiv2018

From BoW to CNN: Two Decades of Texture Representation for Texture Classification

Texture is a fundamental characteristic of many types of images, and texture representation is one of the essential and challenging problems in computer vision and pattern recognition which has attracted extensive research attention. Since 2000, texture representations based on Bag of Words (BoW) and on Convolutional Neural Networks (CNNs) have been extensively studied with impressive performance. Given this period of remarkable evolution, this paper aims to present a comprehensive survey of advances in texture representation over the last two decades. More than 200 major publications are cited in this survey covering different aspects of the research, which includes (i) problem description; (ii) recent advances in the broad categories of BoW-based, CNN-based and attribute-based methods; and (iii) evaluation issues, specifically benchmark datasets and state of the art results. In retrospect of what has been achieved so far, the survey discusses open challenges and directions for future research.

cs.CV↗

arXiv2018

Learning Low-Complexity Autoregressive Models via Proximal Alternating Minimization

We consider the estimation of the state transition matrix in vector autoregressive models, when time sequence data is limited but nonsequence steady-state data is abundant. To leverage both sources of data, we formulate the least squares minimization problem regularized by a Lyapunov penalty. We impose cardinality or rank constraints to reduce the complexity of the autoregressive model. We solve the resulting nonconvex, nonsmooth problem by using the proximal alternating linearization method (PALM). We show that PALM is globally convergent to a critical point and that the estimation error monotonically decreases. Furthermore, we obtain explicit formulas for the proximal operators to facilitate the implementation of PALM. We demonstrate the effectiveness of the developed method on synthetic and real-world data. Our experiments show that PALM outperforms the gradient projection method in both computational efficiency and solution quality.

math.OC↗

arXiv2018

Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders

Deep generative models have achieved remarkable success in various data domains, including images, time series, and natural languages. There remain, however, substantial challenges for combinatorial structures, including graphs. One of the key challenges lies in the difficulty of ensuring semantic validity in context. For examples, in molecular graphs, the number of bonding-electron pairs must not exceed the valence of an atom; whereas in protein interaction networks, two proteins may be connected only when they belong to the same or correlated gene ontology terms. These constraints are not easy to be incorporated into a generative model. In this work, we propose a regularization framework for variational autoencoders as a step toward semantic validity. We focus on the matrix representation of graphs and formulate penalty terms that regularize the output distribution of the decoder to encourage the satisfaction of validity constraints. Experimental results confirm a much higher likelihood of sampling valid graphs in our approach, compared with others reported in the literature.

cs.LG↗

arXiv2018

Revisiting Random Binning Features: Fast Convergence and Strong Parallelizability

Kernel method has been developed as one of the standard approaches for nonlinear learning, which however, does not scale to large data set due to its quadratic complexity in the number of samples. A number of kernel approximation methods have thus been proposed in the recent years, among which the random features method gains much popularity due to its simplicity and direct reduction of nonlinear problem to a linear one. The Random Binning (RB) feature, proposed in the first random-feature paper \cite{rahimi2007random}, has drawn much less attention than the Random Fourier (RF) feature. In this work, we observe that the RB features, with right choice of optimization solver, could be orders-of-magnitude more efficient than other random features and kernel approximation methods under the same requirement of accuracy. We thus propose the first analysis of RB from the perspective of optimization, which by interpreting RB as a Randomized Block Coordinate Descent in the infinite-dimensional space, gives a faster convergence rate compared to that of other random features. In particular, we show that by drawing $R$ random grids with at least $κ$ number of non-empty bins per grid in expectation, RB method achieves a convergence rate of $O(1/(κR))$, which not only sharpens its $O(1/\sqrt{R})$ rate from Monte Carlo analysis, but also shows a $κ$ times speedup over other random features under the same analysis framework. In addition, we demonstrate another advantage of RB in the L1-regularized setting, where unlike other random features, a RB-based Coordinate Descent solver can be parallelized with guaranteed speedup proportional to $κ$. Our extensive experiments demonstrate the superior performance of the RB features over other random features and kernel approximation methods. Our code and data is available at { \url{https://github.com/teddylfwu/RB_GEN}}.

cs.LG↗

arXiv2018

Model Interpretation: A Unified Derivative-based Framework for Nonparametric Regression and Supervised Machine Learning

Interpreting a nonparametric regression model with many predictors is known to be a challenging problem. There has been renewed interest in this topic due to the extensive use of machine learning algorithms and the difficulty in understanding and explaining their input-output relationships. This paper develops a unified framework using a derivative-based approach for existing tools in the literature, including the partial-dependence plots, marginal plots and accumulated effects plots. It proposes a new interpretation technique called the accumulated total derivative effects plot and demonstrates how its components can be used to develop extensive insights in complex regression models with correlated predictors. The techniques are illustrated through simulation results.

stat.ML↗

arXiv2018

Application of Machine Learning in Rock Facies Classification with Physics-Motivated Feature Augmentation

With recent progress in algorithms and the availability of massive amounts of computation power, application of machine learning techniques is becoming a hot topic in the oil and gas industry. One of the most promising aspects to apply machine learning to the upstream field is the rock facies classification in reservoir characterization, which is crucial in determining the net pay thickness of reservoirs, thus a definitive factor in drilling decision making process. For complex machine learning tasks like facies classification, feature engineering is often critical. This paper shows the inclusion of physics-motivated feature interaction in feature augmentation can further improve the capability of machine learning in rock facies classification. We demonstrate this approach with the SEG 2016 machine learning contest dataset and the top winning algorithms. The improvement is roboust and can be $\sim5\%$ better than current existing best F-1 score, where F-1 is an evaluation metric used to quantify average prediction accuracy.

stat.ML↗

arXiv2018

Haze Density Estimation via Modeling of Scattering Coefficients of Iso-depth Regions

Vision based haze density estimation is of practical implications for the purpose of precaution alarm and emergency reactions toward disastrous hazy weathers. In this paper, we introduce a haze density estimation framework based on modeling of scattering coefficients of iso-depth regions. A haze density metric of Normalized Scattering Coefficient (NSC) is proposed to measure current haze density level with reference to two reference scales. Iso-depth regions are determined via superpixel segmentation. Efficient searching and matching of iso-depth units could be carried out for measurements via unstationary cameras. A robust dark SP selection method is used to produce reliable predictions for most out-door scenarios.

cs.CV↗

arXiv2018

A Smooth Double Proximal Primal-Dual Algorithm for a Class of Distributed Nonsmooth Optimization Problem

This technical note studies a class of distributed nonsmooth convex consensus optimization problem. The cost function is a summation of local cost functions which are convex but nonsmooth. Each of the local cost functions consists of a twice differentiable convex function and two lower semi-continuous convex functions. We call this problem as single-smooth plus double-nonsmooth (SSDN) problem. Under mild conditions, we propose a distributed double proximal primal-dual optimization algorithm. The double proximal operator is designed to deal with the difficulty caused by the unproximable property of the summation of those two nonsmooth functions. Besides, it can also guarantee that the proposed algorithm is locally Lipschitz continuous. An auxiliary variable in the double proximal operator is introduced to estimate the subgradient of the second nonsmooth function. Theoretically, we conduct the convergence analysis by employing Lyapunov stability theory. It shows that the proposed algorithm can make the states achieve consensus at the optimal point. In the end, nontrivial simulations are presented and the results demonstrate the effectiveness of the proposed algorithm.

math.OC↗

arXiv2018

Rapid Assessment of Damaged Homes in the Florida Keys after Hurricane Irma

On September 10, 2017, Hurricane Irma made landfall in the Florida Keys and caused significant damage. Informed by hydrodynamic storm surge and wave modeling and post-storm satellite imagery, a rapid damage survey was soon conducted for 1600+ residential buildings in Big Pine Key and Marathon. Damage categorizations and statistical analysis reveal distinct factors governing damage at these two locations. The distance from the coast is significant for the damage in Big Pine Key, as severely damaged buildings were located near narrow waterways connected to the ocean. Building type and size are critical in Marathon, highlighted by the near-complete destruction of trailer communities there. These observations raise issues of affordability and equity that need consideration in damage recovery and rebuilding for resilience.

stat.AP↗

arXiv2018

Saliency Integration: An Arbitrator Model

Saliency integration has attracted much attention on unifying saliency maps from multiple saliency models. Previous offline integration methods usually face two challenges: 1. if most of the candidate saliency models misjudge the saliency on an image, the integration result will lean heavily on those inferior candidate models; 2. an unawareness of the ground truth saliency labels brings difficulty in estimating the expertise of each candidate model. To address these problems, in this paper, we propose an arbitrator model (AM) for saliency integration. Firstly, we incorporate the consensus of multiple saliency models and the external knowledge into a reference map to effectively rectify the misleading by candidate models. Secondly, our quest for ways of estimating the expertise of the saliency models without ground truth labels gives rise to two distinct online model-expertise estimation methods. Finally, we derive a Bayesian integration framework to reconcile the saliency models of varying expertise and the reference map. To extensively evaluate the proposed AM model, we test twenty-seven state-of-the-art saliency models, covering both traditional and deep learning ones, on various combinations over four datasets. The evaluation results show that the AM model improves the performance substantially compared to the existing state-of-the-art integration methods, regardless of the chosen candidate saliency models.

cs.CV↗

arXiv2018

Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework

Light field (LF) cameras provide perspective information of scenes by taking directional measurements of the focusing light rays. The raw outputs are usually dark with additive camera noise, which impedes subsequent processing and applications. We propose a novel LF denoising framework based on anisotropic parallax analysis (APA). Two convolutional neural networks are jointly designed for the task: first, the structural parallax synthesis network predicts the parallax details for the entire LF based on a set of anisotropic parallax features. These novel features can efficiently capture the high frequency perspective components of a LF from noisy observations. Second, the view-dependent detail compensation network restores non-Lambertian variation to each LF view by involving view-specific spatial energies. Extensive experiments show that the proposed APA LF denoiser provides a much better denoising performance than state-of-the-art methods in terms of visual quality and in preservation of parallax details.

cs.CV↗

arXiv2018

Deep Extractor Network for Target Speaker Recovery From Single Channel Speech Mixtures

Speaker-aware source separation methods are promising workarounds for major difficulties such as arbitrary source permutation and unknown number of sources. However, it remains challenging to achieve satisfying performance provided a very short available target speaker utterance (anchor). Here we present a novel "deep extractor network" which creates an extractor point for the target speaker in a canonical high dimensional embedding space, and pulls together the time-frequency bins corresponding to the target speaker. The proposed model is different from prior works in that the canonical embedding space encodes knowledges of both the anchor and the mixture during an end-to-end training phase: First, embeddings for the anchor and mixture speech are separately constructed in a primary embedding space, and then combined as an input to feed-forward layers to transform to a canonical embedding space which we discover more stable than the primary one. Experimental results show that given a very short utterance, the proposed model can efficiently recover high quality target speech from a mixture, which outperforms various baseline models, with 5.2% and 6.6% relative improvements in SDR and PESQ respectively compared with a baseline oracle deep attracor model. Meanwhile, we show it can be generalized well to more than one interfering speaker.

cs.SD↗

arXiv2018

A Frequency-Domain Characterization of Optimal Error Covariance for the Kalman-Bucy Filter

In this paper, we discover that the trace of the division of the optimal output estimation error covariance over the noise covariance attained by the Kalman-Bucy filter can be explicitly expressed in terms of the plant dynamics and noise statistics in a frequency-domain integral characterization. Towards this end, we examine the algebraic Riccati equation associated with Kalman-Bucy filtering using analytic function theory and relate it to the Bode integral. Our approach features an alternative, frequency-domain framework for analyzing algebraic Riccati equations and reduces to various existing related results.

eess.SY↗

arXiv2018

Design of Near Infrared Sky Brightness Monitor and Test Running at Ngari Observatory in Tibet

Tibet is known as the third pole of the earth, as high as the South Pole and North Pole. The Ngari (Ali) observatory in Tibet has the advantage of plenty of photometric night, low precipitable water vapor, high transmittance, good seeing. It is a good site, and promising to be one of the best place for infrared and submillimeter observations in the world. However, there is no data available for sky background brightness in such place, which restrict the astronomical development of the sites. In the near infrared band of J, H, Ks, a NIR sky brightness monitor (NISBM) is designed based on InGaAs photoelectric diode. By using the method of chopper modulation and digital lock-in amplifier processing, the SNR (Signal Noise Ratio), detectivity and the data acquisition speed of the device is greatly improved. For each band of J, H, Ks, an independent instrument is designed and calibrated in laboratory. The NISBM has been installed in Ngari observatory in July of 2017 and obtained the first data of NIR sky brightness at Ngari observatory.

astro-ph.IM↗

arXiv2018

The operational and control software of Multi-channel Antarctic Solar Telescope

MARST (Multi-channel Antarctic Solar Telescope) aims to observe the Sun in multiple wavebands in Antarctica and will be China's first solar telescope in Antarctica. The telescope has two tubes, corresponding to Photosphere observation which uses 11 filters and Chromosphere observation in Hα waveband. The two tubes need to be coordinated to observe at the same time. The telescope will observe the Sun for a long time, so a self-guiding module is needed to improve sun tracking. Besides, performing solar specific flat-field exposure is necessary for analyzing. EPICS is introduced to control each hardware and an autonomous observation system based on RTS2 is designed under such demands. EPICS application modules are implemented for each device: telescope mount & focuser, filter wheel, Hα filter, dome with webcams, Andor CCD and PI CCD. We also integrate EPICS modules into RTS2 framework with an XML format configuration. To control these applications autonomously we have developed a RTS2 executor module where two plan classes are instantiated to control two sets of filters and CCDs, and to ensure only one could control the mount at the same time. Different types of observation plans are designed to describe different series of processes with different priorities. To improve sun tracking, we calculate the centroid of each image to get the offset, then apply the correction to the telescope during observation process. For frontend users, a GUI based on PyQt5 and QML is implemented and connects to rts2-httpd and rts2-proxy modules so that users can control devices, check images and get logs.

astro-ph.IM↗