arXiv subjects

Chen Wang

Publications and source records attributed to Chen Wang.

At least 667 records · Page 37Linked to original sources

arXiv2021

ScalingNet: extracting features from raw EEG data for emotion recognition

Convolutional Neural Networks(CNNs) has achieved remarkable performance breakthrough in a variety of tasks. Recently, CNNs based methods that are fed with hand-extracted EEG features gradually produce a powerful performance on the EEG data based emotion recognition task. In this paper, we propose a novel convolutional layer allowing to adaptively extract effective data-driven spectrogram-like features from raw EEG signals, which we reference as scaling layer. Further, it leverages convolutional kernels scaled from one data-driven pattern to exposed a frequency-like dimension to address the shortcomings of prior methods requiring hand-extracted features or their approximations. The proposed neural network architecture based on the scaling layer, references as ScalingNet, has achieved the state-of-the-art result across the established DEAP benchmark dataset.

eess.SP↗

arXiv2021

Lookup subnet based Spatial Graph Convolutional neural Network

Convolutional Neural Networks(CNNs) has achieved remarkable performance breakthrough in Euclidean structure data. Recently, aggregation-transformation based Graph Neural networks(GNNs) gradually produce a powerful performance on non-Euclidean data. In this paper, we propose a cross-correlation based graph convolution method allowing to naturally generalize CNNs to non-Euclidean domains and inherit the excellent natures of CNNs, such as local filters, parameter sharing, flexible receptive field, etc. Meanwhile, it leverages dynamically generated convolution kernel and cross-correlation operators to address the shortcomings of prior methods based on aggregation-transformation or their approximations. Our method has achieved or matched popular state-of-the-art results across three established graph benchmarks: the Cora, Citeseer, and Pubmed citation network datasets.

cs.LG↗

arXiv2021

SwingBot: Learning Physical Features from In-hand Tactile Exploration for Dynamic Swing-up Manipulation

Several robot manipulation tasks are extremely sensitive to variations of the physical properties of the manipulated objects. One such task is manipulating objects by using gravity or arm accelerations, increasing the importance of mass, center of mass, and friction information. We present SwingBot, a robot that is able to learn the physical features of a held object through tactile exploration. Two exploration actions (tilting and shaking) provide the tactile information used to create a physical feature embedding space. With this embedding, SwingBot is able to predict the swing angle achieved by a robot performing dynamic swing-up manipulations on a previously unseen object. Using these predictions, it is able to search for the optimal control parameters for a desired swing-up angle. We show that with the learned physical features our end-to-end self-supervised learning pipeline is able to substantially improve the accuracy of swinging up unseen objects. We also show that objects with similar dynamics are closer to each other on the embedding space and that the embedding can be disentangled into values of specific physical properties.

cs.RO↗

arXiv2021

Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions

Limited data access is a longstanding barrier to data-driven research and development in the networked systems community. In this work, we explore if and how generative adversarial networks (GANs) can be used to incentivize data sharing by enabling a generic framework for sharing synthetic datasets with minimal expert knowledge. As a specific target, our focus in this paper is on time series datasets with metadata (e.g., packet loss rate measurements with corresponding ISPs). We identify key challenges of existing GAN approaches for such workloads with respect to fidelity (e.g., long-term dependencies, complex multidimensional relationships, mode collapse) and privacy (i.e., existing guarantees are poorly understood and can sacrifice fidelity). To improve fidelity, we design a custom workflow called DoppelGANger (DG) and demonstrate that across diverse real-world datasets (e.g., bandwidth measurements, cluster requests, web sessions) and use cases (e.g., structural characterization, predictive modeling, algorithm comparison), DG achieves up to 43% better fidelity than baseline models. Although we do not resolve the privacy problem in this work, we identify fundamental challenges with both classical notions of privacy and recent advances to improve the privacy properties of GANs, and suggest a potential roadmap for addressing these challenges. By shedding light on the promise and challenges, we hope our work can rekindle the conversation on workflows for data sharing.

cs.LG↗

arXiv2021

Comparisons of Graph Neural Networks on Cancer Classification Leveraging a Joint of Phenotypic and Genetic Features

Cancer is responsible for millions of deaths worldwide every year. Although significant progress hasbeen achieved in cancer medicine, many issues remain to be addressed for improving cancer therapy.Appropriate cancer patient stratification is the prerequisite for selecting appropriate treatment plan, ascancer patients are of known heterogeneous genetic make-ups and phenotypic differences. In thisstudy, built upon deep phenotypic characterizations extractable from Mayo Clinic electronic healthrecords (EHRs) and genetic test reports for a collection of cancer patients, we evaluated variousgraph neural networks (GNNs) leveraging a joint of phenotypic and genetic features for cancer typeclassification. Models were applied and fine-tuned on the Mayo Clinic cancer disease dataset. Theassessment was done through the reported accuracy, precision, recall, and F1 values as well as throughF1 scores based on the disease class. Per our evaluation results, GNNs on average outperformed thebaseline models with mean statistics always being higher that those of the baseline models (0.849 vs0.772 for accuracy, 0.858 vs 0.794 for precision, 0.843 vs 0.759 for recall, and 0.843 vs 0.855 for F1score). Among GNNs, ChebNet, GraphSAGE, and TAGCN showed the best performance, while GATshowed the worst. We applied and compared eight GNN models including AGNN, ChebNet, GAT,GCN, GIN, GraphSAGE, SGC, and TAGCN on the Mayo Clinic cancer disease dataset and assessedtheir performance as well as compared them with each other and with more conventional machinelearning models such as decision tree, gradient boosting, multi-layer perceptron, naive bayes, andrandom forest which we used as the baselines.

cs.LG↗

arXiv2021

Misplaced Subsequences Repairing with Application to Multivariate Industrial Time Series Data

Both the volume and the collection velocity of time series generated by monitoring sensors are increasing in the Internet of Things (IoT). Data management and analysis requires high quality and applicability of the IoT data. However, errors are prevalent in original time series data. Inconsistency in time series is a serious data quality problem existing widely in IoT. Such problem could be hardly solved by existing techniques. Motivated by this, we define an inconsistent subsequences problem in multivariate time series, and propose an integrity data repair approach to solve inconsistent problems. Our proposed repairing method consists of two parts: (1) we design effective anomaly detection method to discover latent inconsistent subsequences in the IoT time series; and (2) we develop repair algorithms to precisely locate the start and finish time of inconsistent intervals, and provide reliable repairing strategies. A thorough experiment on two real-life datasets verifies the superiority of our method compared to other practical approaches. Experimental results also show that our method captures and repairs inconsistency problems effectively in industrial time series in complex IIoT scenarios.

cs.DB↗

arXiv2021

Exploring Data and Knowledge combined Anomaly Explanation of Multivariate Industrial Data

The demand for high-performance anomaly detection techniques of IoT data becomes urgent, especially in industry field. The anomaly identification and explanation in time series data is one essential task in IoT data mining. Since that the existing anomaly detection techniques focus on the identification of anomalies, the explanation of anomalies is not well-solved. We address the anomaly explanation problem for multivariate IoT data and propose a 3-step self-contained method in this paper. We formalize and utilize the domain knowledge in our method, and identify the anomalies by the violation of constraints. We propose set-cover-based anomaly explanation algorithms to discover the anomaly events reflected by violation features, and further develop knowledge update algorithms to improve the original knowledge set. Experimental results on real datasets from large-scale IoT systems verify that our method computes high-quality explanation solutions of anomalies. Our work provides a guide to navigate the explicable anomaly detection in both IoT fault diagnosis and temporal data cleaning.

cs.DB↗

arXiv2020

Distances to molecular clouds in the second Galactic quadrant

We present distances to 76 medium-sized molecular clouds and an extra large-scale one in the second Galactic quadrant ($104.75^\circ <l<150.25^\circ $ and $|b|<5.25^\circ$), 73 of which are accurately measured for the first time. Molecular cloud samples are drawn from $l$-$b$-$V$ space ($-95 < V_{\rm LSR}< 25$ \kms) with the density-based spatial clustering of applications with noise (DBSCAN) algorithm, and distances are measured with the background-eliminated extinction-parallax (BEEP) method using extinctions and Gaia DR2 parallaxes. The range of measured distances to 76 molecular clouds is from 211 to 2631 pc, and the extra large-scale molecular cloud appears to be a coherent structure at about 1 kpc, across about 40° ($\sim$700 pc) in the Galactic longitude.

astro-ph.GA↗

arXiv2020

An overview of SPSA: recent development and applications

There is an increasing need in solving high-dimensional optimization problems under non-deterministic environment. The simultaneous perturbation stochastic approximation (SPSA) algorithm has recently attracted considerable attention for solving high-dimensional optimization problems where the analytical formula cannot be attained. SPSA is designed to estimate the gradient by applying perturbation on a random subset of dimensions at each iteration. SPSA can be easily implemented and is highly efficient in that that it relies on measurements of the objective function, not on measurements of the gradient of the objective function. Since its invention, SPSA has been implemented in various fields such as reinforcement learning, production optimization etc. The paper briefly discuss the recent development of SPSA and its applications.

math.OC↗

arXiv2020

The kpc Scale Fe K$α$ Emission in the Compton Thin Seyfert 2 Galaxy NGC 4388 resolved by Chandra

We present Chandra imaging and spectral observations of Seyfert 2 galaxy NGC 4388. Three extended X-ray structures around the nucleus on kpc scale are well imaged, allowing an in-depth spatially resolved study. Both the extended hard continuum and the Fe K$α$ line show similar morphology, consistent with a scenario where the ionizing emission from nucleus is reprocessed by circumnuclear cold gas, resulting in a weak reflection continuum and an associated neutral Fe K$α$ line. This has been seen in other Compton thick active galactic nuclei (AGN), but NGC 4388 is one of the rare cases with a lower column density ($N_{\rm H} < 1.25\times 10^{24}$ cm$^{-2}$) along the line of sight. Significant differences in equivalent width of the Fe K$α$ emission line are found for the nuclear and extended regions, which could be ascribed to different column densities or scattering angles with respect to the line of sight, rather than variations in iron abundances. The north-east and west extended structures are aligned with the galactic disk and dust lane in the HST $V-H$ map, and located at the peak of molecular gas distribution. The morphology implies that the kpc-scale radio outflow may have compressed the interstellar gas and produced clumps working as the reflector to enhance line emission. Using [OIV] emission as a proxy of the AGN intrinsic luminosity, we find that both of the extended Fe K$α$ emission and reflection continuum are linearly correlated with the [OIV] luminosity, indicating a connection between the AGN and the extended emission.

astro-ph.GA↗

arXiv2020

Congruences concerning generalized central trinomial coefficients

For any $n\in\mathbb{N}=\{0,1,2,\ldots\}$ and $b,c\in\mathbb{Z}$, the generalized central trinomial coefficient $T_n(b,c)$ denotes the coefficient of $x^n$ in the expansion of $(x^2+bx+c)^n$. Let $p$ be an odd prime. In this paper, we determine the summation $\sum_{k=0}^{p-1}T_k(b,c)^2/m^k$ modulo $p^2$ for integers $m$ with certain restrictions. As applications, we confirm some conjectural congruences of Sun [Sci. China Math. 57 (2014), 1375--1400].

math.NT↗

arXiv2020

Measurement and Shaping of Circular Airy Vortex via Cross Phase

We apply the CP to CAVs for the first time experimentally. Firstly, we introduce the propagation properties of a CAV with the LOCP in the process of measuring TCs, and measure the TCs of CAVs in the self-focusing areas experimentally. Secondly, we shape the CAVs via the HOCP and discuss the manipulaiton of singularities.

physics.optics↗

arXiv2020

Time Series Data Imputation: A Survey on Deep Learning Approaches

Time series are all around in real-world applications. However, unexpected accidents for example broken sensors or missing of the signals will cause missing values in time series, making the data hard to be utilized. It then does harm to the downstream applications such as traditional classification or regression, sequential data integration and forecasting tasks, thus raising the demand for data imputation. Currently, time series data imputation is a well-studied problem with different categories of methods. However, these works rarely take the temporal relations among the observations and treat the time series as normal structured data, losing the information from the time data. In recent, deep learning models have raised great attention. Time series methods based on deep learning have made progress with the usage of models like RNN, since it captures time information from data. In this paper, we mainly focus on time series imputation technique with deep learning methods, which recently made progress in this field. We will review and discuss their model architectures, their pros and cons as well as their effects to show the development of the time series imputation methods.

cs.LG↗

arXiv2020

Robust image stitching with multiple registrations

Panorama creation is one of the most widely deployed techniques in computer vision. In addition to industry applications such as Google Street View, it is also used by millions of consumers in smartphones and other cameras. Traditionally, the problem is decomposed into three phases: registration, which picks a single transformation of each source image to align it to the other inputs, seam finding, which selects a source image for each pixel in the final result, and blending, which fixes minor visual artifacts. Here, we observe that the use of a single registration often leads to errors, especially in scenes with significant depth variation or object motion. We propose instead the use of multiple registrations, permitting regions of the image at different depths to be captured with greater accuracy. MRF inference techniques naturally extend to seam finding over multiple registrations, and we show here that their energy functions can be readily modified with new terms that discourage duplication and tearing, common problems that are exacerbated by the use of multiple registrations. Our techniques are closely related to layer-based stereo, and move image stitching closer to explicit scene modeling. Experimental evidence demonstrates that our techniques often generate significantly better panoramas when there is substantial motion or parallax.

cs.CV↗

arXiv2020

Object-centered image stitching

Image stitching is typically decomposed into three phases: registration, which aligns the source images with a common target image; seam finding, which determines for each target pixel the source image it should come from; and blending, which smooths transitions over the seams. As described in [1], the seam finding phase attempts to place seams between pixels where the transition between source images is not noticeable. Here, we observe that the most problematic failures of this approach occur when objects are cropped, omitted, or duplicated. We therefore take an object-centered approach to the problem, leveraging recent advances in object detection [2,3,4]. We penalize candidate solutions with this class of error by modifying the energy function used in the seam finding stage. This produces substantially more realistic stitching results on challenging imagery. In addition, these methods can be used to determine when there is non-recoverable occlusion in the input data, and also suggest a simple evaluation metric that can be used to evaluate the output of stitching algorithms.

cs.CV↗

arXiv2020

HMFlow: Hybrid Matching Optical Flow Network for Small and Fast-Moving Objects

In optical flow estimation task, coarse-to-fine (C2F) warping strategy is widely used to deal with the large displacement problem and provides efficiency and speed. However, limited by the small search range between the first images and warped second images, current coarse-to-fine optical flow networks fail to capture small and fast-moving objects which disappear at coarse resolution levels. To address this problem, we introduce a lightweight but effective Global Matching Component (GMC) to grab global matching features. We propose a new Hybrid Matching Optical Flow Network (HMFlow) by integrating GMC into existing coarse-to-fine networks seamlessly. Besides keeping in high accuracy and small model size, our proposed HMFlow can apply global matching features to guide the network to discover the small and fast-moving objects mismatched by local matching features. We also build a new dataset, named Small and Fast-Moving Chairs (SFChairs), for evaluation. The experimental results show that our proposed network achieves considerable performance, especially at regions with small and fast-moving objects.

cs.CV↗

arXiv2020

Adaptive Ensemble of Classifiers with Regularization for Imbalanced Data Classification

The dynamic ensemble selection of classifiers is an effective approach for processing label-imbalanced data classifications. However, such a technique is prone to overfitting, owing to the lack of regularization methods and the dependence of the aforementioned technique on local geometry. In this study, focusing on binary imbalanced data classification, a novel dynamic ensemble method, namely adaptive ensemble of classifiers with regularization (AER), is proposed, to overcome the stated limitations. The method solves the overfitting problem through implicit regularization. Specifically, it leverages the properties of stochastic gradient descent to obtain the solution with the minimum norm, thereby achieving regularization; furthermore, it interpolates the ensemble weights by exploiting the global geometry of data to further prevent overfitting. According to our theoretical proofs, the seemingly complicated AER paradigm, in addition to its regularization capabilities, can actually reduce the asymptotic time and memory complexities of several other algorithms. We evaluate the proposed AER method on seven benchmark imbalanced datasets from the UCI machine learning repository and one artificially generated GMM-based dataset with five variations. The results show that the proposed algorithm outperforms the major existing algorithms based on multiple metrics in most cases, and two hypothesis tests (McNemar's and Wilcoxon tests) verify the statistical significance further. In addition, the proposed method has other preferred properties such as special advantages in dealing with highly imbalanced data, and it pioneers the research on the regularization for dynamic ensemble methods.

cs.LG↗

arXiv2020

Proof of some supercongruences concerning truncated hypergeometric series

In this paper, we prove some supercongruences concerning truncated hypergeometric series. For example, we show that for any prime $p>3$ and positive integer $r$, $$ \sum_{k=0}^{p^r-1}(3k+1)\frac{(\frac12)_k^3}{(1)_k^3}4^k\equiv p^r+\frac76p^{r+3}B_{p-3}\pmod{p^{r+4}} $$ and $$ \sum_{k=0}^{(p^r-1)/2}(4k+1)\frac{(\frac12)_k^4}{(1)_k^4}\equiv p^r+\frac76p^{r+3}B_{p-3}\pmod{p^{r+4}}, $$ where $(x)_k=x(x+1)\cdots(x+k-1)$ is the Pochhammer symbol and $B_0,B_1,B_2,\ldots$ are Bernoulli numbers. These two congruences confirm conjectures of Sun [Sci. China Math. 54 (2011), 2509--2535] and Guo [Adv. Appl. Math. 120 (2020), Art. 102078], respectively.

math.NT↗