arXiv subjects

Robert C. Qiu

Publications and source records attributed to Robert C. Qiu.

At least 37 records · Page 2Linked to original sources

arXiv2022

Multi-level Contrast Network for Wearables-based Joint Activity Segmentation and Recognition

Human activity recognition (HAR) with wearables is promising research that can be widely adopted in many smart healthcare applications. In recent years, the deep learning-based HAR models have achieved impressive recognition performance. However, most HAR algorithms are susceptible to the multi-class windows problem that is essential yet rarely exploited. In this paper, we propose to relieve this challenging problem by introducing the segmentation technology into HAR, yielding joint activity segmentation and recognition. Especially, we introduce the Multi-Stage Temporal Convolutional Network (MS-TCN) architecture for sample-level activity prediction to joint segment and recognize the activity sequence. Furthermore, to enhance the robustness of HAR against the inter-class similarity and intra-class heterogeneity, a multi-level contrastive loss, containing the sample-level and segment-level contrast, has been proposed to learn a well-structured embedding space for better activity segmentation and recognition performance. Finally, with comprehensive experiments, we verify the effectiveness of the proposed method on two public HAR datasets, achieving significant improvements in the various evaluation metrics.

cs.CV↗

arXiv2022

Learning Efficient Representations for Enhanced Object Detection on Large-scene SAR Images

It is a challenging problem to detect and recognize targets on complex large-scene Synthetic Aperture Radar (SAR) images. Recently developed deep learning algorithms can automatically learn the intrinsic features of SAR images, but still have much room for improvement on large-scene SAR images with limited data. In this paper, based on learning representations and multi-scale features of SAR images, we propose an efficient and robust deep learning based target detection method. Especially, by leveraging the effectiveness of adversarial autoencoder (AAE) which influences the distribution of the investigated data explicitly, the raw SAR dataset is augmented into an enhanced version with a large quantity and diversity. Besides, an auto-labeling scheme is proposed to improve labeling efficiency. Finally, with jointly training small target chips and large-scene images, an integrated YOLO network combining non-maximum suppression on sub-images is used to realize multiple targets detection of high resolution images. The numerical experimental results on the MSTAR dataset show that our method can realize target detection and recognition on large-scene images accurately and efficiently. The superior anti-noise performance is also confirmed by experiments.

cs.CV↗

arXiv2020

Improving Power System State Estimation Based on Matrix-Level Cleaning

Power system state estimation is heavily subjected to measurement error, which comes from the noise of measuring instruments, communication noise, and some unclear randomness. Traditional weighted least square (WLS), as the most universal state estimation method, attempts to minimize the residual between measurements and the estimation of measured variables, but it is unable to handle the measurement error. To solve this problem, based on random matrix theory, this paper proposes a data-driven approach to clean measurement error in matrix-level. Our method significantly reduces the negative effect of measurement error, and conducts a two-stage state estimation scheme combined with WLS. In this method, a Hermitian matrix is constructed to establish an invertible relationship between the eigenvalues of measurements and their covariance matrix. Random matrix tools, combined with an optimization scheme, are used to clean measurement error by shrinking the eigenvalues of the covariance matrix. With great robustness and generality, our approach is particularly suitable for large interconnected power grids. Our method has been numerically evaluated using different testing systems, multiple models of measured noise and matrix size ratios.

eess.SP↗

arXiv2020

Unsupervised Feature Learning for Online Voltage Stability Evaluation and Monitoring Based on Variational Autoencoder

With the increase of uncertain elements in power systems and extensive deployment of online monitoring devices, it is necessary to search a more real-time and robust voltage stability assessment method. This study, using PMU monitoring data, explores a novel data-driven approach for long-term voltage stability assessment based on variational autoencoder (VAE). Our method is capable of extracting the most representative features by an unsupervised data mining method in a probabilistic learning way. Different from most of familiar feature extraction methods, it regularizes latent features in an expected stochastic distribution. Furthermore, a statistical indicator by sampling latent features after variance reduction is proposed to assess long-term voltage stability. Our approach is tested in various simulated power systems with different load increment models. Other cases show the accuracy and speed of our approach for estimating voltage collapse point. These testing cases successfully demonstrate the accuracy and effectiveness of our approach.

eess.SP↗

arXiv2019

Preliminary Exploration on Digital Twin for Power Systems: Challenges, Framework, and Applications

Digital twin (DT) is one of the most promising enabling technologies for realizing smart grids. Characterized by seamless and active---data-driven, real-time, and closed-loop---integration between digital and physical spaces, a DT is much more than a blueprint, simulation tool, or cyber-physical system (CPS). Numerous state-of-the-art technologies such as internet of things (IoT), 5G, big data, and artificial intelligence (AI) serve as a basis for DT. DT for power systems aims at situation awareness and virtual test to assist the decision-making on power grid operation and management under normal or urgent conditions. This paper, from both science paradigms and engineering practice, outlines the backgrounds, challenges, framework, tools, and possible directions of DT as a preliminary exploration. To our best knowledge, it is also the first exploration on DT in the context of power systems. Starting from the fundamental and most frequently used power flow (PF) analysis, some typical application scenarios are presented. Our work is expected to contribute some novel discoveries, as well as some high-dimensional analytics, to the engineering community. Besides, the connection of DT with big data analytics and AI may has deep impact on data science.

eess.SP↗

arXiv2019

A Survey on Nonconvex Regularization Based Sparse and Low-Rank Recovery in Signal Processing, Statistics, and Machine Learning

In the past decade, sparse and low-rank recovery have drawn much attention in many areas such as signal/image processing, statistics, bioinformatics and machine learning. To achieve sparsity and/or low-rankness inducing, the $\ell_1$ norm and nuclear norm are of the most popular regularization penalties due to their convexity. While the $\ell_1$ and nuclear norm are convenient as the related convex optimization problems are usually tractable, it has been shown in many applications that a nonconvex penalty can yield significantly better performance. In recent, nonconvex regularization based sparse and low-rank recovery is of considerable interest and it in fact is a main driver of the recent progress in nonconvex and nonsmooth optimization. This paper gives an overview of this topic in various fields in signal processing, statistics and machine learning, including compressive sensing (CS), sparse regression and variable selection, sparse signals separation, sparse principal component analysis (PCA), large covariance and inverse covariance matrices estimation, matrix completion, and robust PCA. We present recent developments of nonconvex regularization based sparse and low-rank recovery in these fields, addressing the issues of penalty selection, applications and the convergence of nonconvex algorithms. Code is available at https://github.com/FWen/ncreg.git.

cs.IT↗

arXiv2019

Analysis on the Empirical Spectral Distribution of Large Sample Covariance Matrix and Applications for Large Antenna Array Processing

This paper addresses the asymptotic behavior of a particular type of information-plus-noise-type matrices, where the column and row number of the matrices are large and of the same order, while signals are diverged and time delays of the channel are fixed. We prove that the empirical spectral distribution (ESD) of the large dimension sample covariance matrix and a well-studied spiked central Wishart matrix converge to the same distribution. As an application, an asymptotic power function is presented for the general likelihood ratio statistics for testing the presence of signal in large array signal processing.

cs.IT↗

arXiv2019

Spectrum concentration in deep residual learning: a free probability approach

We revisit the initialization of deep residual networks (ResNets) by introducing a novel analytical tool in free probability to the community of deep learning. This tool deals with non-Hermitian random matrices, rather than their conventional Hermitian counterparts in the literature. As a consequence, this new tool enables us to evaluate the singular value spectrum of the input-output Jacobian of a fully-connected deep ResNet for both linear and nonlinear cases. With the powerful tool of free probability, we conduct an asymptotic analysis of the spectrum on the single-layer case, and then extend this analysis to the multi-layer case of an arbitrary number of layers. In particular, we propose to rescale the classical random initialization by the number of residual units, so that the spectrum has the order of $O(1)$, when compared with the large width and depth of the network. We empirically demonstrate that the proposed initialization scheme learns at a speed of orders of magnitudes faster than the classical ones, and thus attests a strong practical relevance of this investigation.

cs.LG↗

arXiv2019

Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks

In this paper, we propose to disentangle and interpret contextual effects that are encoded in a pre-trained deep neural network. We use our method to explain the gaming strategy of the alphaGo Zero model. Unlike previous studies that visualized image appearances corresponding to the network output or a neural activation only from a global perspective, our research aims to clarify how a certain input unit (dimension) collaborates with other units (dimensions) to constitute inference patterns of the neural network and thus contribute to the network output. The analysis of local contextual effects w.r.t. certain input units is of special values in real applications. Explaining the logic of the alphaGo Zero model is a typical application. In experiments, our method successfully disentangled the rationale of each move during the Go game.

cs.CV↗

arXiv2018

Shifting Maximum Eigenvalue Detection in Low SNR Environment

Maximum eigenvalue detection (MED) is an important application of random matrix theory in spectrum sensing and signal detection. However, in small signal-to-noise ratio environment, the maximum eigenvalue of the representative signal is at the edge of Marchenko-Pastur (M-P) law bulk and meets the Tracy-Widom distribution. Since the distribution of Tracy-Widom has no closed-form expression, it brings great difficulty in processing. In this paper, we propose a shifting maximum eigenvalue (SMED) algorithm, which shifts the maximum eigenvalue out of the M-P law bulk by combining an auxiliary signal associated with the signal to be detected. According to the random matrix theory, the shifted maximum eigenvalue is consistent with Gaussian distribution. The proposed SMED not only simplifies the detection algorithm, but also greatly improve the detection performance. In this paper, the performance of SMED, MED and trace (FMD) algorithm is analyzed and the theoretical performance comparisons are obtained. The algorithm and theoretical results are verified by the simulations in different signal environments.

eess.SP↗

arXiv2018

A New Approach of Exploiting Self-Adjoint Matrix Polynomials of Large Random Matrices for Anomaly Detection and Fault Location

Synchronized measurements of a large power grid enable an unprecedented opportunity to study the spatialtemporal correlations. Statistical analytics for those massive datasets start with high-dimensional data matrices. Uncertainty is ubiquitous in a future's power grid. These data matrices are recognized as random matrices. This new point of view is fundamental in our theoretical analysis since true covariance matrices cannot be estimated accurately in a high-dimensional regime. As an alternative, we consider large-dimensional sample covariance matrices in the asymptotic regime to replace the true covariance matrices. The self-adjoint polynomials of large-dimensional random matrices are studied as statistics for big data analytics. The calculation of the asymptotic spectrum distribution (ASD) for such a matrix polynomial is understandably challenging. This task is made possible by a recent breakthrough in free probability, an active research branch in random matrix theory. This is the very reason why the work of this paper is inspired initially. The new approach is interesting in many aspects. The mathematical reason may be most critical. The real-world problems can be solved using this approach, however.

stat.AP↗

arXiv2018

A Data Driven Approach for Resting-state EEG signal Classification of Schizophrenia with Control Participants using Random Matrix Theory

Resting state electroencephalogram (EEG) abnormalities in clinically high-risk individuals (CHR), clinically stable first-episode patients with schizophrenia (FES), healthy controls (HC) suggest alterations in neural oscillatory activity. However, few studies directly compare these anomalies among each types. Therefore, this study investigated whether these electrophysiological characteristics differentiate clinical populations from one another, and from non-psychiatric controls. To address this question, resting EEG power and coherence were assessed in 40 clinically high-risk individuals (CHR), 40 first-episode patients with schizophrenia (FES), and 40 healthy controls (HC). These findings suggest that resting EEG can be a sensitive measure for differentiating between clinical disorders.This paper proposes a novel data-driven supervised learning method to obtain identification of the patients mental status in schizophrenia research. According to Marchenko-Pastur Law, the distribution of the eigenvalues of EEG data is divided into signal subspace and noise subspace. A test statistic named LES that embodies the characteristics of all eigenvalues is adopted. different classifier and different feature(LES test function) are selected for experiments, we have shown that using von Neumann Entropy as LES test function combine with SVM classifier could obtain the best average classification accuracy during three classification among HC, FES and CHR of Schizophrenia group with EEG signal. It is worth noting that the result of LES feature extraction with the highest classification accuracy is around 90% in two classification(HC compare with FES) and around 70% in three classification. Where the classification accuracy higher than 70% could be used to assist clinical diagnosis.

eess.SP↗

arXiv2018

Improvement of Resting-state EEG Analysis Process with Spectrum Weight-Voting based on LES

EEG is a non-invasive technique for recording brain bioelectric activity, which has potential applications in various fields such as human-computer interaction and neuroscience. However, there are many difficulties in analyzing EEG data, including its complex composition, low amplitude as well as low signal-to-noise ratio. Some of the existing methods of analysis are based on feature extraction and machine learning to differentiate the phase of schizophrenia that samples belong to. However, medical research requires the use of machine learning not only to give more accurate classification results, but also to give the results that can be applied to pathological studies. The main purpose of this study is to obtain the weight values as the representation of influence of each frequency band on the classification of schizophrenia phases on the basis of a more effective classification method using the LES feature extraction, and then the weight values are processed and applied to improve the accuracy of machine learning classification. We propose a method called weight-voting to obtain the weights of sub-bands features by using results of classification for voting to fit the actual categories of EEG data, and using weights for reclassification. Through this method, we can first obtain the influence of each band in distinguishing three schizophrenia phases, and analyze the effect of band features on the risk of schizophrenia contributing to the study of psychopathology. Our results show that there is a high correlation between the change of weight of low gamma band and the difference between HC, CHR and FES. If the features revised according to weights are used for reclassification, the accuracy of result will be improved compared with the original classifier, which confirms the role of the band weight distribution.

eess.SP↗

arXiv2018

A Novel Data-Driven Situation Awareness Approach for Future Grids--Using Large Random Matrices for Big Data Modeling

Data-driven approaches, when tasked with situation awareness, are suitable for complex grids with massive datasets. It is a challenge, however, to efficiently turn these massive datasets into useful big data analytics. To address such a challenge, this paper, based on random matrix theory (RMT), proposes a datadriven approach. The approach models massive datasets as large random matrices; it is model-free and requiring no knowledge about physical model parameters. In particular, the large data dimension N and the large time span T, from the spatial aspect and the temporal aspect respectively, lead to favorable results. The beautiful thing lies in that these linear eigenvalue statistics (LESs) built from data matrices follow Gaussian distributions for very general conditions, due to the latest breakthroughs in probability on the central limit theorems of those LESs. Numerous case studies, with both simulated data and field data, are given to validate the proposed new algorithms.

stat.ME↗

arXiv2018

An Accurate and Real-time Self-blast Glass Insulator Location Method Based On Faster R-CNN and U-net with Aerial Images

The location of broken insulators in aerial images is a challenging task. This paper, focusing on the self-blast glass insulator, proposes a deep learning solution. We address the broken insulators location problem as a low signal-noise-ratio image location framework with two modules: 1) object detection based on Fast R-CNN, and 2) classification of pixels based on U-net. A diverse aerial image set of some grid in China is tested to validated the proposed approach. Furthermore, a comparison is made among different methods and the result shows that our approach is accurate and real-time.

cs.CV↗

arXiv2017

Nonconvex Regularization Based Sparse Recovery and Demixing with Application to Color Image Inpainting

This work addresses the recovery and demixing problem of signals that are sparse in some general dictionary. Involved applications include source separation, image inpainting, super-resolution, and restoration of signals corrupted by clipping, saturation, impulsive noise, or narrowband interference. We employ the $\ell_q$-norm ($0 \le q < 1$) for sparsity inducing and propose a constrained $\ell_q$-minimization formulation for the recovery and demixing problem. This nonconvex formulation is approximately solved by two efficient first-order algorithms based on proximal coordinate descent and alternative direction method of multipliers (ADMM), respectively. The new algorithms are convergent in the nonconvex case under some mild conditions and scale well for high-dimensional problems. A convergence condition of the new ADMM algorithm has been derived. Furthermore, extension of the two algorithms for multi-channels joint recovery has been presented, which can further exploit the joint sparsity pattern among multi-channel signals. Various numerical experiments showed that the new algorithms can achieve considerable performance gain over the $\ell_1$-regularized algorithms.

cs.IT↗

arXiv2016

A Novel Approach for Big Data Analytics in Future Grids Based on Free Probability

Based on the random matrix model, we can build statistical models using massive datasets across the power grid, and employ hypothesis testing for anomaly detection. First, the aim of this paper is to make the first attempt to apply the recent free probability result in extracting big data analytics, in particular data fusion. The nature of this work is basic in that new algorithms and analytics tools are proposed to pave the way for the future's research. Second, using the new analytic tool, we are able to make some discovery related to anomaly detection that is very difficult for other approaches. To our best knowledge, there is no similar report in the literature. Third, both linear and nonlinear polynomials of large random matrices can be handled in this new framework. Simulations demonstrate the following: Compared with the linearity, nonlinearity is more flexible in problem modeling and closer to the nature of the reality. In some sense, some other nonlinear matrix polynomials may be more effective for the power grid

stat.AP↗

arXiv2016

Positive Definite Estimation of Large Covariance Matrix Using Generalized Nonconvex Penalties

This work addresses the issue of large covariance matrix estimation in high-dimensional statistical analysis. Recently, improved iterative algorithms with positive-definite guarantee have been developed. However, these algorithms cannot be directly extended to use a nonconvex penalty for sparsity inducing. Generally, a nonconvex penalty has the capability of ameliorating the bias problem of the popular convex lasso penalty, and thus is more advantageous. In this work, we propose a class of positive-definite covariance estimators using generalized nonconvex penalties. We develop a first-order algorithm based on the alternating direction method framework to solve the nonconvex optimization problem efficiently. The convergence of this algorithm has been proved. Further, the statistical properties of the new estimators have been analyzed for generalized nonconvex penalties. Moreover, extension of this algorithm to covariance estimation from sketched measurements has been considered. The performances of the new estimators have been demonstrated by both a simulation study and a gene clustering example for tumor tissues. Code for the proposed estimators is available at https://github.com/FWen/Nonconvex-PDLCE.git.

cs.IT↗