Showing papers by "Shengli Xie published in 2018"

Finite-Time Distributed State Estimation Over Sensor Networks With Round-Robin Protocol and Fading Channels

Abstract: This paper considers finite-time distributed state estimation for discrete-time nonlinear systems over sensor networks. The Round-Robin protocol is introduced to overcome the channel capacity constraint among sensor nodes, and the multiplicative noise is employed to model the channel fading. In order to improve the performance of the estimator under the situation, where the transmission resources are limited, fading channels with different stochastic properties are used in each round by allocating the resources. Sufficient conditions of the average stochastic finite-time boundedness and the average stochastic finite-time stability for the estimation error system are derived on the basis of the periodic system analysis method and Lyapunov approach, respectively. According to the linear matrix inequality approach, the estimator gains are designed. Finally, the effectiveness of the developed results are illustrated by a numerical example.

Robust Estimation for Neural Networks With Randomly Occurring Distributed Delays and Markovian Jump Coupling

Abstract: This paper studies the issue of robust state estimation for coupled neural networks with parameter uncertainty and randomly occurring distributed delays, where the polytopic model is employed to describe the parameter uncertainty. A set of Bernoulli processes with different stochastic properties are introduced to model the randomly occurrences of the distributed delays. Novel state estimators based on the local coupling structure are proposed to make full use of the coupling information. The augmented estimation error system is obtained based on the Kronecker product. A new Lyapunov function, which depends both on the polytopic uncertainty and the coupling information, is introduced to reduce the conservatism. Sufficient conditions, which guarantee the stochastic stability and the $l_{2}-l_\infty $ performance of the augmented estimation error system, are established. Then, the estimator gains are further obtained on the basis of these conditions. Finally, a numerical example is used to prove the effectiveness of the results.

Subspace Clustering via Learning an Adaptive Low-Rank Graph.

Abstract: By using a sparse representation or low-rank representation of data, the graph-based subspace clustering has recently attracted considerable attention in computer vision, given its capability and efficiency in clustering data. However, the graph weights built using the representation coefficients are not the exact ones as the traditional definition is in a deterministic way. The two steps of representation and clustering are conducted in an independent manner, thus an overall optimal result cannot be guaranteed. Furthermore, it is unclear how the clustering performance will be affected by using this graph. For example, the graph parameters, i.e., the weights on edges, have to be artificially pre-specified while it is very difficult to choose the optimum. To this end, in this paper, a novel subspace clustering via learning an adaptive low-rank graph affinity matrix is proposed, where the affinity matrix and the representation coefficients are learned in a unified framework. As such, the pre-computed graph regularizer is effectively obviated and better performance can be achieved. Experimental results on several famous databases demonstrate that the proposed method performs better against the state-of-the-art approaches, in clustering.

Auction Mechanisms for Energy Trading in Multi-Energy Systems

Abstract: In green cities, one of the most promising energy system designs is the multi-energy system, which is capable of integrating different energy resources to supply stable energy for users. To schedule diverse energy efficiently, the energy trading among different energy entities is a big issue in multi-energy systems. This paper proposes auction mechanisms for energy trading in a smart multi-energy district, in which the district manager sells electricity, natural gas, and heating energy to users and meanwhile trades with outer energy networks. Two auction mechanisms are designed under the day-ahead and real-time markets, respectively. For each auction, energy allocation is optimized by solving a social welfare maximization problem, which is strictly subject to constraints of physical multi-energy system models. It is theoretically proven that both auctions are able to guarantee the properties of economic efficiency, truthfulness, and individual rationality. With these properties, users are incentivized to participate into the auctions with fairness. Finally, real data are adopted to evaluate the performance of the proposed mechanisms. The theoretic analysis of the properties is verified as well.

Robust Latent Subspace Learning for Image Classification

Abstract: This paper proposes a novel method, called robust latent subspace learning (RLSL), for image classification. We formulate an RLSL problem as a joint optimization problem over both the latent SL and classification model parameter predication, which simultaneously minimizes: 1) the regression loss between the learned data representation and objective outputs and 2) the reconstruction error between the learned data representation and original inputs. The latent subspace can be used as a bridge that is expected to seamlessly connect the origin visual features and their class labels and hence improve the overall prediction performance. RLSL combines feature learning with classification so that the learned data representation in the latent subspace is more discriminative for classification. To learn a robust latent subspace, we use a sparse item to compensate error, which helps suppress the interference of noise via weakening its response during regression. An efficient optimization algorithm is designed to solve the proposed optimization problem. To validate the effectiveness of the proposed RLSL method, we conduct experiments on diverse databases and encouraging recognition results are achieved compared with many state-of-the-arts methods.

On Charging Scheduling Optimization for a Wirelessly Charged Electric Bus System

Abstract: The introduction of wirelessly charged electric buses (WCEBs) into current public transportation system attracts many attentions in recent years. As the wireless charging technology enables energy transfer from power transmitters to electric vehicles (EVs) on road, it provides a promising solution to reduce the huge cost of battery with large size and long charging time, which are two critical impediments for EV applications. However, the system cost of WCEBs is huge. Under the dynamic electricity demands and the fluctuating electricity prices, the system operating electricity cost highly depends on the charging schedule. In this paper, according to the typical day-ahead electricity market, we explore an optimal charging scheduling scheme in a WCEB system to minimize the system operating electricity cost, while the characteristic of WCEBs is considered. The price of electricity fluctuates with the accumulated energy demands in both spatial and temporal domains. We first present a day-ahead reserved wholesale electricity determination algorithm, in which, the average speeds of WCEBs are presumed. Then, we propose an optimal charging scheduling algorithm, in which the WCEB charging schedules in slots are optimized sequentially. Both the reserved electricity and the predicted speeds in the slot are used. Simulation results demonstrate the efficiency of our proposed WCEB charging schedules.

On Stability and Robustness of Demand Response in V2G Mobile Energy Networks

Abstract: Demand response (DR) plays a significant role in enhancing the reliability of future smart grids. Electric vehicles (EVs) can be exploited to facilitate DR because their batteries, as a form of flexible energy storage, can be controlled to consume energy from or feed energy back to the grid depending on user needs. However, EVs’ mobility is inherently probabilistic, which presents a challenge for system stability particularly. This paper analyzes the stability of DR in which mobile EVs participate. Using the methodology of dynamical complex networks, we present a DR model of vehicle-to-grid mobile energy network in which the EVs generally move across different districts represented as network nodes. EV fleets, therefore, transport energy and energy storage capacity among these nodes in general. A difference equation system is developed to model the DR dynamics of the nodes, which mutually affect each other. A DR algorithm is proposed to control the demand for EV charging and discharging. It is proved that the stability of the algorithm is robust to internode coupling. Numerical results show that incoming EVs that bring new energy and storage into a district can impact the DR stability. Real-world traces of vehicle mobility are used in simulations to illustrate the DR model.

ADMM-Based Distributed Auction Mechanism for Energy Hub Scheduling in Smart Buildings

Abstract: Energy hub integrates various energy conversion and storage technologies, which can yield complementarity among multiple energy and provide consumers with stable energy services, such as electricity, heating, and cooling. This enables energy hub to be an ideal energy system design for smart and green buildings. This paper proposes a distributed auction mechanism for multi-energy scheduling of an energy hub that serves numbers of building energy users. In the auction, users first submit their demand data to the hub manager. Then, the hub manager allocates energy to users via optimization of energy scheduling based on the users’ data. The auction mechanism is designed to be incentive compatible, meaning that users are incentivized to truthfully submit their demand data. Next, to mitigate the computational burden of the hub manager, a distributed implementation of the auction is developed, in which an algorithm based on alternating direction method of multipliers (ADMM) is adopted to offload auction computation onto the users. Distributed computation offloading may bring in new chances for users to manipulate the auction outcome since the users participate part of the auction computation. It is proven that the proposed distributed auction mechanism can achieve incentive compatibility in a Nash equilibrium, which indicates that rational users will faithfully report demand data and complete the assigned computation as well. Finally, simulation results based on a household energy consumption dataset are presented to evaluate the energy scheduling performance and to verify the incentive compatibility of the auction mechanism.

Filtering for Fuzzy Systems With Multiplicative Sensor Noises and Multidensity Quantizer

Abstract: This paper considers the problem of $l_2-l_\infty$ filtering for discrete-time Takagi–Sugeno (T–S) fuzzy systems with multiplicative sensor noises over the channels with limited capacity. A more general multidensity logarithmic quantizer is designed to increase the utilization of the communication resources, and a sojourn-time-dependent Markov chain is used to model the variation of the quantizer density. Then, the fuzzy basis-, quantizer density-, and sojourn-time-dependent filter is designed for T–S fuzzy systems on the basis of the quantized measurements to improve the performance of the filter. Sufficient conditions are proposed to guarantee that the filtering error system is exponentially mean-square stable and achieves a prescribed $l_2-l_\infty$ performance. Finally, three examples are given to illustrate the developed new design techniques.

Adaptive Asymptotic Neural Network Control of Nonlinear Systems With Unknown Actuator Quantization

Abstract: In this paper, we propose an adaptive neural-network-based asymptotic control algorithm for a class of nonlinear systems subject to unknown actuator quantization. To this end, we exploit the sector property of the quantization nonlinearity and transform actuator quantization control problem into analyzing its upper bounds, which are then handled by a dynamic loop gain function-based approach. In our adaptive control scheme, there is only one parameter required to be estimated online for updating weights of neural networks. Within the framework of Lyapunov theory, it is shown that the proposed algorithm ensures that all the signals in the closed-loop system are ultimately bounded. Moreover, an asymptotic tracking error is obtained by means of introducing Barbalat’s lemma to the proposed adaptive law.

Long non-coding RNA GAS5 and ZFAS1 are prognostic markers involved in translation targeted by miR-940 in prostate cancer.

Abstract: Identification of prognostic biomarkers helps facilitate the prediction of patient outcomes as well as guide treatments. Accumulating evidence now suggests that long non-coding RNAs (lncRNAs) play key roles in tumor progression with diagnostic and prognostic values. However, little is known about the biological functions of lncRNAs and how they contribute to the pathogenesis of cancer. Herein, we performed weighted correlation network analysis (WGCNA) on 380 RNA-seq samples from prostate cancer patients to create networks comprising of microRNAs, lncRNAs, and protein-coding genes. Our analysis revealed expression modules that associated with pathological parameters. More importantly, we identified a gene module that is involved in protein translation and is associated with patient survival. In this gene module, we explored the regulation axis involving GAS5, ZFAS1, and miR-940. We show that GAS5, ZFAS1, and miR-940 are up-regulated in tumors relative to normal prostate tissues, and high expression of either lncRNA is an indicator of poor patient outcome. Finally, we constructed a co-expression network involving GAS5, ZFAS1, and miR-940, as well as the targets of miR-940. Our results show that GAS5 and ZFAS1 are targeted by miR-940 via NAA10 and RPL28. Taken together, co-expression analysis of gene expression profiling from RNA-seq can accelerate the identification and functional characterization of novel prognostic markers in prostate cancer.

Stabilization and destabilization of nonlinear systems via intermittent stochastic noise with application to memristor-based system

Abstract: This paper considers the stabilization and destabilization of a given nonlinear system by an intermittent Brownian noise perturbation. We give some distinct conditions and conclusions on almost sure exponential stability and instability, which are related to the control period T and the noise width δ. These results are then exploited to examine stabilization and destabilization via intermittent stochastic perturbation and applied to the stabilization of a memristor-based chaotic system. Two numerical examples are presented to illustrate the theoretical results.

Learning the Hierarchical Parts of Objects by Deep Non-Smooth Nonnegative Matrix Factorization

Abstract: Nonsmooth nonnegative matrix factorization (nsNMF) is capable of producing more localized, less overlapped feature representations than other variants of NMF while keeping satisfactory fit to data. However, nsNMF as well as other existing NMF methods are incompetent to learn hierarchical features of complex data due to its shallow structure. To fill this gap, we propose a deep nsNMF method coined by the fact that it possesses a deeper architecture compared with standard nsNMF. The deep nsNMF not only gives part-based features due to the nonnegativity constraints but also creates higher level, more abstract features by combing lower level ones. The in-depth description of how deep architecture can help to efficiently discover abstract features in dnsNMF is presented, suggesting that the proposed model inherits the major advantages from both deep learning and NMF. Extensive experiments demonstrate the standout performance of the proposed method in clustering analysis.

Robust Multinomial Logistic Regression Based on RPCA

Abstract: Multiclass classification tasks are ubiquitous recently. In this scenario, the class label usually takes more than two possible discrete outcomes. As a simple and successful model, the multinomial logistic regression, also known as the softmax regression, is widely used in many multiclass classification applications. However, the existing method often experiences significant performance degradation when gross outliers are present in data features. To this end, in this paper, a novel robust multinomial logistic regression method is proposed by solving a rank minimization problem. In particular, the recovery of clean data and the logistic regression learning are conducted jointly. As such, the detection of the intra-sample outliers within data, by robust principal component analysis, is performed in a supervised way. Although the problem is nonconvex and nonsmooth, the convergence is guaranteed by the recent theoretical advance of alternating direction method of multipliers. Experimental analysis on synthetic and real-world data demonstrates that our method outperforms other state-of-the-art ones, in terms of classification accuracy.

Supervised threshold-based heart sound classification algorithm.

Abstract: Objective Deep classification networks have been one of the predominant methods for classifying heart sound recordings. To satisfy their demand for sample size, the most commonly used method for data augmentation is that which divides each heart sound instance into a number of segments, with each segment labelled as the same category as its origin and used as a new sample for training or forecasting. However, performing this poses a crucial issue as to how to determine the category of a predicted heart sound instance from its segments' prediction results. Approach To solve this issue, this paper establishes a mathematical formula to connect the classification performance of these heart sound instances with the prediction results of their segments via a threshold which is supervised by the training set. The optimal value of the proposed threshold is calculated by maximizing the prediction accuracy of the training instances. Seeking the optimal threshold by a gradient-based method, we prove that a continuous function can closely approximate a part of the function of accuracy which transforms the discrete function of accuracy into a continuous function. The optimal threshold is used to recognize the undetermined heart sound recording. Main results Experimental results show the classification performance from a 10-fold cross-validation, measured by the commonly used scales of sensitivity, specificity and mean accuracy (MAcc). The proposed algorithm improves the MAcc by about 4% by modifying the baseline. In addition, the MAcc surpasses the champion of the PhysioNet/Computing in Cardiology Challenge 2016. Significance Our study develops a methodology to determine the category of a predicted heart sound instance from its segments' prediction results, thus assisting in the data augmentation exercise which is necessary to provide sufficient data for deep classification networks. Our method significantly improves the classification performance.

Robust Spectral Subspace Clustering Based on Least Square Regression

Abstract: In recent years, graph based subspace clustering has attracted considerable attentions in computer vision, as its capability of clustering data efficiently. However, the graph weights built by using representation coefficients are not the exact ones as the traditional definition. That is, the two steps are conducted in independent manner such that an overall optimal result cannot be guaranteed. To this end, in this paper, a novel subspace clustering via learning an adaptive graph affinity matrix is proposed, where the soft label and the representation coefficients of data are learned in an unified framework. First, the proposed method learns a robust representation for the data through least square regression, which reveals the subspace structure within data and captures various noises inside. Second, the segmentation is sought by conducting spectral clustering simultaneously. Most importantly, during the optimization process, the segmentation is utilized to iteratively enhance the block-diagonal structure of the learned representation to further assist the clustering process. Experimental results on several famous databases demonstrate that the proposed method performs better against the state-of-the-art approaches, in clustering.

Proximal Alternating Minimization for Analysis Dictionary Learning and Convergence Analysis

Abstract: The sparse analysis model is an alternative approach to the sparse synthesis model that has emerged recently. Most analysis dictionary learning problems based on the sparse analysis model require solving a class of challenging nonsmooth and even nonconvex optimization problems. Despite the fact that many numerical methods have been developed for solving these problems, it remains an open problem to find a numerical method that is not only empirically fast, but also has mathematically guaranteed strong convergence. In this paper, to promote stronger sparsity in solutions than the $\ell _{1}$ -norm, we employ the nonsmooth and nonconvex $\ell _{1/2}$ -norm as a regularizer, and then we propose to use the proximal alternating minimization scheme for solving the nonconvex and nonsmooth problem, leading to an efficient and fast algorithm. More importantly, a rigorous convergence analysis shows that the proposed method satisfies the global convergence property: The whole sequence of iterates is convergent and converges to a critical point. The proposed algorithm has two stages: the analysis sparse-coding stage and the analysis dictionary-update stage. Besides the theoretical soundness, the practical benefit of the proposed method is validated by the synthetic and real-world data. Experiments show that the proposed method achieves better results with faster convergence compared to the state-of-the-art algorithms.

Adaptive inverse compensation for actuator backlash with piecewise time-varying parameters

Abstract: Existing adaptive inverse compensation methods for cancelling actuator backlash nonlinearity are all restricted to handle constant backlash parameters. In other words, when discontinuity and time v...

Compressed-sensing wavenumber-scanning interferometry

Abstract: The Fourier transform (FT), the nonlinear least-squares algorithm (NLSA), and eigenvalue decomposition algorithm (EDA) are used to evaluate the phase field in depth-resolved wavenumber-scanning interferometry (DRWSI). However, because the wavenumber series of the laser's output is usually accompanied by nonlinearity and mode-hop, FT, NLSA, and EDA, which are only suitable for equidistant interference data, often lead to non-negligible phase errors. In this work, a compressed-sensing method for DRWSI (CS-DRWSI) is proposed to resolve this problem. By using the randomly spaced inverse Fourier matrix and solving the underdetermined equation in the wavenumber domain, CS-DRWSI determines the nonuniform sampling and spectral leakage of the interference spectrum. Furthermore, it can evaluate interference data without prior knowledge of the object. The experimental results show that CS-DRWSI improves the depth resolution and suppresses sidelobes. It can replace the FT as a standard algorithm for DRWSI.

Domain Confusion with Self Ensembling for Unsupervised Adaptation

Abstract: Data collection and annotation are time-consuming in machine learning, expecially for large scale problem. A common approach for this problem is to transfer knowledge from a related labeled domain to a target one. There are two popular ways to achieve this goal: adversarial learning and self training. In this article, we first analyze the training unstablity problem and the mistaken confusion issue in adversarial learning process. Then, inspired by domain confusion and self-ensembling methods, we propose a combined model to learn feature and class jointly invariant representation, namely Domain Confusion with Self Ensembling (DCSE). The experiments verified that our proposed approach can offer better performance than empirical art in a variety of unsupervised domain adaptation benchmarks.

Sparse Gene Coexpression Network Analysis Reveals EIF3J-AS1 as a Prognostic Marker for Breast Cancer

Abstract: Predictive and prognostic biomarkers facilitate the selection of treatment strategies that can improve the survival of patients. Accumulating evidence indicates that long noncoding RNAs (lncRNAs) play important roles in cancer progression, with diagnostic and prognostic potential. However, few prognostic lncRNAs are reported for breast cancer, and little is known about their functions that contribute to cancer pathogenesis. In this paper, we used weighted correlation network analysis (WGCNA) to construct networks containing noncoding and protein-coding genes based on their expression in 1097 breast cancer patients. The differentially expressed genes were significantly overlapped with gene modules regulating cell cycle and cell adhesion. The cell cycle-related lncRNAs were consistently downregulated in breast cancer. One lncRNA, EIF3J-AS1, is significantly associated with clinicopathological characteristics, including tumor size, lymph node metastasis, estrogen receptor (ER), and progesterone receptor (PR) status. Kaplan–Meier survival analysis revealed that EIF3J-AS1, a downregulated lncRNA in breast tumor, is a potential prognostic marker for breast cancer. EIF3J-AS1 may function in an estrogen-independent manner and could be inhibited by the compound FDI-6. Therefore, integrating sparse gene coexpression network and clinicopathological features can accelerate identification and functional characterization of novel prognostic lncRNAs in breast cancer.

Learning the Hierarchical Parts of Objects by Deep Non-Smooth Nonnegative Matrix Factorization

Abstract: Nonsmooth Nonnegative Matrix Factorization (nsNMF) is capable of producing more localized, less overlapped feature representations than other variants of NMF while keeping satisfactory fit to data. However, nsNMF as well as other existing NMF methods is incompetent to learn hierarchical features of complex data due to its shallow structure. To fill this gap, we propose a deep nsNMF method coined by the fact that it possesses a deeper architecture compared with standard nsNMF. The deep nsNMF not only gives parts-based features due to the nonnegativity constraints, but also creates higher-level, more abstract features by combing lower-level ones. The in-depth description of how deep architecture can help to efficiently discover abstract features in dnsNMF is presented. And we also show that the deep nsNMF has close relationship with the deep autoencoder, suggesting that the proposed model inherits the major advantages from both deep learning and NMF. Extensive experiments demonstrate the standout performance of the proposed method in clustering analysis.

Wavenumber synthesis approach to high-resolution wavenumber scanning interference using a mode-hoped laser.

Abstract: A new method for the synthesis of wavenumber series before and after mode hopping is proposed for depth-resolved wavenumber scanning interferometry. The classical Fourier transform is not suitable for mode hopping; consequently, the wavenumber scanning range of diode lasers is rather narrow, reducing the depth resolution and measurement accuracy. We show that the discontinuity in wavenumber domain interferograms caused by mode hopping can be removed by introducing the phase compensation of the interference spectrum. Thus, the wavenumber series before and after mode hopping can be synthesized. Experiments and numerical simulations validate the proposed method, and the measurement error is within 5nm.

Low-Rank Tensor Decomposition via Multiple Reshaping and Reordering Operations.

Abstract: Tensor decomposition has been widely applied to find low-rank representations for real-world data and more recently for neural-network parameters too. For the latter, the unfolded matrices may not always be low-rank because the modes of the parameter tensor do not usually have any physical meaning that can be exploited for efficiency. This raises the following question: how can we find low-rank structures when the tensor modes do not have any physical meaning associated with them? For this purpose, we propose a new decomposition method in this paper. Our method uses reshaping and reordering operations that are strictly more general than the unfolding operation. These operations enable us to discover new low-rank structures that are beyond the reach of existing tensor methods. We prove an important theoretical result establishing conditions under which our method results in a unique solution. The experimental results confirm the correctness of our theoretical works and the effectiveness of our methods for weight compression in deep neural networks.