A control theoretic analysis of oscillator Ising machines.

This work advances the understanding of oscillator Ising machines (OIMs) as a nonlinear dynamic system for solving computationally hard problems. Specifically, we classify the infinite number of all possible equilibrium points of an OIM, including non-0/π ones, into three types based on their structural stability properties. We then employ the stability analysis techniques from control theory to analyze the stability property of all possible equilibrium points and obtain the necessary and sufficient condition for their stability. As a result of these analytical results, we establish, for the first time, the threshold of the binarization in terms of the coupling strength and strength of the second harmonic signal. Furthermore, we provide an estimate of the domain of attraction of each asymptotically stable equilibrium point by employing the Lyapunov stability theory. Finally, we illustrate our theoretical conclusions by numerical simulation.

CAT: Centerness-Aware Anchor-Free Tracker.

Accurate and robust scale estimation in visual object tracking is a challenging task. To obtain a scale estimation of the target object, most methods rely either on a multi-scale searching scheme or on refining a set of predefined anchor boxes. These methods require heuristically selected parameters, such as scale factors of the multi-scale searching scheme, or sizes and aspect ratios of the predefined candidate anchor boxes. On the contrary, a centerness-aware anchor-free tracker (CAT) is designed in this work. First, the location and scale of the target object are predicted in an anchor-free fashion by decomposing tracking into parallel classification and regression problems. The proposed anchor-free design obviates the need for hyperparameters related to the anchor boxes, making CAT more generic and flexible. Second, the proposed centerness-aware classification branch can identify the foreground from the background while predicting the normalized distance from the location within the foreground to the target center, i.e., the centerness. The proposed centerness-aware classification branch improves the tracking accuracy and robustness significantly by suppressing low-quality state estimates. The experiments show that our centerness-aware anchor-free tracker, with its appealing features, achieves salient performance in a wide variety of tracking scenarios.

Adaptive Dynamic Programming for Model-Free Global Stabilization of Control Constrained Continuous-Time Systems.

This article addresses the problem of global stabilization of continuous-time linear systems subject to control constraints using a model-free approach. We propose a gain-scheduled low-gain feedback scheme that prevents saturation from occurring and achieves global stabilization. The framework of parameterized algebraic Riccati equations (AREs) is employed to design the low-gain feedback control laws. An adaptive dynamic programming (ADP) method is presented to find the solution of the parameterized ARE without requiring the knowledge of the system dynamics. In particular, we present an iterative ADP algorithm that searches for an appropriate value of the low-gain parameter and iteratively solves the parameterized ADP Bellman equation. We present both state feedback and output feedback algorithms. The closed-loop stability and the convergence of the algorithm to the nominal solution of the parameterized ARE are shown. The simulation results validate the effectiveness of the proposed scheme.

Reinforcement Learning Based Optimal Tracking Control Under Unmeasurable Disturbances With Application to HVAC Systems.

This paper presents the design of an optimal controller for solving tracking problems subject to unmeasurable disturbances and unknown system dynamics using reinforcement learning (RL). Many existing RL control methods take disturbance into account by directly measuring it and manipulating it for exploration during the learning process, thereby preventing any disturbance induced bias in the control estimates. However, in most practical scenarios, disturbance is neither measurable nor manipulable. The main contribution of this article is the introduction of a combination of a bias compensation mechanism and the integral action in the Q-learning framework to remove the need to measure or manipulate the disturbance, while preventing disturbance induced bias in the optimal control estimates. A bias compensated Q-learning scheme is presented that learns the disturbance induced bias terms separately from the optimal control parameters and ensures the convergence of the control parameters to the optimal solution even in the presence of unmeasurable disturbances. Both state feedback and output feedback algorithms are developed based on policy iteration (PI) and value iteration (VI) that guarantee the convergence of the tracking error to zero. The feasibility of the design is validated on a practical optimal control application of a heating, ventilating, and air conditioning (HVAC) zone controller.

Cancer diagnosis using generative adversarial networks based on deep learning from imbalanced data.

BACKGROUND AND OBJECTIVE: Cancer is a serious global disease due to its high mortality, and the key to effective treatment is accurate diagnosis. However, limited by sampling difficulty and actual sample size in clinical practice, data imbalance is a common problem in cancer diagnosis, while most conventional classification methods assume balanced data distribution. Therefore, addressing the imbalanced learning problem to improve the predictive performance of cancer diagnosis is significant. METHODS: In the study, we dissect the data imbalance prevalent in cancer gene expression data and present an improved deep learning based Wasserstein generative adversarial network (WGAN) model, which provides a reliable training progress indicator and deeply explores the characteristics of data. The WGAN generates new samples from the minority class and solves the imbalance problem at the data level. RESULTS: We analyze three publicly available data sets on RNA-seq of three kinds of cancer using the proposed WGAN and compare the results with those from two commonly adopted sampling methods. According to the results, through addressing the data imbalance problem, the balanced data distribution and the expanding sample size increase the prediction accuracy in all three data sets. CONCLUSIONS: Therefore, the proposed WGAN method is superior in solving the imbalanced learning problem of gene expression data, providing significantly better prediction performance in cancer diagnosis.

PID Control for Synchronization of Complex Dynamical Networks With Directed Topologies.

Over the past decades, the synchronization of complex networks with directed topologies has received considerable attention owing to its extensive applications in the realistic world. Design of proportional-integral-derivative (PID) control protocols for achieving synchronization with directed networks is known to be a challenging task. The purpose of this paper is to establish a connection between the PID control protocols and synchronization of complex dynamical networks with directed topologies. Based on the classical complex network model, we investigate global synchronization with PD controller of a balanced strongly connected directed network and global synchronization with PI controller of a strongly connected directed network, and a directed network containing a spanning tree, respectively. Several sets of sufficient conditions are established under which the network reaches global synchronization. The simulation examples are presented to verify the efficiency of the theoretical results.

SITUP: Scale Invariant Tracking using Average Peak-to-Correlation Energy.

Robust and accurate scale estimation of a target object is a challenging task in visual object tracking. Most existing tracking methods cannot accommodate large scale variation in complex image sequences and thus result in inferior performance. In this paper, we propose to incorporate a novel criterion called the average peak-to-correlation energy into the multi-resolution translation filter framework to obtain robust and accurate scale estimation. The resulting system is named SITUP: Scale Invariant Tracking using Average Peak-to-Correlation Energy. SITUP effectively tackles the problem of fixed template size in standard discriminative correlation filter based trackers. Extensive empirical evaluation on the publicly available tracking benchmark datasets demonstrates that the proposed scale searching framework meets the demands of scale variation challenges effectively while providing superior performance over other scale adaptive variants of standard discriminative correlation filter based trackers. Also, SITUP obtains favorable performance compared to state-of-the-art trackers for various scenarios while operating in real-time on a single CPU.

Reinforcement Learning-Based Linear Quadratic Regulation of Continuous-Time Systems Using Dynamic Output Feedback.

In this paper, we propose a model-free solution to the linear quadratic regulation (LQR) problem of continuous-time systems based on reinforcement learning using dynamic output feedback. The design objective is to learn the optimal control parameters by using only the measurable input-output data, without requiring model information. A state parametrization scheme is presented which reconstructs the system state based on the filtered input and output signals. Based on this parametrization, two new output feedback adaptive dynamic programming Bellman equations are derived for the LQR problem based on policy iteration and value iteration (VI). Unlike the existing output feedback methods for continuous-time systems, the need to apply discrete approximation is obviated. In contrast with the static output feedback controllers, the proposed method can also handle systems that are state feedback stabilizable but not static output feedback stabilizable. An advantage of this scheme is that it stands immune to the exploration bias issue. Moreover, it does not require a discounted cost function and, thus, ensures the closed-loop stability and the optimality of the solution. Compared with earlier output feedback results, the proposed VI method does not require an initially stabilizing policy. We show that the estimates of the control parameters converge to those obtained by solving the LQR algebraic Riccati equation. A comprehensive simulation study is carried out to verify the proposed algorithms.

Output Feedback Q-Learning Control for the Discrete-Time Linear Quadratic Regulator Problem.

Approximate dynamic programming (ADP) and reinforcement learning (RL) have emerged as important tools in the design of optimal and adaptive control systems. Most of the existing RL and ADP methods make use of full-state feedback, a requirement that is often difficult to satisfy in practical applications. As a result, output feedback methods are more desirable as they relax this requirement. In this paper, we present a new output feedback-based Q-learning approach to solving the linear quadratic regulation (LQR) control problem for discrete-time systems. The proposed scheme is completely online in nature and works without requiring the system dynamics information. More specifically, a new representation of the LQR Q-function is developed in terms of the input-output data. Based on this new Q-function representation, output feedback LQR controllers are designed. We present two output feedback iterative Q-learning algorithms based on the policy iteration and the value iteration methods. This scheme has the advantage that it does not incur any excitation noise bias, and therefore, the need of using discounted cost functions is circumvented, which in turn ensures closed-loop stability. It is shown that the proposed algorithms converge to the solution of the LQR Riccati equation. A comprehensive simulation study is carried out, which illustrates the proposed scheme.

A semi-supervised deep learning method based on stacked sparse auto-encoder for cancer prediction using RNA-seq data.

BACKGROUND AND OBJECTIVE: Cancer has become a complex health problem due to its high mortality. Over the past few decades, with the rapid development of the high-throughput sequencing technology and the application of various machine learning methods, remarkable progress in cancer research has been made based on gene expression data. At the same time, a growing amount of high-dimensional data has been generated, such as RNA-seq data, which calls for superior machine learning methods able to deal with mass data effectively in order to make accurate treatment decision. METHODS: In this paper, we present a semi-supervised deep learning strategy, the stacked sparse auto-encoder (SSAE) based classification, for cancer prediction using RNA-seq data. The proposed SSAE based method employs the greedy layer-wise pre-training and a sparsity penalty term to help capture and extract important information from the high-dimensional data and then classify the samples. RESULTS: We tested the proposed SSAE model on three public RNA-seq data sets of three types of cancers and compared the prediction performance with several commonly-used classification methods. The results indicate that our approach outperforms the other methods for all the three cancer data sets in various metrics. CONCLUSIONS: The proposed SSAE based semi-supervised deep learning model shows its promising ability to process high-dimensional gene expression data and is proved to be effective and accurate for cancer prediction.

Design of Distributed Observers in the Presence of Arbitrarily Large Communication Delays.

This paper focuses on the construction of distributed observers in the presence of arbitrarily large communication time delays. In contrast with the traditional centralized observer with the ability to acquire full output of the plant, we design a set of distributed observers, each having access to partial output of the plant through a distributed sensor network. More specifically, each observer obtains partial plant output and communicates with its neighboring observers through consensus protocols. The communication among the network is subject to arbitrarily large time delays. We consider three representative network topologies and for each topology establish conditions to guarantee the observation error systems be exponentially stable. We also consider the design of a pinning synchronization problem as a dual problem of the design of distributed observers. Numerical simulation is carried out to verify the effectiveness of our theoretical analysis.

A deep learning-based multi-model ensemble method for cancer prediction.

BACKGROUND AND OBJECTIVE: Cancer is a complex worldwide health problem associated with high mortality. With the rapid development of the high-throughput sequencing technology and the application of various machine learning methods that have emerged in recent years, progress in cancer prediction has been increasingly made based on gene expression, providing insight into effective and accurate treatment decision making. Thus, developing machine learning methods, which can successfully distinguish cancer patients from healthy persons, is of great current interest. However, among the classification methods applied to cancer prediction so far, no one method outperforms all the others. METHODS: In this paper, we demonstrate a new strategy, which applies deep learning to an ensemble approach that incorporates multiple different machine learning models. We supply informative gene data selected by differential gene expression analysis to five different classification models. Then, a deep learning method is employed to ensemble the outputs of the five classifiers. RESULTS: The proposed deep learning-based multi-model ensemble method was tested on three public RNA-seq data sets of three kinds of cancers, Lung Adenocarcinoma, Stomach Adenocarcinoma and Breast Invasive Carcinoma. The test results indicate that it increases the prediction accuracy of cancer for all the tested RNA-seq data sets as compared to using a single classifier or the majority voting algorithm. CONCLUSIONS: By taking full advantage of different classifiers, the proposed deep learning-based multi-model ensemble method is shown to be accurate and effective for cancer prediction.

Characterization of DNA Methylation Associated Gene Regulatory Networks During Stomach Cancer Progression.

DNA methylation plays a critical role in tumorigenesis through regulating oncogene activation and tumor suppressor gene silencing. Although extensively analyzed, the implication of DNA methylation in gene regulatory network is less characterized. To address this issue, in this study we performed an integrative analysis on the alteration of DNA methylation patterns and the dynamics of gene regulatory network topology across distinct stages of stomach cancer. We found the global DNA methylation patterns in different stages are generally conserved, whereas some significantly differentially methylated genes were exclusively observed in the early stage of stomach cancer. Integrative analysis of DNA methylation and network topology alteration yielded several genes which have been reported to be involved in the progression of stomach cancer, such as IGF2, ERBB2, GSTP1, MYH11, TMEM59, and SST. Finally, we demonstrated that inhibition of SST promotes cell proliferation, suggesting that DNA methylation-associated SST suppression possibly contributes to the gastric cancer progression. Taken together, our study suggests the DNA methylation-associated regulatory network analysis could be used for identifying cancer-related genes. This strategy can facilitate the understanding of gene regulatory network in cancer biology and provide a new insight into the study of DNA methylation at system level.

Identification of Biomarkers for Predicting Lymph Node Metastasis of Stomach Cancer Using Clinical DNA Methylation Data.

BACKGROUND: Lymph node (LN) metastasis was an independent risk factor for stomach cancer recurrence, and the presence of LN metastasis has great influence on the overall survival of stomach cancer patients. Thus, accurate prediction of the presence of lymph node metastasis can provide guarantee of credible prognosis evaluation of stomach cancer patients. Recently, increasing evidence demonstrated that the aberrant DNA methylation first appears before symptoms of the disease become clinically apparent. OBJECTIVE: Selecting key biomarkers for LN metastasis presence prediction for stomach cancer using clinical DNA methylation based on a machine learning method. METHODS: To reduce the overfitting risk of prediction task, we applied a three-step feature selection method according to the property of DNA methylation data. RESULTS: The feature selection procedure extracted several cancer-related and lymph node metastasis-related genes, such as TP73, PDX1, FUT8, HOXD1, NMT1, and SEMA3E. The prediction performance was evaluated on the public DNA methylation dataset. The results showed that the three-step feature procedure can largely improve the prediction performance and implied the reliability of the biomarkers selected. CONCLUSIONS: With the selected biomarkers, the prediction method can achieve higher accuracy in detecting LN metastasis and the results also proved the reliability of the selected biomarkers indirectly.

Consensus of a class of discrete-time nonlinear multi-agent systems in the presence of communication delays.

In this paper, we study the consensus problem for a class of discrete-time nonlinear multi-agent systems. The dynamics of each agent is input affine and the agents are connected through a connected undirected communication network. Distributed control laws are proposed and consensus analysis is conducted both in the absence and in the presence of communication delays. Both theoretical analysis and numerical simulation show that our control laws ensure state consensus of the multi-agent system.

Convergence Rate for Discrete-Time Multiagent Systems With Time-Varying Delays and General Coupling Coefficients.

Multiagent systems (MASs) are ubiquitous in our real world. There is an increasing attention focusing on the consensus (or synchronization) problem of MASs over the past decade. Although there are numerous results reported on the convergence of a discrete-time MAS based on the infinite products of matrices, few results are on the convergence rate. Because of the switching topology, the traditional eigenvalue analysis and the Lyapunov function methods are both invalid for the convergence rate analysis of an MAS with a switching topology. Therefore, the estimation of the convergence rate for a discrete-time MAS with time-varying delays remains a difficult problem. To overcome the essential difficulty of switching topology, this paper aims at developing a contractive-set approach to analyze the convergence rate of a discrete-time MAS in the presence of time-varying delays and generalized coupling coefficients. Using the proposed approach, we obtain an upper bound of the convergence rate under the condition of joint connectivity. In particular, the proposed method neither requires the nonnegative property of the coupling coefficients nor the basic assumption of a uniform lower bound for all positive coupling coefficients, which have been widely applied in the existing works on this topic. As an application of the main results, we will show that the classical Vicsek model with time delays can realize synchronization if the initial topology is connected.

Distributed Synchronization Control of Multiagent Systems With Unknown Nonlinearities.

This paper revisits the distributed adaptive control problem for synchronization of multiagent systems where the dynamics of the agents are nonlinear, nonidentical, unknown, and subject to external disturbances. Two communication topologies, represented, respectively, by a fixed strongly-connected directed graph and by a switching connected undirected graph, are considered. Under both of these communication topologies, we use distributed neural networks to approximate the uncertain dynamics. Decentralized adaptive control protocols are then constructed to solve the cooperative tracker problem, the problem of synchronization of all follower agents to a leader agent. In particular, we show that, under the proposed decentralized control protocols, the synchronization errors are ultimately bounded, and their ultimate bounds can be reduced arbitrarily by choosing the control parameter appropriately. Simulation study verifies the effectiveness of our proposed protocols.

Large scale gene regulatory network inference with a multi-level strategy.

Transcriptional regulation is a basis of many crucial molecular processes and an accurate inference of the gene regulatory network is a helpful and essential task to understand cell functions and gain insights into biological processes of interest in systems biology. Inspired by the Dialogue for Reverse Engineering Assessments and Methods (DREAM) projects, many excellent gene regulatory network inference algorithms have been proposed. However, it is still a challenging problem to infer a gene regulatory network from gene expression data on a large scale. In this paper, we propose a gene regulatory network inference method based on a multi-level strategy (GENIMS), which can give results that are more accurate and robust than the state-of-the-art methods. The proposed method mainly consists of three levels, which are an original feature selection step based on guided regularized random forest, normalization of individual feature selection and the final refinement step according to the topological property of the gene regulatory network. To prove the accuracy and robustness of our method, we compare our method with the state-of-the-art methods on the DREAM4 and DREAM5 benchmark networks and the results indicate that the proposed method can significantly improve the performance of gene regulatory network inference. Additionally, we also discuss the influence of the selection of different parameters in our method.

A system level analysis of gastric cancer across tumor stages with RNA-seq data.

Gastric cancer is the third leading cause of cancer-related death in the world. Over the past few decades, with the development of high-throughput technologies and the application of various statistical tools, cancer research has witnessed remarkable advancements. However, no system level analysis has taken into account the cancer stages, which are known to be extremely important in prognosis and therapy. In this study, we aimed to carry out a system level analysis of the dynamics of the network structure across the normal phenotype and the four tumor stage phenotypes. We analyzed 276 samples of primary tumor tissues including normal and four tumor stage phenotypes to reveal the dynamics of the five phenotype-specific co-expression networks. Our analysis reveals that the structure of the normal network is dramatically different from that of a tumor network. The analysis of connectivity dynamics shows that hub genes present in the normal network but not in the tumor networks play important roles in tumorigenesis and hub genes unique to a tumor network are enriched in specific biological terms. Moreover, we found three interesting clusters of genes which possess specific dynamic features across the five phenotypes and are enriched in stage-specific biological terms. Integrating the results from the expression analysis and the connectivity analysis shows that the stages of tumor should be taken into consideration and a system level analysis serves as a complement to and a refinement of the traditional expression analysis.