Data-Driven Event-Triggered Sliding Mode Secure Control for Autonomous Vehicles Under Actuator Attacks.

This article investigates a comprehensive data-driven event-triggered secure lateral control of autonomous vehicles under actuator attacks. We consider stabilization issues of autonomous vehicles subject to modeling difficulties, limited communication resources, and actuator attacks. The dynamic model decomposition (DMD) from data is exploited to characterize the inherent lateral dynamics model of autonomous vehicles, the event-triggered transmission scheme is utilized to alleviate communication burden for limited bandwidth network, and the sliding mode control scheme is designed to ensure the security of autonomous vehicles under actuator attacks.

TMP: Temporal Motion Propagation for Online Video Super-Resolution.

Online video super-resolution (online-VSR) highly relies on an effective alignment module to aggregate temporal information, while the strict latency requirement makes accurate and efficient alignment very challenging. Though much progress has been achieved, most of the existing online-VSR methods estimate the motion fields of each frame separately to perform alignment, which is computationally redundant and ignores the fact that the motion fields of adjacent frames are correlated. In this work, we propose an efficient Temporal Motion Propagation (TMP) method, which leverages the continuity of motion field to achieve fast pixel-level alignment among consecutive frames.

Reactive oxygen species regulation by NCF1 governs ferroptosis susceptibility of Kupffer cells to MASH.

Impaired self-renewal of Kupffer cells (KCs) leads to inflammation in metabolic dysfunction-associated steatohepatitis (MASH). Here, we identify neutrophil cytosolic factor 1 (NCF1) as a critical regulator of iron homeostasis in KCs. NCF1 is upregulated in liver macrophages and dendritic cells in humans with metabolic dysfunction-associated steatotic liver disease and in MASH mice.

Dynamic Gain Reduced-Order Observer-Based Global Adaptive Neural-Network Tracking Control for Nonlinear Time-Delay Systems.

In this article, a globally adaptive neural-network tracking control strategy based on the dynamic gain observer is proposed for a class of uncertain output-feedback systems with unknown time-varying delays. A reduced-order observer with novel dynamic gain is proposed. An n th-order continuously differentiable switching function is constructed to achieve the continuous switching control of the system, thus further ensuring that all the closed-loop signals are globally uniformly ultimately bounded (GUUB).

Globally Adaptive Neural Network Output-Feedback Control for Uncertain Nonlinear Systems.

In this article, a globally neural-network-based adaptive control strategy with flat-zone modification is proposed for a class of uncertain output feedback systems with time-varying bounded disturbances. A high-order continuously differentiable switching function is introduced into the filter dynamics to achieve global compensation for uncertain functions, thus further to ensure that all the closed-loop signals are globally uniformity ultimately bounded (GUUB). It is proven that the output tracking error converges to the prespecified neighborhood of the origin.

A Componentwise Approach to Weakly Supervised Semantic Segmentation Using Dual-Feedback Network.

Recent weakly supervised semantic segmentation methods generate pseudolabels to recover the lost position information in weak labels for training the segmentation network. Unfortunately, those pseudolabels often contain mislabeled regions and inaccurate boundaries due to the incomplete recovery of position information. It turns out that the result of semantic segmentation becomes determinate to a certain degree.

Globally Adaptive Neural Network Tracking for Uncertain Output-Feedback Systems.

This article investigates the problem of global neural network (NN) tracking control for uncertain nonlinear systems in output feedback form under disturbances with unknown bounds. Compared with the existing NN control method, the differences of the proposed scheme are as follows. The designed actual controller consists of an NN controller working in the approximate domain and a robust controller working outside the approximate domain, in addition, a new smooth switching function is designed to achieve the smooth switching between the two controllers, in order to ensure the globally uniformly ultimately bounded of all closed-loop signals.

Computer-Aided Diagnosis of Congenital Abnormalities of the Kidney and Urinary Tract in Children Using a Multi-Instance Deep Learning Method Based on Ultrasound Imaging Data.

Ultrasound images are widely used for diagnosis of congenital abnormalities of the kidney and urinary tract (CAKUT). Since a typical clinical ultrasound image captures 2D information of a specific view plan of the kidney and images of the same kidney on different planes have varied appearances, it is challenging to develop a computer aided diagnosis tool robust to ultrasound images in different views. To overcome this problem, we develop a multi-instance deep learning method for distinguishing children with CAKUT from controls based on their clinical ultrasound images, aiming to automatic diagnose the CAKUT in children based on ultrasound imaging data.

Reduced-Order Filters-Based Adaptive Backstepping Control for Perturbed Nonlinear Systems.

In this article, a robust adaptive output-feedback control approach is presented for a class of nonlinear output-feedback systems with parameter uncertainties and time-varying bounded disturbances. A reduced-order filter driven by control input is proposed to reconstruct unmeasured states. The state estimation error is shown to be bounded by dynamic signals driven by system output.

Practical Stabilization of Networked Takagi-Sugeno Fuzzy Systems via Improved Jensen Inequalities.

This work addresses the problem of aperiodically sampled control for the networked Takagi-Sugeno (T-S) fuzzy systems, where the aperiodically sampled input is generated by a periodic sampler and an event-triggered mechanism (ETM). The purpose of ETM is used to reduce the computational and communication burdens. For guaranteeing controller robustness, the practical stability of T-S fuzzy systems is considered by using the Lyapunov method and linear matrix inequality (LMI) technique.

Push-Sum Distributed Online Optimization With Bandit Feedback.

In this article, we concentrate on distributed online convex optimization problems over multiagent systems, where the communication between nodes is represented by a class of directed graphs that are time varying and uniformly strongly connected. This problem is in bandit feedback, in the sense that at each time only the cost function value at the committed point is revealed to each node. Then, nodes update their decisions by exchanging information with their neighbors only.

Multi-instance Deep Learning of Ultrasound Imaging Data for Pattern Classification of Congenital Abnormalities of the Kidney and Urinary Tract in Children.

Objective: To reliably and quickly diagnose children with posterior urethral valves (PUV), we developed a multi-instance deep learning method to automate image analysis.

Methods: We built a robust pattern classifier to distinguish 86 children with PUV from 71 children with mild unilateral hydronephrosis based on ultrasound images (3504 in sagittal view and 2558 in transverse view) obtained during routine clinical care.

Results: The multi-instance deep learning classifier performed better than classifiers built on either single sagittal images or single transverse images.

An Implicit Function-Based Adaptive Control Scheme for Noncanonical-Form Discrete-Time Neural-Network Systems.

This article proposes a new implicit function-based adaptive control scheme for the discrete-time neural-network systems in a general noncanonical form. Feedback linearization for such systems leads to the output dynamics nonlinear dependence on the system states, the control input, and uncertain parameters, which leads to the nonlinear parametrization problem, the implicit relative degree problem, and the difficulty to specify an analytical adaptive controller. To address these problems, we first develop a new adaptive parameter estimation strategy to deal with all uncertain parameters, especially, those of nonlinearly parameterized forms, in the output dynamics.

Multi-instance Deep Learning with Graph Convolutional Neural Networks for Diagnosis of Kidney Diseases Using Ultrasound Imaging.

Ultrasound imaging (US) is commonly used in nephrology for diagnostic studies of the kidneys and lower urinary tract. However, it remains challenging to automate the disease diagnosis based on clinical 2D US images since they provide partial anatomic information of the kidney and the 2D images of the same kidney may have heterogeneous appearance. To overcome this challenge, we develop a novel multi-instance deep learning method to build a robust classifier by treating multiple 2D US images of each individual subject as multiple instances of one bag.

Event-Triggered Adaptive Neural Network Control for Nonstrict-Feedback Nonlinear Time-Delay Systems With Unknown Control Directions.

In this article, the event-triggered-based adaptive neural network control problem is studied for a class of nonlinear time-delay systems with nonstrict-feedback structures and unknown control directions. First, a compensation system is introduced to handle the input delay and an observer is also designed to estimate the unmeasurable states. Then, by employing the neural networks and the variable separation approach, the adaptive backstepping method is applied to control the nonlinear systems with nonstrict-feedback structures.

FULLY-AUTOMATIC SEGMENTATION OF KIDNEYS IN CLINICAL ULTRASOUND IMAGES USING A BOUNDARY DISTANCE REGRESSION NETWORK.

It remains challenging to automatically segment kidneys in clinical ultrasound images due to the kidneys' varied shapes and image intensity distributions, although semi-automatic methods have achieved promising performance. In this study, we developed a novel boundary distance regression deep neural network to segment the kidneys, informed by the fact that the kidney boundaries are relatively consistent across images in terms of their appearance. Particularly, we first use deep neural networks pre-trained for classification of natural images to extract high-level image features from ultrasound images, then these feature maps are used as input to learn kidney boundary distance maps using a boundary distance regression network, and finally the predicted boundary distance maps are classified as kidney pixels or non-kidney pixels using a pixel classification network in an end-to-end learning fashion.

Molecular and clinical progress in follicular lymphoma lacking the t(14;18) translocation (Review).

Although the majority of patients with follicular lymphoma (FL) harbor the t(14;18)(q32;q21) IGH/BCL2 gene rearrangement that leads to the overexpression of BCL2 protein, approximately 20% of FL cases lack t(14;18)(q32;q21). It is considered that BCL2 overexpression underscores the development of the majority of cases of FL and their transformation to more aggressive lymphoma [known as transformed FL (tFL)]. However, FL cases lacking the t(14;18)(q32;q21) translocation exhibit symptoms analogous to their t(14;18)‑positive counterparts.

Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networks.

It remains challenging to automatically segment kidneys in clinical ultrasound (US) images due to the kidneys' varied shapes and image intensity distributions, although semi-automatic methods have achieved promising performance. In this study, we propose subsequent boundary distance regression and pixel classification networks to segment the kidneys automatically. Particularly, we first use deep neural networks pre-trained for classification of natural images to extract high-level image features from US images.

Cooperative Tracking Control of Multiagent Systems: A Heterogeneous Coupling Network and Intermittent Communication Framework.

This paper proposes a heterogeneous coupling network framework to address the cooperative tracking control problem for multiagent systems with dynamic interaction topology and bounded intermittent communication. By considering the underlying dynamic interaction topology and introducing the adjustable heterogeneous coupling weighting parameters, a bounded consensus condition of cooperative tracking control is proposed. With considering a bounded intermittent communication condition, a class of intermittent cooperative tracking control protocol is designed based on the combination of the individual agent dynamic and the exchange of information among the agents under an appropriate consensus speed constraint.

Adaptive output feedback tracking of nonlinear systems with uncertain nonsymmetric dead-zone input.

In this paper, the problem of adaptive practical tracking is investigated by output feedback for a class of uncertain nonlinear systems subject to nonsymmetric dead-zone input nonlinearity with parameters of dead-zone being unknown. Instead of constructing the inverse of dead-zone nonlinearity, an adaptive robust control scheme is developed by designing an output compensator including two dynamic gains based respectively on identification and non-identification mechanism. With the aid of dynamic high-gain scaling approach and Backstepping method, stability analysis of the closed-loop system is proceeded using non-separation principle, which shows that the proposed controller guarantees that all closed-loop signal is bounded while the output of system tracks a broad class of bounded reference trajectories by arbitrarily small error prescribed previously.

Further Results on Adaptive Stabilization of High-Order Stochastic Nonlinear Systems Subject to Uncertainties.

This paper concerns the adaptive state-feedback control for a class of high-order stochastic nonlinear systems with uncertainties including time-varying delay, unknown control gain, and parameter perturbation. The commonly used growth assumptions on system nonlinearities are removed, and the adaptive control technique is combined with the sign function to deal with the unknown control gain. Then, with the help of the radial basis function neural network approximation approach and Lyapunov-Krasovskii functional, an adaptive state-feedback controller is obtained through the backstepping design procedure.

Event-Based Control for Networked T-S Fuzzy Systems via Auxiliary Random Series Approach.

This paper presents an auxiliary random series approach to model the effect of network induced problems, such as data losses and transmission delay subject to event-based communication scheme for nonlinear continuous time systems. T-S fuzzy model is employed to describe the nonlinear systems. In order to save the bandwidth and energy, we introduce the event-triggered mechanism to reduce the number of data for transmission and computation.

Relative Degrees and Implicit Function-Based Control of Discrete-Time Noncanonical Form Neural Network Systems.

This paper studies the relative degrees of discrete-time neural network systems in a general noncanonical form, and develops a new feedback control scheme for such systems, based on implicit function theory and feedback linearization. After time-advance operation on output of such systems, the output dynamics nonlinearly depends on the control input. To address this issue, we use implicit function theory to define the relative degrees, and to establish a normal form.

Extended dissipative filter design for T-S fuzzy systems with multiple time delays.

This paper deals with the fuzzy filtering problem for a class of nonlinear time-delay systems described by T-S fuzzy models. Different from the existing schemes in the literature, this paper aims to solve the fuzzy filtering problem by considering the H, L - L and dissipative performance constraints in a unified way. To achieve this purpose, the recently proposed notion of extended dissipativity is applied, which provides an inequality covering the well-known H, L - L and dissipative performances.