Critical Network Research Articles

Neurological outcome following out of hospital cardiac arrest: Evaluation of performance of existing risk prediction models in a UK cohort.

Out of hospital cardiac arrest (OHCA) is a common problem. Rates of survival are low and a proportion of survivors are left with an unfavourable neurological outcome. Four models have been developed to predict risk of unfavourable outcome at the time of critical care admission - the Cardiac Arrest Hospital Prognosis (CAHP), MIRACLE2, Out of Hospital Cardiac Arrest (OHCA), and Targeted Temperature Management (TTM) models. This evaluation evaluates the performance of these four models in a United Kingdom population and provides comparison to performance of the Acute Physiology and Chronic Health Evaluation II (APACHE-II) score. A retrospective evaluation of the performance of the models was conducted over a 43-month period in 414 adult, non-pregnant patients presenting consecutively following non-traumatic OHCA to the five units in our regional critical care network. Scores were generated for each model for where patients had complete data (CAHP = 347, MIRACLE2 = 375, OHCA = 356, TTM = 385). Cerebral Performance Category (CPC) outcome was calculated for each patient at last documented follow up and an unfavourable outcome defined as CPC ⩾ 3. Performance for discrimination of unfavourable outcome was tested by generating receiver operating characteristic (ROC) curves for each model and comparing the area under the curve (AUC). Best performance for discrimination of unfavourable outcome was demonstrated by the high risk group of the CAHP score with an AUC of 0.87 [95% CI 0.83-0.91], specificity of 97.1% [95% CI 93.8-100] and positive predictive value (PPV) of 96.3% [95% CI 92.2-100]. The high risk group of the MIRACLE2 model, which is significantly easier to calculate, had an AUC of 0.81 [95% CI 0.76-0.86], specificity of 92.3% [95% CI 87.2-97.4] and PPV of 95.2% [95% CI 91.9-98.4]. The CAHP, MIRACLE2, OHCA and TTM scores all perform comparably in a UK population to the original development and validation cohorts. All four scores outperform APACHE-II in a population of patients resuscitated from OHCA. CAHP and TTM perform best but are more complex to calculate than MIRACLE2, which displays inferior performance.

Treatment of preterm brain injury via gut-microbiota-metabolite-brain axis.

Brain injury in preterm infants potentially disrupts critical structural and functional connective networks in the brain. It is a major cause of neurological sequelae and developmental deficits in preterm infants. Interesting findings suggest that the gut microbiota (GM) and their metabolites contribute to the programming of the central nervous system (CNS) during developmental stages and may exert structural and functional effects throughout the lifespan. To summarize the existing knowledge of the potential mechanisms related to immune, endocrine, neural, and blood-brain barrier (BBB) mediated by GM and its metabolites in neural development and function. We review the recent literature and included 150 articles to summarize the mechanisms through which GM and their metabolites work on the nervous system. Potential health benefits and challenges of relevant treatments are also discussed. This review discusses the direct and indirect ways through which the GM may act on the nervous system. Treatment of preterm brain injury with GM or related derivatives, including probiotics, prebiotics, synbiotics, dietary interventions, and fecal transplants are also included. This review summarizes mechanisms underlying microbiota-gut-brain axis and novel therapeutic opportunities for neurological sequelae in preterm infants. Optimizing the initial colonization and microbiota development in preterm infants may represent a novel therapy to promote brain development and reduce long-term sequelae.

Adaptive-critic-design based tracking controller for boost complement glide vehicle with performance constraint and input saturation

In order to achieve high precision and fast response flight control, an adaptive-critic-design (ACD) based tracking controller is proposed for boost complement glide vehicle (BCGV) with performance constraint and input saturation. The desired tracking performance is prescribed by error behavior boundary. Firstly, a tracking differentiator and a disturbance observer are proposed to allocate tracking command and resist disturbance, respectively. Then, a composite variable is constructed with the transformation mechanism and anti-saturation auxiliary variable, which quantifies the transformed tracking system with input saturation. Finally, a robust ACD with composite variable is proposed to enforce the performance constraint in a minimally invasive fashion, which optimizes the control actions with iterative learning online. Especially, the uncertainty is considered in the learning mechanism to improve the robustness. Besides, the proposed policy iteration is implemented by a single critic network to reduce the computing cost and complexity. Simulations show the effectiveness of the proposed controller and advantages compared with other methods.

Analyzing Autoencoder-Based Intrusion Detection System Performance

The rise in cyberattacks targeting critical network infrastructure has spurred an increased emphasis on the development of robust cybersecurity measures. In this context, there is a growing exploration of effective Intrusion Detection Systems (IDS) that leverage Machine Learning (ML) and Deep Learning (DL), with a particular emphasis on autoencoders. Recognizing the pressing need to mitigate cyber threats, our study underscores the crucial importance of advancing these methodologies. Our study aims to identify the optimal architecture for an Intrusion Detection System (IDS) based on autoencoders, with a specific focus on configuring the number of hidden layers. To achieve this objective, we designed four distinct sub-models, each featuring a different number of hidden layers: Test 1 (one hidden layer), Test 2 (two hidden layers), Test 3 (three hidden layers), and Test 4 (four hidden layers).We subjected our models to rigorous training and testing, maintaining consistent neuron counts of 30 and 60. The outcomes of our experimental study reveal that the model with a single hidden layer consistently outperformed its counterparts, achieving an accuracy of 95.11% for NSL-KDD and an impressive 98.6% for CIC-IDS2017. The findings of our study indicate that our proposed system is viable for implementation on critical network infrastructure as a proactive measure against cyber-attacks.

Actor–critic learning based PID control for robotic manipulators

In this paper, we propose a reinforcement learning structure for auto-tuning PID gains by solving an optimal tracking control problem for robot manipulators. Capitalizing on the actor–critic framework implemented by neural networks, we achieve optimal tracking performance, estimating unknown system dynamics simultaneously. The critic network is used to approximate the cost function, which serves as an indicator of control performance. With feedback from the critic, the actor network learns time-varying PID gains over time to optimize control input, thereby steering the system toward optimal performance. Furthermore, we utilize Lyapunov’s direct method to demonstrate the stability of the closed-loop system. This approach provides an analytical procedure for a stable robot manipulator system to systematically adjust PID gains, bypassing the ad-hoc and painstaking process. The resultant actor–critic PID-like control exhibits stable adaptive and learning capabilities while maintaining a simple structure and inexpensive online computational demands. Numerical simulations underscore the effectiveness and advantages of the proposed actor–critic neural network PID control.

Trajectory tracking control for underactuated autonomous vehicles via adaptive dynamic programming

In this paper, the trajectory tracking control problem for underactuated autonomous vehicles moving in 2-D space is studied. Firstly, the trajectory tracking error dynamics with the equivalent point being the origin are given. Since both model and input uncertainties of vehicles are considered, a robust control problem is formulated by giving the extended trajectory tracking error dynamics. Through showing that a robust control law is equivalent to an optimal control law for a nominal system under some conditions, the robust control problem is transformed into an equivalent optimal control problem and a cost function composed of uncertainty bounds and discount factor is constructed. In order to solve the optimal control problem, a policy iteration-based ADP algorithm is proposed, in which two neural networks, called critic and actor networks, are applied respectively to describe the unknown value function and control law. The weights of the two networks are tuned through the gradient descent method at each iteration and the optimality and convergence properties are provided in the sequel. At last, simulation results are given to illustrate the validity of the proposed algorithm.

Deep reinforcement learning based collision avoidance system for autonomous ships

Autonomous ships is a key to avoid accidents caused by human errors and improve maritime safety. However, unlike the autonomous vehicles counterpart, collision avoidance for autonomous ships faces many challenges due to the hash driving environments, difficult ship control and large stopping distance. In this paper, we investigate a collision avoidance system for autonomous ships under complex encounter scenarios, such as busy ports. In the system various sensors are used to detect objects and perceive the maritime environments. To help the autonomous ships handle the complex and dynamic scenarios that may be encountered, a collision map used to describe the ships encounter scenarios is generated and utilized as the input of a deep reinforcement learning (DRL) model. The DRL model is applied to make collision avoidance and safe driving decisions. New reward functions are proposed to train the DRL model to generate safe ship maneuver actions to reduce collisions and ensure compliance with the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs). Furthermore, a self-adaptive parameters sharing approach is designed for fast convergence and collision avoidance performance of the DRL model, where the parameters of the fully connected layers are shared and the correlation layers are self adapted for the DRL critic and actor networks. Simulation results show that the proposed system has high DRL convergence speed and excellent collision avoidance.

Optimized intelligent tracking control for a quadrotor unmanned aerial vehicle with actuator failures

This work investigates the implementation of tracking control for a quadrotor unmanned aerial vehicle exposed to disturbances and actuator failures. Cost reduction in control processes is not usually considered in conventional control methods. To overcome this limitation, this work proposes an optimized intelligent control scheme that utilizes adaptive dynamic programming. Firstly, a critic-only structure is employed to learn the nominal control strategies, including two critic neural network update laws, lifting the persistent excitation condition. Subsequently, two specifically designed observers are developed on the radial basis function neural network (RBFNN) to reconstruct the disturbances and actuator failures and compensate for the nominal strategies. The observers achieve fixed-time convergence by employing the fixed-time update laws of the RBFNNs. Moreover, two variable vectors using the Gaussian error function are introduced to reduce the impact caused by the observation errors. Additionally, the superior performance of the proposed control scheme is validated through numerical simulations.

Hsa-miR-548k blocks the drug resistance cascade in NSCLC cancer by targeting the key genes involved in various chemotherapy resistance pathways

Although new therapeutic approaches have been developed, and efforts have been made to understand cancer signaling pathways, drug resistance remains the most common cause of tumor recurrence and therapy. microRNAs degrade mRNAs or target their specific sequences as translation repressors. miRNA disruption may alter the drug sensitivity of cancer cells and influence tumor cell resistance to chemotherapy. Modulation of miRNAs through antagomiRs or mimics inhibit tumor cell proliferation and enhance drug sensitivity by regulating critical gene networks and signaling pathways. miRNAs that simultaneously involve the 3′-UTR of genes responsible for various drug resistance pathways in lung cancer were identified with the miRvestigator algorithm. Its validity was confirmed with TargetScan and the expression level of introduced genes was investigated under the influence of its mimic. Finally, the percentage of viable cells was determined using the apoptosis assay. Hsa-miR-548k was identified as a potential gene regulator of multiple drug resistance signaling in lung cancer using miRvestigator bioinformatics algorithms. Hsa-miR-548k mimics were transiently transfected into A549 cells to investigate the effect of hsa-miR-548k on the expression of ATP-binding cassette super-family G member 2 (ABCG2), epidermal growth factor receptor (EGFR), signal transducer and activator of transcription 3 (STAT3), Yes1 Associated Transcriptional Regulator (YAP), and vascular endothelial growth factor (VEGF). Quantitative analyses confirmed significant downregulation of the gene expression levels involved in lung cancer drug resistance pathways by hsa-miR-548k. Furthermore, hsa-miR-548k overexpression increased the apoptosis of A549 cells. This study not only confirmed the significance of hsa-miR-548k in regulating drug resistance pathways but also identified it as a new target for the treatment of lung cancer.

Efficient Online Globalized Dual Heuristic Programming With an Associated Dual Network.

Globalized dual heuristic programming (GDHP) is the most comprehensive adaptive critic design, which employs its critic to minimize the error with respect to both the cost-to-go and its derivatives simultaneously. Its implementation, however, confronts a dilemma of either introducing more computational load by explicitly calculating the second partial derivative term or sacrificing the accuracy by loosening the association between the cost-to-go and its derivatives. This article aims at increasing the online learning efficiency of GDHP while retaining its analytical accuracy by introducing a novel GDHP design based on a critic network and an associated dual network. This associated dual network is derived from the critic network explicitly and precisely, and its structure is in the same level of complexity as dual heuristic programming critics. Three simulation experiments are conducted to validate the learning ability, efficiency, and feasibility of the proposed GDHP critic design.

Suboptimal Leader-to-Coordination Control for Nonlinear Systems With Switching Topologies: A Learning-Based Method.

In the cooperative control for multiagent systems (MASs), the key issues of distributed interaction, nonlinear characteristics, and optimization should be considered simultaneously, which, however, remain intractable theoretically even to this day. Considering these factors, this article investigates leader-to-formation control and optimization for nonlinear MASs using a learning-based method. Under time-varying switching topology, a fully distributed state observer based on neural networks is designed to reconstruct the dynamics and the state trajectory of the leader signal with arbitrary precision under jointly connected topology assumption. Benefitted from the observers, formation for MASs under switching topologies is transformed into tracking control for each subsystem with continuous state generated by the observers. An augmented system with discounted infinite LQR performance index is considered to optimize the control effect. Due to the complexity of solving the Hamilton-Jacobi-Bellman equation, the optimal value function is approximated by a critic network via the integral reinforcement learning method without the knowledge of drift dynamics. Meanwhile, an actor network is also presented to assure stability. The tracking errors and estimation weighted matrices are proven to be uniformly ultimately bounded. Finally, two illustrative examples are given to show the effectiveness of this method.

Adaptive-Critic-Based Event-Triggered Intelligent Cooperative Control for a Class of Second-Order Constrained Multiagent Systems

An event-based intelligent cooperative control policy is developed in this paper for a class of second-order multiagent systems (MASs). The followers are subject to external disturbances and output constraints, in which the constraint ranges are asymmetric and time-varying. By using one-to-one nonlinear mapping technique to obtain equivalent unconstrained systems and designing a distributed observer to estimate the leader's states, a simplified unconstrained tracking control task is established for each follower. After that, event-driven distributed optimal <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$H_\infty$</tex-math></inline-formula> controllers are designed to mitigate the effects of external disturbances, which are obtained from a set of decoupled Hamilton-Jacobi-Isaacs (HJI) equations, where the proposed event-triggered strategy is dynamic. Aiming at solving the HJI equations more efficiently, an event-based adaptive dynamic programming (ADP) learning algorithm applying only critic neural networks (NNs) is developed. And the critic NN weights are convergent by using stored data under finite excitation condition. Finally, the validity of the developed control scheme is demonstrated by multiple single-link robot arm systems.

A Motion Planning Method for Visual Servoing Using Deep Reinforcement Learning in Autonomous Robotic Assembly

Assembly positioning by visual servoing (VS) is a basis for autonomous robotic assembly. In practice, VS control suffers potential stability and convergence problems due to image and physical constraints, e.g., field of view constraints, image local minima, obstacle collisions, and occlusion. Therefore, this article proposes a novel deep reinforcement learning-based hybrid visual servoing (DRL-HVS) controller for motion planning of VS tasks. DRL-HVS controller takes current observed image features and camera pose as inputs, and the core parameters of hybrid VS are dynamically optimized using a deep deterministic policy gradient (DDPG) algorithm to obtain an optimal motion scheme, considering image/physical constraints and robot motion performance. In addition, an adaptive exploration strategy is proposed to further improve the training efficiency by adaptively tuning the exploration noise parameters. In this way, the offline pretrained DRL-HVS controller in the virtual environment, where the DDPG actor–critic network is continuously optimized, can be quickly deployed to a real robot system for real-time control. Experiments based on an eye-in-hand VS system are conducted with a calibrated HIKVISION RGB camera mounted on the end-effector of a GSK-RB03A1 six degree-of-freedom (6-DoF) robot. Basic VS task experiments show that the proposed controller achieves better performance than the existing methods: the servoing time is 24% smaller than that of the five-dimensional VS method, a 100% success rate with the perturbed ranges of the initial position within 25 mm for translation and 20° for rotation, and a 48% efficiency improvement. Moreover, a planetary gear component assembly process case study, where the robot aims to automatically put the gears on the gear shafts, is conducted to demonstrate the applicability of the proposed method in practice.

Deep Reinforcement Learning Object Tracking Based on Actor-Double Critic Network

Deep Reinforcement Learning Object Tracking Based on Actor-Double Critic Network

Self-Supervised Learning IoT Device Features With Graph Contrastive Neural Network for Device Classification in Social Internet of Things

Device Classification (DC) is one of the critical network management means in the Internet of Things (IoT). Most of machine learning-driven DC methods are implemented in two steps, i.e., extracting device features and then training the classifier. Thus, for the same classifier, the quality of device features plays a decisive role. However, for one thing, these methods usually merely consider device traffic or device attributed features, ignoring the complex relationship between devices in Social IoT. For another thing, these features fed to the classifier are often selected manually without automatic learning. These two factors seriously affect the performance and flexibility of the algorithm. To address the above issues, we propose a novel Graph Contrastive Neural Network-based algorithm for DC dubbed GCNNDC. Specifically, based on the complex relationship between heterogeneous objects in Social IoT and the attribute information of the device itself, we first construct four kinds of homogeneous device-device attributed networks as the input of the neural network. Then, we train a novel GCNN model to learn informative device features in a self-supervised learning fashion. Finally, we leverage the features to train a classifier to complete the DC task. Experimental results on real-world IoT network dataset demonstrate the superiority of GCNNDC.

Coins have both sides: Revealing the structure and pattern of global interdependence network for five critical metals

Evaluating the trade interdependence among countries is the key to understanding critical metal minerals security. By constructing a novel interdependence network, this paper reveals a more comprehensive world hierarchy and risk system of critical metals, and focuses on the interdependencies between China and the US-led MSP countries before and after the Sino-US trade disputes. The results indicate that the global interdependence network of critical metals has declined, with antimony interdependence being the loosest. China and the U.S. are gradually separating into different communities and driving the camp-based world pattern. In addition, the world is increasingly less dependent on China, but China is increasingly dependent on the world. China only remains the world's most indispensable in both lithium and tungsten alone, but it is the most world-dependent country in all four critical metal interdependence networks except tungsten. Meanwhile, China and Western countries such as the U.S. are at high risk of dependence on critical metal chains, while most of the others are gradually getting better. Interestingly, MSP countries and China maintain strong interdependencies. MSP countries' dependencies on China have significantly decreased, While China's dependence on MSP has gradually deepened.

Evaluation and Selection of a Cybersecurity Platform ─ Case of the Power Sector in India

Maintaining interconnected infrastructures such as transportation, communication, power grids, and pipeline networks is paramount in emerging economies. One of the critical interruptions is the targeted attacks on the operating cyber-physical systems to disconnect operations, inspection, or monitoring of the system. Therefore, adopting a cybersecurity system (or platform) that provides holistic protection is vital for protecting the integrity of critical infrastructure networks. As such, this research aspires to provide a decision support system for cybersecurity managers or practitioners (in the Indian power sector) to select the best and appropriate platform for protection against cyber-attacks. A three-phase method is adopted. First, a literature search followed by an expert panel discussion identified alternatives (cybersecurity platforms) and selection criteria. Next, a questionnaire was developed. Thirdly, a hybrid Best-Worst Improved and COmprehensive distance-Based RAnking (BWM-I and COBRA) method was proposed and applied to evaluate the cybersecurity platform alternatives. Four alternatives (Cloud-Based Platforms, Web-Based Platforms, Application-Based Platforms, and AI-Based Platforms), six primary criteria, and fifteen unique sub-criteria were identified. Responses were collected from 80 power utility managers on a pan-India basis, ranking "End-to-End Coverage" criteria and the AI-Based platform as best. This approach identified the best cybersecurity platform that, if adopted, can be extended to other critical infrastructures, with an appropriate adjustment in the selection criteria. The study can be helpful to practitioners in evaluating cybersecurity platforms. Furthermore, it addresses a research gap in its application in a developing country like India.

Characterization of the microRNA408-LACCASE5 module as a regulatory axis for photosynthetic efficiency in Medicago ruthenica: implications for forage yield enhancement

Medicago ruthenica is closely related to Medicago sativa, a commonly cultivated forage. Characterized by its high tolerance to environmental stress, M. ruthenica is a valuable genetic resource. However, low yield limits its large-scale utilization. Leaf morphology, an important agronomic trait, is closely related to forage yield and photosynthetic efficiency. In the presented study, “Correlation of Leaf Morphology and Photosynthetic Performance with Forage Yield in Medicago ruthenica: The Underlying Molecular Mechanisms,” comprehensive data analysis revealed a significant positive association between leaf width and leaf area with forage yield in Medicago ruthenica (p &amp;lt; 0.05). The specific cultivar “Mengnong No.1 (MN No.1) had a large leaf area, and its physiological parameters related to photosynthetic characteristics were superior. Anatomical examination revealed that the leaves of MN No.1 had strong palisade tissue and compact cell structure. Subsequent investigations, utilizing small RNA and transcriptome sequencing, discerned critical miRNA-target gene networks that underpin the high photosynthetic efficiency in M. ruthenica. A total of 63 differentially expressed miRNAs (DEMs) were identified, inclusive of several well-characterized miRNAs such as miR408, miR171, and miR398. These miRNAs were predicted to target 55 genes (mRNAs), of which 6 miRNA-target gene pairs, particularly those involving miR408and miR171, exhibited inverse expression patterns. Among the six postulated miRNA-target gene pairs, the targeted cleavage of LACCASE5 (LAC5) by miR408 was conclusively validated through degradome sequencing, with the cleavage site pinpointed between the 9th and 10th nucleotides from the 5′end of miR408 via the 5′-RLM-RACE assay. Therefore, it is posited that the miR408-MrLAC5 module constitutes a central mechanism in fostering high photosynthetic efficiency in M. ruthenica. Moreover, these findings also provide valuable information for further study of the regulatory genes and miRNA functions of forage yield in legume forage.

Stable approximate Q-learning under discounted cost for data-based adaptive tracking control

In this paper, the stability of tracking error dynamics under the data-based discounted iterative Q-learning is investigated. First, a novel performance index with a discount factor is introduced into the iterative Q-learning-based tracking control. Then, considering the approximation errors caused by the Q-function approximator, the finite error bound between the iterative and optimal Q-functions is established. Moreover, based on the new stability analysis, the selection rule of the discount factor is developed, which ensures that the corresponding optimal control policy is admissible. Next, to ensure the stability of the tracking error dynamics under iterative control policies, the stability condition about the approximate Q-function is established. It is guaranteed that iterative control policies derived from the critic network drive the tracking error to zero. Additionally, considering the adopted policy function approximator, the upper bound function of the approximation errors is developed. It is ensured that the trained action network stabilizes the tracking error dynamics. Finally, a simulation example is utilized to implement the data-based discounted iterative Q-learning and verify the present theoretical results.

Adaptive-Dynamic-Programming-Based Robust Control for a Quadrotor UAV with External Disturbances and Parameter Uncertainties

Thiswork addresses the trajectory-tracking-control problem for a quadrotor unmanned aerial vehicle with external disturbances and parameter uncertainties. A novel adaptive-dynamic-programming-based robust control method is proposed to eliminate the effects of lumped uncertainties (including external disturbances and parameter uncertainties) and to ensure the approximate optimal control performance. Its novelty lies in that two radial basis function neural network observers with fixed-time convergence properties were first established to reconstruct the lumped uncertainties. Notably, they tune only the scalar parameters online and have low computational complexities. Subsequently, two actor–critic neural networks were designed to approximate the optimal cost functions and control policies for the nominal system. In this design, two new actor–critic neural network weight update laws are proposed to eliminate the persistent excitation condition. Then, two adaptive-dynamic-programming-based robust control laws were obtained by integrating the observer reconstruction information and the nominal control policies. The uniformly ultimately bounded stability of the closed-loop tracking control systems was ensured using the Lyapunov methodology. Finally, numerical results are shown to verify the effectiveness and superiority of the proposed control scheme.