Full Feedback Research Articles

Adaptive Active Disturbance Rejection Control for Vehicle Steer-by-Wire under Communication Time Delays

In this paper, an adaptive active disturbance rejection control is newly designed for precise angular steering position tracking of the uncertain and nonlinear SBW system with time delay communications. The proposed adaptive active disturbance rejection control comprises the following two elements: (1) An adaptive extended state observer and (2) an adaptive state error feedback controller. The adaptive extended state observer with adaptive gains is employed for estimating the unmeasured velocity, acceleration, and compound disturbance which consists of system parameter uncertainties, nonlinearities, exterior disturbances, and time delay in which the observer gains are dynamically adjusted based on the estimation error to enhance estimation performances. Based on the accurate estimations of the adaptive extended state observer, the proposed adaptive full state error feedback controller is equipped with variable gains driven by the tracking error to develop control precision. The integration of the advantages of the adaptive extended state observer and the adaptive full state error feedback controller can improve the dynamic transient and static steady-state effectiveness, respectively. To assess the superior performance of the proposed adaptive active disturbance rejection control, a comparative analysis is conducted between the proposed control scheme and the classical active disturbance rejection control in two different cases. It is worth noting that the active disturbance rejection control serves as a benchmark for evaluating the performance of the proposed control approach. The results from the comparison studies executing two simulated cases validate the superiority of the suggested control, in which estimation, tracking response rate, and steering angle precision are greatly improved by the scheme proposed in this article.

The cosmic baryon partition between the IGM and CGM in the SIMBA simulations

ABSTRACT We use the simba suite of cosmological hydrodynamical simulations to investigate the importance of various stellar and active galactic nuclei (AGN) feedback mechanisms in partitioning the cosmic baryons between the intergalactic (IGM) and circumgalactic (CGM) media in the z ≤ 1 Universe. We identify the AGN jets as the most prominent mechanism for the redistribution of baryons between the IGM and CGM. In contrast to the full feedback models, deactivating AGN jets results in ≈20 per cent drop in fraction of baryons residing in the IGM and a consequent increase of CGM baryon fraction by ≈50 per cent. We find that stellar feedback modifies the partition of baryons on a 10 per cent level. We further examine the physical properties of simulated haloes in different mass bins, and their response to various feedback models. On average, a sixfold decrease in the CGM mass fraction due to the inclusion of feedback from AGN jets is detected in $10^{12}\, {\rm M}_{\odot } \le M_{\rm 200} \le 10^{14}\, {\rm M}_{\odot }$ haloes. Examination of the average radial gas density profiles of $M_{200} \gt 10^{12}\, {\rm M}_{\odot }$ haloes reveals up to an order of magnitude decrease in gas densities due to the AGN jet feedback. We compare gas density profiles from simba simulations to the predictions of the modified Navarro–Frenk–White model, and show that the latter provides a reasonable approximation within the virial radii of the full range of halo masses, but only when rescaled by the appropriate mass-dependent CGM fraction of the halo. The relative partitioning of cosmic baryons and, subsequently, the feedback models can be constrained observationally with fast radio bursts in upcoming surveys.

Flight Tracking Control for Helicopter Attitude and Altitude Systems Using Output Feedback Method under Full State Constraints

In this paper, we propose an output feedback flight tracking control scheme for helicopter attitude and altitude systems with unmeasured states under full state constraints. Firstly, a state observer is constructed based on the measured output signals, which is proven to be rigorous since all states are constrained within the desired and assigned scopes. Secondly, the flight tracking controller is built using the state estimations with the full state constraints control method. Then, the Barrier Lyapunov function method is adopted to guarantee the stability of the composite closed-loop nonlinear error systems. Meanwhile, the linear matrix inequality technology is applied to calculate the gains of the state observer. Finally, a numerical simulation example is provided to confirm the reasonableness of the full state constraint output feedback flight tracking control method.

Testing the somatic marker hypothesis in decisions-from-experience with non-stationary outcome probabilities.

The Somatic Marker Hypothesis (SMH) posits that in experience-based choice, people develop physiological reactions that mark options as either positive or negative. These somatic markers aid decision making because they differentiate between "good" and "bad" options during pre-choice deliberation. We examined this proposed role for somatic states in two decision-from-experience tasks (each N = 36) in which participants selected repeatedly with full feedback (i.e., for obtained and forgone outcomes) between two unlabeled options that returned wins or losses, with half receiving an additional summary of past outcomes. The probabilities of good and bad outcomes changed at an unannounced point. Participants completed a 100-trial game with a switch in the optimal option after trial 40 (Study 1) or a 200-trial game with switch points after trial 40 and trial 120 (Study 2). Skin conductance (SC) was measured continuously as an index of emotional intensity, from which we extracted measures of anticipatory SC (pre-choice) and outcome SC (post-choice). Participants reliably selected the optimal option prior to any switches. They also altered their choices appropriately when the payoffs changed, though optimal play following payoff switches was reduced. Losses resulted in a greater outcome SC than wins, but only in Study 1, as did the finding that the outcome SC was greater when the forgone outcome was positive. Anticipatory SC did not reliably predict optimal play in either study. These results provide little support for the SMH. Our studies point to the importance of using diverse tasks and measures and very large sample sizes when testing the role of somatic states in decision making.

Which Information Feedback Approach Is Beneficial to Improve the Supply of Quasi-Public Forestry Infrastructure? An Experimental Economics Approach

Forestry infrastructure plays a critical role in promoting tree growth to achieve carbon-neutral targets. However, as a quasi-public good, it faces challenges because of its non-excludability, meaning that everyone can use it whether they pay for it or not, which results in a phenomenon known as ‘free-riding’ and poor supply. In China, the government can regulate the supply behaviour by adjusting information feedback approaches, such as disclosing the supply value and revenue. This study examined three information feedback approaches: full feedback (disclosing supply and revenue), half feedback (disclosing only supply), and no feedback (no disclosure). It then combined these three information feedback methods with other three groups of variables, namely whether there was a reward or punishment mechanism, whether the return rate of forestry infrastructure was certain, and whether the foresters could communicate with each other, and 20 policy scenarios were designed. Using experimental economics, foresters’ supply behaviours in these policy scenarios were simulated. The results revealed that: (1) The scenario yielded the highest supply, which is with half feedback, certain return rate of forestry infrastructure, with a reward or punishment mechanism, and no communication. (2) When there is no reward or punishment mechanism, no communication, and the return rate of forestry infrastructure is certain, no feedback increases the supply. In the presence of rewards and punishments, half feedback leads to the highest supply. If there are no rewards or punishments but with a certain return rate and communication, full feedback results in the highest supply. (3) Implementing a reward or punishment mechanism and information feedback simultaneously increases the supply more effectively. The theoretical analysis and policy recommendations of this study aim to improve the supply status of forestry infrastructure.

Multi-Action Dialog Policy Learning from Logged User Feedback

Multi-action dialog policy (MADP), which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses. Existing MADP models usually imitate action combinations from the labeled multi-action dialog samples. Due to data limitations, they generalize poorly toward unseen dialog flows. While reinforcement learning-based methods are proposed to incorporate the service ratings from real users and user simulators as external supervision signals, they suffer from sparse and less credible dialog-level rewards. To cope with this problem, we explore to improve MADPL with explicit and implicit turn-level user feedback received for historical predictions (i.e., logged user feedback) that are cost-efficient to collect and faithful to real-world scenarios. The task is challenging since the logged user feedback provides only partial label feedback limited to the particular historical dialog actions predicted by the agent. To fully exploit such feedback information, we propose BanditMatch, which addresses the task from a feedback-enhanced semi-supervised learning perspective with a hybrid learning objective of SSL and bandit learning. BanditMatch integrates pseudo-labeling methods to better explore the action space through constructing full label feedback. Extensive experiments show that our BanditMatch improves MADPL over the state-of-the-art methods by generating more concise and informative responses. The source code and the appendix of this paper can be obtained from https://github.com/ShuoZhangXJTU/BanditMatch.

Learning-Ability of Discrete-Time Iterative Learning Control Systems with Feedforward

This paper considers the learning-ability for discrete-time iterative learning control (ILC) systems with feedforward. More specifically, the relation between the output realizability and the feedforward matrix is first established. Then, the learning-ability of four ILC systems is considered. It is shown that the proportional type (P-type) update law can only ensure the fully asymptotic learning-ability. By only using the feedforward matrix, a more efficient point-wise P-type update law is developed, which can ensure the fully -step learning-ability, where is the trial length. In the case that the state is measurable and controllable, it is proven that the update law with current state feedback can ensure the fully monotone learning-ability and the fully 2-step learning-ability, respectively. In addition, by only using the output data at the previous trial, a full output feedback update law is proposed, which can respectively ensure the fully 2-step learning-ability and the fully monotonic learning-ability.

Full Feedback Dynamic Neural Network with Exogenous Inputs for Dynamic Data‐Driven Modeling in Nonlinear Dynamic Power Systems

AbstractDynamic neural networks (DNNs) are widely used in data‐driven modeling of nonlinear control systems. Due to the complexity of the actual operating nonlinear power systems, rigorous dynamic models are always unknown. DNNs can focus on methods that only use input and output information to establish accurate dynamic models and reduce noise in measured data, which is called data‐driven modeling. The core of the DNN is the feedback with memory function. This paper analyzes the traditional Elman neural network (ENN) and nonlinear auto‐regression with exogenous input (NARX) neural network with different structure feedback structures, and proposes a full feedback dynamic neural network (FF‐DNN) with exogenous input. Eight different kinds of neural networks (including ENN, NARX, etc.) are compared and analyzed. The eight kinds of neural networks are applied on the experimental data of the DC‐AC inverter and the power system of Zhejiang Juchuang Smart Technology Company Park in Wenzhou. The experimental results are used to compare the performance of the data‐driven models established by eight different kinds of neural networks under different noise conditions, verify the robustness and generalization performance of dynamic data‐driven modeling based on FF‐DNN, and demonstrate the feasibility and effectiveness of FF‐DNN in actual power systems. © 2023 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Research on gas wave refrigeration application of full feedback periodic jet oscillator

Static gas wave refrigeration (SGWR) is a mechanic equipment with no moving parts which realize refrigeration by working on gas through pressure energy. This paper introduces full feedback jet oscillator as the jet distributor of the gas wave refrigerator and shows the switching mechanism of the oscillator in detail through dynamics description. The range of influence of wedge distance (distance between wedge tip and the nozzle) on the pressure retention rate and frequency at the oscillator outlet is discussed, and a SGWR experiment platform is set up to make comparison of the pressure waveform as well as cooling efficiency of the impulse jet from two oscillators with different wedge distance in the gas wave tube. The result shows that jet oscillator performance varies along with the wedge distance, thus influencing the cooling efficiency. To expand the efficient operation range, the principle of jet frequency changing and the impact of narrowing the oscillator structure on jet frequency are discussed in detail, the variation rule equation of the jet switching frequency is derived. Matching experiments of jet oscillator and size of gas wave tube have been conducted under conditions of specific frequency and variable frequency. It is concluded that there exists fluctuation value in gas wave tube refrigeration efficiency versus gas injection frequency curve, which can be up to 15% or more. Based on the present results, the jet frequency control method can make the gas wave tube operate at the refrigeration's peak frequency, thus improving SGWR refrigeration efficiency.

Design and Validation of a Low-Level Controller for Hierarchically Controlled Exoskeletons.

In this work, a generalized low-level controller is presented for sensor collection, motor input, and networking with a high-level controller. In hierarchically controlled exoskeletal systems, which utilize series elastic actuators (SEAs), the hardware for sensor collection and motor command is separated from the computationally expensive high-level controller algorithm. The low-level controller is a hardware device that must collect sensor feedback, condition and filter the measurements, send actuator inputs, and network with the high-level controller at a real-time rate. This research outlines the hardware of two printed circuit board (PCB) designs for collecting and conditioning sensor feedback from two SEA subsystems and an inertial measurement unit (IMU). The SEAs have a joint and motor encoder, motor current, and force sensor feedback that can be measured using the proposed generalized low-level controller presented in this work. In addition, the high and low-level networking approach is discussed in detail, with a full breakdown of the data storage within a communication frame during the run-time operation. The challenges of device synchronization and updates rates of high and low-level controllers are also discussed. Further, the low-level controller was validated using a pendulum test bed, complete with full sensor feedback, including IMU results for two open-loop scenarios. Moreover, this work can be extended to other hierarchically controlled robotic systems that utilize SEA subsystems, such as humanoid robots, assistive rehabilitation robots, training simulators, and robotic-assisted surgical devices. The hardware and software designs presented in this work are available open source to enable researchers with a direct solution for data acquisition and the control of low-level devices in a robotic system.

Good-bye to determinism: the circle of innovation

An argument, lasting from the 19th century through the present day, has to do with whether social changes create technological innovation ('technological determinism') or vice versa ('social determinism'). Advocates of either argued that both could not be true. Modern interactive information technology allows us to see that neither view is fully correct, and that in fact there is full circular feedback from social and organisational effects to technological innovation and back again. This paper offers instances of the Circle of Innovation. It analyses and attempts to resolve the nuances of both determinist positions. It ties a third determinist tradition, linguistic determinism, to technology management practice. Implications of this theoretical discussion for research, for public policy, and for business include the need for renewed dialogue between economics and sociology; the need for a new embrace of nonlinear analysis; and the potential for greater profits from new looks at technology assessment and market segmentation.

Adaptive training‐feedback scheme for FDD in massive MIMO systems

AbstractAccurate acquisition of channel state information (CSI) is crucial but difficult in frequency division duplex (FDD) massive multiple‐input multiple‐output (MIMO) systems. To improve the estimation accuracy and to minimize the training consumption, an adaptive training‐feedback scheme based on spatial reciprocity in FDD is proposed. The main idea of this scheme is to construct a reference frame that matches the channel structure. Reference vectors with the strongest correlation with the uplink channel are selected to design the pilots. The pilots can adapt to channel changes in this proposed scheme, which lead to substantial reduction of the training and feedback overheads. The simulation results show that under full feedback, the throughput of proposed adaptive training‐feedback scheme can approach to the optimal performance, and under finite‐bit feedback, the channel utilization is also significantly high with less training.

Modeling and Nonlinear Control of dc–dc Converters for Microgrid Applications

This paper proposes a high-performance control strategy for dc–dc converters supplying combined loads (constant current/power, and/or linear loads). This strategy combines a feedback law with a feedforward compensation. The feedback law is based on full feedback linearization, which guarantees that zero dynamics are avoided. To design a single controller for the three basic converter topologies (i.e., buck, boost and buck–boost), a unified model for these converters is introduced. From the resulting combined control law, the specific control law for each type of converter can be obtained by setting three constant coefficient to 0 or 1. The feedforward compensation is based on the estimated values of the load obtained via a nonlinear observer. The main advantage of this unified approach is that it is implemented by using a single algorithm which can be executed in a dedicated hardware, for instance, a single integrated circuit, providing a unified solution for the control of the mentioned topologies. The good performance of the proposed scheme is verified through simulations and tested via experimental application cases, concluding that this is a good unified solution to control dc–dc converters used in microgrid applications.

The rhizosphere microbiome and host plant glucosinolates exhibit feedback cycles in Brassica rapa.

The rhizosphere microbiome influences many aspects of plant fitness, including production of secondary compounds and defence against insect herbivores. Plants also modulate the composition of the microbial community in the rhizosphere via secretion of root exudates. We tested both the effect of the rhizosphere microbiome on plant traits, and host plant effects on rhizosphere microbes using recombinant inbred lines (RILs) of Brassica rapa that differ in production of glucosinolates (GLS), secondary metabolites that contribute to defence against insect herbivores. First, we investigated the effect of genetic variation in GLS production on the composition of the rhizosphere microbiome. Using a Bayesian Dirichlet-multinomial regression model (DMBVS), we identified both negative and positive associations between bacteria from six genera and the concentration of five GLS compounds produced in plant roots. Additionally, we tested the effects of microbial inoculation (an intact vs. disrupted soil microbiome) on GLS production and insect damage in these RILs. We found a significant microbial treatment × genotype interaction, in which total GLS was higher in the intact relative to the disrupted microbiome treatment in some RILs. However, despite differences in GLS production between microbial treatments, we observed no difference in insect damage between treatments. Together, these results provide evidence for a full feedback cycle of plant-microbe interactions mediated by GLS; that is, GLS compounds produced by the host plant "feed-down" to influence rhizosphere microbial community and rhizosphere microbes "feed-up" to influence GLS production.

Establishment of a medical device adverse event management system for hospitals

BackgroundThe management of medical device adverse event (MDAE) is one of the most important aspects of improving medical quality and safety management. Nonetheless, hospitals still lack standardized and unified initiatives to improve MDAE management.MethodsThis study, thus, established a MDAE monitoring system on May 1 in 2011 for suspected adverse events and designed a hospital-based dynamic warning system, aiming to standardize the process of MDAE handling and provide real-time monitoring for MDAEs in a hospital. This system was used in the First Affiliated Hospital of Zhejiang University School of Medicine. Numbers and the compound growth rate of MDAE reports from 2010 to 2020 were compared to test the effectiveness of the MDAE monitoring system. Numbers of MDAE reported to the National Adverse Event Monitoring System were also compared over 2013 to 2020, due to the loss of data before 2013 after shutdown of the old system. Efficacy and usability of the hospital-based dynamic warning system was then verified by analyzing risk and warning levels of MDAEs in 2020. Descriptive statistics was used for data analysis in this study.ResultsResults showed that the compound annual growth rates of MDAE reports and those submitted to the National Adverse Event Monitoring System from 2013 to 2020 were 35.0% and 31.5%, respectively. A standardized management of MDAE with full participant, timely response and effective feedback was formed in the hospital by establishment of the MDAE system.ConclusionsThis system effectively improved the monitoring level of MDAEs, helping to improve early detection, early warning, and early intervention of risk of medical device. This study may provide suggestions for medical institutions to establish a MDAE monitoring system, and may promote development of medical quality and safety management for hospitals to some extent.

Regret minimization in online Bayesian persuasion: Handling adversarial receiver's types under full and partial feedback models

In Bayesian persuasion, an informed sender has to design a signaling scheme that discloses the right amount of information so as to influence the behavior of a self-interested receiver. This kind of strategic interaction is ubiquitous in real-world economic scenarios. However, the seminal model by Kamenica and Gentzkow makes some stringent assumptions that limit its applicability in practice. One of the most limiting assumptions is, arguably, that the sender is required to know the receiver's utility function to compute an optimal signaling scheme. We relax this assumption through an online learning framework in which the sender repeatedly faces a receiver whose type is unknown and chosen adversarially at each round from a finite set of possible types. We are interested in no-regret algorithms prescribing a signaling scheme at each round of the repeated interaction with performances close to that of a best-in-hindsight signaling scheme. First, we prove a hardness result on the per-round running time required to achieve no-α-regret for any α<1. Then, we provide algorithms for the full and partial feedback models with regret bounds sublinear in the number of rounds and polynomial in the size of the instance. Finally, we show that, by relaxing the persuasiveness constraints on signaling schemes, it is possible to design an algorithm with a better running time and small regret.

Sequential Transmission Over Binary Asymmetric Channels With Feedback

In this paper, we consider variable-length coding over the memoryless binary asymmetric channel (BAC) with full noiseless feedback, including the binary symmetric channel (BSC) as a special case. In 2012, Naghshvar et al. introduced a coding scheme, which we refer to as the small-enough-difference (SED) coding scheme. For symmetric binary-input channels, the deterministic variable-length feedback (VLF) code constructed with the SED coding scheme asymptotically achieves both capacity and Burnashev’s optimal error exponent. Building on the work of Naghshvar et al., this paper extends the SED coding scheme to the BAC and develops a non-asymptotic VLF achievability bound that is shown to achieve both capacity and the optimal error exponent. For the specific case of the BSC, we develop an additional non-asymptotic VLF achievability bound using a two-phase analysis that leverages both a submartingale synthesis and a Markov chain time of first passage analysis. Numerical evaluations show that both new VLF achievability bounds outperform Polyanskiy’s achievability bound for variable-length stop-feedback codes.

Ефективність системи трисотової мережі для граничних користувачів з використанням попереднього кодування, регулювання завади і зворотним зв’язком квантованого обмеженого каналу

Користувачі на загальній границі багатокористувацької трисотової MIMO системи з низхідною лінією зв’язку страждають від низької потужності сигналу у власній соті, а також від сигналу завад рівної потужності від сусідніх двох сот. В даному випадку для покращення загальної роботи системи застосовуються схеми придушення завад. Крім того, повний CSI зворотний зв’язок від користувачів до базової станції сильно навантажує канал зворотного зв’язку. Зворотний зв’язок інформаційного квантованого редукованого каналу може зменшити навантаження майже наполовину на зворотний канал від користувача до передавача, та підвищити швидкість передачі даних системи. Методи попереднього кодування на основі кодової книги LTE покращують сумарну швидкість. Розроблено метод попереднього кодування з використанням сингулярного розкладання SVD (singular value decomposition) на вибраних кодових векторах на основі максимізації вектору еквівалентного коду каналу SVD-ECC (SVD Equivalent Channel-Code) і максимізації вектору SINR-коду SVD-SINRC (SVD SINR-Code). Обидва методи забезпечують вищу сумарну швидкість передачі даних системи в порівнянні з методом попереднього кодування на основі ZF (zero forcing), причому швидкість більша для SVD-ECC, ніж для SVD-SINRC. Також проведено дослідження для користувачів з ортогональними еквівалентними каналами та подальшим SVD на вибраному каналі користувача SVD-ORT (SVD orthogonal). Отримано результати зі зміною SNR користувача, кількості вибраних користувачів K і загальної кількості активних користувачів L у соті.

Online transfer learning with partial feedback

Online learning for multi-class classification is a well-studied topic in machine learning. The standard multi-class classification online learning setting assumes continuous availability of the ground-truth class labels. However, in many real-life applications, only partial feedback of the predicted label can be obtained and only the correctness of the prediction is available. Hence, knowledge of the correct label is missing in the case of erroneous predictions. In this case, learning may be slower and classifiers less accurate than in the full feedback scenario. Although several online learning algorithms with partial feedback have been proposed, real-world applications would still benefit from further performance improvement. In this paper, we exploit transfer learning to improve learning in the case of erroneous predictions. We propose the Partial Feedback Online Transfer Learning (PFOTL) algorithm, which uses learned knowledge from the source domain in addition to received partial feedback, and present analysis and a mistake bound for the algorithm. In our experimental results on four benchmark datasets, the proposed algorithm achieves higher online cumulative accuracy than the comparable state-of-the-art algorithms. Two potential applications of our work would be online recommender systems and privacy protection.

Toward Large-Scale Hybrid Edge Server Provision: An Online Mean Field Learning Approach

The efficiency of a large-scale edge computing system primarily depends on three aspects: i) edge server provision, ii) task migration, and iii) computing resource configuration. In this paper, we study the dynamic resource configuration for hybrid edge server provision under two decentralized task migration schemes. We formulate the dynamic resource configuration as an online cost minimization problem, aiming to jointly minimize performance degradation and operation expenditure. Due to the stochastic nature, it is an online learning problem with partial feedback. To address it, we derive a deterministic mean field model to approximate the stochastic edge computing system. We show that the mean field model provides the increasingly accurate full feedback as the system scales. We then propose a learning policy based on the mean field model, and show that our proposed policy performs asymptotically as well as the offline optimal configuration. We provide two ways of setting the policy parameters, which achieve a constant competitive ratio (under certain mild conditions) and a sub-linear regret, respectively. Numerical results show that the mean field model significantly improves the convergence speed. Moreover, our proposed policy under the decentralized task migration schemes considerably reduces the operating cost (by 23%) and incurs little communication overhead.