Adaptive Constraint Research Articles

SAR Target Detection Based on Domain Adaptive Faster R-CNN with Small Training Data Size

It is expensive and time-consuming to obtain a large number of labeled synthetic aperture radar (SAR) images. In the task of small training data size, the results of target detection on SAR images using deep network approaches are usually not ideal. In this study, considering that optical remote sensing images are much easier to be labeled than SAR images, we assume to have a large number of labeled optical remote sensing images and a small number of labeled SAR images with the similar scenes, propose to transfer knowledge from optical remote sensing images to SAR images, and develop a domain adaptive Faster R-CNN for SAR target detection with small training data size. In the proposed method, in order to make full use of the label information and realize more accurate domain adaptation knowledge transfer, an instance level domain adaptation constraint is used rather than feature level domain adaptation constraint. Specifically, generative adversarial network (GAN) constraint is applied as the domain adaptation constraint in the adaptation module after the proposals of Faster R-CNN to achieve instance level domain adaptation and learn the transferable features. The experimental results on the measured SAR image dataset show that the proposed method has higher detection accuracy in the task of SAR target detection with small training data size than the traditional Faster R-CNN.

Improving water markets in Spain: Lesson-drawing from the Murray-Darling Basin in Australia

The transfer of successful water market governance between international settings is increasingly attractive to policy makers under globalization. This paper tests lesson-drawing approaches to water market governance transfers using data from Spain and the Murray-Darling Basin, Australia. Spain is the blueprint country for water market adoption in Europe, while Australia is often presented as a world leader in innovative water market arrangements. A preliminary comparative analysis framework linking water market governance principles to observed institutional arrangements and outcomes is provided. Finally, some key lessons, problems and policy transfer potential to stimulate and enhance Spanish water markets from lesson-drawing approaches are drawn, with an emphasis on adaptive capacity as an institutional performance metric. We find that Spain’s current water governance institutions and arrangements offer a solid platform for marketing reform, where some key adaptive capacity constraints are able to be addressed. The lessons drawn from this study highlight those areas of change which, while challenging, can be achieved in our view.

Hierarchical speed control for autonomous electric vehicle through deep reinforcement learning and robust control

For the speed control system of autonomous electric vehicle (AEV), challenge happens with how to determine an appropriate driving speed to satisfy the dynamic environment while resisting uncertainty and disturbance. Therefore, this paper proposes a robust optimal speed control approach based on hierarchical architecture for AEV through combining deep reinforcement learning (DRL) and robust control. In decision-making layer, a deep maximum entropy proximal policy optimization (DMEPPO) algorithm is presented to obtain an optimal speed via dynamic environment information, heuristic target entropy and adaptive entropy constraint. In motion control layer, to track the learned optimal speed while resisting uncertainty and disturbance, a robust speed controller is designed by the linear matrix inequality (LMI). Finally, simulation experiment results show that the proposed robust optimal speed control scheme based on hierarchical architecture for AEV is feasible and effective.

Adaptive livelihood strategies among small-scale fishing households to climate change-related stressors in Central Coast Vietnam

PurposeThis paper aims to examine adaptive livelihood strategies used by small-scale fishing households in the two coastal communities in Central Vietnam under the context of climate change-related stressors.Design/methodology/approachField data were collected through mixed quantitative and qualitative methods including a review of secondary data, key-informant interviews, group discussions and household surveys with 300 sampled fishing households. The qualitative data support the analysis and discussion of quantitative data.FindingsThe results showed local households’ perception of the presence and influence of multiple non-climate and climate stressors on their fishery-based livelihoods in terms of employment and income in many ways. The affected households exerted to develop a diversity of adaptation methods within and out of fishing to sustain their livelihoods and cover a deficit in household income. The household socio-demographic characteristics particularly education, labour force, fishing equipment and social support played significant importance in characterising the categories of adaptation strategies among the survey households. The role of local governments in creating an enabling environment for local-level adaptation, as well as protecting marine and coastal ecosystems was rather limited despite their recognized importance.Originality/valueThe paper provides an empirical case of how small-scale fishing households in coastal communities in Central Vietnam are adapting to climate-related stressors. It suggests policy should promote livelihood diversification opportunities and address household-level constraints for adaptation. Fisheries management plan is urgently needed to control illegal fishing activities for sustainable use of coastal and marine fishery resources and the appropriate mechanism is important to stretch local governments’ resources for better supporting local-level adaptation.

Performance‐based optimal control for stochastic nonlinear systems with unknown dead‐zone

AbstractThis article studies the problem of performance‐guaranteed adaptive fuzzy optimal compensator control for stochastic affine nonlinear systems with dead‐zone and unknown nonlinear dynamics. First, by using the error transformation techniques, the original system is transformed into an equivalent unconstraint system. Then, a feedforward fuzzy compensator is constructed to offset the influence raised by unknown dead‐zone. By designing identifier‐critic‐actor construction reinforcement learning, an adaptive fuzzy optimal performance constraint compensate control algorithm is presented. The developed control scheme can ensure that all signals of the controlled system are uniformly ultimately bounded, and the output can track the reference signal with a prescribed accuracy. Finally, simulation results are given to illustrate the effectiveness of the developed control algorithm and theorem.

Fuzzy adaptive event-triggered finite-time constraint control for output-feedback uncertain nonlinear systems

A fuzzy adaptive event-triggered finite-time constraint control for the uncertain nonlinear system with input hysteresis is developed. Input hysteresis, uncertain and nonlinear characteristic, widely existing in the actual control system, which seriously affect the performance and convergence time of control system. Thus, a fuzzy adaptive event-triggered control method is constructed to overcome the above issues under the limited communication recourses. Furthermore, to ensure the system converges in finite time, an event-triggered finite-time control method is proposed where the communication resources are limited. Finally, some simulation experiments verify the system converges in finite time and the bandwidth resources can be effectively saved under the proposed method.

Real-Time Cloth Simulation Using Compute Shader in Unity3D for AR/VR Contents

While the cloth component in Unity engine has been used to represent the 3D cloth object for augmented reality (AR) and virtual reality (VR), it has several limitations in term of resolution and performance. The purpose of our research is to develop a stable cloth simulation based on a parallel algorithm. The method of a mass–spring system is applied to real-time cloth simulation with three types of springs. However, cloth simulation using the mass–spring system requires a small integration time-step to use a large stiffness coefficient. Furthermore, constraint enforcement is applied to obtain the stable behavior of the cloth model. To reduce the computational burden of constraint enforcement, the adaptive constraint activation and deactivation (ACAD) technique that includes the mass–spring system and constraint enforcement method is applied to prevent excessive elongation of the cloth. The proposed algorithm utilizes the graphics processing unit (GPU) parallel processing, and implements it in Compute Shader that executes in different pipelines to the rendering pipeline. In this paper, we investigate the performance and compare the behavior of the mass–spring system, constraint enforcement, and ACAD techniques using a GPU-based parallel method.

Two-layer structure strategy for large-scale systems integrating online adaptive constraints adjustment method and cooperative distributed DMC algorithm

In this paper, a distributed two-layer structure strategy for large-scale systems is described. In the upper level of the structure, usually known as the Steady State Target Optimizer (SSTO) layer, we fully consider the possible constraints in the industrial process as well as their priority order and put forward an online adaptive constraints adjustment (OACA) scheme to ensure the stable operation of the production device. Based on Pareto optimal, a new cooperative distributed dynamic matrix control (CDDMC) algorithm is proposed for the lower MPC layer. The algorithm makes use of the finite step response model and Dynamic Matrix Control (DMC) method which are commonly applied in the process industry, decomposes the large-scale system into multiple interconnected subsystems for a significantly reduced computational burden, and works over a cooperative way based on Jacobi-type iteration to achieve the global optimal solution. Then the convergence of the CDDMC algorithm is investigated and the offset-free control of the strategy is discussed. Finally, the two-layer structure distributed strategy is applied to two examples to analyze its applicability and effectiveness in comparison with the centralized one.

Observer-Based Adaptive Neural Output Feedback Constraint Controller Design for Switched Systems Under Average Dwell Time

Aiming at a class of switched uncertain nonlinear strict-feedback systems under the action of average dwell time switching signal, this paper proposes a novel adaptive neural network output feedback tracking control based on the consideration of the full state constraints. The controller is proposed based on neural networks. One of the key characteristics of the system discussed is that the state variables cannot be measured and the system states need to be kept within the constraint ranges. For the sake of estimating the unmeasured states, the observer is constructed. In order to ensure all states which are within the time-varying boundary, the tangent barrier Lyapunov function (BLF-Tan) is selected in the design process. The boundedness of the closed-loop signals with average dwell time is guaranteed by the designed controllers and all the states limit in their constrained sets. It has been proved that the output tracking error converge to a small neighborhood of zero. In addition, the significance of the presented control strategy is verified and tested by a simulation example.

Multi-Agent Planning with Mixed-Integer Programming and Adaptive Interaction Constraint Generation (Extended Abstract)

We consider multi-agent planning in which the agents' optimal plans are solutions to mixed-integer programs (MIP) that are coupled via integer constraints. While in principle, one could find the joint solution by combining the separate problems into one large joint centralized MIP, this approach rapidly becomes intractable for growing numbers of agents and large problem domains. To address this issue, we propose an iterative approach that combines conflict detection with constraint-generation whereby the agents plan repeatedly until all conflicts are resolved. In each planning iteration, the agents plan with as few other agents and interaction-constraints as possible. This yields an optimal method that can reduce computation markedly. We test our approach in the context of multi-agent collision avoidance in graphs with indivisible flows. Our initial simulations on randomized graph routing problems confirm predicted optimality and reduced computational effort.

Adaptive graph guided concept factorization on Grassmann manifold

Motivated by applications in clustering and optimization, there has been significant interest in the variant for which the database models are high-dimensional data (such as imagesets or videos). Matrix factorization approaches, particularly Nonnegative Matrix Factorization (NMF) have achieved favorable results for data clustering tasks. However, these methods suffer from two major drawbacks. First, matrix factorization approaches only partially explore the inter- or intra- relationships between vector-valued data and are unable to handle high-dimensional data. Second, the clustering results largely rely on the predefined similarity matrix, which usually contain large amounts of noise. In this paper, we propose a novel Adaptive Graph Guided Concept Factorization model on Grassmann manifold (AG3CF) for imageset clustering in an unsupervised fashion, which imposes concept factorization over the space of linear subspaces. To further explore the structure of data and assign ideal neighbors, an adaptive graph regularization constraint is designed to automatically capture the local relationships of data samples and integrated well into concept factorization framework. An efficient algorithm is also derived to tackle the resulting optimization problem. Experimental results on several public datasets validate that the proposed approach achieves competitive performance in high-dimensional data clustering.

Estimation and computations for Gaussian mixtures with uniform noise under separation constraints

In this paper we study a finite Gaussian mixture model with an additional uniform component that has the role to catch points in the tails of the data distribution. An adaptive constraint enforces a certain level of separation between the Gaussian mixture components and the uniform component representing noise and outliers in the tail of the distribution. The latter makes the proposed tool particularly useful for robust estimation and outlier identification. A constrained ML estimator is introduced for which existence and consistency is shown. One of the attractive features of the methodology is that the noise level is estimated from data. We also develop an EM-type algorithm with proven convergence. Based on numerical evidence we show how the methods developed in this paper are useful for several fundamental data analysis tasks: outlier identification, robust location-scale estimation, clustering, and density estimation.

Adaptive Finite-Time Fault-Tolerant Control for Half-Vehicle Active Suspension Systems with Output Constraints and Random Actuator Failures

The problem of adaptive finite-time fault-tolerant control (FTC) and output constraints for a class of uncertain nonlinear half-vehicle active suspension systems (ASSs) are investigated in this work. Markovian variables are used to denote in terms of different random actuators failures. In adaptive backstepping design procedure, barrier Lyapunov functions (BLFs) are adopted to constrain vertical motion and pitch motion to suppress the vibrations. Unknown functions and coefficients are approximated by the neural network (NN). Assisted by the stochastic practical finite-time theory and FTC theory, the proposed controller can ensure systems achieve stability in a finite time. Meanwhile, displacement and pitch angle in systems would not violate their maximum values, which imply both ride comfort and safety have been enhanced. In addition, all the signals in the closed-loop systems can be guaranteed to be semiglobal finite-time stable in probability (SGFSP). The simulation results illustrate the validity of the established scheme.

There Once Was a Really Bad Poet, It Was Automated but You Didn’t Know It

Abstract Limerick generation exemplifies some of the most difficult challenges faced in poetry generation, as the poems must tell a story in only five lines, with constraints on rhyme, stress, and meter. To address these challenges, we introduce LimGen, a novel and fully automated system for limerick generation that outperforms state-of-the-art neural network-based poetry models, as well as prior rule-based poetry models. LimGen consists of three important pieces: the Adaptive Multi-Templated Constraint algorithm that constrains our search to the space of realistic poems, the Multi-Templated Beam Search algorithm which searches efficiently through the space, and the probabilistic Storyline algorithm that provides coherent storylines related to a user-provided prompt word. The resulting limericks satisfy poetic constraints and have thematically coherent storylines, which are sometimes even funny (when we are lucky).

Adversarial training regularization for negative sampling based network embedding

The aim of network embedding is to learn compact node representations. This has been shown to be effective in various downstream learning tasks, such as link prediction and node classification. Most methods focus on preserving different network structures and properties, ignoring the fact that networks are usually noisy and incomplete, thus such methods potentially lack robustness and suffer from the overfitting issue. Recently, generative adversarial networks based methods have been exploited to impose a prior distribution on node embeddings to encourage a global smoothness, but their model architecture is very complicated and they suffer from the non-convergence problem. Here, we propose adversarial training (AdvT), a more succinct and effective local regularization method, for negative-sampling-based network embedding to improve model robustness and generalization ability. Specifically, we first define the adversarial perturbations in the embedding space instead of in the discrete graph domain to circumvent the challenge of generating discrete adversarial examples. Then, to enable more effective regularization, we design the adaptive l2 norm constraints on adversarial perturbations that depend upon the connectivity pattern of node pairs. We integrate AdvT into several famous models including DeepWalk, LINE and node2vec, and conduct extensive experiments on benchmark datasets to verify its effectiveness.

Smallholder Farmers’ Perceptions, Adaptation Constraints, and Determinants of Adaptive Capacity to Climate Change in Chengdu

This study assessed smallholder farmers’ perceptions, adaptation constraints, and determinants of adaptive capacity to climate change. The study used severity and problem confrontation index estimations to examine the farmers’ perceptions of climate warming and barriers to climate adaptation. The results indicated that the farmers were cognizant of climate change and its adverse impacts on their livelihood. It was evident that most surveyed rice farmers perceived changes in climatic conditions to affect rice production adversely. The farmers claimed that unpredictable weather conditions, limited farm size, inadequate farm labor, scarce water resources, high cost of farm inputs, and insufficient information on weather conditions had impeded their adoption of climate change adaptive strategies. Based on the results of the principal component analysis, economic resources, physical resources, information, human resources, and technology significantly influence smallholder farmers’ responsive ability to climate warming. Therefore, policymakers must design policy frameworks and measures that consider these significant factors explaining farmers’ constraints to climate change adaptation.

Multipath extraction and mitigation for static relative positioning based on adaptive layer wavelet packets, bootstrapped searches and CNR constraints

Multipath extraction and mitigation for static relative positioning based on adaptive layer wavelet packets, bootstrapped searches and CNR constraints

Adaptive constraint differential evolution for optimal power flow

The optimal power flow (OPF) problem featured as a non-linear, non-convex, large-scale and constrained, still remains a popular and challenging work in power systems optimization. Although various optimization algorithms have been devoted to solving this problem, they suffer from some weak points such as insufficient accuracy as well as most of them are unconstrained optimization algorithms that result in optimal solutions that violate certain security operational constraints. To this end, this paper presents an adaptive constraint differential evolution (ACDE) algorithm, in which the novelty lies primarily in these three points: i) the crossover rate (CR) sorting mechanism is employed to build the relationship of CR and individual fitness values; ii) reusing successful evolution direction is proposed to guide the individual evolution towards promising regions; iii) an advanced constraint handling technique named superiority of feasible solutions (SF) is introduced to effectively deal with constraints in power systems. In order to verify the performance of the presented approach to the OPF problem, the standard IEEE-30 bus system is selected as the test case, in which six optimization objectives including total fuel cost, total fuel cost considering the valve-point effect, real active power losses, voltage deviation, voltage stability and emission are studied. The experimental results demonstrate that the presented approach can provide the smaller cost (800.41132$/h), reducing by up to 3.76% compared to the MPIO-COSR. In terms of the emission, ACDE emits the least emissions (0.204817ton/h). In addition, the proposed method also obtains the best results on the real active power losses (3.084041 MW) and voltage deviation (0.085636p.u.) when compared with other state-of-the-art methods.

Revisiting the drivers of acoustic similarities in tropical anuran assemblages.

Acoustic signaling is key in mediating mate choice, which directly impacts individual fitness. Because background noise and habitat structure can impair signal transmission, the acoustic space of mixed-species assemblages has long been hypothesized to reflect selective pressures against signal interference and degradation. However, other potential drivers that received far less attention can drive similar outputs on the acoustic space. Phylogenetic niche conservatism and allometric constraints may also modulate species acoustic features, and the acoustic space of communities could be a side-effect of ecological assembly processes involving other traits (e.g., environmental filtering). Additionally, the acoustic space can also reflect the sorting of species relying on public information through extended communication networks. Using an integrative approach, we revisit the potential drivers of the acoustic space by addressing the distribution of acoustic traits, body size, and phylogenetic relatedness in tropical anuran assemblages across gradients of environmental heterogeneity in the Pantanal wetlands. We found the overall acoustic space to be aggregated compared with null expectations, even when accounting for confounding effects of body size. Across assemblages, acoustic and phylogenetic differences were positively related, while acoustic and body size similarities were negatively related, although to a minor extent. We suggest that acoustic partitioning, acoustic adaptation, and allometric constraints play a minor role in shaping the acoustic output of tropical anuran assemblages and that phylogenetic niche conservatism and public information use would influence between-assemblage variation. Our findings highlight an overlooked multivariate nature of the acoustic dimension and underscore the importance of including the ecological context of communities to understand drivers of the acoustic space.

A hybrid sequential approach for solving environmentally constrained optimal scheduling in co-generation systems

The ever-growing trend of electricity demand and environmental concerns have mandated the operation of electrical energy grids in a more economical and environmentally friendly manner. In the past few years, the integration of combined heat and power units has offered a promising solution to these concerns, however, at the same time a new challenging problem has revealed itself that is finding a simultaneous optimal solution between two competing criteria of power and heat. Furthermore, this problem will be more complex when the reduction of emission gasses is taken into consideration. Thus, to solve optimal scheduling of combined heat and power units, this study proposes an intelligent sequential algorithm based on the hybridization of teaching and learning-based optimization algorithm and an improved version of particle swarm optimization. The proposed algorithm is uniquely capable of the concurrent minimization of total generation costs and multi-pollutant gasses while several physical, operational, and environmental constraints are considered. Also, to ensure the safe maintenance of systems’ constraints, this study employs an adaptive violation constraint handling technique in conjunction with the proposed hybridized optimization algorithm. Finally, the performance of the proposed algorithm is compared to the recently developed methods, in which the proposed algorithm of the study outperforms all the other algorithms and achieves up to 2.2% lower overall costs of operation in most of the studied cases.