Global Constraints Research Articles

Toward Space-Time WaveFunctionCollapse for Level and Solution Generation

WaveFunctionCollapse (WFC) is a constraint-satisfaction-based approach to procedural content generation via machine learning (PCGML). It is relatively easy to implement and requires very little training data, making it a popular approach. Generated game levels are guaranteed to look locally similar totheir example tilemaps; however, local adjacency rules often fail to capture global solvability rules, potentially making many such levels unplayable. Existing approaches to improving the solvability of WFC-generated levels typically require adding additional game-specific information in the form of global constraints, substantially increasing the complexity and time required for setup. The purpose of this work is to explore whether using level solutions as training data can allow WFC to learn solvability constraints and game mechanics. We have implemented a novel space-time approach that uses three-dimensional space-time blocks representing solutions to 2D levels as both input and output. Experiments using this method show that space-time WFC is capable of demonstrating localized game mechanics and creating small playable levels with given solutions. However, levels are slow to generate, and some high-level constraints are still not captured.

LiDAR-Inertial SLAM with DEM-driven Global Constraints for Planetary Rover Exploration

LiDAR-Inertial SLAM with DEM-driven Global Constraints for Planetary Rover Exploration

Coordinating multi-agent reinforcement learning via dual collaborative constraints

Many real-world multi-agent tasks exhibit a nearly decomposable structure, where interactions among agents within the same interaction set are strong while interactions between different sets are relatively weak. Efficiently modeling the nearly decomposable structure and leveraging it to coordinate agents can enhance the learning efficiency of multi-agent reinforcement learning algorithms for cooperative tasks, while existing works typically fail. To overcome this limitation, this paper proposes a novel algorithm named Dual Collaborative Constraints (DCC) that identifies the interaction sets as subtasks and achieves both intra-subtask and inter-subtask coordination. Specifically, DCC employs a bi-level structure to periodically distribute agents into multiple subtasks, and proposes both local and global collaborative constraints based on mutual information to facilitate both intra-subtask and inter-subtask coordination among agents. These two constraints ensure that agents within the same subtask reach a consensus on their local action selections and all of them select superior joint actions that maximize the overall task performance. Experimentally, we evaluate DCC on various cooperative multi-agent tasks, and its superior performance against multiple state-of-the-art baselines demonstrates its effectiveness.

A Novel Fusion of Machine Learning Methods for Enhancing Named Entity Recognition in Indonesian Language Text

One of the important implementations in machine learning is Named Entity Recognition (NER), which is used to process text and extract entities such as people, organizations, laws, religions, and locations. NER for the Indonesian language still faces significant challenges due to the lack of high-quality labelled datasets, which limits the development of more advanced models. To address this issue, we utilized several pre-trained BERT models (bert-base-uncased, indobenchmark/indobert-base-p1, indolem/indobert-base-uncased) and datasets (NERGRIT-IndoNLU, NERGRIT-Corpus, NERUGM, and NERUI). This study proposes a novel fusion approach by integrating deep learning architectures such as CNN, Bi-LSTM, Bi-GRU, and CRF to detect 19 entities. This approach enhances BERT’s sequence modelling and feature extraction capabilities, while CRF improves entity prediction by enforcing global word-sequence constraints. Experimental results demonstrate that the fusion approach outperforms previous methods. On the bert-base-uncased dataset, accuracy reached 94.75%, while indobenchmark/indobert-base-p1 achieved 95.75%, and indolem/indobert-base-uncased achieved 95.85%. This study emphasizes the effectiveness of combining deep learning architectures with pre-trained transformers to improve NER performance in the Indonesian language. The proposed methodology offers significant advancements in entity extraction for languages with limited datasets, such as Indonesian.

Watching subtitled videos with the sound off affects viewers' comprehension, cognitive load, immersion, enjoyment, and gaze patterns: A mixed-methods eye-tracking study.

Every day, millions of viewers worldwide engage with subtitled content, and an increasing number choose to watch without sound. In this mixed-methods study, we examine the impact of sound presence or absence on the viewing experience of both first-language (L1) and second-language (L2) viewers when they watch subtitled videos. We explore this novel phenomenon through comprehension and recall post-tests, self-reported cognitive load, immersion, and enjoyment measures, as well as gaze pattern analysis using eye tracking. We also investigate viewers' motivations for opting for audiovisual content without sound and explore how the absence of sound impacts their viewing experience, using in-depth, semi-structured interviews. Our goal is to ascertain whether these effects are consistent among L2 and L1 speakers from different language varieties. To achieve this, we tested L1-British English, L1-Australian English and L2-English (L1-Polish) language speakers (n = 168) while they watched English-language audiovisual material with English subtitles with and without sound. The findings show that when watching videos without sound, viewers experienced increased cognitive load, along with reduced comprehension, immersion and overall enjoyment. Examination of participants' gaze revealed that the absence of sound significantly affected the viewing experience, increasing the need for subtitles and thus increasing the viewers' propensity to process them more thoroughly. The absence of sound emerged as a global constraint that made reading more effortful. Triangulating data from multiple sources made it possible to tap into some of the metacognitive strategies employed by viewers to maintain comprehension in the absence of sound. We discuss the implications within the context of the growing trend of watching subtitled videos without sound, emphasising its potential impact on cognitive processes and the viewing experience.

Relationship detection for manipulation in object stacking scene with fully connected CRF

Relationship detection for manipulation in object stacking scenes is an actively studied problem in recent years. Since the stacked objects may occlude and block each other, it is necessary to model relationships among them for safety. Almost all existing solutions to this problem model object relationships separately and ignore their dependencies on each other. In this paper, we propose a fully connected Conditional Random Field (CRF) to impose global constraints on the object stacking scenes. Since the inference of fully connected CRF is usually intractable, we propose efficient methods for the exact inference and the variational inference to solve the proposed CRFs. Furthermore, the variational inference is implemented as an RNN for end-to-end training. Experimental results on Visual Manipulation Relationship Dataset VMRD and REGRAD suggest that the proposed CRF can, with a clear margin, improve the accuracy of manipulation relationship detection in object stacking scenes. Finally, the proposed models are also deployed on a physical robot to build a relation-aware grasping system. Results demonstrate that our algorithms can be generalized to real-world scenes well and help the robot perform safe grasping in object stacking scenes.

A branch-and-price approach for the nurse rostering problem with multiple units

In this paper, we study the nurse rostering problem that considers multiple units and many soft time-related constraints. An efficient branch and price solution approach that relies on a fast algorithm to solve the pricing subproblem of the column generation process is presented. For the nurse rostering problem, its pricing subproblem can be formulated as a shortest path problem with resource constraints, which has been the backbone of several solutions for several classical problems like vehicle routing problems. However, approaches that perform well on these problems cannot be used since most constraints in the nurse rostering problem are soft. Based on ideas borrowed from global constraints in constraint programming to model rostering problems, an efficient dynamic programming algorithm with novel label definitions and dominating rules specific to soft time-related constraints is proposed. In addition, several acceleration strategies are employed to improve the branch and price algorithm. Computational results on two sets of instances ranging from 2 to 4 units over a horizon of 2 or 4 weeks demonstrate the effectiveness of the proposed algorithms. The accelerated dynamic programming algorithm is able to solve pricing subproblems to optimality with the fewest extended labels. When contrasted with Cplex, the branch and price approach yields solutions that are either equivalent or superior across all instances.

Hydrodynamics of multicomponent vesicles: A phase-field approach

In this paper, we introduce a thermodynamically-consistent phase-field model to investigate the hydrodynamics of inextensible multicomponent vesicles in various fluid flows with inertial forces. Our model couples the fluid field, surface concentration field representing chemical species on the membrane, and vesicle dynamics, while enforcing global area and volume constraints through a Lagrange multiplier method. Specifically, we employ full Navier–Stokes equations for the fluid field, the Cahn–Hilliard equations for the species concentration on the membrane, a nonlinear advection–diffusion equation to describe the evolution of the vesicle membrane, and an additional equation to enforce local inextensibility. We utilize a residual-based variational multiscale method for the Navier–Stokes equations and a standard Galerkin finite element framework for the remaining equations. The PDEs are solved using an implicit, monolithic scheme based on the generalized-α time integration method. We extend previous models for homogeneous vesicles (Aland et al., 2014; Valizadeh and Rabczuk, 2022) to multicomponent vesicles, introducing Cahn–Hilliard equations while maintaining thermodynamic consistency. Additionally, we employ isogeometric analysis (IGA) for higher accuracy. We present a variety of two-dimensional numerical examples, including multicomponent vesicles in shear flow and Poiseuille flow with and without obstructions, using the resistive immersed surface method to handle obstructions. Furthermore, we provide three-dimensional simulations of multicomponent vesicles in Poiseuille flow.

Stress-constrained concurrent multiscale topological design of porous composites based on discrete material optimisation

Porous composites have attracted increasing attention in recent decades. This study develops a concurrent multiscale topology optimisation (CMTO) method under a prescribed stress constraint for designing porous composites with multi-domain microstructures. First, to address the difficulty of predicting local stress due to varying of microstructural type throughout the optimisation process, a continuous and differentiable stress measure is proposed to effectively approximate the local stress. Second, an inverse homogenisation method based on isogeometric analysis (IGA) is developed to improve the accuracy of stress prediction, and then it is integrated into a CMTO which is developed based on the discrete material optimisation (DMO) interpolation scheme. Third, a stress constraint which is differentiable with respect to both macro and micro design variables is proposed to enable the stress-constrained concurrent optimisation of the macrostructural configuration, microstructural configuration and distribution. Fourth, a novel post-processing approach is established to achieve smooth while volume preserving contour of unit cells with layouts. Finally, two benchmark design examples, namely l-bracket and Crack problems, are implemented using the presented CMTO under a global stress constraint to demonstrate the effectiveness of the proposed method. The result indicates that the proposed method can effectively decrease the stress concentration via three design manners, i.e., the macrostructural configuration, microstructural configuration and distribution. Also, an “interface-enlarging” phenomenon was interestingly but reasonably found in those cases when subjected to stress-constraint considerations.

Lower and upper bounds for scheduling a real-life assembly problem with precedences and resource constraints

In this work, we consider a real-life scheduling problem involving the production of off-road vehicles using a three-level assembly process, subject to precedence, machines, and resource constraints. This problem shares multiple characteristics with other scheduling problems such as the Parallel Machine Scheduling and Flexible Flow Shop Problems. However, it also comprises less investigated aspects such as a specific job precedence structure resulting in a directed rooted in-tree and a global resource constraint limiting the number of simultaneously active machines. We present a straightforward adaptation of a time-indexed mathematical formulation to the problem and introduce a new lower-bounding procedure. To solve the problem, we propose constructive heuristics based on classical priority rules and adaptations of job sequencing heuristics. We also propose CORE, a specialized approach tailored to leverage the problem structure. All the algorithms are extensively evaluated on two benchmark sets, various shop floor configurations, and eight real-life scenarios. Our results reveal the general effectiveness of job sequencing approaches and demonstrate the overall superiority of CORE.

Research on the technology path selection of China's manufacturing industry under the high-quality development strategy

As the foundation and leading force of national economic development, manufacturing determines a country's comprehensive strength and international competitiveness, and is the key to achieving transformation, upgrading and high-quality development. Based on the perspective of global value chain embedding, this paper explores the issue of technology path selection and high-end development in my country's manufacturing industry. Against the background of Internet development, this paper analyzes the basis for technology path selection in my country's manufacturing industry to achieve intelligent transformation and high-quality development. By constructing an analytical framework for technology path selection from two aspects of internal and external factors, the theoretical basis for technology path selection in my country is proposed. Guided by high-quality development, this paper studies the internal mechanism of technology path selection that can promote the high-end, intelligent, service-oriented and green development of manufacturing industry, and discusses the technology path selection for manufacturing industry to achieve green and sustainable development. Based on an in-depth analysis of the impact and mechanism of global value chain embedding, Internet development, productive services and environmental constraints on technology path selection, this paper proposes the optimal decision equation for R&D resource allocation in my country based on factor endowment conditions, thereby promoting the transformation of manufacturing industry from factor-driven to innovation-driven, accelerating the process of achieving high-end, intelligent, service-oriented and green development, which is of great significance to promoting the high-quality development of manufacturing industry.

Mental Resilience in Crisis: Examining the Mental Health and Well‐Being of Iranian Athletes During the COVID‐19 Pandemic

ABSTRACTThe pervasive impact of COVID‐19 and economic sanctions has significantly influenced the well‐being of Iranian athletes, leaving lasting imprints on both their physical and mental health. During this challenging time, this comprehensive study delves into the nuanced disparities among various cohorts of Iranian athletes across multiple dimensions, including insomnia severity, psychological distress, anxiety, depression, intrusive thoughts, life satisfaction, and hope. Stratifying the participants based on their professionalism level, age, education, sports activity engagement, and COVID‐19 infection status, our survey‐based findings from a cohort of 280 athletes reveal compelling insights: Male athletes exhibit higher levels of distress, anxiety, and depression compared to their female counterparts. Professional athletes manifest elevated psychological distress, anxiety, and depression in contrast to semi‐professional and amateur athletes. Insomnia severity is more prevalent among professional athletes, concurrently accompanied by higher levels of hope within this group. Young athletes and those with higher educational attainment report increased intrusive thoughts. Local and national athletes demonstrate higher levels of life satisfaction and hope compared to their international counterparts. Athletes not infected with Coronavirus experience heightened psychological distress compared to their COVID‐19‐infected counterparts. This nuanced exploration underscores the intricate interplay between various factors and their profound implications for the mental well‐being of Iranian athletes in the face of global health challenges and economic constraints. By recognizing the vulnerabilities exposed during the pandemic and sanctions, policymakers can work toward a more resilient and robust sports sector, ensuring that the mental health and psychosocial well‐being of athletes remain at the forefront of policy considerations.

Current and potential materials for the low-carbon cement production: Life cycle assessment perspective

Given the carbon-intensive nature of cement production, conducting a comprehensive environmental evaluation using life cycle assessment (LCA) modeling is paramount to achieving eco-friendly cement standards. This study meticulously compiles and evaluates LCA findings from diverse analyses of current and potential supplementary cementitious materials (SCMs) within the blended cement sector. It underscores the impact of the functional unit (FU) within the LCA approach, supply chain considerations, and technical and regulatory factors on the sustainability of blended cement mixtures. Most of LCAs studied herein show that integrating SCMs into the cement matrix typically reduces land use, energy consumption, and greenhouse gas (GHG) emissions, thereby lowering the global warming potential (GWP) of ordinary portland cement (OPC) samples from 831 to 980 kg of CO2-eq to 768-481 kg of CO2-eq per ton of cement. However, in some instances, environmental indicators like abiotic depletion potential-elements (ADP-E) and human toxicity potential (HTP) rise due to increased mining, electricity, and transportation demand for SCMs. Regarding the environmental potential of alkali-activated cementitious materials and low-carbon clinker formulations, we found that limitations arise in fully replacing OPC due to global raw material availability constraints, rendering them economically unfavorable and impeding their widespread adoption. Among the SCMs examined in this study, clays, which are more widely available compared to industrially sourced materials like fly ash, slag, and silica fume, exhibited a more favorable environmental profile when evaluated using a mass-based FU. Incorporating compressive strength into the FU resulted in greater environmental benefits from high-strength blendedcement composites. However, this approach might lead to inaccurate results because higher strength does not always correspond to a lower environmental impact. Thus, establishing a FU that accurately reflects the environmental impact of blended cement and its composites (e.g., concrete and mortar) is crucial. Despite the potential of various pozzolanic materials to reduce clinker content in cement mixtures, their wide utilization remains restricted due to the absence of widescale market-based initiatives, green procurement strategies, and effective policy measures, which hampers their industrial and public acceptance. Consequently, governmental support is essential for developing and integrating sustainable cement solutions.

Decentralized dynamic system for optimal power dispatch in wind farms based on node-dependence nature

Meeting the power demand from the transmission system operator is an important objective for power dispatch, which introduces a power supply-demand equality constraint coupling all the wind turbines among the wind farm into the optimization problem. For a large-scale wind farm, processing the global equality constraint in a centralized or distributed framework is time-consuming and computationally complex. Here we considered the fast and localized execution issue of the power optimal dispatch problems. A completely decentralized dynamic system was designed to optimize power flow while satisfying the electricity supply constraints. A voltage optimization problem with the global power constraints was decoupled into local wind turbine controllers based on the node-dependence nature, which is an inherent characteristic of wind farms and was fitted to the power sensitivity matrix in this paper. The local optimization problem was solved iteratively using the gradient projection method, and the system converged linearly to the equilibrium point. The simulations for the case studies performed in Simulink demonstrate that the proposed method achieves a near-global optimal performance using only local measurements.

Camouflaged Object Detection via Dual-branch Fusion and Dual Self-similarity constraints

Camouflaged Object Detection (COD) remains a challenging task due to the inherent difficulty in distinguishing concealed objects from their surroundings, primarily owing to their high visual similarity. Current research efforts have been insufficient in distinguishing the similarity differences between camouflaged objects and their corresponding backgrounds, leading to suboptimal performance, particularly when locating small-scale objects. To solve this issue, we introduce a novel Dual-branch Fusion and Dual Self-similarity Network (DSNet) comprising three modules. The first, a dual-branch fusion, mimics human observation of camouflaged objects and extracts multi-angle information. Dual-branch features are then decoded using a symmetric joint decoder module with channel interaction via multi-stage inter-group interaction. Inspired by natural organisms’ self-similarity, the self-similarity constraint module employs global and mutual constraints to identify subtle foreground-background differences. DSNet shows superior performance in experiments, and the constraint module can enhance other models as a plug-and-play component, further boosting overall performance.

Laboratory Abnormal Behavior Detection Based on Multimodal Information Fusion

The traditional laboratory anomaly detection methods mainly focus on the hidden dangers caused by chemical leaks and other items, ignoring the impact of abnormal behaviors such as incorrect operations and improper behavior on safety in the laboratory. This paper proposes a laboratory abnormal behavior detection method based on multimodal information fusion. The method generates a dense optical flow field of RGB image sequences based on optical flow theory and global smoothing constraints, and mines motion mode information. Meanwhile, the contour modal information of behavior is captured through convolution and adjacency matrix operations. Using decision level and proximity functions to integrate student behavior motion mode information and contour mode information, and using the maximum value as the behavior detection result. The experimental results show that the method can effectively detect abnormal behavior in the laboratory environment, with small detection errors and a specificity close to 1.00, effectively ensuring the safety of the laboratory environment.

Global constraints on exhumation rates during porphyry copper formation and supergene enrichment: applications to exploration as illustrated from the Central Andes

Global constraints on exhumation rates during porphyry copper formation and supergene enrichment: applications to exploration as illustrated from the Central Andes

Polyculture of pikeperch (Sander lucioperca) and Russian sturgeon (Acipenser gueldenstaedtii) using an artificial common pellet – Implications on feed to fish nutrient transfers in recirculating aquaculture system (RAS)

The purpose of this research was to investigate the effects of monoculture and polyculture on the utilization of an artificial common pellet to produce nutritious products, specifically pikeperch and Russian sturgeon, in a recirculating aquaculture system (RAS) for 84 days. The experiment was conducted under controlled conditions, with specific parameters for: water temperature (21.8±0.4 °C), initial weight of the fish (pikeperch: 18.17±2.65 g; sturgeon: 18.23±3.62 g), volume of the containers (working volume of 272 litres) and feeding rate (1.5 %). Five experimental groups were tested in triplicates, including monoculture groups (pikeperch: 63.46±18.49 g; sturgeon: 93.52±50.40 g) and three polyculture combinations [P90: 90 % pikeperch (68.63±13.79 g) + 10 % sturgeon (86.10±33.38 g); P80: 80 % pikeperch (76.88±18.06 g) + 20 % sturgeon (103.53±44.60 g); P70: 70 % pikeperch (81.51±19.24 g) + 30 % Russian sturgeon (94.48±33.25 g)]. The results indicated that the addition of Russian sturgeon to pikeperch tanks could lead to efficient transfer of feed lipid to fish biomass through sturgeons, but not pikeperch. Polycultures showed better lipid absorption (P70 lipid-ADC 96.06±1.96 %) from the common pellet than monocultures (pikeperch: lipid-ADC 91.93±6.37 %; sturgeon: lipid-ADC 97.08±2.07 %). Fillet lipid content of pikeperch remained unaltered across RAS monocultures and polycultures but changed positively in Russian sturgeon in polyculture (P70 2.64±0.71 % > P0 1.75±0.75 %). In both species, polyculture fillets accumulated 5–7 % higher MUFA (oleic acid, C18:1n-9) than monoculture fillets. The major conclusions drawn from this research are that polyculture group P90 had both fish species flesh with highest muscle reserves of glycine and proline. In polyculture, critically indispensable muscle lysine reserves depleted in pikeperch, but Russian sturgeon muscle amino acid profile was stable. Given the global constraints on land availability, the study proposes RAS polyculture as a potentially productive and nutritious aquaculture system of the future. The research also suggests that resilient species for RAS polyculture need to be identified, proposing Russian sturgeon as a possible candidate.

Reinforcement learning-based satellite formation attitude control under multi-constraint

As the complexity of space missions increases, the constraints on satellite attitude control become more stringent, particularly for satellites working in orbit formation. This paper introduces a novel method, based on the categorization and modeling of different constraints, for attitude control of satellite formations under multiple constraints. The method employs the Phased Priority Reinforcement Learning (PPRL) approach, which utilizes Deep Deterministic Policy Gradient (DDPG) technology. Considering the complexity of constraints and the challenge posed by the high control dimensionality due to multi-satellite coordination, the method addresses these challenges through a two-step training strategy. The first step addresses the multi-constraint issue for individual satellites and increases the priority of single-satellite training experience data in the experience replay buffer of the second step to enhance data utilization efficiency. To address the issue of reward sparsity in complex high-dimensional constraint models, a detailed reward mechanism is proposed, incorporating both local and global constraints into the reward function, thereby achieving both efficient and effective attitude control. This approach not only meets dynamic, state, and performance constraints but also demonstrates adaptability and robustness through numerical simulations. Compared to traditional methods, this approach achieves significant improvements in control performance and constraint satisfaction, offering a novel solution pathway for high-dimensional control problems in multi-constraint satellite formations.

Global Environmental Constraints on Magnetic Reconnection at the Magnetopause From In Situ Measurements

AbstractProgress in locating the X‐line on the magnetopause beyond the atypical due south interplanetary magnetic field (IMF) condition is hampered by the fact that the global plasma and field spatial distributions constraining where reconnection could develop on the magnetopause are poorly known. This work presents global maps of the magnetic shear, current density and reconnection rate, on the global dayside magnetopause, reconstructed from two decades of measurements from Cluster, Double Star, THEMIS and MMS missions. These maps, generated for various IMF and dipole tilt angles, offer a unique comparison point for models and observations. The magnetic shear obtained from vacuum magnetostatic draping is shown to be inconsistent with observed shear maps for IMF cone angles in 12.5° ± 2.5° ≤ |θco| ≤ 45° ± 5°. Modeled maximum magnetic shear lines fail to incline toward the equator as the IMF clock angle increases, in contrast to those from observations and MHD models. Reconnection rate and current density maps are closer together than they are from the shear maps, but this similarity vanishes for increasingly radial IMF orientations. The X‐lines maximizing the magnetic shear are the only ones to sharply turns toward and follow the anti‐parallel ridge at high latitude. We show the behavior of X‐lines with varying IMF clock and dipole tilt angles to be different as the IMF cone angle varies. Finally, we discuss a fundamental disagreement between X‐lines maximizing a given quantity on the magnetopause and predictions of local X‐line orientations.