As the focus on environmental sustainability sharpens, the significance of low-carbon manufacturing and energy conservation continues to rise. While traditional flexible job shop scheduling strategies are primarily concerned with minimizing completion times, they often overlook the energy consumption of machines. To address this gap, this paper introduces a novel solution utilizing deep reinforcement learning. The study begins by defining the Low-carbon Flexible Job Shop Scheduling problem (LC-FJSP) and constructing a disjunctive graph model. A sophisticated representation, based on the Markov Decision Process (MDP), incorporates a low-carbon graph attention network featuring multi-head attention modules and graph pooling techniques, aimed at boosting the model’s generalization capabilities. Additionally, Bayesian optimization is employed to enhance the solution refinement process, and the method is benchmarked against conventional models. The empirical results indicate that our algorithm markedly enhances scheduling efficiency by 5% to 12% and reduces carbon emissions by 3% to 8%. This work not only contributes new insights and methods to the realm of low-carbon manufacturing and green production but also underscores its considerable theoretical and practical implications.
25 April 2016 in ACM Transactions on Intelligent Systems and Technology
Parsing the semantic structure of a web page is a key component of web information extraction. Successful extraction algorithms usually require large-scale training and evaluation datasets, which are difficult to acquire. Recently, crowdsourcing has proven to be an effective method of collecting large-scale training data in domains that do not require much domain knowledge. For more complex domains, researchers have proposed sophisticated quality control mechanisms to replicate tasks in parallel or sequential ways and then aggregate responses from multiple workers. Conventional annotation integration methods often put more trust in the workers with high historical performance; thus, they are called performance-based methods. Recently, Rzeszotarski and Kittur have demonstrated that behavioral features are also highly correlated with annotation quality in several crowdsourcing applications. In this article, we present a new crowdsourcing system, called Wernicke, to provide annotations for web information extraction. Wernicke collects a wide set of behavioral features and, based on these features, predicts annotation quality for a challenging task domain: annotating web page structure. We evaluate the effectiveness of quality control using behavioral features through a case study where 32 workers annotate 200 Q&A web pages from five popular websites. In doing so, we discover several things: (1) Many behavioral features are significant predictors for crowdsourcing quality. (2) The behavioral-feature-based method outperforms performance-based methods in recall prediction, while performing equally with precision prediction. In addition, using behavioral features is less vulnerable to the cold-start problem, and the corresponding prediction model is more generalizable for predicting recall than precision for cross-website quality analysis. (3) One can effectively combine workers’ behavioral information and historical performance information to further reduce prediction errors.
Automated defect detection for printed fabric manufacturing faces critical challenges in balancing industrial-grade accuracy with real-time deployment efficiency. To address this, we propose RT-DETR-FFD, a knowledge-distilled detector optimized for printed fabric defect inspection. Firstly, the student model integrates a Fourier cross-stage mixer (FCSM). This module disentangles defect features from periodic textile backgrounds through spectral decoupling. Secondly, we introduce FuseFlow-Net to enable dynamic multi-scale interaction, thereby enhancing discriminative feature representation. Additionally, a learnable positional encoding (LPE) module transcends rigid geometric constraints, strengthening contextual awareness. Furthermore, we design a dynamic correlation-guided loss (DCGLoss) for distillation optimization. Our loss leverages masked frequency-channel alignment and cross-domain fusion mechanisms to streamline knowledge transfer. Experiments demonstrate that the distilled model achieves an mAP@0.5 of 82.1%, surpassing the baseline RT-DETR-R18 by 6.3% while reducing parameters by 11.7%. This work establishes an effective paradigm for deploying high-precision defect detectors in resource-constrained industrial scenarios, advancing real-time quality control in textile manufacturing.
The node representation learning capability of Graph Convolutional Networks (GCNs) is fundamentally constrained by dynamic instability during feature propagation, yet existing research lacks systematic theoretical analysis of stability control mechanisms. This paper proposes a Stability-Optimized Graph Convolutional Network (SO-GCN) that enhances training stability and feature expressiveness in shallow architectures through continuous–discrete dual-domain stability constraints. By constructing continuous dynamical equations for GCNs and rigorously proving conditional stability under arbitrary parameter dimensions using nonlinear operator theory, we establish theoretical foundations. A Precision Weight Parameter Mechanism is introduced to determine critical Frobenius norm thresholds through feature contraction rates, optimized via differentiable penalty terms. Simultaneously, a Dynamic Step-size Adjustment Mechanism regulates propagation steps based on spectral properties of instantaneous Jacobian matrices and forward Euler discretization. Experimental results demonstrate SO-GCN’s superiority: 1.1–10.7% accuracy improvement on homophilic graphs (Cora/CiteSeer) and 11.22–12.09% enhancement on heterophilic graphs (Texas/Chameleon) compared to conventional GCN. Hilbert–Schmidt Independence Criterion (HSIC) analysis reveals SO-GCN’s superior inter-layer feature independence maintenance across 2–7 layers. This study establishes a novel theoretical paradigm for graph network stability analysis, with practical implications for optimizing shallow architectures in real-world applications.
1 January 2007 in Journal of Zhejiang University-SCIENCE A
In this paper we investigate a variant of the scheduling problem on two uniform machines with speeds 1 and s. For this problem, we are given two potential uniform machines to process a sequence of independent jobs. Machines need to be activated before starting to process, and each machine activated incurs a fixed machine activation cost. No machines are initially activated, and when a job is revealed, the algorithm has the option to activate new machines. The objective is to minimize the sum of the makespan and the machine activation cost. We design optimal online algorithms with competitive ratio of (2s+1)/(s+1) for every s≥1.
Graph attention networks are pivotal for modeling non-Euclidean data, yet they face dual challenges: training oscillations induced by projection-based high-dimensional constraints and gradient anomalies due to poor adaptation to heterophilic structure. To address these issues, we propose LDC-GAT (Lyapunov-Stable Graph Attention Network with Dynamic Filtering and Constraint-Aware Optimization), which jointly optimizes both forward and backward propagation processes. In the forward path, we introduce Dynamic Residual Graph Filtering, which integrates a tunable self-loop coefficient to balance neighborhood aggregation and self-feature retention. This filtering mechanism, constrained by a lower bound on Dirichlet energy, improves multi-head attention via multi-scale fusion and mitigates overfitting. In the backward path, we design the Fro-FWNAdam, a gradient descent algorithm guided by a learning-rate-aware perceptron. An explicit Frobenius norm bound on weights is derived from Lyapunov theory to form the basis of the perceptron. This stability-aware optimizer is embedded within a Frank–Wolfe framework with Nesterov acceleration, yielding a projection-free constrained optimization strategy that stabilizes training dynamics. Experiments on six benchmark datasets show that LDC-GAT outperforms GAT by 10.54% in classification accuracy, which demonstrates strong robustness on heterophilic graphs.