E2CO-lite: A scalable deep-learning surrogate for efficient nonlinearly constrained robust production optimization

Distributionally robust bi-level optimization for reliability management of medical waste reverse logistics network under uncertainty

Distributionally robust geometric joint chance-constrained optimization: Neurodynamic approaches

Dual-stage evolutionary association and hierarchical archiving for robust multi-objective optimization: Application to order scheduling

Visible light positioning with dynamic covariance and robust optimization fusion in shadowed underground mines

A new robust bi-level optimization framework for biomass supply chain network and its accelerated Benders decomposition

HexOpt: Efficient and robust hexahedral mesh optimization using Rectified Hybrid Quadratic Jacobian and geometry-aware mapping

Optimization problems are a fundamental component of engineering and scientific research, particularly in energy systems, where growing industrial demands necessitate the development of robust and efficient optimization algorithms. The Combined Heat and Power Economic Dispatch (CHPED) problem seeks to minimize the operating costs of power and heat generation units while satisfying complex operational constraints, including valve-point effects, transmission losses, generation capacity limits, and heat-power coupling in cogeneration units. This study proposes a hybrid optimization framework that integrates the Firefly Algorithm (FA) with Sequential Quadratic Programming (SQP), termed HFASQP. The hybrid HFASQP approach leverages the global search ability of FA and the local refinement strength of SQP to address the non-convex, highly constrained nature of CHPED problems. The proposed method is validated on a set of benchmarks CHPED systems, including traditional test cases with 5, 7, and 48 units, as well as two newly introduced large-scale systems with 96 and 192 units to evaluate scalability. The proposed method achieved a cost reduction of up to 1.7% and 1.9% compared to FA, SQP and outperformed several state-of-the-art algorithms in terms of solution quality and computational efficiency. In addition, the performance of HFASQP is comparatively evaluated against other recently developed metaheuristic algorithms, including the Kangaroo Optimization Algorithm (KOA) and the Heap-Based Optimizer (HBO), to provide a more comprehensive assessment. To further evaluate robustness and generalizability, the HFASQP algorithm is tested on 23 standard benchmark functions from the optimization literature. The results confirm its consistent accuracy and competitiveness across all test cases, demonstrating its effectiveness beyond CHPED applications and highlighting its potential for broader engineering problems. • Developing a stability-enhanced FA–SQP hybrid for reliable optimization on highly nonconvex CHPED landscapes. • Using an adaptive trigger to invoke SQP selectively, reducing computational load while improving accuracy. • Achieving stronger constraint-feasibility than existing hybrid metaheuristics under nonlinear and valve-point effects. • Ensuring robust performance on non-smooth, multi-modal CHPED models through targeted global–local coordination. • Demonstrating scalable behavior via complexity assessment and benchmarks across multi-size CHPED systems.

Diversity-driven self-regulation for robust high-dimensional black-box optimization

High-fidelity 3D tree mesh models have broad applications in virtual geographic environments, forest ecology, and digital entertainment. Although laser point clouds provide precise data, existing point cloud-based methods struggle with accuracy and completeness due to tree structural complexity, leaf occlusion, and data gaps. To address these challenges, we propose a novel framework that integrates data-driven and morphology-knowledge-driven techniques for generating high-fidelity tree mesh models with accurate trunk and overall crown morphology. The proposed framework consists of three main stages. First, in the trunk separation stage, non-scattering feature clustering is employed to extract the main trunk points. Second, in the robust trunk mesh generation and optimization stage, a coarse-to-fine skeleton extraction and refinement method is proposed, followed by weighted Levenberg–Marquardt cylindrical fitting to generate the trunk geometry. Finally, we propose a novel method that integrates improved space colonization with Alpha Shape constraints to overcome challenges of reconstructing fine branches within the crown, thereby generating complete tree mesh models with accurate trunk and crown morphology. The method was evaluated on laser-scanned, 3D Gaussian, and synthetic point clouds, and benchmarked against state-of-the-art techniques. Results demonstrate superior accuracy and robustness across diverse point cloud types, with strong resilience to noise and incomplete data.

Spatio-temporal topological encoding via dual-pathway ST-GCN and attention-enhanced BiLSTM for robust human pose optimization

Distributionally robust fairness-based last-mile relief network optimization with casualty uncertainty

Semi-supervised domain generalization for fault diagnosis using adaptive pseudo-label selection and distributionally robust optimization

Data-driven two-stage robust optimization for wind-photovoltaic-hydrogen integrated energy system based on BiLSTM-RKDE uncertainty modeling

A reliability-oriented conflict robust optimization model for berth allocation under operational disturbances

Scenario-based robust optimization for large-scale traffic networks

As automated classification systems become increasingly prevalent, concerns have emerged over their potential to reinforce and amplify existing societal biases. In the light of this issue, many methods have been proposed to enhance the fairness guarantees of classifiers. Most of the existing interventions assume access to group information for all instances, a requirement rarely met in practice. Fairness without access to demographic information has often been approached through robust optimization techniques, which target worst-case outcomes over a set of plausible distributions known as the uncertainty set. However, their effectiveness is strongly influenced by the chosen uncertainty set. In fact, existing approaches often overemphasize outliers or overly pessimistic scenarios, compromising both overall performance and fairness. To overcome these limitations, we introduce SPECTRE, a minimax-fair method that adjusts the spectrum of a simple Fourier feature mapping and constrains the extent to which the worst-case distribution can deviate from the empirical distribution. We perform extensive experiments on the American Community Survey datasets involving 20 states. The safeness of SPECTRE comes as it provides the highest average values on fairness guarantees together with the smallest interquartile range in comparison to state-of-the-art approaches, even compared to those with access to demographic group information. In addition, we provide a theoretical analysis that derives computable bounds on the worst-case error for both individual groups and the overall population, as well as characterizes the worst-case distributions responsible for these extremal performances.

A multi-objective robust optimization based on evolutionary algorithm for container routing problem under risks and uncertainties

A self-driving metabolomics laboratory has long been envisioned but remains largely unrealized due to the complexity of analytical method design. As an initial step toward this goal, we developed BAGO, a self-optimizing framework for automated liquid chromatography (LC) gradient design in mass spectrometry-based untargeted metabolomics. BAGO aims to enhance global metabolite detection by improving the separation of all compounds, regardless of whether their identities are known or unknown. It operates through a data-driven Bayesian optimization process that iteratively learns from acquired MS data to propose improved gradients. To support this, we propose a global separation index that quantifies coelution among both annotated and unannotated features, enabling robust and structure-agnostic optimization across diverse sample types. Benchmarking across four metabolomics assays involving diverse sample matrices, column chemistries, and gradient durations, BAGO achieved substantial improvements within only 10 optimization iterations by balancing exploration and exploitation. The optimized gradients led to increased numbers of Gaussian-shaped peaks, higher MS/MS acquisition rates, and more annotated metabolites using both identity and analog search approaches. We further applied BAGO to a sex-differentiated metabolomics study of Drosophila abdominal carcasses, completing the workflow in parallel under both initial and optimized gradients. The optimized method resulted in a 41.9% increase in Gaussian-shaped peaks, a 36.8% increase in MS/MS-acquired peaks, and the identification of 18 additional biologically significant metabolites, including sex-associated compounds such as octopamine and pyroglutamic acid. BAGO (https://github.com/HuanLab/bago) is freely available as an open-source tool and represents a generalizable step toward fully automated, self-optimizing experimental workflows in untargeted metabolomics.

Prospective clinical implementation of the robust optimization planning technique in long-course photon radiotherapy treatment for lung cancer.