A differential evolution-based joint optimization method for full-process near-infrared spectral modeling and its application to leaf litter moisture prediction.

Due to the increasing volume of freight traffic and the growing practice of structural monitoring for existing bridges, it has become crucial to exploit modal analysis to identify the magnitudes of axle loads and the frequency content of the structural response induced by vehicle crossings. In this paper, starting from the comparison between a simplified analytical model of the bridge and the relevant experimental responses, a multi-parameter identification method is proposed to identify the magnitude, the number, the axle distance, and the eccentricity of moving loads crossing the bridge. A bending-torsional beam model subjected to travelling loads characterized by non-uniform spacing and magnitudes, has been adopted to describe the bridge dynamics. The identification procedure is based on the Differential Evolution genetic algorithm. The proposed method is tested and validated using numerically simulated dynamic responses including the presence of noise. The main contribution of this work concerns the combined use of a beam model and the DE algorithm to identify heavy vehicle load distributions for skew road bridges. • A multi-parameter identification method is proposed to identify bridge moving loads. • The intensity, number, axle distance, and eccentricity of loads are identified. • The adopted 1-D beam model integrates bending and torsional responses. • Both load eccentricity and deck skewness can be considered. • Governing equations have been solved starting from a Faedo–Galerkin approach. • The differential evolution algorithm was adopted for the inverse problem. • An alternative convergence criterion (called “swarm criterion”) was proposed.

Interpretable machine learning framework for predicting cement adhesive bond strength in NSM FRP systems using differential evolution and SHAP analysis

Wearable devices, such as actigraphy monitors and continuous glucose monitors (CGMs), capture high-frequency data, which are often summarized by the percentages of time spent within fixed thresholds. For example, actigraphy data are categorized into sedentary, light, and moderate-to-vigorous activity, while CGM data are divided into hypoglycemia, normoglycemia, and hyperglycemia based on a standard glucose range of 70-180 mg/dL. Although scientific and clinical guidelines inform the choice of thresholds, it remains unclear whether this choice is optimal and whether the same thresholds should be applied across different populations. In this work, we define threshold optimality with loss functions that quantify discrepancies between the full empirical distributions of wearable device measurements and their discretizations based on specific thresholds. We introduce two loss functions: one that aims to accurately reconstruct the original distributions and another that preserves the pairwise sample distances. Using the Wasserstein distance as the base measure, we reformulate the loss minimization as optimal piecewise linearization of quantile functions. We solve this optimization via stepwise algorithms and differential evolution. We also formulate semi-supervised approaches where some thresholds are predefined based on scientific rationale. Applications to CGM datasets from diverse populations, including individuals with type 1 diabetes, type 2 diabetes, and normal glycemic control, demonstrate that data-driven thresholds vary by population, improve discriminative power, and yield stronger associations with clinical variables over fixed thresholds.

Morlet-controlled parameter adaptive differential evolution with diversity-triggered restart for high-precision photovoltaic model parameter identification

Integration of multiple constraint-treating approaches for uncertain automatic parking path optimization utilizing competition and cooperation-driven differential evolution

Cooperative 4D trajectory planning for multi aerial vehicles combining receding horizon optimization and differential evolution algorithm in dynamic battlefield environment

Research on intelligent beam tuning for 2x3.0 MV tandem accelerator based on enhanced parameter adaptive differential evolution algorithm

Differential Evolution based Cluster Search Method for Image Reconstruction in Diffuse Optical Tomography

A dynamic neighborhood multi-objective differential evolution algorithm based on knee point preferences and its application in portfolio optimization

A hybrid differential evolution with discrete cosine transform-based mutation strategy and dynamic diversity mechanism

One of the most essential processes in manufacturing is continuous operations without any downtime. The Energy Balanced Hybrid Flow Shop Scheduling Problem (EMBHFSP) is an interesting study as it provides huge impact on machine effectiveness while balancing between minimizing completion time and energy consumption. Limited study has focused on hybrid flow shops (HFS) with a concentration on energy-machine balanced production. This paper aims to develop a computational model and evaluate the exploration effectiveness of Differential Evolution in optimizing the EMBHFSP. The most popular as well as latest optimization algorithms including Simulated Annealing, Grey Wolf Optimization, Henry Gas Solubility Optimization, Harmony Search, Imperialist Competitive Algorithm, Multi-verse Optimizer, and Thermal Exchange Optimization were evaluated against Differential Evolution utilizing the EMBHFSP model across 20 Optimization repetitions. The experimental results indicate that the Differential evolution algorithm surpassed others by 45% in mean fitness value and exhibited a 67.5% enhancement in standard deviation across all benchmark problems. In addition, a case study was performed in a manufacturing facility to validate the applicability of the model. Three different scheduling solutions, optimizing makespan, energy balance and machine utilization balance are generated using differential evolution. The results show the ability of the model to solve trade-offs between efficiency of production and sustainability in real industrial environments.

Accurate characterization of the initial in-situ stress field is essential for stability assessment, support design, and surrounding rock control in deep underground engineering, yet field measurements are often highly scattered and three-dimensional inversion is computationally expensive. This study develops a robust and efficient inversion framework for a deeply buried underground powerhouse in the southeastern Tibetan Plateau. First, a three-dimensional borehole stress synthesis method is established by combining particle swarm optimization, the Huber loss, Levenberg-Marquardt iteration, and regularization to denoise multi-source measurements, suppress local outliers, and alleviate ill-conditioning in stress-tensor reconstruction. Second, a surrogate-assisted differential evolution workflow is constructed using a radial basis function network within a prediction-verification-correction active-learning loop to reduce the cost of repeated forward simulations while preserving global optimization capability. Application to the powerhouse shows that the mean relative error decreases from 14.12 to 9.34%, and the deviation variance decreases from 2.98 to 1.33 after optimization. The proposed framework improves both the reliability of inversion input data and the efficiency of field-scale stress reconstruction, providing practical support for stability evaluation and surrounding rock control in deep, geologically complex underground caverns.

This study develops a constrained multi-objective optimization framework for public Electric Vehicle (EV) charging infrastructure planning that simultaneously addresses spatial coverage, traffic-driven demand satisfaction, investment cost, and equity in capacity allocation. The framework integrates the 2025-2027 public charging station rollout plan for Jinyun County, China, with empirically observed 2024 traffic flow data from 13 continuous observation stations and applies a Differential Evolution (DE) strategy to search the feasible deployment space under budget and rollout constraints. The optimized deployment selects 15 stations from 43 planned candidates, yielding a total installed capacity of 6000kW with an investment of ¥6.24 million, while achieving complete town-level coverage and near-complete demand satisfaction with high cost efficiency. Spatial analysis indicates an average effective service radius of 11.4km and a marked reduction in coverage gaps along high-traffic corridors. Equity assessment based on the Gini coefficient indicates a more balanced distribution of charging capacity relative to traffic demand. Sensitivity and robustness analyses show stable performance under variations in budget availability, demand intensity, and key parameters, which confirms the value of demand-aware station selection and capacity allocation for data-driven and equitable EV charging infrastructure planning.

Efficient facility location in insurgency-affected regions demands methods that balance risk, cost, and scalability. This study proposes a hybrid cuckoo search approach integrating differential evolution crossover and local search, optimized via the Taguchi method. Real-world case in Yala Province, Thailand, demonstrates its applicability to agricultural logistics in conflict-prone environments. Results from 24 benchmark instances and a real case demonstrate that the proposed method outperforms traditional metaheuristics, reducing total costs by 41.1%, 30.4%, 29.6%, 20.9% and 9.2% compared with ant colony optimization, differential evolution, success-history-based adaptive differential evolution, covariance matrix adaptation evolution strategy and standard cuckoo search, respectively. The proposed approach handles high-dimensional constraints and real insurgency data, ensuring resilient and efficient logistics planning. Its convergence performance and adaptability to large-scale instances affirm its suitability for dynamic, risk-sensitive environments. Beyond agriculture, this method can support decision making in logistics, manufacturing and renewable energy siting, where traditional optimization fails under disruption.

ABSTRACT Video surveillance cameras are a critical component of urban security systems, yet traditional deployment strategies often result in blind spots, redundant coverage, and suboptimal resource utilization, particularly in complex three-dimensional environments. To address these issues, this study introduces the spatial adaptive differential evolution algorithm (SA-DEA), a novel approach to optimize surveillance camera placement based on multi-constraint spatial visibility analysis of high-precision 3D geospatial models. This method ensures comprehensive coverage, maximizes resource efficiency, and incorporates spatial significance. The key innovations of the SA-DEA include: (1) joint optimization of camera positions and orientations with adaptive parameter control to refine the search process and enhance convergence; (2) multi-type mutation mechanisms and harmony search crossover to improve adaptability to complex geographical environments; and (3) a multi-attribute weighted aggregation fitness function that integrates coverage, redundancy, and spatial importance for a comprehensive evaluation. Experimental results demonstrate that the proposed approach outperforms existing methods in terms of area coverage, reduced redundancy, and enhanced surveillance of critical regions. In complex 3D environments, the SA-DEA exhibits robust global search capabilities and significant practical value, offering new insights into spatial optimization for urban intelligent surveillance systems.

The association between near-death experiences (NDEs) and physiological indicators remains an unsolved mystery, which hinders in-depth understanding of the essence of consciousness and life processes. Traditional single-indicator analysis methods have limitations, and a comprehensive multi-modal research approach is urgently needed to advance relevant explorations in the fields of medicine, neuroscience, and philosophy. Multi-modal physiological monitoring data, including electroencephalogram (EEG) and electrocardiogram (ECG), from critical care settings (ICU, emergency department) were integrated. Signal analysis was conducted by drawing analogies from the concepts of in-mold electronics (IME) and injection molding node displacement. Latin Hypercube Sampling (LHS) was used to collect injection molding parameters, and the Multi-Strategy Differential Evolution (MSDE) algorithm (incorporating elite-sharing, perturbation-backtracking, and adaptive-tuning strategies) was combined to optimize the injection molding process of the brain-computer interface (BCI). A node displacement prediction model was constructed through Moldex3D simulation and Kriging interpolation. During the out-of-body sensation phase of NDEs, EEG showed an increase in gamma waves and a decrease in alpha waves, while ECG exhibited arrhythmia, confirming the coordinated changes between the brain and the heart. In BCI manufacturing, the MSDE algorithm reduced the average node displacement from 0.289mm to 0.021mm (with an optimization rate of 92.73%), the volume shrinkage rate from 10.162% to 6.39%, and the optimized voltage difference from 5.78V to 0.42V, which was consistent with the improvement in displacement. Multi-dimensional analysis is crucial for decoding the mechanism of NDEs. The optimized BCI hardware enables accurate collection of NDE-related physiological signals, providing scientific support for end-of-life care, optimization of resuscitation protocols, and consciousness research, while also building a cross-disciplinary bridge between engineering and life sciences.

The seismic design response spectrum is a vital parameter for determining the potential seismic load of the engineering structure. Differential evolution algorithm (DE) with a novel hybrid mutation operator is utilized to calibrate the spectral parameters in order to enhance iteration efficiency. This study calibrates the seismic design response spectrum for China based on the Chinese seismic intensity scale and compares the results with the Code for Seismic Design of Buildings (CSDB2010).The calibration spectra are based on strong ground motion records with destructive power exceeding the Chinese seismic intensity 7 and above. The characteristics of the calibration spectral parameters are analyzed and subsequently compared with the design spectra of the Code for Seismic Design of Buildings (CSDB2010). It is found that: Increasing the number of iterations can enhance the fitting goodness of DE between the calibration spectrum and the record response spectrum. The average site characteristic period (Tg) for rock and hard soil site conditions (Class I and II) is greater than the Tg specified in CSDB2010. The average Tg for intensity 10 + is greater than the average Tg for intensity 7, 8, and 9. Tg increases with the seismic intensity. The average spectra platform value (βmax) from this study gradually approaches the βmax in CSDB2010 as the intensity increases. The average attenuation index (γ) at different intensities of this study is greater than γ in CSDB2010.

Background/Objectives: In gas chromatography-mass spectrometry (GC-MS) library-based compound identification, spectrum preprocessing and associated tuning parameters critically influence identification performance. These parameters are conventionally optimized using grid search, which requires predefined parameter spaces and becomes computationally inefficient as dimensionality increases, often failing to identify optimal values because of discretization. Differential evolution (DE), a population-based metaheuristic optimization algorithm, provides a flexible alternative through efficient global exploration of the parameter space. This study compared the performance of DE and grid search for optimizing compound identification. Methods: Cosine similarity was applied to the NIST GC-MS library. DE was used to maximize either cross-validated accuracy or mean reciprocal rank (MRR). Results were compared with those from a grid search over five equally spaced parameter values. Identification performance was evaluated using accuracy, MRR, and area under the receiver operating characteristic curve (AUC). Results: When all four parameters were optimized simultaneously, DE achieved slightly higher cross-validated accuracy and MRR than grid search, although the absolute differences were modest. More pronounced differences were observed in specific unidimensional tuning scenarios, particularly for the intensity weight factor. Simultaneous multidimensional parameter optimization yielded better performance than isolated parameter tuning. Conclusions: Grid search may be computationally advantageous when the parameter space is known and limited, whereas DE provides a more flexible approach for unknown or high-dimensional search spaces. Overall, DE achieved comparable identification performance to grid search, with modest improvements observed in some optimization settings. A command line Julia-based tool, MSTune, was developed for spectrum preprocessing parameter optimization and is publicly available on GitHub.

Additive manufacturing (AM) allows for complex, lightweight designs but introduces process-specific constraints that traditional benchmarks often overlook. We introduce a manufacturing-aware benchmark designed for PLA/FDM that includes nine design variables covering geometry, process, and orientation; six competing objectives (material weight, build time, structural efficiency, support volume, surface quality, and total cost); and 20 physics-based manufacturability constraints grouped into eight categories. The framework combines feasible-set exploration using Latin Hypercube Sampling (LHS) (n=10,000), multi-method sensitivity analysis, sample-based Pareto front extraction, and standardized algorithm evaluation under equal budgets for differential evolution (DE), particle swarm optimization (PSO), Bayesian optimization (BO), simulated annealing (SA), and a hybrid algorithm (HA). Statistical comparisons employ nonparametric tests and effect sizes, while multi-objective performance is analyzed using dominance relations and hypervolume. Sample-based feasibility is roughly evenly split (49.8% feasible), with violations mainly caused by print speed and thermal/support limits; print speed, support density, and build orientation are the main factors affecting feasibility and performance; build time and cost are nearly collinear; and improving surface quality generally requires slower speeds and thinner layers. Feasibility-based Pareto analysis shows significant reductions in weight and support volume while maintaining strength, revealing clear trade-offs and knee solutions. Boundary checks show 96.7% interior solutions, indicating the problem is not boundary-driven, and the few layer-height violations are minor and correctable. Algorithmically, scalarized results favor the hybrid approach (with PSO ≈ DE), while multi-objective indicators highlight complementary strengths in front coverage. Performance differences are highly significant (Kruskal–Wallis H = 179.23, p < 0,001; η² = 0.717; ω² = 0.711); the hybrid achieved the best scalarized outcome with tight uncertainty (95% CI [−4.9163, −4.7979], CV = 4.48%), and BO attained the highest mean hypervolume (0.847). The benchmark offers a reproducible, realistic testbed that bridges algorithmic evaluation with manufacturing feasibility and can be expanded with higher-fidelity models and materials.