Search Results (34)

Feature selection (FS) is a pivotal preprocessing task in data mining aimed at identifying optimal feature subsets to improve model generalization and reduce computational overhead. However, its NP-hard nature poses significant challenges for traditional optimizers in terms of search efficiency and solution quality. The Harris Hawks Optimization (HHO) algorithm is a state-of-the-art population-based metaheuristic method that demonstrates powerful capabilities in various optimization challenges. Despite its advantages, HHO encounters problems such as early stagnation and reduced accuracy. To mitigate these problems, we introduce an advanced algorithm called the Hybrid Strategy Harris Hawks Optimization (HSHHO). The HSHHO combines three key enhancements to support global search diversity and local refinement: (1) an exploration mechanism that utilizes the Self-Parameterized Map (SPM) alongside a dynamic logarithmic spiral to expand search breadth; (2) a nonlinear adjustment to the escape energy parameter for improved phase equilibrium; and (3) an elite perturbation approach that uses Cauchy–Gaussian mutation to strengthen local optimization and solution quality. We assessed HSHHO against eight well-known algorithms on 30 benchmark functions, where it exhibited superior results in the majority of cases. Finally, HSHHO is applied to address 18 feature selection tasks. The results demonstrated that HSHHO achieved highly competitive outcomes in terms of objective values, feature subset size, and classification performance in most datasets, reaching an average accuracy of 94.47%. Full article

With the deep integration of artificial intelligence and big data, intelligent optimization algorithms have become key tools for solving many complex problems. However, as problem scale and complexity grow rapidly, the performance of traditional algorithms often faces significant challenges. The Teaching Learning Based Optimization algorithm has attracted widespread attention for its simple structure, few parameters, and high solution efficiency, and has been successfully applied across various engineering and scientific fields. Nevertheless, when dealing with high-dimensional, multimodal global optimization problems and real-world applications, the standard Teaching Learning Based Optimization still exhibits certain limitations, such as reduced accuracy of the optimal solution due to insufficient initial population diversity, and difficulty in escaping local optima caused by premature convergence. To address these issues, this paper proposes an Improved Teaching Learning Based Optimization algorithm. The improved ITLBO upgrades original TLBO from three perspectives: first, a population interaction strategy combining chaotic disturbance and Gaussian mutation is designed to enrich initial population diversity; second, bipolar cooperative search utilizing dynamic weighting of optimal and worst individuals balances global exploration and local exploitation to avoid premature convergence; third, oscillatory random mapping learning with sinusoidal oscillation factor periodically perturbs individuals to continuously replenish population diversity in iterations. Numerical results show that the proposed method exhibits superior convergence performance and stability on classical global optimization benchmarks. Furthermore, the algorithm is applied to practical cloud resource scheduling problems, and experimental outcomes verify that ITLBO improves solution accuracy by approximately one order of magnitude over original TLBO and reduces small-scale cloud scheduling cost by 12% while achieving preferable robustness. Full article

Grid-forming virtual synchronous generator control can improve the frequency-support capability of converter-interfaced systems. However, under successive disturbances and varying operating conditions, fixed inertia and damping settings often struggle to balance inertial response, oscillation suppression, and recovery speed. To address this issue, this paper develops an adaptive parameter coordination strategy for grid-forming virtual synchronous generators by using frequency deviation and rate of change of frequency as dynamic indicators. A piecewise regulation law is established to adjust virtual inertia and damping during different transient stages, while an improved parrot optimization algorithm is introduced for the offline coordinated tuning of the adaptive-law parameters. In the proposed optimizer, SPM-chaotic initialization, adaptive probability adjustment, and Cauchy-Gaussian hybrid mutation are incorporated to improve population diversity, convergence efficiency, and local refinement capability. Simulation results obtained in MATLAB/Simulink under successive disturbance events show that the proposed strategy achieves smaller frequency excursions, weaker secondary oscillations, and shorter settling times than fixed-parameter control and standard PO-based tuning. The results demonstrate that the proposed method can effectively enhance the dynamic support capability and disturbance adaptability of grid-forming virtual synchronous generators under complex operating conditions. Full article

Background/Objectives: Poly (ADP-ribose) polymerase (PARP1) has emerged as a promising therapeutic target in human breast cancer particularly in BRCA1/2 mutation carriers where a synthetic lethal interaction leads to massive tumor cell death upon specific inhibitors’ administration. Current clinically approved PARP inhibitors (Talazoparib and Olaparib) show outstanding therapeutic capabilities but suffer from severe side effects. Most importantly, some of them can cause life-threatening cardiotoxicity through hERG off-target effects. Here, we performed an extensive study to identify lead compounds with improved binding modes and favorable predicted pharmacokinetics using an integrated computational strategy. Methods: An artificial intelligence-driven drug design (AIDDISON™ v2023) workflow was employed to search ultra-large chemical space libraries for active compounds, which were then optimized via computer-aided methods to form a PARP-Tailored Database (PTD). This database was then analyzed through a virtual screening workflow, molecular docking studies, molecular dynamics (MD) simulations, MM/GBSA binding free energy calculations, DFT analysis and ADME/Tox predictions using the Schrödinger suite (v2023-2), MobaXterm v25.2, Gaussian 16.0, ProTox-3 and Pred-hERG v5.0 respectively. Results: Three compounds (1a–1c) were identified as promising candidates. Among them 1a appeared to be the most active compound with a favorable docking score (−9.488 kcal/mol) that is not only higher than 1b and 1c but also higher than that of Talazoparib (−6.778 kcal/mol). MD simulations of 1a–1c in the active site revealed an average RMSD of ~2.5–3.6 Å which is better compared to the parent Talazoparib (5.6 Å). Interestingly, on the 250 ns extended MD study, 1a exhibited a slightly reduced RMSD between 2.4 and 3.2 Å, whereas Talazoparib retained higher fluctuations of ~5 Å to 6 Å. MM/GBSA binding energy analysis indicated 1a to have better predicted binding affinity (−67.820 kcal/mol), which is also better than Talazoparib (−63.734 kcal/mol). DFT calculations showed good electronic properties and in silico ADMET studies also indicated 1a to have good drug-likeness and lower predicted hepatotoxicity and cardiotoxicity risk. Conclusions: These findings identify compound 1a as a promising lead, while compounds 1b and 1c remain viable candidates for further optimization. However, experimental validation is critical to confirm the predicted biological activity and safety profiles. Full article

Coverage optimization of wireless sensor networks (WSNs) faces challenges such as uneven node distribution and vulnerability to coverage blind spots. This paper introduces and improves the Northern Goshawk Optimization (NGO) algorithm: the Logistic chaotic map is adopted to initialize the population for enhanced ergodicity, a nonlinear dynamic weight is introduced to balance global exploration and local exploitation, and a Gaussian–Lévy hybrid mutation mechanism is integrated to strengthen the ability to escape from local optima. Experiments on standard test functions show that the improved algorithm (INGO) can stably approach the theoretical optimal values for both unimodal and multimodal functions. The convergence speed and solution accuracy are significantly superior to those of the original NGO, with a smaller standard deviation and stronger robustness. INGO is applied to the coverage optimization of 2D and 3D WSNs, with coverage rate as the fitness function, and the optimal node deployment coordinates are output through iterative optimization. Simulation results show that INGO achieves a best coverage rate of 98.32% in the 2D scenario, which is 7.72 percentage points higher than the 90.6% of NGO. In the 3D scenario, the best coverage rate reaches 72.32%, 6.78 percentage points higher than the 65.54% of NGO. Meanwhile, INGO yields more uniform node deployment and effectively reduces coverage blind spots. Its convergence curve is smooth and oscillation-free in the late iteration stage, and the stability is significantly better than that of NGO. With proper settings of population size and iteration times, INGO can achieve better coverage performance, providing a reliable technical solution for the efficient deployment of wireless sensor networks in complex environments. Full article

Efficient exploitation of evolutionary knowledge while preserving population diversity remains a central challenge in optimization. Existing knowledge-learning evolutionary algorithms primarily rely on successful experiences, overlooking structural information embedded in failed search attempts. This asymmetric learning limits adaptability and may cause premature convergence in high-dimensional landscapes. To address this issue, a failure-aware bidirectional evolutionary knowledge assimilation framework is developed within the honey badger optimization algorithm. Unsuccessful offspring are treated as negative knowledge carriers and transformed through symmetric adversarial reflection, enabling simultaneous extraction of positive and negative structural information. A time-dependent regulation mechanism dynamically adjusts knowledge assimilation intensity across evolutionary phases to balance exploration and exploitation. In addition, a continuous mutation spectrum transition strategy adaptively integrates Cauchy and Gaussian perturbations, facilitating smooth migration from global exploration to local refinement. Comprehensive experiments conducted on the CEC 2017 benchmark suite across 10, 30, and 50 dimensions validate the proposed framework, establishing a novel failure-aware bidirectional evolutionary learning paradigm for knowledge-driven optimization. The results demonstrate that our method achieves statistically significant and consistent performance improvements over classical baseline algorithms. Furthermore, its robustness and cross-domain adaptability are corroborated through successful application to a real-world constrained engineering problem: welded beam design. Full article

Ignoring the dynamic output recovery of distributed renewable energy sources (dRESs) during distribution network restoration may lead to low voltage in the initial stage, which can cause dRESs and loads to trip and even prevent the recovery of the entire distribution system. To address this issue, this paper proposes a dynamic restoration control framework for distribution networks with dRES integration. In this framework, a topology reconfiguration method is established to capture the time-varying characteristics of dRESs during the restoration process, and a double-time-section power flow calculation strategy is incorporated to verify operational constraints throughout the restoration period. The resulting optimization problem is solved by an improved hybrid Aquila Optimizer–Binary Particle Swarm Optimization algorithm, in which pre-scheme initialization and enhanced Gaussian mutation are introduced to improve convergence and solution quality. Case studies demonstrate that the proposed framework can obtain optimal schemes of topology reconfiguration for dRES-penetrated distribution networks within dozens of seconds while avoiding off-normal voltage and unsuccessful dRES reconnection, thereby enhancing the restoration capability of the distribution system. Full article

A miniaturized variant of the artificial luciferase (ALuc), named picALuc, has been generated through the deletion of N- and C-terminal residues in ALuc. Although picALuc is small and active, questions remain regarding its the structural organization and inter-residue interactions in the protein. Here, combining computational analysis and mutational studies, we show that the E50A mutation in picALuc results in an increased bioluminescence activity of the protein. Specifically, we generated a structural model of picALuc using the available structure of the Gaussia luciferase (GLuc) that revealed a ‘hole’ in the structure due to the deletion of N-terminal α-helices. Gaussian-accelerated molecular dynamics (GaMD) simulation revealed a rapid ‘compaction’ of the picALuc structure during the initial phase of the simulation and a number of residues such as E10, E50, and D94 showed salt bridge interactions. Mutation of the residues E10, E50, and D94 individually to an A revealed increased bioluminescence activity of the E50A mutant, while E10A and D94A mutants showed activities similar to the WT protein in living cells. In vitro assays revealed an increase in the V_max of the E50A mutant, while K_half and thermal stability of the mutant remained unchanged. Further, dynamic cross-correlation and principal component analyses of the GaMD simulation trajectories of the WT and the E50A mutant picALuc revealed altered collective dynamics in the protein. Finally, we developed a protein fragment complementation assay using picALuc that allows for the monitoring protein–protein interactions (PPIs) in live cells. We envisage that the brighter picALuc reported here will find broad applicability in developing bioluminescence-based assays. Full article

With the rapid development of big data and artificial intelligence, agricultural product price forecasting is evolving toward more intelligent and accurate approaches. However, such prices are affected by complex factors including natural conditions, market dynamics, and policy changes, resulting in strong nonlinearity and noise. To address the above challenges and achieve accurate agricultural price forecasts, this study proposes a hybrid framework that integrates a secondary decomposition algorithm with an improved Human Evolutionary Optimization Algorithm specifically tailored for the agricultural domain. The original price series is first decomposed using complete ensemble empirical mode decomposition with adaptive noise, and the high-frequency component is further processed using variational mode decomposition to enhance feature extraction. The improved optimization algorithm introduces Gaussian mutation and adaptive weights to optimize neural network parameters. Experiments on wheat, Chinese cabbage, and broiler chicken demonstrate that the proposed model significantly improves prediction accuracy, with determination coefficients increasing by 6.69, 8.87, and 6.43 percentage points, respectively. The results confirm the model’s effectiveness in reducing noise, capturing multi-scale features, and improving forecasting performance. Full article

Accurate Short-Term Load Forecasting (STLF) is paramount for the stable and economical operation of power systems, particularly in the context of high renewable energy penetration, which exacerbates load volatility and non-stationarity. The prevailing advanced “decomposition–ensemble” paradigm, however, faces two significant challenges when processing non-stationary signals: (1) The performance of Variational Mode Decomposition (VMD) is highly dependent on its hyperparameters (K, α), and traditional meta-heuristic algorithms (e.g., GA, GWO, PSO) are prone to converging to local optima during the optimization process; (2) Deep learning predictors struggle to dynamically weigh the importance of multi-dimensional, heterogeneous features (such as the decomposed Intrinsic Mode Functions (IMFs) and external climatic factors). To address these issues, this paper proposes a novel, adaptive hybrid forecasting framework, namely IRIME-VMD-CDA-LSTNet. Firstly, an Improved Rime Optimization Algorithm (IRIME) integrated with a Gaussian Mutation strategy is proposed. This algorithm adaptively optimizes the VMD hyperparameters by targeting the minimization of average sample entropy, enabling it to effectively escape local optima. Secondly, the optimally decomposed IMFs are combined with climatic features to construct a multi-dimensional information matrix. Finally, this matrix is fed into an innovative Cross-Dimensional Attention (CDA) LSTNet model, which dynamically allocates weights to each feature dimension. Ablation experiments conducted on a real-world dataset from a distribution substation demonstrate that, compared to GA-VMD, GWO-VMD, and PSO-VMD, the proposed IRIME-VMD method achieves a reduction in Root Mean Square Error (RMSE) of up to 18.9%. More importantly, the proposed model effectively mitigates the “prediction lag” phenomenon commonly observed in baseline models, especially during peak load periods. This framework provides a robust and high-accuracy solution for non-stationary load forecasting, holding significant practical value for the operation of modern power systems. Full article

Magnetic localization technology plays a significant role in medical device navigation and human–computer interaction. However, existing localization methods based on local optimization suffer from poor initial solutions and slow convergence. To address the aforementioned challenges, this paper presents a hybrid localization approach, referred to as the Improved Artificial Lemming Algorithm (IALA) Integrated with Levenberg–Marquardt (LM) Optimization. Building upon the Artificial Lemming Algorithm (ALA), the proposed method incorporates an adaptive Gaussian–Lévy hybrid mutation strategy designed to enhance search performance through improved exploration–exploitation dynamics, as quantitatively demonstrated by the diversity-based analysis where IALA maintains higher exploration percentages on multimodal functions while achieving superior optimization results on high-dimensional problems. By introducing a competitive foraging mechanism inspired by the aggressive behavior of the Tasmanian Devil Optimization (TDO) algorithm, it enhances population diversity and search initiative. Furthermore, a time-varying tracking and escape strategy is adopted to improve dynamic optimization performance in complex solution spaces. The proposed method leverages IALA to generate high-quality initial solutions, significantly accelerating the convergence speed and stability of the LM algorithm, thereby improving the overall performance of the permanent magnet localization system. The experimental results show that, using a horizontal test platform of 60 mm × 60 mm with 41 uniformly distributed test points, and acquiring data at vertical heights ranging from 15 mm to 65 mm in 5 mm increments for two distinct orientations of the permanent magnet, the IALA-LM algorithm achieves an average localization success rate of 96.9% over 902 trials, with a mean position error of 1.1 mm and a mean orientation error of 0.17°. Compared with the standard LM algorithm, the proposed IALA-LM algorithm reduces the position error by approximately 66.7% (from 3.3 mm to 1.1 mm) and the orientation error by approximately 94.3% (from 3.0° to 0.17°). Consequently, the proposed method enables high-precision, high-stability, and high-efficiency localization of permanent magnets. It can provide reliable spatial pose estimation support for demanding applications such as miniature implantable or ingestible medical devices (e.g., capsule endoscopy, intramedullary nail fixation, and tumor localization), human–computer interaction, and industrial inspection. Full article

The inactivation of thrombin by antithrombin is highly enhanced by the presence of heparin chains forming “bridges” between the two proteins. X-ray structures for such ternary complexes have been published, but the molecular background of the lower efficiency of smaller heparinoids on thrombin inhibition remains poorly understood. Antithrombin-resistant prothrombin mutants (mutations affecting Arg596 in prothrombin) have been reported that cause severe thrombophilia. Our aim was to study the interactions in the antithrombin–thrombin Michaelis complex both in the presence and the absence of a heparinoid chain and in the presence of pentasaccharide by using molecular dynamics. We also intended to study the complexes of thrombin mutants as well as a known alternative antithrombin conformation at the “hinge” region built using docking. The binding between the proteins was investigated by Gaussian Accelerated Molecular Dynamics (GaMD). We compared the contribution of several amino acids at the binding “exosites” between AT and the wild type and mutant thrombins and between systems containing or not containing a heparinoid. In the docking-based simulations, several of the analyzed amino acid pairs no longer contributed to the interaction, suggesting that the open “hinge” conformation has limited biological relevance. We could identify multiple conformational types using clustering, revealing high flexibility in mutants and systems without heparinoid, probably indicating lower stability. We were also able to detect the allosteric effects of the ligands on the bound thrombin. In summary, we were able to obtain conformations using GaMD that can explain the better protein–protein interactions in the ternary complexes and the impaired AT binding of the thrombin Arg596 mutants at an atomic level. Full article

Target tracking in typical radar applications faces critical challenges in complex environments, including nonlinear dynamics, non-Gaussian noise, and sensor outliers. Current robustness-enhanced approaches remain constrained by empirical kernel tuning and computational trade-offs, failing to achieve balanced noise suppression and real-time efficiency. To address these limitations, this paper proposes the variational Bayesian-based maximum correntropy criterion cubature Kalman filter (VBMCC-CKF), which integrates variational Bayesian inference with CKF to establish a fully adaptive robust filtering framework for nonlinear systems. The core innovation lies in constructing a joint estimation framework of state and kernel size, where the kernel size is modeled as an inverse-gamma distributed random variable. Leveraging the conjugate properties of Gaussian-inverse gamma distributions, the method synchronously optimizes the state posterior distribution and kernel size parameters via variational Bayesian inference, eliminating reliance on manual empirical adjustments inherent to conventional correntropy-based filters. Simulation confirms the robust performance of the VBMCC-CKF framework in both single and multi-target tracking under non-Gaussian noise conditions. For the single-target case, it achieves a reduction in trajectory average root mean square error (Avg-RMSE) by at least 14.33% compared to benchmark methods while maintaining real-time computational efficiency. Integrated with multi-Bernoulli filtering, the method achieves a 40% lower optimal subpattern assignment (OSPA) distance even under 10-fold covariance mutations, accompanied by superior hit rates (HRs) and minimal trajectory position RMSEs in cluttered environments. These results substantiate its precision and adaptability for dynamic tracking scenarios. Full article

The basic Salp Swarm Algorithm (SSA) offers advantages such as a simple structure and few parameters. However, it is prone to falling into local optima and remains inadequate for seed classification tasks that involve hyperparameter optimization of machine learning classifiers such as Support Vector Machines (SVMs). To overcome these limitations, an Enhanced Knowledge-based Salp Swarm Algorithm (EKSSA) is proposed. The EKSSA incorporates three key strategies: Adaptive adjustment mechanisms for parameters $c_1$ and $\alpha$ to better balance exploration and exploitation within the salp population; a Gaussian walk-based position update strategy after the initial update phase, enhancing the global search ability of individuals; and a dynamic mirror learning strategy that expands the search domain through solution mirroring, thereby strengthening local search capability. The proposed algorithm was evaluated on thirty-two CEC benchmark functions, where it demonstrated superior performance compared to eight state-of-the-art algorithms, including Randomized Particle Swarm Optimizer (RPSO), Grey Wolf Optimizer (GWO), Archimedes Optimization Algorithm (AOA), Hybrid Particle Swarm Butterfly Algorithm (HPSBA), Aquila Optimizer (AO), Honey Badger Algorithm (HBA), Salp Swarm Algorithm (SSA), and Sine–Cosine Quantum Salp Swarm Algorithm (SCQSSA). Furthermore, an EKSSA-SVM hybrid classifier was developed for seed classification, achieving higher classification accuracy. Full article

Solar greenhouses are an important component of modern facility agriculture, and the dynamic changes in their internal environment directly affect crop growth and yield. Among these factors, crop transpiration releases water vapor through transpiration, directly altering the indoor humidity balance and forming a dynamic coupling with factors such as temperature and light. The environment of solar greenhouses exhibits highly nonlinear and multivariate coupling characteristics, leading to insufficient prediction accuracy in existing models. However, accurate predictions are crucial for regulating crop growth and yield. However, current mainstream greenhouse environmental prediction models still have obvious limitations when dealing with such complexity: traditional machine learning models and single-variable-driven models have issues such as insufficient accuracy (average MAE is 15–20% higher than in this study) and weak adaptability to nonlinear environmental changes in multi-environmental factor coupling predictions, making it difficult to meet the needs of precision farming. A review of relevant research over the past five years shows that while LSTM-based models perform well in time series prediction, they ignore the spatial correlations between environmental factors. Models incorporating attention mechanisms can capture key variables but suffer from high computational costs. To address these issues, this study proposes a prediction model based on multi-strategy optimization and gradient-boosting (GBDT) algorithms. By introducing a multi-scale feature fusion module, it addresses the accuracy issues in multi-factor coupling prediction. Additionally, it employs a lightweight network design to balance prediction performance and computational efficiency, filling the gap in existing research applications under complex greenhouse environments. The model optimizes data preprocessing and model parameters through Sobol sequence initialization, adaptive t-distribution perturbation strategies, and Gaussian–Cauchy mixture mutation strategies and combines CatBoost for modeling to enhance prediction accuracy. Experimental results show that the MSCSO–CatBoost model performs excellently in temperature prediction, with the mean absolute error (MAE) and root mean square error (RMSE) reduced by 22.5% (2.34 °C) and 24.4% (3.12 °C), respectively, and the coefficient of determination (R²) improved to 0.91, significantly outperforming traditional regression methods and combinations of other optimization algorithms. Additionally, the model demonstrates good generalization capability in predicting multiple environmental variables such as temperature, humidity, and light intensity, adapting to environmental fluctuations under different climatic conditions. This study confirms that combining multi-strategy optimization with gradient-boosting algorithms can significantly improve the prediction accuracy of solar greenhouse environments, providing reliable support for precision agricultural management. Future research could further explore the model’s adaptive optimization in complex climatic regions. Full article