Search Results (2,474)

The Dung Beetle Optimization Algorithm (DBO) is characterized by its great convergence accuracy and quick convergence speed. However, like other swarm intelligent optimization algorithms, it also has the disadvantages of having an unbalanced ability to explore the world and to use local resources, as well as being prone to settling into local optimal search in the latter stages of optimization. In order to address these issues, this research suggests a multi-strategy fusion dung beetle optimization method (MSFDBO). To enhance the quality of the first solution, the refractive reverse learning technique expands the algorithm search space in the first stage. The algorithm’s accuracy is increased by adding an adaptive curve to control the dung beetle population size and prevent it from reaching a local optimum. In order to improve and balance local exploitation and global exploration, respectively, a triangle wandering strategy and a fusion subtractive averaging optimizer were later added to Rolling Dung Beetle and Breeding Dung Beetle. Individual beetles will congregate at the current optimal position, which is near the optimal value, during the last optimization stage of the MSFDBO; however, the current optimal value could not be the global optimal value. Thus, to variationally perturb the global optimal solution (so that it leaps out of the local optimal solution in the final optimization stage of the MSFDBO) and to enhance algorithmic performance (generally and specifically, in the effect of optimizing the search), an adaptive Gaussian–Cauchy hybrid variational perturbation factor is introduced. Using the CEC2017 benchmark function, the MSFDBO’s performance is verified by comparing it to seven different intelligence optimization algorithms. The MSFDBO ranks first in terms of average performance. The MSFDBO can lower the labor and production expenses associated with welding beam and reducer design after testing two engineering application challenges. When it comes to lowering manufacturing costs and overall weight, the MSFDBO outperforms other swarm intelligence optimization methods. Full article

The Internet of Vehicles (IoV), a burgeoning technology, merges advancements in the internet, vehicle electronics, and wireless communications to foster intelligent vehicle interactions, thereby enhancing the efficiency and safety of transportation systems. Nonetheless, the continual and high-frequency communications among vehicles, coupled with regional limitations in system capacity, precipitate significant challenges in allocating wireless resources for vehicular networks. In addressing these challenges, this study formulates the resource allocation issue as a multi-agent deep reinforcement learning scenario and introduces a novel multi-agent actor-critic framework. This framework incorporates a prioritized experience replay mechanism focused on distributed execution, which facilitates decentralized computing by structuring the training processes and defining specific reward functions, thus optimizing resource allocation. Furthermore, the framework prioritizes empirical data during the training phase based on the temporal difference error (TD error), selectively updating the network with high-priority data at each sampling point. This strategy not only accelerates model convergence but also enhances the learning efficacy. The empirical validations confirm that our algorithm augments the total capacity of vehicle-to-infrastructure (V2I) links by 9.36% and the success rate of vehicle-to-vehicle (V2V) transmissions by 6.74% compared with a benchmark algorithm. Full article

The integration of pedestrian movement analysis with Unmanned Aerial Vehicle (UAV)-based remote sensing enables comprehensive monitoring and a deeper understanding of human dynamics within urban environments, thereby facilitating the optimization of urban planning and public safety strategies. However, human behavior inherently involves uncertainty, particularly in the prediction of pedestrian trajectories. A major challenge lies in modeling the multimodal nature of these trajectories, including varying paths and targets. Current methods often lack a theoretical framework capable of fully addressing the multimodal uncertainty inherent in trajectory predictions. To tackle this, we propose a novel approach that models uncertainty from two distinct perspectives: (1) the behavioral factor, which reflects historical motion patterns of pedestrians, and (2) the stochastic factor, which accounts for the inherent randomness in future trajectories. To this end, we introduce a global framework named LSN-GTDA, which consists of a pair of symmetrical U-Net networks. This framework symmetrically distributes the semantic segmentation and trajectory prediction modules, enhancing the overall functionality of the network. Additionally, we propose a novel thermal diffusion process, based on signal and system theory, which manages uncertainty by utilizing the full response and providing interpretability to the network. Experimental results demonstrate that the LSN-GTDA method outperforms state-of-the-art approaches on benchmark datasets such as SDD and ETH-UCY, validating its effectiveness in addressing the multimodal uncertainty of pedestrian trajectory prediction. Full article

Many real-world expensive industrial and engineering multi-objective optimization problems (MOPs) are driven by historical, experimental, or simulation data. In such scenarios, due to the expensive cost and time required, we are only left with a small amount of labeled data to perform the optimization. These offline data-driven MOPs are usually solved by multi-objective evolutionary algorithms (MOEAs) with the help of surrogate models constructed from offline historical data. The key challenge in developing these data-driven MOEAs is that they have to replace multiple conflicting fitness functions by approximating these objective functions, which may produce cumulative approximation errors and misguide the search. In order to build a reliable surrogate model from a small amount of multi-output offline data and solve the DDMOPs, we have proposed an adaptive model selection method with a reliable individual-based model management-driven MOEA. The proposed algorithm dynamically selects between DNN and XGBoost by comparing their k-fold cross-validation MAE error, which can capture the true generalization ability of the surrogates on unseen data. Then, the selected surrogate is updated with a reliable individual selection strategy, where the individual who is closest, both in the decision and objective space, to the most preferred solution among labeled offline data is chosen. As a result, these two strategies guide the underlying MOEA to the Pareto optimal solutions. The empirical results of the ZDT and DTLZ benchmark test suite validate the use of the three state-of-the-art offline DDMOEAs, showing that our algorithm is able to achieve highly competitive results in terms of convergence and diversity for 2–3 objectives. Finally, our algorithm is applied to an offline data-driven multi-objective problem—transonic airfoil (RAE 2822) shape optimization— to validate its efficiency on real-world DDMOPs. Full article

Despite rapid progress in UAV-based infrared vehicle detection, achieving reliable target recognition remains challenging due to dynamic viewpoint variations and platform instability. The inherent limitations of infrared imaging, particularly low contrast ratios and thermal crossover effects, significantly compromise detection accuracy. Moreover, the computational constraints of edge computing platforms pose a fundamental challenge in balancing real-time processing requirements with detection performance. Here, we present MonoSeg, a novel instance segmentation framework optimized for UAV perspective infrared vehicle detection. Our approach introduces three key innovations: (1) the Ghost Feature Bottle Cross module (GFBC), which enhances backbone feature extraction efficiency while significantly reducing computational over-head; (2) the Scale Feature Recombination module (SFR), which optimizes feature selection in the Neck stage through adaptive multi-scale fusion; and (3) Comprehensive Loss function that enforces precise instance boundary delineation. Extensive experimental evaluation on bench-mark datasets demonstrates that MonoSeg achieves state-of-the-art performance across standard metrics, including Box mAP and Mask mAP, while maintaining substantially lower computational requirements compared to existing methods. Full article

Sustainable waste management for orange peel waste is a global concern that presents a concomitant opportunity. In this study, a combined process was developed to optimize the simultaneous recovery of pectin, essential oils, and sugars from industrial orange peel waste. The sequential recovery process was used as a benchmark, while a one-pot combined process was optimized through the design of the experiments. A multi-objective desirability function was computed to maximize process performance while balancing opposing optimal conditions. The aim was to find a model able to confidently predict yields while reducing the process environmental footprint, potentially giving the necessary multi-product flexibility in modern biorefining. As a result, the combined process under optimal conditions, liquid-to-solid ratio of 2.5, pH value of 3.7, and residence time of 130 min, yielded 0.52% of essential oils and 11% of pectin on a dry basis. The environmental factor 18 is relevant to the fine chemicals industry, which is the target sector of this study. Finally, the process mass balance was calculated, demonstrating the opportunity to further enhance process environmental sustainability and efficiency by upgrading the resulting solid fraction. Full article

Predicting the relative solvent accessibility (RSA) of a protein is critical to understanding its 3D structure and biological function. RSA prediction, especially when homology transfer cannot provide information about a protein’s structure, is a significant step toward addressing the protein structure prediction challenge. Today, deep learning is arguably the most powerful method for predicting RSA and other structural features of proteins. In particular, recent breakthroughs in deep learning—driven by the integration of natural language processing (NLP) algorithms—have significantly advanced the field of protein research. Inspired by the remarkable success of NLP techniques, this study leverages pre-trained language models (PLMs) to enhance RSA prediction. We present a deep neural network architecture based on a combination of bidirectional recurrent neural networks and convolutional layers that can analyze long-range interactions within protein sequences and predict protein RSA using ESM-2 encoding. The final predictor, PaleAle 6.0, predicts RSA in real values as well as two-state (exposure threshold of 25%) and four-state (exposure thresholds of 4%, 25%, and 50%) discrete classifications. On the 2022 test set dataset, PaleAle 6.0 achieved over 82% accuracy for two-state RSA (RSA_2C) and 59.75% accuracy for four-state RSA (RSA_4C), with a Pearson correlation coefficient (PCC) of 77.88 for real-value RSA prediction. When evaluated on the more challenging 2024 test set, PaleAle 6.0 maintained a strong performance, achieving 79.74% accuracy in the two-state prediction and 55.30% accuracy in the four-state prediction, with a PCC of 73.08 for real-value predictions, outperforming all previously benchmarked predictors. Full article

The incorporation of machine learning (ML) into healthcare information systems (IS) has transformed multi-objective healthcare management by improving patient monitoring, diagnostic accuracy, and treatment optimization. Notwithstanding its revolutionizing capacity, the area lacks a systematic understanding of how these models are divided and analyzed, leaving gaps in normalization and benchmarking. The present research usually overlooks holistic models for comparing ML-enabled ISs, significantly considering pivotal function criteria like accuracy, precision, sensitivity, and specificity. To address these gaps, we conducted a broad exploration of 306 state-of-the-art papers to present a novel taxonomy of ML-enabled IS for multi-objective healthcare management. We categorized these studies into six key areas, namely diagnostic systems, treatment-planning systems, patient monitoring systems, resource allocation systems, preventive healthcare systems, and hybrid systems. Each category was analyzed depending on significant variables, uncovering that adaptability is the most effective parameter throughout all models. In addition, the majority of papers were published in 2022 and 2023, with MDPI as the leading publisher and Python as the most prevalent programming language. This extensive synthesis not only bridges the present gaps but also proposes actionable insights for improving ML-powered IS in healthcare management. Full article

Accurate forecasting of multivariate traffic flow poses formidable challenges, primarily due to the ever-evolving spatio-temporal dynamics and intricate spatial heterogeneity, where the heterogeneity signifies that the correlations among locations are not just related to distance. However, few of the existing models are designed to fully and effectively integrate the above-mentioned features. To address these complexities head-on, this paper introduces a novel solution in the form of Dynamic Pattern-aware Spatio-Temporal Convolutional Networks (DPSTCN). Temporally, the model introduces a novel temporal module, containing a temporal convolutional network (TCN) enriched with an enhanced pattern-aware self-attention mechanism, adept at capturing temporal patterns, including local/global dependencies, dynamics, and periodicity. Spatially, the model constructs static and dynamic pattern-aware convolutions, leveraging geographical and area-functional information to effectively capture intricate spatial patterns, including dynamics and heterogeneity. Evaluations across four distinct traffic benchmark datasets consistently demonstrate the state-of-the-art capacity of our model compared to the existing eleven approaches, especially great improvements in RMSE (Root Mean Squared Error) value. Full article

Buckling-Restrained Braces (BRBs) are widely utilized in structures as an anti-seismic system to enhance performance against lateral excitations. While BRBs are designed to yield symmetrically under both tension and compression without significant buckling, their effectiveness is often limited to moderate seismic events. During high-intensity earthquakes, repetitive yielding can lead to core failure, resulting in the loss of BRB functionality and potentially causing structural collapse. This study proposes an innovative design for BRBs to improve energy dissipation capacity under severe seismic activity. The new design incorporates Ultra-High-Performance Fiber-Reinforced Concrete (UHPFRC) filler and hyper-elastic rubber components as primary load-bearing elements. Through extensive testing and simulation, the proposed Rubber Buckling-Restrained Brace (RBRB) was developed and manufactured by integrating hyper-elastic rubber between the concrete and core to enhance the device’s strength. Additionally, a prototype of the conventional BRB device was fabricated to serve as a benchmark for evaluating the performance of the RBRB. Experimental testing of both the conventional BRB and the proposed RBRB prototypes was conducted using a heavy-duty dynamic actuator to assess the RBRB’s performance under applied loads. Based on the experimental results, an analytical model of the proposed RBRB was formulated for use in finite element modeling and analysis. Furthermore, a specialized seismic design procedure for structures equipped with the RBRB was developed, according to the performance-based design method. This procedure was applied to the design of a seven-story steel structure, and the impact of the RBRB on the seismic response of the structure was investigated through finite element simulations. The analysis results demonstrated that the RBRB significantly improves the loading capacity and energy dissipation capabilities of structures, thereby enhancing their overall performance against earthquake excitations. Full article

The grey wolf optimization (GWO) algorithm is a simple and effective meta-heuristic algorithm that mimics the leadership of grey wolves and the social behavior of wolves in nature. However, the updating of GWO population positions only relies on the guidance of $\alpha$-wolf, $\beta$-wolf, and $\delta$-wolf, and individuals are updated with equal weights. This results in the GWO search process being unable to utilize the knowledge of superior wolves better. Therefore, in this study, we propose for the first time an attention mechanism-based GWO (AtGWO). Firstly, when each position is updated, the attention strategy can adaptively assign the weight of the corresponding leader wolf to improve the global exploration ability. Second, with the introduction of omega-wolves, each position update is not only guided by the three leader wolves but also learns from their current optimal values. Finally, a hyperbolic tangent nonlinear function is used to control the convergence factor to better balance exploration and exploitation. To validate its effectiveness, AtGWO is compared with the latest GWO variant with other popular algorithms on the CEC-2014 (dim 30, 50) and CEC-2017 (dim 30, 50, 100) benchmark function sets. The experimental results indicate that AtGWO outperforms the GWO-related variants almost all the time in terms of mean, variance, and best value, which indicates its superior ability and robustness to find optimal solutions. And it is also competitive when compared to other algorithms in multimodal functions. AtGWO outperforms the comparison algorithms in terms of the mean and best value in six real-world engineering optimization problems. Full article

Trajectory prediction is a critical component of autonomous driving, intelligent transportation systems, and human–robot interactions, particularly in complex environments like intersections, where diverse road constraints and multi-agent interactions significantly increase the risk of collisions. To address these challenges, a Heterogeneous Risk-Aware Graph Encoder with Continuous Parameterized Decoder for Trajectory Prediction (HRGC) is proposed. The architecture integrates a heterogeneous risk-aware local graph attention encoder, a low-rank temporal transformer, a fusion lane and global interaction encoder layer, and a continuous parameterized decoder. First, a heterogeneous risk-aware edge-enhanced local attention encoder is proposed, which enhances edge features using risk metrics, constructs graph structures through graph optimization and spectral clustering, maps these enhanced edge features to corresponding graph structure indices, and enriches node features with local agent-to-agent attention. Risk-aware edge attention is aggregated to update node features, capturing spatial and collision-aware representations, embedding crucial risk information into agents’ features. Next, the low-rank temporal transformer is employed to reduce computational complexity while preserving accuracy. By modeling agent-to-lane relationships, it captures critical map context, enhancing the understanding of agent behavior. Global interaction further refines node-to-node interactions via attention mechanisms, integrating risk and spatial information for improved trajectory encoding. Finally, a trajectory decoder utilizes the aforementioned encoder to generate control points for continuous parameterized curves. These control points are multiplied by dynamically adjusted basis functions, which are determined by an adaptive knot vector that adjusts based on velocity and curvature. This mechanism ensures precise local control and the superior handling of sharp turns and speed variations, resulting in more accurate real-time predictions in complex scenarios. The HRGC network achieves superior performance on the Argoverse 1 benchmark, outperforming state-of-the-art methods in complex urban intersections. Full article

To solve the coverage problem caused by the random deployment of wireless sensor network nodes in the forest fire-monitoring system, a modified marine predator algorithm (MMPA) is proposed. Four modifications have been made based on the standard marine predator algorithm (MPA). Firstly, tent mapping is integrated into the initialization step to improve the searching ability of the early stage. Secondly, a hybrid search strategy is used to enhance the ability to search and jump out of local optimum. Thirdly, the golden sine guiding mechanism is applied to accelerate the convergence of the algorithm. Finally, a stage-adjustment strategy is proposed to make the transition of stages more smoothly. Six specific test functions chosen from the CEC2017 function and the benchmark function are used to evaluate the performance of MMPA. It shows that this modified algorithm has good optimization capability and stability compared to MPA, grey wolf optimizer, sine cosine algorithm, and sea horse optimizer. The results of coverage tests show that MMPA has a better uniformity of node distribution compared to MPA. The average coverage rates of MMPA are the highest compared to the commonly used metaheuristic-based algorithms, which are 91.8% in scenario 1, 95.98% in scenario 2, and 93.88% in scenario 3, respectively. This demonstrates the superiority of this proposed algorithm in coverage optimization of the wireless sensor network. Full article

This study presents a new approach to optimize the dynamic evacuation process through a dynamic traffic assignment model formulated using mixed-integer linear programming (MILP). The model approximates the travel time for evacuee groups with a piecewise linear function that accounts for variations in travel time due to load-dependent factors. Significant delays are transferred to subsequent groups to simulate delay propagation. The primary objective is to minimize the network clearance time—the total time required for the last group of evacuees to reach safety from the start of the evacuation. Given the model’s computational intensity, a simplified version is introduced for comparison. Both the original and simplified models are tested on small networks and benchmarked against the Cell Transmission Model, a well-regarded method in dynamic traffic assignment literature. Additional objectives, including average travel time and average evacuation time, are explored. A sensitivity analysis is conducted to assess how varying the number of evacuee groups impacts model outcomes. Full article

Classic enhanced self-correcting battery equivalent models require proper model parameters and initial conditions such as the initial state of charge for its unbiased functioning. Obtaining parameters is often conducted by optimization using evolutionary algorithms. Obtaining the initial state of charge is often conducted by measurements, which can be burdensome in practice. Incorrect initial conditions can introduce bias, leading to long-term drift and inaccurate state of charge readings. To address this, we propose two simple and efficient equivalent model frameworks that are optimized by a genetic algorithm and are able to determine the initial conditions autonomously. The first framework applies the feedback loop mechanism that gradually with time corrects the externally given initial condition that is originally a biased arbitrary value within a certain domain. The second framework applies the genetic algorithm to search for an unbiased estimate of the initial condition. Long-term experiments have demonstrated that these frameworks do not deviate from controlled benchmarks with known initial conditions. Additionally, our experiments have shown that all implemented models significantly outperformed the well-known ampere-hour coulomb counter integration method, which is prone to drift over time and the extended Kalman filter, that acted with bias. Full article