Search Results (652)

Neural networks (NNs) achieve breakthroughs in computer vision and natural language processing,yet their “black box” nature persists. Traditional methods prioritise parameter optimisation and loss design, overlooking NNs’ fundamental structure as topologically organised nonlinear computational systems. This work proposes a complex network theory framework decoding structure–function coupling by mapping convolutional layers, fully connected layers, and Dropout modules into graph representations. To overcome limitations of heuristic compression techniques, we develop a topology-sensitive adaptive pruning algorithm that evaluates critical paths via node strength centrality, preserving structural–functional integrity. On CIFAR-10, our method achieves 55.5% parameter reduction with only 7.8% accuracy degradation—significantly outperforming traditional approaches. Crucially, retrained pruned networks exceed original model accuracy by up to 2.63%, demonstrating that topology optimisation unlocks latent model potential. This research establishes a paradigm shift from empirical to topologically rationalised neural architecture design, providing theoretical foundations for deep learning optimisation dynamics. Full article

Multimodal object detection leverages the complementary characteristics of visible (RGB) and infrared (IR) imagery, making it well-suited for challenging scenarios such as low illumination, occlusion, and complex backgrounds. However, most existing fusion-based methods rely on static or heuristic strategies, limiting their adaptability to dynamic environments. To address this limitation, we propose CLSANet, a cognitive learning-based self-adaptive network that enhances detection performance by dynamically selecting and integrating modality-specific features. CLSANet consists of three key modules: (1) a Dominant Modality Identification Module that selects the most informative modality based on global scene analysis; (2) a Modality Enhancement Module that disentangles and strengthens shared and modality-specific representations; and (3) a Self-Adaptive Fusion Module that adjusts fusion weights spatially according to local scene complexity. Compared to existing methods, CLSANet achieves state-of-the-art detection performance with significantly fewer parameters and lower computational cost. Ablation studies further demonstrate the individual effectiveness of each module under different environmental conditions, particularly in low-light and occluded scenes. CLSANet offers a compact, interpretable, and practical solution for multimodal object detection in resource-constrained settings. Full article

Unmanned Aerial Vehicles (UAVs) face significant challenges in global path planning within complex terrains, as traditional algorithms (e.g., A*, PSO, APF) struggle to balance computational efficiency, path optimality, and safety. This study proposes a Voronoi–A* fusion algorithm, combining Voronoi-vertex-based rapid trajectory generation with A* supplementary expansion for enhanced performance. First, an adaptive DEM layering strategy divides the terrain into horizontal planes based on obstacle density, reducing computational complexity while preserving 3D flexibility. The Voronoi vertices within each layer serve as a sparse waypoint network, with greedy heuristic prioritizing vertices that ensure safety margins, directional coherence, and goal proximity. For unresolved segments, A* performs localized searches to ensure complete connectivity. Finally, a line-segment interpolation search further optimizes the path to minimize both length and turning maneuvers. Simulations in mountainous environments demonstrate superior performance over traditional methods in terms of path planning success rates, path optimality, and computation. Our framework excels in real-time scenarios, such as disaster rescue and logistics, although it assumes static environments and trades slight path elongation for robustness. Future research should integrate dynamic obstacle avoidance and weather impact analysis to enhance adaptability in real-world conditions. Full article

The growing adoption of serverless computing has highlighted critical challenges in resource allocation, policy fairness, and energy efficiency within multitenancy cloud environments. This research proposes a reinforcement learning (RL)-based adaptive resource allocation framework to address these issues. The framework models resource allocation as a Markov Decision Process (MDP) with dynamic states that include latency, resource utilization, and energy consumption. A reward function is designed to optimize the throughput, latency, and energy efficiency while ensuring fairness among tenants. The proposed model demonstrates significant improvements over heuristic approaches, achieving a 50% reduction in latency (from 250 ms to 120 ms), a 38.9% increase in throughput (from 180 tasks/s to 250 tasks/s), and a 35% improvement in energy efficiency. Additionally, the model reduces operational costs by 40%, achieves SLA compliance rates above 98%, and enhances fairness by lowering the Gini coefficient from 0.25 to 0.10. Under burst loads, the system maintains a service level objective success rate of 94% with a time to scale of 6 s. These results underscore the potential of RL-based solutions for dynamic workload management, paving the way for more scalable, cost-effective, and sustainable serverless multitenancy systems. Full article

Superb Fairy-wren Optimization Algorithm (SFOA) is an animal-based meta-heuristic algorithm derived from Fairy-wren’s behavior of growing, feeding, and avoiding natural enemies. The SFOA has some shortcomings when facing complex environments. Its switching mechanism is not enough to adapt to complex optimization problems, and it faces a weakening of population diversity in the late stage of optimization, leading to a higher possibility of falling into local optima. In addition, its global search ability needs to be improved. To address the above deficiencies, this paper proposes an Adaptive Superb Fairy-wren Optimization Algorithm (ASFOA). To assess the ability of the proposed ASFOA, three groups of experiments are conducted in this paper. Firstly, the effectiveness of the proposed improved strategies is checked on the CEC2018 test set. Second, the ASFOA is compared with eight classical/highly cited/newly proposed metaheuristics on the CEC2018 test set, in which the ASFOA performed the best overall, with average rankings of 1.621, 1.138, 1.483, and 1.966 in the four-dimensional cases, respectively. Then the convergence and robustness of ASFOA is verified on the CEC2022 test set. The experimental results indicate that the proposed ASFOA is a competitive metaheuristic algorithm variant with excellent performance in terms of convergence and distribution of solutions. In addition, we further validate the ability of ASFOA to solve real optimization problems. The average ranking of the proposed ASFOA on 10 engineering constrained optimization problems is 1.500. In summary, ASFOA is a promising variant of metaheuristic algorithms. Full article

In modern vehicles, Autonomous Driving Systems (ADSs) are designed to operate partially or fully without human intervention. The ADS pipeline comprises multiple layers, including sensors, perception, localization, mapping, path planning, and control. The Robot Operating System (ROS) is a widely adopted framework that supports the modular development and integration of these layers. Among them, the path-planning and control layers remain particularly challenging due to several limitations. Classical path planners often struggle with non-smooth trajectories and high computational demands. Meta-heuristic optimization algorithms have demonstrated strong theoretical potential in path planning; however, they are rarely implemented in real-time ROS-based systems due to integration challenges. Similarly, traditional PID controllers require manual tuning and are unable to adapt to system disturbances. This paper proposes a ROS-based ADS architecture composed of eight integrated nodes, designed to address these limitations. The path-planning node leverages a meta-heuristic optimization framework with a cost function that evaluates path feasibility using occupancy grids from the Hector SLAM and obstacle clusters detected through the DBSCAN algorithm. A dynamic goal-allocation strategy is introduced based on the LiDAR range and spatial boundaries to enhance planning flexibility. In the control layer, a modified Pure Pursuit algorithm is employed to translate target positions into velocity commands based on the drift angle. Additionally, an adaptive PID controller is tuned in real time using the Differential Evolution (DE) algorithm, ensuring robust speed regulation in the presence of external disturbances. The proposed system is practically validated on a four-wheel differential drive robot across six scenarios. Experimental results demonstrate that the proposed planner significantly outperforms state-of-the-art methods, ranking first in the Friedman test with a significance level less than 0.05, confirming the effectiveness of the proposed architecture. Full article

This paper addresses text simplification task for Kazakh, a morphologically rich, low-resource language, by introducing KazSim, an instruction-tuned model built on multilingual large language models (LLMs). First, we develop a heuristic pipeline to identify complex Kazakh sentences, manually validating its performance on 400 examples and comparing it against a purely LLM-based selection method; we then use this pipeline to assemble a parallel corpus of 8709 complex–simple pairs via LLM augmentation. For the simplification task, we benchmark KazSim against standard Seq2Seq systems, domain-adapted Kazakh LLMs, and zero-shot instruction-following models. On an automatically constructed test set, KazSim (Llama-3.3-70B) achieves BLEU 33.50, SARI 56.38, and F1 87.56 with a length ratio of 0.98, outperforming all baselines. We also explore prompt language (English vs. Kazakh) and conduct human evaluation with three native speakers: KazSim scores 4.08 for fluency, 4.09 for meaning preservation, and 4.42 for simplicity—significantly above GPT-4o-mini. Error analysis shows that remaining failures cluster into tone change, tense change, and semantic drift, reflecting Kazakh’s agglutinative morphology and flexible syntax. Full article

With the rapid development of smart devices and the Internet of Things (IoT), the explosive growth of data has placed increasingly higher demands on real-time processing and intelligent decision making. Cloud-edge collaborative computing has emerged as a mainstream architecture to address these challenges. However, in sky-ground integrated systems, the limited computing capacity of edge devices and the inconsistency between cloud-side fusion results and edge-side detection outputs significantly undermine the reliability of edge inference. To overcome these issues, this paper proposes a cloud-edge collaborative model adaptation framework that integrates deep reinforcement learning via Deep Q-Networks (DQN) with local feature transfer. The framework enables category-level dynamic decision making, allowing for selective migration of classification head parameters to achieve on-demand adaptive optimization of the edge model and enhance consistency between cloud and edge results. Extensive experiments conducted on a large-scale multi-view remote sensing aircraft detection dataset demonstrate that the proposed method significantly improves cloud-edge consistency. The detection consistency rate reaches 90%, with some scenarios approaching 100%. Ablation studies further validate the necessity of the DQN-based decision strategy, which clearly outperforms static heuristics. In the model adaptation comparison, the proposed method improves the detection precision of the A321 category from 70.30% to 71.00% and the average precision (AP) from 53.66% to 53.71%. For the A330 category, the precision increases from 32.26% to 39.62%, indicating strong adaptability across different target types. This study offers a novel and effective solution for cloud-edge model adaptation under resource-constrained conditions, enhancing both the consistency of cloud-edge fusion and the robustness of edge-side intelligent inference. Full article

Emergency material scheduling (EMS) is a core component of post-disaster emergency response, with its efficiency directly impacting rescue effectiveness and the satisfaction of affected populations. However, due to severe road damage, limited availability of resources, and logistical challenges after disasters, current EMS practices often suffer from uneven resource distribution. To address these issues, this paper proposes a priority-based, multi-stage EMS approach with drone coordination. First, we construct a three-level EMS network “storage warehouses–transit centers–disaster areas” by integrating the advantages of large-scale transportation via trains and the flexible delivery capabilities of drones. Second, considering multiple constraints, such as the priority level of disaster areas, drone flight range, transport capacity, and inventory capacities at each node, we formulate a bilevel mixed-integer nonlinear programming model. Third, given the NP-hard nature of the problem, we design a hybrid algorithm—the Tabu Genetic Algorithm combined with Branch and Bound (TGA-BB), which integrates the global search capability of genetic algorithms, the precise solution mechanism of branch and bound, and the local search avoidance features of Tabu search. A stage-adjustment operator is also introduced to better adapt the algorithm to multi-stage scheduling requirements. Finally, we designed eight instances of varying scales to systematically evaluate the performance of the stage-adjustment operator and the Tabu search mechanism within TGA-BB. Comparative experiments were conducted against several traditional heuristic algorithms. The experimental results show that TGA-BB outperformed the other algorithms across all eight test cases, in terms of both average response time and average runtime. Specifically, in Instance 7, TGA-BB reduced the average response time by approximately 52.37% compared to TGA-Particle Swarm Optimization (TGA-PSO), and in Instance 2, it shortened the average runtime by about 97.95% compared to TGA-Simulated Annealing (TGA-SA).These results fully validate the superior solution accuracy and computational efficiency of TGA-BB in drone-coordinated, multi-stage EMS. Full article

The aim of this study is to analyze the factors that influence consumer referents or reference points and their interaction during the decision-making process, along with the principles of prospect theory in the metaverse with market and retail examples. We conducted an integrative literature review. Consumers’ preference for reference points is determined and structured during the buying process, which can be affected by potential signals and biased decisions. To guide consumers’ shopping experiences and purchasing behavior in the most effective way, marketers and organizations must investigate the factors that influence consumer reference points beyond physical or tangible attributes. Businesses must be adaptable and adapt their strategies to changing consumer preferences based on reference points. Our findings can advance discussions about how reference points are being used in the market by using consumer decision-making claims in the discursive construction of the metaverse. By comprehending this, developers can create better experiences and assist users in navigating virtual risks. Our research aids us in better comprehending the influence of referents on consumer purchasing decisions in the marketing communications field. Numerous opportunities for academic research into consumer reference points have arisen, in which individuals as digital consumers are influenced by the same biases and heuristics that guide their behavior in reality. Full article

This article investigates the institutional and informational foundations of water governance in Southern Europe amid escalating climate stress. Focusing on Portugal, Spain, Italy, and Greece, it develops a multi-level analytical framework to explore how information asymmetries and governance fragmentation undermine coordinated responses to water scarcity. Integrating theories of information economics, polycentric governance, and critical institutionalism, this study applies a stylized economic model and comparative institutional analysis to assess how agents—such as farmers, utilities, regulators, and civil society—respond to varying incentives, data access, and coordination structures. Using secondary data, normalized indicators, and scenario-based simulations, the model identifies three key structural parameters—institutional friction (θ_i), information cost (β_i), and incentive strength (α_i)—as levers for governance reform. The simulations are stylized and not empirically calibrated, serving as heuristic tools rather than predictive forecasts. The results show that isolated interventions yield limited improvements, while combined reforms significantly enhance both equity and effectiveness. Climate stress simulations further reveal stark differences in institutional resilience, with Greece and Italy showing systemic fragility and Portugal emerging as comparatively robust. This study contributes a flexible, policy-relevant tool for diagnosing governance capacity and informing reform strategies while also underscoring the need for integrated, equity-oriented approaches to adaptive water governance. Full article

To address the modeling complexity and multi-objective collaborative optimization challenges in multi-depot and multiple unmanned aerial vehicle (UAV) delivery task planning, this paper proposes a bi-layer planning framework, which comprehensively considers resource constraints, multi-depot coordination, and the coupling characteristics of path execution. The novelty of this work lies in the seamless integration of an enhanced genetic algorithm and tailored swarm optimization within a unified two-tier architecture. The upper layer tackles the task assignment problem by formulating a multi-objective optimization model aimed at minimizing economic costs, delivery delays, and the number of UAVs deployed. The Enhanced Non-Dominated Sorting Genetic Algorithm II (ENSGA-II) is developed, incorporating heuristic initialization, goal-oriented search operators, an adaptive mutation mechanism, and a staged evolution control strategy to improve solution feasibility and distribution quality. The main contributions are threefold: (1) a novel ENSGA-II design for efficient and well-distributed task allocation; (2) an improved PSO-based path planner with chaotic initialization and adaptive parameters; and (3) comprehensive validation demonstrating substantial gains over baseline methods. The lower layer addresses the path planning problem by establishing a multi-objective model that considers path length, flight risk, and altitude variation. An improved particle swarm optimization (PSO) algorithm is proposed by integrating chaotic initialization, linearly adjusted acceleration coefficients and maximum velocity, a stochastic disturbance-based position update mechanism, and an adaptively tuned inertia weight to enhance algorithmic performance and path generation quality. Simulation results under typical task scenarios demonstrate that the proposed model achieves an average reduction of 47.8% in economic costs and 71.4% in UAV deployment quantity while significantly reducing delivery window violations. The framework exhibits excellent capability in multi-objective collaborative optimization. The ENSGA-II algorithm outperforms baseline algorithms significantly across performance metrics, achieving a hypervolume (HV) value of 1.0771 (improving by 72.35% to 109.82%) and an average inverted generational distance (IGD) of 0.0295, markedly better than those of comparison algorithms (ranging from 0.0893 to 0.2714). The algorithm also demonstrates overwhelming superiority in the C-metric, indicating outstanding global optimization capability in terms of distribution, convergence, and the diversity of the solution set. Moreover, the proposed framework and algorithm are both effective and feasible, offering a novel approach to low-altitude urban logistics delivery problems. Full article

Path planning for picking safflowers is a key component in ensuring the efficient operation of robotic safflower-picking systems. However, existing single-arm picking devices have become a bottleneck due to their limited operating range, and a breakthrough in multi-arm cooperative picking is urgently needed. To address the issue of inadequate adaptability in current path planning strategies for dual-arm systems, this paper proposes a novel path planning method for dual-arm picking (LTSACO). The technique centers on a dynamic-weight heuristic strategy and achieves optimization through the following steps: first, the K-means clustering algorithm divides the target area; second, the heuristic mechanism of the Ant Colony Optimization (ACO) algorithm is improved by dynamically adjusting the weight factor of the state transition probability, thereby enhancing the diversity of path selection; third, a 2-OPT local search strategy eliminates path crossings through neighborhood search; finally, a cubic Bézier curve heuristically smooths and optimizes the picking trajectory, ensuring the continuity of the trajectory’s curvature. Experimental results show that the length of the parallelogram trajectory, after smoothing with the Bézier curve, is reduced by 20.52% compared to the gantry trajectory. In terms of average picking time, the LTSACO algorithm reduces the time by 2.00%, 2.60%, and 5.60% compared to DCACO, IACO, and the traditional ACO algorithm, respectively. In conclusion, the LTSACO algorithm demonstrates high efficiency and strong robustness, providing an effective optimization solution for multi-arm cooperative picking and significantly contributing to the advancement of multi-arm robotic picking systems. Full article

Emergency communication networks play a crucial role in disaster relief operations. Current automated deployment strategies based on rule-driven or heuristic algorithms struggle to adapt to the dynamic and heterogeneous network environments in disaster scenarios, while manual command deployment is constrained by personnel expertise and response time requirements, leading to suboptimal trade-offs between deployment efficiency and reliability. To address these challenges, this study proposes a novel deep reinforcement learning framework with a fully convolutional value network architecture, which achieves breakthroughs in multi-dimensional spatial decision-making through end-to-end feature extraction. This design effectively mitigates the “curse of dimensionality” inherent in traditional reinforcement learning methods for topology planning. Experimental results demonstrate that the proposed method effectively accomplishes the planning tasks of emergency communication hub elements, significantly improving deployment efficiency while maintaining robustness in complex environments. Full article

Gamification has emerged as a powerful strategy in digital education, enhancing engagement, motivation, and learning outcomes. However, most research lacks theoretical grounding and often applies multiple and uncontextualized game elements, limiting its impact and replicability. To address these gaps, this study introduces a Systemic Gamification Theory (SGT)—a comprehensive, human-centered model for designing and evaluating inclusive and effective gamified educational environments. Sustained in Education, Human–Computer Interaction, and Psychology, SGT is structured around four core principles, emphasizing the importance of integrating game elements (1—Integration) into cohesive systems that generate emergent outcomes (2—Emergence) aligned synergistically (3—Synergy) with contextual needs (4—Context). The theory supports inclusivity by accounting for individual traits, situational dynamics, spatial settings, and cultural diversity. To operationalize SGT, we developed two tools: i. a set of 10 Heuristics to guide and analyze effective and inclusive gamification; and ii. a Framework for designing and evaluating gamified systems, as well as comparing research methods and outcomes across different contexts. These tools demonstrated how SGT enables robust, adaptive, and equitable gamified learning experiences. By advancing theoretical and practical development, SGT fosters a transformative approach to gamification, enriching multimedia learning through thoughtful system design and reflective evaluation practices. Full article