Search Results (2,003)

Traditional unmanned aerial vehicle (UAV) detection and tracking methods have long faced the twin challenges of high cost and poor efficiency. In real-world battlefield environments with complex backgrounds, occlusions, and varying speeds, existing techniques struggle to track small UAVs accurately and stably. To tackle these issues, this paper presents an enhanced YOLOv8N-Drone-based algorithm for improved target tracking of small UAVs. Firstly, a novel module named C2f-DSFEM (Depthwise-Separable and Sobel Feature Enhancement Module) is designed, integrating Sobel convolution with depthwise separable convolution across layers. Edge detail extraction and multi-scale feature representation are synchronized through a bidirectional feature enhancement mechanism, and the discriminability of target features in complex backgrounds is thus significantly enhanced. For the feature confusion problem, the improved lightweight Context Anchored Attention (CAA) mechanism is integrated into the Neck network, which effectively improves the system’s adaptability to complex scenes. By employing a position-aware weight allocation strategy, this approach enables adaptive suppression of background interference and precise focus on the target region, thereby improving localization accuracy. At the level of loss function optimization, the traditional classification loss is replaced by the focal loss (Focal Loss). This mechanism effectively suppresses the contribution of easy-to-classify samples through a dynamic weight adjustment strategy, while significantly increasing the priority of difficult samples in the training process. The class imbalance that exists between the positive and negative samples is then significantly mitigated. Experimental results show the enhanced YOLOv8 boosts mean average precision (Map@0.5) by 12.3%, hitting 99.2%. In terms of tracking performance, the proposed YOLOv8 N-Drone algorithm achieves a 19.2% improvement in Multiple Object Tracking Accuracy (MOTA) under complex multi-scenario conditions. Additionally, the IDF1 score increases by 6.8%, and the number of ID switches is reduced by 85.2%, indicating significant improvements in both accuracy and stability of UAV tracking. Compared to other mainstream algorithms, the proposed improved method demonstrates significant advantages in tracking performance, offering a more effective and reliable solution for small-target tracking tasks in UAV applications. Full article

In clinical decision support systems (CDSSs), where accurate classification of drug–drug interactions (DDIs) can directly affect treatment safety and outcomes, identifying drug interactions is a major challenge, introducing a scalable approach for classifying DDIs utilizing a finely-tuned biomedical language model. The method shown here uses BiomedBERT, a domain-specific version of bidirectional encoder representations from transformers (BERT) that was pre-trained on biomedical literature, to reduce the number of resources needed during fine-tuning. Low-rank adaptation (LoRA) was used to fine-tune the model on the DrugBank dataset. The objective was to classify DDIs into two clinically distinct categories, that is, synergistic and antagonistic interactions. A pseudo-labeling strategy was created to deal with the problem of not having enough labeled data. A curated ground-truth dataset was constructed using polarity-labeled interaction entries from DrugComb and verified DrugBank antagonism pairs. The fine-tuned model is used to figure out what kinds of interactions there are in the rest of the unlabeled data. A checkpointing system saves predictions and confidence scores in small pieces, which means that the process can be continued and is not affected by system crashes. The framework is designed to log every prediction it makes, allowing results to be refined later, either manually or through automated updates, without discarding low-confidence cases, as traditional threshold-based methods often do. The method keeps a record of every output it generates, making it easier to revisit earlier predictions, either by experts or with improved tools, without depending on preset confidence cutoffs. It was built with efficiency in mind, so it can handle large amounts of biomedical text without heavy computational demands. Rather than focusing on model novelty, this research demonstrates how existing biomedical transformers can be adapted to polarity-aware DDI classification with minimal computational overhead, emphasizing deployment feasibility and clinical relevance. Full article

Effective energy management in Low Earth Orbit satellites is critical, as inefficient energy management can significantly affect mission objectives. The dynamic and harsh space environment further complicates the development of effective energy management strategies. To address these challenges, we propose a Deep Reinforcement Learning approach using Deep-Q Network to develop an adaptive energy management framework for Low Earth Orbit satellites. Compared to traditional techniques, the proposed solution autonomously learns from environmental interaction, offering robustness to uncertainty and online adaptability. It adjusts to changing conditions without manual retraining, making it well-suited for handling modeling uncertainties and non-stationary dynamics typical of space operations. Training is conducted using a realistic satellite electric power system model with accurate component parameters and single-orbit power profiles derived from real space missions. Numerical simulations validate the controller performance across diverse scenarios, including multi-orbit settings, demonstrating superior adaptability and efficiency compared to conventional Maximum Power Point Tracking methods. Full article

To solve the problem of traditional engineering drilling rig propulsion systems being difficult to adapt to complex working conditions due to their bulky structure and poor load adaptability, this study proposes a new type of mechanical hydraulic composite electro-hydraulic proportional propulsion system. The system innovatively adopts a composite design of parallel hydraulic cylinders and movable pulley groups in mechanical structure, aiming to achieve system lightweighting through displacement multiplication effect. In terms of control strategy, a fuzzy adaptive PID controller based on position feedback was designed to improve the dynamic tracking performance and robustness of the system under nonlinear time-varying loads. The study established a multi physics domain mathematical model of the system and conducted joint simulation using AMESim and MATLAB/Simulink to deeply verify the overall performance of the proposed scheme. The simulation results show that the mechanical structure can stably achieve a 2:1 displacement multiplication effect, providing a feasible path for shortening the system size. Compared with traditional PID control, the proposed fuzzy adaptive PID control strategy significantly improves the positioning accuracy of the system. The maximum tracking errors of the master and slave hydraulic cylinders are reduced from 6.3 mm and 10.4 mm to 2.3 mm and 5.6 mm, respectively, and the accuracy is improved by 63.49% and 46.15%, providing theoretical support and technical reference for the design of engineering drilling rig propulsion control systems. Full article

Cardiovascular disease (CVD) remains Europe’s leading cause of mortality, responsible for >45% of deaths. Beyond established risk factors (hypertension, diabetes, dyslipidaemia, smoking, obesity), psychosocial elements—depression, anxiety, financial stress, personality traits, and trauma—significantly influence CVD development and progression. Behavioural Cardiology addresses this connection by systematically incorporating psychosocial factors into prevention and rehabilitation protocols. This review examines the HEARTBEAT model, developed by Greece’s first Behavioural Cardiology Unit, which aligns with current European guidelines. The model serves dual purposes: primary prevention (targeting at-risk individuals) and secondary prevention (treating established CVD patients). It is a personalised medicine approach that integrates psychosocial profiling with traditional risk assessment, utilising tailored evaluation tools, caregiver input, and multidisciplinary collaboration to address personality traits, emotional states, socioeconomic circumstances, and cultural contexts. The model emphasises three critical implementation aspects: (1) digital health integration, (2) cost-effectiveness analysis, and (3) healthcare system adaptability. Compared to international approaches, it highlights research gaps in psychosocial interventions and advocates for culturally sensitive adaptations, particularly in resource-limited settings. Special consideration is given to older populations requiring tailored care strategies. Ultimately, Behavioural Cardiology represents a transformative systems-based approach bridging psychology, lifestyle medicine, and cardiovascular treatment. This integration may prove pivotal for optimising chronic disease management through personalised interventions that address both biological and psychosocial determinants of cardiovascular health. Full article

Willow stands (Salix spp.) are an essential part of riparian ecosystems, as they sustain biodiversity and provide bioenergy solutions. The present review synthesizes the global scientific literature about the management of willow stands. In order to achieve this goal, we used a dual approach combining bibliometric analysis with traditional literature review. As such, we consulted 416 publications published between 1978 and 2024. This allowed us to identify key species, ecosystem services, conservation strategies, and management issues. The results we have obtained show a diversity of approaches, with an increase in short-rotation coppice (SRC) systems and the multiple roles covered by willow stands (carbon sequestration, biomass production, riparian restoration, and habitat provision). The key trends we have identified show a shift toward topics such as climate resilience, ecological restoration, and precision forestry. This trend has become especially pronounced over the past decade (2014–2024), as reflected in the increasing use of these keywords in the literature. However, as willow systems expand in scale and function—from biomass production to ecological restoration—they also raise complex challenges, including invasive tendencies in non-native regions and uncertainties surrounding biodiversity impacts and soil carbon dynamics over the long term. The present review is a guide for forest policies and, more specifically, for future research, linking the need to integrate and use adaptive strategies in order to maintain the willow stands. Full article

With the rapid development of video streaming services, adaptive bitrate (ABR) algorithms have become a core technology for ensuring optimal viewing experiences. Traditional ABR strategies, predominantly rule-based or reinforcement learning-driven, typically employ uniform quality assessment metrics that overlook users’ subjective preference differences regarding factors such as video quality and stalling. To address this limitation, this paper proposes an adaptive video bitrate selection system that integrates preference modeling with reinforcement learning. By incorporating a preference learning module, the system models and scores user viewing trajectories, using these scores to replace conventional rewards and guide the training of the Proximal Policy Optimization (PPO) algorithm, thereby achieving policy optimization that better aligns with users’ perceived experiences. Simulation results on DASH network bandwidth traces demonstrate that the proposed optimization method improves overall Quality of Experience (QoE) by over 9% compared to other mainstream algorithms. Full article

Synthetic Aperture Radar (SAR) images and optical imagery have high potential for extracting digital elevation models (DEMs). The two main approaches for deriving elevation models from SAR data are interferometry (InSAR) and radargrammetry. Adapted from photogrammetric principles, radargrammetry relies on disparity model estimation as its core component. Matching strategies in radargrammetry typically follow local, global, or semi-global methodologies. Local methods, while having higher accuracy, especially in low-texture SAR images, require larger kernel sizes, leading to quadratic computational complexity. Conversely, global and semi-global models produce more consistent and higher-quality disparity maps but are computationally more intensive than local methods with small kernels and require more memory (RAM). In this study, inspired by the advantages of local matching algorithms, a computationally efficient and novel model is proposed for extracting corresponding pixels in SAR-intensity stereo images. To enhance accuracy, the proposed two-stage algorithm operates without an image pyramid structure. Notably, unlike traditional local and global models, the computational complexity of the proposed approach remains stable as the input size or kernel dimensions increase while memory consumption stays low. Compared to a pyramid-based local normalized cross-correlation (NCC) algorithm and adaptive semi-global matching (SGM) models, the proposed method maintains good accuracy comparable to adaptive SGM while reducing processing time by up to 50% relative to pyramid SGM and achieving a 35-fold speedup over the local NCC algorithm with an optimal kernel size. Validated on a Sentinel-1 stereo pair with a 10 m ground-pixel size, the proposed algorithm yields a DEM with an average accuracy of 34.1 m. Full article

Traffic congestion in large-scale road networks significantly impacts urban sustainability. Traditional traffic signal control methods lack adaptability to dynamic traffic conditions. Recently, deep reinforcement learning (DRL) has emerged as a promising solution for optimizing signal control. This study proposes a Multi-Agent Deep Reinforcement Learning (MADRL) framework for large-scale traffic signal control. The framework employs spatio-temporal attention networks to extract relevant traffic patterns and a hierarchical reinforcement learning strategy for coordinated multi-agent optimization. The problem is formulated as a Markov Decision Process (MDP) with a novel reward function that balances vehicle waiting time, throughput, and fairness. We validate our approach on simulated large-scale traffic scenarios using SUMO (Simulation of Urban Mobility). Experimental results demonstrate that our framework reduces vehicle waiting time by 25% compared to baseline methods while maintaining scalability across different road network sizes. The proposed spatio-temporal multi-agent reinforcement learning framework effectively optimizes large-scale traffic signal control, providing a scalable and efficient solution for smart urban transportation. Full article

In the 6G era, the proliferation of smart devices has led to explosive growth in data volume. The traditional cloud computing can no longer meet the demand for efficient processing of large amounts of data. Edge computing can solve the energy loss problems caused by transmission delay and multi-level forwarding in cloud computing by processing data close to the data source. In this paper, we propose a cloud–edge–end collaborative task offloading strategy with task response time and execution energy consumption as the optimization targets under a limited resource environment. The tasks generated by smart devices can be processed using three kinds of computing nodes, including user devices, edge servers, and cloud servers. The computing nodes are constrained by bandwidth and computing resources. For the target optimization problem, a genetic particle swarm optimization algorithm considering three layers of computing nodes is designed. The task offloading optimization is performed by introducing (1) opposition-based learning algorithm, (2) adaptive inertia weights, and (3) adjustive acceleration coefficients. All metaheuristic algorithms adopt a symmetric training method to ensure fairness and consistency in evaluation. Through experimental simulation, compared with the classic evolutionary algorithm, our algorithm reduces the objective function value by about 6–12% and has higher algorithm convergence speed, accuracy, and stability. Full article

Adversarial attacks in Natural Language Processing (NLP) present a critical challenge, particularly in sentiment analysis, where subtle input modifications can significantly alter model predictions. In search of more robust defenses against adversarial attacks on sentimental analysis, this research work introduces two novel defense mechanisms: the Lexicon-Based Random Substitute Model (LRSM) and the Word-Variant Voting Model (WVVM). LRSM employs randomized substitutions from a dataset-specific lexicon to generate diverse input variations, disrupting adversarial strategies by introducing unpredictability. Unlike traditional defenses requiring synonym dictionaries or precomputed semantic relationships, LRSM directly substitutes words with random lexicon alternatives, reducing overhead while maintaining robustness. Notably, LRSM not only neutralizes adversarial perturbations but occasionally surpasses the original accuracy by correcting inherent model misclassifications. Building on LRSM, WVVM integrates LRSM, Frequency-Guided Word Substitution (FGWS), and Synonym Random Substitution and Voting (RS&V) in an ensemble framework that adaptively combines their outputs. Logistic Regression (LR) emerged as the optimal ensemble configuration, leveraging its regularization parameters to balance the contributions of individual defenses. WVVM consistently outperformed standalone defenses, demonstrating superior restored accuracy and F1 scores across adversarial scenarios. The proposed defenses were evaluated on two well-known sentiment analysis benchmarks: the IMDB Sentiment Dataset and the Yelp Polarity Dataset. The IMDB dataset, comprising 50,000 labeled movie reviews, and the Yelp Polarity dataset, containing labeled business reviews, provided diverse linguistic challenges for assessing adversarial robustness. Both datasets were tested using 4000 adversarial examples generated by established attacks, including Probability Weighted Word Saliency, TextFooler, and BERT-based Adversarial Examples. WVVM and LRSM demonstrated superior performance in restoring accuracy and F1 scores across both datasets, with WVVM excelling through its ensemble learning framework. LRSM improved restored accuracy from 75.66% to 83.7% when compared to the second-best individual model, RS&V, while the Support Vector Classifier WVVM variation further improved restored accuracy to 93.17%. Logistic Regression WVVM achieved an F1 score of 86.26% compared to 76.80% for RS&V. These findings establish LRSM and WVVM as robust frameworks for defending against adversarial text attacks in sentiment analysis. Full article

Rapid urbanization and demographic shifts present significant challenges to spatial justice in green space provision. Traditional static assessments have become increasingly inadequate for guiding park planning, which now requires a dynamic, future-oriented analytical approach. To address this gap, this study incorporates population dynamics into urban park planning by developing a dynamic evaluation framework for park accessibility. Building on the Gaussian-based two-step floating catchment area (Ga2SFCA) method, we propose the human-population-projection-Ga2SFCA (HPP-Ga2SFCA) model, which integrates population forecasts to assess park service efficiency under future demographic pressures. Using neighborhood-committee-level census data from 2000 to 2020 and detailed park spatial data, we identified five types of population change and forecast demographic distributions for both short- and long-term scenarios. Our findings indicate population decline in the urban core and outer suburbs, with growth concentrated in the transitional inner-suburban zones. Long-term projections suggest that 66% of communities will experience population growth, whereas short-term forecasts indicate a decline in 52%. Static models overestimate park accessibility by approximately 40%. In contrast, our dynamic model reveals that accessibility is overestimated in 71% and underestimated in 7% of the city, highlighting a potential mismatch between future population demand and current park supply. This study offers a forward-looking planning framework that enhances the responsiveness of park systems to demographic change and supports the development of more equitable, adaptive green space strategies. Full article

The accelerating integration of electric vehicles (EVs) into contemporary transportation infrastructure has underscored significant limitations in traditional charging paradigms, particularly in accommodating heterogeneous user requirements within dynamic operational environments. This study presents a differentiated optimization framework for EV charging strategies through the systematic classification of user types. A multidimensional decision-making environment is established for three representative user categories—residential, commercial, and industrial—by synthesizing time-variant electricity pricing models with dynamic carbon emission pricing mechanisms. A bi-level optimization architecture is subsequently formulated, leveraging deep reinforcement learning (DRL) to capture user-specific demand characteristics through customized reward functions and adaptive constraint structures. Validation is conducted within a high-fidelity simulation environment featuring 90 autonomous EV charging agents operating in a metropolitan parking facility. Empirical results indicate that the proposed typology-driven approach yields a 32.6% average cost reduction across user groups relative to baseline charging protocols, with statistically significant improvements in expenditure optimization (p < 0.01). Further interpretability analysis employing gradient-weighted class activation mapping (Grad-CAM) demonstrates that the model’s attention mechanisms are well aligned with theoretically anticipated demand prioritization patterns across the distinct user types, thereby confirming the decision-theoretic soundness of the framework. Full article

Background and Objectives: Depression is a leading cause of disability globally, with treatment challenges including limited access, stigma, and poor adherence. Gamification, which applies game elements such as points, levels, and storytelling into non-game contexts, offers a promising strategy to enhance engagement and augment traditional treatments. Our research is the first study designed to explore the implementation of gamification within the Malaysian context. The objective was to explore the feasibility of implementation of gamification as an adjunctive treatment for adults with depression. Materials and Methods: Focus group discussions were held with five mental health professionals and ten patients diagnosed with moderate depression. The qualitative component assessed perceptions of gamified interventions, while quantitative measures evaluated participants’ depressive and anxiety symptomatology. Results: Three key themes were identified: (1) understanding of gamification as a treatment option, (2) factors influencing its acceptance, and (3) characteristics of a practical and feasible intervention. Clinicians saw potential in gamification to boost motivation, support psychoeducation, and encourage self-paced learning, but they expressed concerns about possible addiction, stigma, and the complexity of gameplay for some patients. Patients spoke of gaming as a source of comfort, escapism, and social connection. Acceptance was shaped by engaging storylines, intuitive design, balanced difficulty, therapist guidance, and clear safety measures. Both groups agreed that gamification should be used in conjunction with standard treatments, be culturally sensitive, and be presented as a meaningful therapeutic approach rather than merely as entertainment. Conclusions: Gamification emerges as an acceptable and feasible supplementary approach for managing depression in Malaysia. Its success depends on culturally sensitive design, robust clinical oversight, and seamless integration with existing care pathways. Future studies should investigate long-term outcomes and establish guidelines for the safe and effective implementation of this approach. We recommend targeted investment into culturally adapted gamified tools, including training, policy development, and collaboration with key stakeholders to realistically implement gamification as a mental health intervention in Malaysia. Full article

The aircraft nose-wheel steering system serves as a critical component for ensuring ground taxiing safety and maneuvering efficiency. However, its dynamic control stability faces significant challenges under complex operational conditions. Existing research predominantly focuses on single-discipline modeling, with insufficient in-depth analysis of the coupling effects between hydraulic system dynamics and mechanical dynamics. Traditional PID controllers exhibit limitations in scenarios involving nonlinear time-varying conditions caused by normal load fluctuations of the landing gear buffer strut during high-speed landing phases, including increased control overshoot and inadequate adaptability to abrupt load variations. These issues severely compromise the stability of high-speed deviation correction and overall aircraft safety. To address these challenges, this study constructs a digital twin model based on real aircraft data and innovatively implements multidisciplinary co-simulation via Simcenter 3D, AMESim 2021.1, and MATLAB R2020a. A fuzzy adaptive PID controller is specifically designed to achieve adaptive adjustment of control parameters. Comparative analysis through co-simulation demonstrates that the proposed mechanical–electrical–hydraulic collaborative control strategy significantly reduces response delay, effectively minimizes control overshoot, and decreases hydraulic pressure-fluctuation amplitude by over 85.2%. This work provides a novel methodology for optimizing steering stability under nonlinear interference scenarios, offering substantial engineering applicability and promotion value. Full article