Search Results (193)

Unmanned platforms such as unmanned aerial vehicles, unmanned ground vehicles, and autonomous underwater vehicles often face challenges of data, device, and model heterogeneity when performing collaborative data processing tasks. Existing research does not simultaneously address issues from these three aspects. To address this issue, this study designs an unmanned platform cluster architecture inspired by the cloud-edge-end model. This architecture integrates federated learning for privacy protection, leverages the advantages of distributed model training, and utilizes edge computing’s near-source data processing capabilities. Additionally, this paper proposes a federated edge intelligence method (DSIA-FEI), which comprises two key components. Based on traditional federated learning, a data sharing mechanism is introduced, in which data is extracted from edge-side platforms and placed into a data sharing platform to form a public dataset. At the beginning of model training, random sampling is conducted from the public dataset and distributed to each unmanned platform, so as to mitigate the impact of data distribution heterogeneity and class imbalance during collaborative data processing in unmanned platforms. Moreover, an intelligent model aggregation strategy based on similarity measurement and loss gradient is developed. This strategy maps heterogeneous model parameters to a unified space via hierarchical parameter alignment, and evaluates the similarity between local and global models of edge devices in real-time, along with the loss gradient, to select the optimal model for global aggregation, reducing the influence of device and model heterogeneity on cooperative learning of unmanned platform swarms. This study carried out extensive validation on multiple datasets, and the experimental results showed that the accuracy of the DSIA-FEI proposed in this paper reaches 0.91, 0.91, 0.88, and 0.87 on the FEMNIST, FEAIR, EuroSAT, and RSSCN7 datasets, respectively, which is more than 10% higher than the baseline method. In addition, the number of communication rounds is reduced by more than 40%, which is better than the existing mainstream methods, and the effectiveness of the proposed method is verified. Full article

Recent years have seen frequent heavy rainfall events in Japan, often linked to Baiu fronts and typhoons. These events are exacerbated by global warming, leading to an increased frequency and intensity. As floods represent a serious threat to sustainable urban development and community resilience, this study contributes to sustainability-focused risk reduction through integrated analysis. This study focuses on the 2 June 2023 heavy rain disaster in Toyohashi City, Japan, which caused extensive damage due to flooding from the Yagyu and Umeda Rivers. Using numerical models, this study accurately reproduces flooding patterns, revealing that high tides amplified the inundation area by 1.5 times at the Yagyu River. A resident questionnaire conducted in collaboration with Toyohashi City identifies key trends in evacuation behavior and disaster information usage. Traditional media such as TV remain dominant, but younger generations leverage electronic devices for disaster updates. These insights emphasize the need for targeted information dissemination and enhanced disaster preparedness strategies, including online materials and flexible training programs. The methods and findings presented in this study can inform local and regional governments in building adaptive disaster management policies, which contribute to a more sustainable society. Full article

Vaccine equity and access remain critical challenges in global health, particularly in regions with complex socio-political landscapes, like the Middle East. This review examines disparities in vaccine distribution within the Middle Eastern context, analyzing the unique challenges and opportunities across the region. It provides an overview of the area’s diverse finances and its impact on healthcare accessibility. We examine vaccination rates and identify critical barriers to vaccination, which may be particular issues in developing countries, such as vaccine thermostability, logistical hurdles, financial constraints, and socio-cultural factors, or broader problems, like political instability, economic limitations, and deficiencies in healthcare infrastructure. However, we also highlight successful efforts at the regional and national levels to improve vaccine equity, along with their outcomes and impacts. Ultimately, by drawing on the experiences of previous programs and initiatives, we propose strategies to bridge the gaps in vaccine access through sustainable financing, local manufacturing, and the strengthening of health systems. This approach emphasizes the importance of regional collaboration and long-term self-sufficiency in enhancing global health security and achieving more equitable outcomes in the Middle East. Full article

Urban areas are at the forefront in addressing global challenges such as climate change and biodiversity loss. Among the key responses are nature-based solutions, which are increasingly being integrated into policy frameworks but which require strong community engagement for their effective implementation. This paper presents the findings of surveys conducted within the Place Lab in Katowice, Poland, an initiative developed as part of an international project and used as a participatory tool for co-creating and implementing green infrastructure. The project applies both place-based and people-centred approaches to support European cities in their transition towards regenerative urbanism. Place Lab activities encourage collaboration between local authorities and residents, enhancing awareness and fostering participation in environmental initiatives. The survey data collected during the project allowed for the evaluation of changes in public attitudes and levels of engagement and for the identification of broader societal phenomena that may influence the implementation of nature-based solutions. The findings revealed, for instance, that more women were interested in supporting the project, that residents tended to be sceptical of governmental actions on climate change, and that views were divided on the trade-off between urban infrastructure such as parking and roads and the presence of green areas. Furthermore, questions of responsibility, awareness, and long-term commitment were frequently raised. Building on the survey results and the existing literature, the study proposes a set of indicators to assess the contribution of citizen participation to the adoption of nature-based solutions. While the effectiveness of nature-based solutions in mitigating climate change impacts can be assessed relatively directly, evaluating civic engagement is more complex. Nevertheless, when conducted transparently and interpreted by experts, indicator-based assessment can offer valuable insights. This study introduces a novel perspective by considering not only drivers of engagement but also the obstacles. The proposed indicators provide a foundation for evaluating community readiness and commitment to nature-based approaches and may be adapted for application in other urban settings and in future research on climate resilience strategies. Full article

Hyperspectral imaging for seed vigor detection faces the challenges of handling high-dimensional spectral data, information loss after dimensionality reduction, and low feature differentiation between vigor levels. To address the above issues, this study proposes an improved dynamic optimize MDS (DO-MDS) dimensionality reduction algorithm based on multidimensional scaling transformation. DO-MDS better preserves key features between samples during dimensionality reduction. Secondly, a dual-stream spectral collaborative attention (DSCA) module is proposed. The DSCA module adopts a dual-modal fusion approach combining global feature capture and local feature enhancement, deepening the characterization capability of spectral features. This study selected commonly used rice seed varieties in Zhejiang Province and constructed three individual spectral datasets and a mixed dataset through aging, spectral acquisition, and germination experiments. The experiments involved using the DO-MDS processed datasets with a convolutional neural network embedded with the DSCA attention module, and the results demonstrate vigor discrimination accuracy rates of 93.85%, 93.4%, and 96.23% for the Chunyou 83, Zhongzao 39, and Zhongzu 53 datasets, respectively, achieving 94.8% for the mixed dataset. This study provides effective strategies for spectral dimensionality reduction in hyperspectral seed vigor detection and enhances the differentiation of spectral information for seeds with similar vigor levels. Full article

Federated learning (FL) enables collaborative model building among a large number of participants without sharing sensitive data to the central server. Because of its distributed nature, FL has limited control over local data and the corresponding training process. Therefore, it is susceptible to data poisoning attacks where malicious workers use malicious training data to train the model. Furthermore, attackers on the worker side can easily manipulate local data by swapping the labels of training instances, adding noise to training instances, and adding out-of-distribution training instances in the local data to initiate data poisoning attacks. And local workers under such attacks carry incorrect information to the server, poison the global model, and cause misclassifications. So, the prevention and detection of such data poisoning attacks is crucial to build a robust federated training framework. To address this, we propose a prevention strategy in federated learning, namely confident federated learning, to protect workers from such data poisoning attacks. Our proposed prevention strategy at first validates the label quality of local training samples by characterizing and identifying label errors in the local training data, and then excludes the detected mislabeled samples from the local training. To this aim, we experiment with our proposed approach on both the image and audio domains, and our experimental results validated the robustness of our proposed confident federated learning in preventing the data poisoning attacks. Our proposed method can successfully detect the mislabeled training samples with above 85% accuracy and exclude those detected samples from the training set to prevent data poisoning attacks on the local workers. However, our prevention strategy can successfully prevent the attack locally in the presence of a certain percentage of poisonous samples. Beyond that percentage, the prevention strategy may not be effective in preventing attacks. In such cases, detection of the attacked workers is needed. So, in addition to the prevention strategy, we propose a novel detection strategy in the federated learning framework to detect the malicious workers under attack. We propose to create a class-wise cluster representation for every participating worker by utilizing the neuron activation maps of local models and analyze the resulting clusters to filter out the workers under attack before model aggregation. We experimentally demonstrated the efficacy of our proposed detection strategy in detecting workers affected by data poisoning attacks, along with the attack types, e.g., label-flipping or dirty labeling. In addition, our experimental results suggest that the global model could not converge even after a large number of training rounds in the presence of malicious workers, whereas after detecting the malicious workers with our proposed detection method and discarding them from model aggregation, we ensured that the global model achieved convergence within very few training rounds. Furthermore, our proposed approach stays robust under different data distributions and model sizes and does not require prior knowledge about the number of attackers in the system. Full article

As a core component of automated logistics systems, delivery robots hold significant application value in the field of unmanned delivery. This research addresses the robot path planning problem, aiming to enhance delivery efficiency and reduce operational costs through systematic improvements to the RIME optimization algorithm. Through in-depth analysis, we identified several major drawbacks in the standard RIME algorithm for path planning: insufficient global exploration capability in the initial stages, a lack of diversity in the hard RIME search mechanism, and oscillatory phenomena in soft RIME step size adjustment. These issues often lead to undesirable phenomena in path planning, such as local optima traps, path redundancy, or unsmooth trajectories. To address these limitations, this study proposes the Multi-Strategy Controlled Rime Algorithm (MSRIME), whose innovation primarily manifests in three aspects: first, it constructs a multi-strategy collaborative optimization framework, utilizing an infinite folding Fuch chaotic map for intelligent population initialization to significantly enhance the diversity of solutions; second, it designs a cooperative mechanism between a controlled elite strategy and an adaptive search strategy that, through a dynamic control factor, autonomously adjusts the strategy activation probability and adaptation rate, expanding the search space while ensuring algorithmic convergence efficiency; and finally, it introduces a cosine annealing strategy to improve the step size adjustment mechanism, reducing parameter sensitivity and effectively preventing path distortions caused by abrupt step size changes. During the algorithm validation phase, comparative tests were conducted between two groups of algorithms, demonstrating their significant advantages in optimization capability, convergence speed, and stability. Further experimental analysis confirmed that the algorithm’s multi-strategy framework effectively suppresses the impact of coordinate and dimensional differences on path quality during iteration, making it more suitable for delivery robot path planning scenarios. Ultimately, path planning experimental results across various Building Coverage Rate (BCR) maps and diverse application scenarios show that MSRIME exhibits superior performance in key indicators such as path length, running time, and smoothness, providing novel technical insights and practical solutions for the interdisciplinary research between intelligent logistics and computer science. Full article

Skin cancer is one of the most prevalent forms of cancer worldwide, and early and accurate diagnosis critically impacts patient outcomes. Given the sensitive nature of medical data and its fragmented distribution across institutions (data silos), privacy-preserving collaborative learning is essential to enable knowledge-sharing without compromising patient confidentiality. While federated learning (FL) offers a promising solution, existing methods struggle with heterogeneous and missing modalities across institutions, which reduce the diagnostic accuracy. To address these challenges, we propose an effective and flexible Personalized Multimodal Federated Learning framework (PMM-FL), which enables efficient cross-client knowledge transfer while maintaining personalized performance under heterogeneous and incomplete modality conditions. Our study contains three key contributions: (1) A hierarchical aggregation strategy that decouples multi-module aggregation from local deployment via global modular-separated aggregation and local client fine-tuning. Unlike conventional FL (which synchronizes all parameters in each round), our method adopts a frequency-adaptive synchronization mechanism, updating parameters based on their stability and functional roles. (2) A multimodal fusion approach based on multitask learning, integrating learnable modality imputation and attention-based feature fusion to handle missing modalities. (3) A custom dataset combining multi-year International Skin Imaging Collaboration(ISIC) challenge data (2018–2024) to ensure comprehensive coverage of diverse skin cancer types. We evaluate PMM-FL through diverse experiment settings, demonstrating its effectiveness in heterogeneous and incomplete modality federated learning settings, achieving 92.32% diagnostic accuracy with only a 2% drop in accuracy under 30% modality missingness, with a 32.9% communication overhead decline compared with baseline FL methods. Full article

In rice detection tasks, accurate identification of leaf streaks, pest and disease distribution, and spikelet hierarchies relies on high-quality images to distinguish between texture and hierarchy. However, existing images often suffer from texture blurring and contour shifting due to equipment and environment limitations, which affects the detection performance. In view of the fact that pests and diseases affect the whole situation and tiny details are mostly localized, we propose a rice image reconstruction method based on an adaptive two-branch heterogeneous structure. The method consists of a low-frequency branch (LFB) that recovers global features using orientation-aware extended receptive fields to capture streaky global features, such as pests and diseases, and a high-frequency branch (HFB) that enhances detail edges through an adaptive enhancement mechanism to boost the clarity of local detail regions. By introducing the dynamic weight fusion mechanism (CSDW) and lightweight gating network (LFFN), the problem of the unbalanced fusion of frequency information for rice images in traditional methods is solved. Experiments on the 4× downsampled rice test set demonstrate that the proposed method achieves a 62% reduction in parameters compared to EDSR, 41% lower computational cost (30 G) than MambaIR-light, and an average PSNR improvement of 0.68% over other methods in the study while balancing memory usage (227 M) and inference speed. In downstream task validation, rice panicle maturity detection achieves a 61.5% increase in mAP50 (0.480 → 0.775) compared to interpolation methods, and leaf pest detection shows a 2.7% improvement in average mAP50 (0.949 → 0.975). This research provides an effective solution for lightweight rice image enhancement, with its dual-branch collaborative mechanism and dynamic fusion strategy establishing a new paradigm in agricultural rice image processing. Full article

Real-time train rescheduling is a widely used strategy to minimize knock-on delays in railway networks. While recent research has introduced intelligent solutions to railway traffic management, the tight interdependence of train timetables and the intrinsic complexity of railway networks have hindered the scalability of these approaches to large-scale systems. This paper proposes a multi-agent system (MAS) that addresses these challenges by decomposing the network into single-junction levels, significantly reducing the search space for real-time rescheduling. The MAS employs a Condorcet voting-based collaborative approach to ensure global feasibility and prevent overly localized optimization by individual junction agents. This decentralized approach enhances both the quality and scalability of train rescheduling solutions. We tested the MAS on a railway network in the UK and compared its performance with the First-Come-First-Served (FCFS) and Timetable Order Enforced (TTOE) routing methods. The computational results show that the MAS significantly outperforms FCFS and TTOE in the tested scenarios, yielding up to a 34.11% increase in network capacity as measured by the defined objective function, thus improving network line capacity. Full article

This paper addresses the issues of Beidou navigation signal interference and blockage in complex substation environments by proposing an intelligent collaborative navigation model based on Beidou high-precision navigation and binocular vision recognition. The model is designed with Beidou navigation providing global positioning references and binocular vision enabling local environmental perception through a collaborative fusion strategy. The Unscented Kalman Filter (UKF) is used to integrate data from multiple sensors to ensure high-precision positioning and dynamic obstacle avoidance capabilities for robots in complex environments. Simulation results show that the Beidou–Binocular Cooperative Navigation (BBCN) model achieves a global positioning error of less than 5 cm in non-interference scenarios, and an error of only 6.2 cm under high-intensity electromagnetic interference, significantly outperforming the single Beidou model’s error of 40.2 cm. The path planning efficiency is close to optimal (with an efficiency factor within 1.05), and the obstacle avoidance success rate reaches 95%, while the system delay remains within 80 ms, meeting the real-time requirements of industrial scenarios. The innovative fusion approach enables unprecedented reliability for autonomous robot inspection in high-voltage environments, offering significant practical value in reducing human risk exposure, lowering maintenance costs, and improving inspection efficiency in power industry applications. This technology enables continuous monitoring of critical power infrastructure that was previously difficult to automate due to navigation challenges in electromagnetically complex environments. Full article

This study explores how private sector initiatives within the tourism industry can contribute to public health outcomes and Sustainable Development Goal 3 (SDG 3) through sustainable agricultural practices. Using a mixed-methods approach that combines a systematic literature review with an in-depth case study, the research examines how integrated strategies—such as pesticide-free farming, biodiversity enhancement, and edible landscape design—can reduce environmental health risks, improve nutritional quality, and promote local resilience. A series of sustainability interventions are analyzed using key performance indicators (KPIs) related to pesticide use, organic production, pollinator conservation, and community engagement. The findings reveal that business-led sustainability models can support systemic change when grounded in clear metrics and cross-sector collaboration. Although the absence of pre-2019 baseline data and direct health outcome measurements limit causal inference, the study provides a valuable blueprint for aligning private enterprise practices with global health and sustainability objectives. The implications are relevant for policymakers, hospitality operators, and public health stakeholders aiming to foster synergies between tourism, agriculture, and well-being. Full article

Federated Learning (FL), a key paradigm in privacy-preserving and distributed machine learning (ML), enables collaborative model training across decentralized data sources without requiring raw data exchange. FL enables collaborative model training across decentralized data sources while preserving privacy. However, selecting appropriate clients remains a major challenge, especially in heterogeneous environments with diverse battery levels, privacy needs, and learning capacities. In this work, a centralized reward-based payoff strategy (RBPS) with cooperative intent is proposed for client selection. In RBPS, each client evaluates participation based on locally measured battery level, privacy requirement, and the model’s accuracy in the current round computing a payoff from these factors and electing to participate if the payoff exceeds a predefined threshold. Participating clients then receive the updated global model. By jointly optimizing model accuracy, privacy preservation, and battery-level constraints, RBPS realizes a multi-objective selection mechanism. Under realistic simulations of client heterogeneity, RBPS yields more robust and efficient training compared to existing methods, confirming its suitability for deployment in resource-constrained FL settings. Experimental analysis demonstrates that RBPS offers significant advantages over state-of-the-art (SOA) client selection methods, particularly those relying on a single selection criterion such as accuracy, battery, or privacy alone. These one-dimensional approaches often lead to trade-offs where improvements in one aspect come at the cost of another. In contrast, RBPS leverages client heterogeneity not as a limitation, but as a strategic asset to maintain and balance all critical characteristics simultaneously. Rather than optimizing performance for a single device type or constraint, RBPS benefits from the diversity of heterogeneous clients, enabling improved accuracy, energy preservation, and privacy protection all at once. This is achieved by dynamically adapting the selection strategy to the strengths of different client profiles. Unlike homogeneous environments, where only one capability tends to dominate, RBPS ensures that no key property is sacrificed. RBPS thus aligns more closely with real-world FL deployments, where mixed-device participation is common and balanced optimization is essential. Full article

The rapid growth of computationally intensive tasks in the Internet of Vehicles (IoV) poses a triple challenge to the efficiency, security, and stability of Mobile Edge Computing (MEC). Aiming at the problems that traditional optimization algorithms tend to fall into, where local optimum in task offloading and edge computing nodes are exposed to the risk of data tampering, this paper proposes a secure offloading strategy that integrates the Improved Polar Lights Optimization algorithm (IPLO) and blockchain. First, the truncation operation when a particle crosses the boundary is improved to dynamic rebound by introducing a rebound boundary processing mechanism, which enhances the global search capability of the algorithm; second, the blockchain framework based on the Delegated Byzantine Fault Tolerance (dBFT) consensus is designed to ensure data tampering and cross-node trustworthy sharing in the offloading process. Simulation results show that the strategy significantly reduces the average task processing latency (64.4%), the average system energy consumption (71.1%), and the average system overhead (75.2%), and at the same time effectively extends the vehicle’s power range, improves the real-time performance of the emergency accident warning and dynamic path planning, and significantly reduces the cost of edge computing usage for small and medium-sized fleets, providing an efficient, secure, and stable collaborative computing solution for IoV. Full article

Few-shot object detection (FSOD) in remote sensing remains challenging due to the scarcity of annotated samples and the complex background environments in aerial images. Existing methods often struggle to capture fine-grained local features or suffer from bias during global adaptation to novel categories, leading to misclassification as background. To address these issues, we propose a framework that simultaneously enhances local feature learning and global feature adaptation. Specifically, we design an Extensible Local Feature Aggregator Module (ELFAM) that reconstructs object structures via multi-scale recursive attention aggregation. We further introduce a Self-Guided Novel Adaptation (SGNA) module that employs a teacher-student collaborative strategy to generate high-quality pseudo-labels, thereby refining the semantic feature distribution of novel categories. In addition, a Teacher-Guided Dual-Branch Head (TG-DH) is developed to supervise both classification and regression using pseudo-labels generated by the teacher model to further stabilize and enhance the semantic features of novel classes. Extensive experiments on DlOR and iSAlD datasets demonstrate that our method achieves superior performance compared to existing state-of-the-art FSOD approaches and simultaneously validate the effectiveness of all proposed components. Full article