Search Results (3,743)

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

Lesbian, Gay, Bisexual, Transgender, Questioning, or Queer (LGBTQ) students with disabilities face unique challenges in the educational environment, and educators must provide support based on intersectionality. However, research on LGBTQ students in special needs education is limited, and the extent of educators’ awareness and support is not well documented. Therefore, this study explored the awareness, knowledge, and support practices of special needs school educators regarding LGBTQ students. We conducted a nationwide survey of educators in special needs schools in Japan, and 2024 valid responses were analyzed using multiple correspondence and cluster analyses. The results revealed that many educators lacked an understanding of basic LGBTQ terminology and may have been unaware of their discriminatory behaviors. Additionally, most educators had never encountered LGBTQ students with disabilities, potentially hindering these students’ opportunities to seek support. Furthermore, educators who had received LGBTQ training reported higher awareness and being more proactive in supporting LGBTQ students than those who had not. Thus, training may be associated with support-related attitudes. This highlights the need for ongoing training programs that address LGBTQ identity and disability, considering their intersectionality. These preliminary findings suggest the potential for creating an inclusive environment for LGBTQ students with disabilities; nevertheless, structural barriers remain. Full article

Privacy-sensitive electricity scene classification requires robust models under data localization constraints, making federated learning (FL) a suitable framework. Existing FL frameworks face two critical challenges in multi-label electricity scene classification: (1) Label correlations and their strengths significantly impact classification performance. (2) Electricity scene data and labels show distributional inconsistencies across regions. However, current FL frameworks lack explicit modeling of label correlation strengths, and locally trained regional models naturally capture these differences, leading to regional differences in their model parameters. In this scenario, the server’s standard single-stage aggregation often over-averages the global model’s parameters, reducing its discriminative ability. To address these issues, we propose FMMAN, a federated multi-stage attention neural network for multi-label electricity scene classification. The main contributions of this FMMAN lie in label correlation learning and the stepwise model aggregation. It splits the client–server interaction into multiple stages: (1) Clients train models locally to encode features and label correlation strengths after receiving the server’s initial model. (2) The server clusters these locally trained models into K groups to ensure that models within a group have more consistent parameters and generates K prototype models via intra-group aggregation to reduce over-averaging. The K models are then distributed back to the clients. (3) Clients refine their models using the K prototypes with contrastive group-specific consistency regularization to further mitigate over-averaging, and sends the refined model back to the server. (4) Finally, the server aggregates the models into a global model. Experiments on multi-label benchmarks verify that FMMAN outperforms baseline methods. Full article

CareCoach seeks to enhance self-efficacy in family caregivers of people living with dementia and has been feasibility tested in a multicentre randomised controlled trial. The intervention offers two face-to-face sessions with a trained coach and access to an online platform with nine modules. This paper reports findings from an embedded qualitative process evaluation assessing implementation from the implementer’s (‘coach’s’) (n = 8) perspective using individual interviews and implementer group discussions. Qualitative data were transcribed verbatim, inductively coded and analysed using Normalisation Process Theory. Implementers demonstrated (1) ‘Coherence’ by seeking to understand how CareCoach compared to current practice, highlighting the importance of supporting coaches to differentiate and identify boundaries between their new ‘coach role’ and usual practice; (2) ‘Cognitive Participation’ by reviewing training and resources to understand their role own responsibilities and facilitate delivery of coaching sessions; group supervision and peer support were also emphasised; (3) ‘Collective Action’ through interactions with carers to deliver key behavioural aspects such as goal setting, problem solving, and providing feedback; and (4) ‘Reflexive Monitoring’ by appraising the intervention to gain useful insights that could facilitate refinement of CareCoach training and delivery. This study provides a theoretically informed understanding of the implementation of CareCoach for caregivers of people living with dementia and provides recommendations to enhance training for coaches, intervention delivery and carer engagement. Full article

Inspired by the human ability to learn continuously and adapt to changing environments, researchers have proposed Online Open-World Object Detection (OLOWOD). This emerging paradigm faces the challenges of detecting known categories, discovering unknown ones, continuously learning new categories, and mitigating catastrophic forgetting. To address these challenges, we propose Category Prototype-guided Streaming Multi-Level Perturbation, PSMP, a plug-and-play method for OLOWOD. PSMP, comprising semantic-level, enhanced data-level, and enhanced feature-level perturbations jointly guided by category prototypes, operates at different representational levels to collaboratively extract latent knowledge across tasks and improve adaptability. In addition, PSMP constructs the “contrastive tension” based on the relationships among category prototypes. This mechanism inherently leverages the symmetric structure formed by class prototypes in the latent space, where prototypes of semantically similar categories tend to align symmetrically or equidistantly. By guiding perturbations along these symmetric axes, the model can achieve more balanced generalization between known and unknown categories. PSMP requires no additional annotations, is lightweight in design, and can be seamlessly integrated into existing OWOD methods. Extensive experiments show that PSMP achieves an improvement of approximately 1.5% to 3% in mAP for known categories compared to conventional online training methods while significantly increasing the Unknown Recall (UR) by around 4.6%. Full article

Background: Pain is a problem faced by critically ill surgical patients and has a major impact on their outcomes. Pain assessment is therefore essential for effective pain management, with a combination of pharmacological and non-pharmacological treatment. Clinical supervision, supported by models such as SafeCare, can improve professional development, safety and the quality of care in intensive care units. Objectives: This study aimed to: (1) assess current pain assessment practices in a polyvalent Intensive Care Unit (ICU) in the Porto district; (2) identify nurses’ training needs regarding the Clinical Supervision-Sensitive Indicator—Pain; and (3) evaluate the impact of clinical supervision sessions on pain assessment practices. Methods: A quantitative, quasi-experimental, cross-sectional study with a pre- and post-intervention design was conducted. Based on the SafeCare model, it included a situational diagnosis, 6 clinical supervision sessions (February 2023), and outcome evaluation via nursing record audits (November 2022 and May 2023) in 31 total critical ill patients. Pain was assessed using standardised tools, in line with institutional protocols. Data was analysed using Software Statistical Package for the Social Sciences v25.0. Results: Pain was highly prevalent in the first 24 h, decreasing during hospitalisation. Generalised acute abdominal pain predominated, with mild to moderate intensity, and was exacerbated by wound care and mobilisation/positioning. Pain management combined pharmacological and non-pharmacological treatment. There was an improvement in all the parameters of the pain indicator post-intervention. Conclusions: Despite routine assessments, gaps remained in reassessing pain post-analgesia and during invasive procedures. Targeted clinical supervision and ongoing training proved effective in improving compliance with protocols and supporting safer, more consistent pain management. Full article

As the global population ages, older adults face growing psychological challenges such as loneliness, cognitive decline, and loss of social roles. Meanwhile, artificial intelligence (AI) technologies, including chatbots and voice-based systems, offer new pathways to emotional support and mental stimulation. However, older adults often encounter significant barriers in accessing and effectively using AI tools. This review examines the current landscape of AI applications aimed at enhancing psychological well-being among older adults, identifies key challenges such as digital literacy and usability, and highlights design and training strategies to bridge the digital divide. Using socioemotional selectivity theory and technology acceptance models as guiding frameworks, we argue that AI—especially in the form of conversational agents—holds transformative potential in reducing isolation and promoting emotional resilience in aging populations. We conclude with recommendations for inclusive design, participatory development, and future interdisciplinary research. Full article

Air pollution threatens human health and ecosystems, making timely forecasting essential. The spatiotemporal dynamics of pollutants, shaped by various factors, challenge traditional methods. Therefore, spatiotemporal graph-based deep learning has gained attention for its ability to capture spatial and temporal dependencies within monitoring networks. However, many existing models, despite their high predictive accuracy, face computational complexity and scalability challenges. This study introduces clustered and lightweight spatio-temporal graph convolutional network with gated recurrent unit (ClusLite-STGCN-GRU), a hybrid model that integrates spatial clustering based on pollutant time series for graph construction, Copula-based dependency analysis for selecting relevant pollutants to predict PM_2.5, and graph convolution combined with gated recurrent units to extract spatiotemporal features. Unlike conventional approaches that require learning or dynamically updating adjacency matrices, ClusLite-STGCN-GRU employs a fixed, simple cluster-based structure. Experimental results on Tehran air quality data demonstrate that the proposed model not only achieves competitive predictive performance compared to more complex models, but also significantly reduces computational cost—by up to 66% in training time, 83% in memory usage, and 84% in number of floating-point operations—making it suitable for real-time applications and offering a practical balance between accuracy, interpretability, and efficiency. Full article

The highway and bridge industry is facing persistent challenges related to the high turnover of technical personnel, which poses risks to the continuity and sustainability of infrastructure development. Although Geographic Information System (GIS) training has increasingly been advocated as a strategy to stabilize the workforce, its practical application remains relatively limited across China. Drawing on the Conservation of Resources (COR) theory, this study examines whether GIS training is associated with lower turnover intention among technical staff, potentially through enhanced perceptions of career growth and reduced work-related anxiety. Based on 412 valid responses—primarily from technical personnel employed by major infrastructure enterprises such as regional subsidiaries of the China Communications Construction Group (CCCG) and China State Construction Engineering Corporation (CSCEC)—the study employs Partial Least Squares Structural Equation Modeling (PLS-SEM) to assess the proposed relationships. The findings indicate that GIS training is negatively associated with turnover intention, with career growth partially mediating this association. Additionally, work anxiety moderates the relationship, such that the link between GIS training and turnover intention appears weaker under higher levels of anxiety. This research contributes to bridging the gap between training practices and theoretical understanding, offering insights to inform workforce retention strategies in technology-intensive industries. Full article

Community detection in complex networks plays a pivotal role in modern scientific research, including in social network analysis and protein structure analysis. Traditional community detection methods face challenges in integrating heterogeneous multi-source information, capturing global semantic relationships, and adapting to dynamic network evolution. This paper proposes a novel unsupervised multimodal community detection algorithm (UMM) based on fractal iteration. The core idea is to design a dual-channel encoder that comprehensively considers node semantic features and network topological structures. Initially, node representation vectors are derived from structural information (using feature vectors when available, or singular value decomposition to obtain feature vectors for nodes without attributes). Subsequently, a parameter-free graph convolutional encoder (PFGC) is developed based on fractal iteration principles to extract high-order semantic representations from structural encodings without requiring any training process. Furthermore, a semantic–structural dual-channel encoder (DC-SSE) is designed, which integrates semantic encodings—reduced in dimensionality via UMAP—with structural features extracted by PFGC to obtain the final node embeddings. These embeddings are then clustered using the K-means algorithm to achieve community partitioning. Experimental results demonstrate that the UMM outperforms existing methods on multiple real-world network datasets. Full article

Background/Objectives: Despite legal frameworks acknowledging the need to protect the rights of female prisoners, penitentiary systems often neglect gender-specific needs, particularly for foreign women. Among them, Muslim women face distinct challenges linked to cultural and religious practices, which are frequently unmet in prison contexts. This review aims to explore the academic literature on the experiences of Muslim women in detention. Methods: A systematic review was conducted using three major bibliographic databases—Scopus, PubMed, and Web of Science—covering the period from 2010 to 2024. Inclusion criteria focused on peer-reviewed studies examining the condition of Muslim women in prison. Of the initial pool, only four articles met the criteria and were included in the final analysis. Results: The review reveals a marked scarcity of research on Muslim women in prison at both national and international levels. This gap may be due to their limited representation or cultural factors that hinder open discourse. The selected studies highlight key issues, including restricted access to services, limited ability to practice religion, and language and cultural barriers. These challenges contribute to increased psychological vulnerability, which is often underestimated in prison settings. Conclusions: There is an urgent need for targeted research and culturally competent training for prison staff to adequately support Muslim women in detention. Greater academic and institutional attention is essential to develop inclusive policies that consider the intersection of gender, religion, and migration, particularly in the post-release reintegration process. Full article

Tea cultivation faces significant threats from red spider mite (RSM: Oligonychus coffeae) infestations, which reduce yields and economic viability in major tea-producing regions. Current automated detection methods rely on supervised deep learning models requiring extensive labeled data, limiting scalability for smallholder farmers. This article proposes AIM-Net (AI-based Infestation Mapping Network) by evaluating SwAV (Swapping Assignments between Views), a self-supervised learning framework, for classifying RSM infestation severity (Mild, Moderate, Severe) using a geo-referenced, field-acquired dataset of RSM infested tea-leaves, Cam-RSM. The methodology combines SwAV pre-training on unlabeled data with fine-tuning on labeled subsets, employing multi-crop augmentation and online clustering to learn discriminative features without full supervision. Comparative analysis against a fully supervised ResNet-50 baseline utilized 5-fold cross-validation, assessing accuracy, F1-scores, and computational efficiency. Results demonstrate SwAV’s superiority, achieving 98.7% overall accuracy (vs. 92.1% for ResNet-50) and macro-average F1-scores of 98.3% across classes, with a 62% reduction in labeled data requirements. The model showed particular strength in Mild_RSM-class detection (F1-score: 98.5%) and computational efficiency, enabling deployment on edge devices. Statistical validation confirmed significant improvements (p < 0.001) over baseline approaches. These findings establish self-supervised learning as a transformative tool for precision pest management, offering resource-efficient solutions for early infestation detection while maintaining high accuracy. Full article

Coarse-grained soils serve as essential fill materials in earth–rock dam engineering, where their mechanical properties critically influence dam deformation and stability, directly impacting project safety. Artificial intelligence (AI) techniques are emerging as powerful tools for predicting the mechanical properties of coarse-grained soils. However, AI-based prediction models for these properties face persistent challenges, particularly in parameter tuning—a process requiring substantial computational resources, extensive time, and specialized expertise. To address these limitations, this study proposes a novel prediction model that integrates Adaptive Simulated Annealing (ASA) with an improved Particle Swarm Optimization (PSO) algorithm to optimize the Elman Neural Network (ENN). The methodology encompasses three key aspects: First, the standard PSO algorithm is enhanced by dynamically adjusting its inertial weight and learning factors. The ASA algorithm is then employed to optimize the Adaptive PSO (APSO), effectively mitigating premature convergence and local optima entrapment during training, thereby ensuring convergence to the global optimum. Second, the refined PSO algorithm optimizes the ENN, overcoming its inherent limitations of slow convergence and susceptibility to local minima. Finally, validation through real-world engineering case studies demonstrates that the ASA-PSO-optimized ENN model achieves high accuracy in predicting the mechanical properties of coarse-grained soils. This model provides reliable constitutive parameters for stress–strain analysis in earth–rock dam engineering applications. Full article

Marine biomass, particularly from waste streams, by-products, underutilized, invasive, or potential cultivable marine species, offers a sustainable source of high-value biopolymers such as collagen and chitin. These macromolecules have gained significant attention due to their biocompatibility, biodegradability, functional versatility, and broad applicability across health, food, wellness, and environmental fields. This review highlights recent advances in the uses of marine-derived collagen and chitin/chitosan. In alignment with the United Nations Sustainable Development Goals (SDGs), we analyze how these applications contribute to sustainability, particularly in SDGs related to responsible consumption and production, good health and well-being, and life below water. Furthermore, we contextualize the advancement of product development using marine collagen and chitin/chitosan within the European Union’s Blue bioeconomy strategies, highlighting trends in scientific research and technological innovation through bibliometric and patent data. Finally, the review addresses challenges facing the development of robust value chains for these marine biopolymers, including collaboration, regulatory hurdles, supply-chain constraints, policy and financial support, education and training, and the need for integrated marine resource management. The paper concludes with recommendations for fostering innovation and sustainability in the valorization of these marine resources. Full article

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