Search Results (772)

Efficient task offloading for delay-sensitive applications, such as autonomous driving, presents a significant challenge in multi-hop Vehicular Edge Computing (VEC) networks, primarily due to high vehicle mobility, dynamic network topologies, and complex end-to-end congestion problems. To address these issues, this paper proposes a graph attention-based reinforcement learning algorithm, named GAPO. The algorithm models the dynamic VEC network as an attributed graph and utilizes a graph neural network (GNN) to learn a network state representation that captures the global topological structure and node contextual information. Building on this foundation, an attention-based Actor–Critic framework makes joint offloading decisions by intelligently selecting the optimal destination and collaboratively determining the ratios for offloading and resource allocation. A multi-objective reward function, designed to minimize task latency and to alleviate link congestion, guides the entire learning process. Comprehensive simulation experiments and ablation studies show that, compared to traditional heuristic algorithms and standard deep reinforcement learning methods, GAPO significantly reduces average task completion latency and substantially decreases backbone link congestion. In conclusion, by deeply integrating the state-aware capabilities of GNNs with the decision-making abilities of DRL, GAPO provides an efficient, adaptive, and congestion-aware solution to the resource management problems in dynamic VEC environments. Full article

Background: Cervical cancer poses a threat to the health of women globally. Adolescent girls are the primary target population for HPV vaccination, and guardians’ attitude towards the HPV vaccine plays a significant role in determining the vaccination status among adolescent girls. Objectives: This study aimed to explore the factors influencing guardians’ HPV vaccine acceptance for their girls and provide clues for the development of health intervention strategies. Methods: Combining the health belief model as a theoretical framework, a questionnaire-based survey was conducted. A total of 2157 adolescent girls and their guardians were recruited. The multivariable logistic model was applied to explore associated factors. Results: The guardians had a high HPV vaccine acceptance rate (86.7%) for their girls, and they demonstrated a relatively good level of awareness regarding HPV and HPV vaccines. Factors influencing guardians’ HPV vaccine acceptance for girls included guardians’ education background (OR = 0.57, 95%CI = 0.37–0.87), family income (OR = 1.94, 95%CI = 1.14–3.32), risk of HPV infection (OR = 3.15, 95%CI = 1.40–7.10) or importance of the HPV vaccine for their girls (OR = 6.70, 95%CI = 1.61–27.83), vaccination status surrounding them (OR = 2.03, 95%CI = 1.41–2.92), awareness of negative information about HPV vaccines (OR = 0.59, 95%CI = 0.43–0.82), and recommendations from medical staff (OR = 2.32, 95%CI = 1.65–3.25). Also, guardians preferred to get digital information on vaccines via government or CDC platforms, WeChat platforms, and medical knowledge platforms. Conclusions: Though HPV vaccine willingness was high among Chinese guardians, they preferred to vaccinate their daughters at the age of 17–18 years, later than WHO’s recommended optimal age period (9–14 years old), coupled with safety concerns. Future work should be conducted based on these findings to explore digital intervention effects on girls’ vaccination compliance. Full article

The successful deployment of sustainable building construction (SBC) is connected to sound knowledge sharing. Concerning SBC, knowledge sharing has been identified to directly and indirectly increase innovation, environmental performance, cost saving, regulatory compliance awareness and so on. The necessity of enhancing SBC practice globally has been emphasised by earlier research. Consequently, this study aims to investigate knowledge-sharing elements to enhance SBC in South Africa (SA). Utilising a questionnaire survey, this study elicited data from 281 professionals in the built environment. Data analysis was performed with “descriptive statistics”, the “Kruskal–Wallis H-test”, and “principal component analysis” to determine the principal knowledge-sharing features (KSFs). This study found that “creating public awareness of sustainable practices”, the “content of SBC training, raising awareness of green building products”, “SBC integration in professional certifications”, an “information hub or repository for sustainable construction”, and “mentoring younger professionals in sustainable practices” are the most critical KSFs for SBC deployment. These formed a central cluster, the Green Education Initiative and Eco-Awareness Alliance. The results achieved a reliability test value of 0.956. It was concluded that to embrace the full adoption of SBC, corporate involvement is critical, and all stakeholders must embrace the sustainability paradigm. It is recommended that the principal knowledge-sharing features revealed in this study should be carefully considered to help construction stakeholders in fostering knowledge sharing for a sustainable built environment. Full article

This study aims to evaluate the level of awareness and practical adoption of green wall systems in the Nigerian construction industry. It seeks to examine the current state of green wall implementation and recommend strategies to enhance their integration into construction practices among Nigerian construction professionals. A thorough review of the existing literature was conducted to identify different types of green wall systems. Insights from this review informed the design of a structured questionnaire, which was distributed to construction professionals based in Lagos State. The data collected were analyzed using statistical tests. The study reveals that while there is generally high awareness of green wall systems among Nigerian construction professionals, the practical use remains low, with just 8 out of the 18 systems being actively implemented, eclipsing the mean value of 3.0. The findings underscore the need for targeted education, industry incentives, and increased advocacy to encourage the use of green wall systems in the Nigerian construction sector. The results have significant implications for the Nigerian construction industry. The limited awareness and adoption of green wall systems highlight the need for strategic actions from policymakers, industry leaders and educational institutions. Promoting the use of green walls could drive more sustainable building practices, improve environmental outcomes and support the broader goals of decarbonization and circularity in construction. This research adds to the body of knowledge on sustainable construction by offering a detailed evaluation of green wall awareness and adoption within the Nigerian context. While green wall systems have been studied globally, this research provides a regional perspective, which in this case focuses on Lagos State. The study’s recognition of the gap between awareness and implementation highlights an important area for future research and industry development. Full article

Target detection is essential in intelligent transportation and autonomous control of unmanned aerial vehicles (UAVs), with single-stage detection algorithms used widely due to their speed. However, these algorithms face limitations in detecting small targets, especially in aerial photography from unmanned aerial vehicles (UAVs), where small targets are often occluded, multi-scale semantic information is easily lost, and there is a trade-off between real-time processing and computational resources. Existing algorithms struggle to effectively extract multi-dimensional features and deep semantic information from images and to balance detection accuracy with model complexity. To address these limitations, we developed FFG-YOLO, a lightweight small-target detection method for UAVs based on YOLOv8. FFG-YOLO incorporates three modules: a feature enhancement block (FEB), a feature concat block (FCB), and a global context awareness block (GCAB). These modules strengthen feature extraction from small targets, resolve semantic bias in multi-scale feature fusion, and help differentiate small targets from complex backgrounds. We also improved the positioning accuracy of small targets using the Wasserstein distance loss function. Experiments showed that FFG-YOLO outperformed other algorithms, including YOLOv8n, in small-target detection due to its lightweight nature, meeting the stringent real-time performance and deployment requirements of UAVs. Full article

Self-medication is a subject of global importance. If practiced responsibly, self-medication represents a part of self-care or positive care of an individual or a community in promoting their own health. However, today’s practices of self-medication are often inappropriate and irresponsible, and as such appear all over the world. Inappropriate self-medication can be connected with possible serious health risks and consequences. Therefore, it represents a global health issue. It can even generate additional health problems, which will eventually become a burden to healthcare systems and can induce significant costs, which also raises socioeconomic concerns. Hence, self-medication attracts the attention of researchers and practitioners globally in efforts to clarify the current status and define feasible measures that should be implemented to address this issue. This narrative review aims to give an overview of the situation in the field of self-medication globally, including current practices and attitudes, as well as implications for actions needed to improve this problem. A PubMed/MEDLINE search was conducted for articles published in the period from 1995 up to March 2025 using keywords “self-medication” or “selfmedication” alone or in combinations with terms related to specific subthemes related to self-medication, such as COVID-19, antimicrobials, healthcare professionals, and storing habits of medicines at home. Studies were included if self-medication was their main focus. Publications that only mentioned self-medication in different contexts, but not as their main focus, were excluded. Considering the outcomes of research on self-medication in various contexts, increasing awareness of responsible self-medication through education and informing, together with surveillance of particular medicines and populations, could lead to more appropriate and beneficial self-medication in the future. Full article

Stereoscopic omnidirectional images (SOIs) have gained significant attention for their immersive viewing experience by providing binocular depth with panoramic scenes. However, evaluating their visual quality remains challenging due to its unique spherical geometry, binocular disparity, and viewing conditions. To address these challenges, this paper proposes a dual-branch deep learning framework that integrates spherical structural features and perceptual binocular cues to assess the quality of SOIs without reference. Specifically, the global branch leverages spherical convolutions to capture wide-range spatial distortions, while the local branch utilizes a binocular difference module based on discrete wavelet transform to extract depth-aware perceptual information. A feature complementarity module is introduced to fuse global and local representations for final quality prediction. Experimental evaluations on two public SOIQA datasets—NBU-SOID and SOLID—demonstrate that the proposed method achieves state-of-the-art performance, with PLCC/SROCC values of 0.926/0.918 and 0.918/0.891, respectively. These results validate the effectiveness and robustness of our approach in stereoscopic omnidirectional image quality assessment tasks. Full article

The growing integration of technology in education has heightened awareness of global risks, such as the spread of disinformation. This awareness is vital for fostering the well-being of individuals, especially teenagers, by promoting critical thinking and responsible digital practices. By cultivating these skills, sustainable education empowers individuals to identify potential threats, protect themselves, and advocate for informed, positive change. As part of a European project, this study aims to analyze the current level of awareness among secondary school students (12 to 17) and their teachers. Differences between both are analyzed in how they deal with disinformation in terms of (1) perceptions, (2) feelings and practices, and (3) knowledge and management. A quantitative approach was adopted for this study, which surveyed 1186 minors and 166 teachers. The analysis was based on non-parametric statistics; the Mann–Whitney U statistic was applied as the appropriate measure for comparing independent samples (teachers and students) with a non-normal distribution (p < 0.05). The results were surprising in that they highlighted that minors were more expert than expected in their use of technology and their awareness of the risks of disinformation. These conclusions make it clear that technological tools have the potential to raise awareness of the dangers of disinformation and improve the sustainability of education. Full article

Background: Mental health issues among medical students have gained increasing attention globally, with studies indicating a high prevalence of psychological disorders within this population. The use of antidepressants and anti-anxiety medications has become a common response to these mental health challenges. However, it is crucial to understand the extent of their usage and associated effects on students’ mental health and academic performance. This cross-sectional study explored the use of antidepressants and anti-anxiety drugs and their impact on the mental health of medical students in Saudi Arabia. Methods: A cross-sectional survey of 561 medical students from 34 universities was conducted between March and July 2024. An anonymous online questionnaire was used to collect sociodemographic, mental health, and medication usage-related information. Results: Most of the participants were female (71.5%) and aged 21–25 years (62.7%). Approximately 23.8% of them used antidepressants, 5.6% reported using anti-anxiety medications, and 14.0% used both types of medication. Among the medication users, 71.7% were using selective serotonin reuptake inhibitors (SSRIs), and 28.3% were using other medications. Adverse drug reactions were reported by 58.8% of the participants, and 39.6% changed drugs with inadequate efficacy. Notably, 49.0% of the respondents who have ever used medications discontinued their medication without consulting a healthcare professional. Despite these challenges, 62.0% of the participants felt that their medications had a positive impact on their academic performance, 73.4% believed that the benefits outweighed the drawbacks, and 76.2% expressed a willingness to continue taking their medication. In particular, 77.6% agreed that treatment with these drugs could prevent mental breakdowns. Sleep duration, physical activity, and family history of psychiatric disorders were significantly associated with medication use, with p values of 0.002, 0.014, and 0.042, respectively. Conclusions: These results shed light on the need to understand the prescribing practices of antidepressant and anti-anxiety drugs among medical students while promoting the appropriate use of these medications among the students. There is a need to incorporate mental health interventions into counseling services and awareness programs to support students. Future longitudinal studies are needed to explore long-term trends. Full article

In recent years, a growing number of real-time semantic segmentation networks have been developed to improve segmentation accuracy. However, these advancements often come at the cost of increased computational complexity, which limits their inference efficiency, particularly in scenarios such as autonomous driving, where strict real-time performance is essential. Achieving an effective balance between speed and accuracy has thus become a central challenge in this field. To address this issue, we present a lightweight semantic segmentation model tailored for the perception requirements of autonomous vehicles. The architecture follows an encoder–decoder paradigm, which not only preserves the capability for deep feature extraction but also facilitates multi-scale information integration. The encoder leverages a high-efficiency backbone, while the decoder introduces a dynamic fusion mechanism designed to enhance information interaction between different feature branches. Recognizing the limitations of convolutional networks in modeling long-range dependencies and capturing global semantic context, the model incorporates an attention-based feature extraction component. This is further augmented by positional encoding, enabling better awareness of spatial structures and local details. The dynamic fusion mechanism employs an adaptive weighting strategy, adjusting the contribution of each feature channel to reduce redundancy and improve representation quality. To validate the effectiveness of the proposed network, experiments were conducted on a single RTX 3090 GPU. The Dynamic Real-time Integrated Vision Encoder–Segmenter Network (DriveSegNet) achieved a mean Intersection over Union (mIoU) of 76.9% and an inference speed of 70.5 FPS on the Cityscapes test dataset, 74.6% mIoU and 139.8 FPS on the CamVid test dataset, and 35.8% mIoU with 108.4 FPS on the ADE20K dataset. The experimental results demonstrate that the proposed method achieves an excellent balance between inference speed, segmentation accuracy, and model size. Full article

High-resolution range profile (HRRP) recognition serves as a foundational task in radar automatic target recognition (RATR), enabling robust classification under all-day and all-weather conditions. However, existing approaches often struggle to simultaneously capture the multi-scale spatial dependencies and global spectral relationships inherent in HRRP signals, limiting their effectiveness in complex scenarios. To address these limitations, we propose a novel multi-scale domain perception network tailored for HRRP-based target recognition, called MSDP-Net. MSDP-Net introduces a hybrid spatial–spectral representation learning strategy through a multiple-domain perception HRRP (DP-HRRP) encoder, which integrates multi-head convolutions to extract spatial features across diverse receptive fields, and frequency-aware filtering to enhance critical spectral components. To further enhance feature fusion, we design a hierarchical scale fusion (HSF) branch that employs stacked semantically enhanced scale fusion (SESF) blocks to progressively aggregate information from fine to coarse scales in a bottom-up manner. This architecture enables MSDP-Net to effectively model complex scattering patterns and aspect-dependent variations. Extensive experiments on both simulated and measured datasets demonstrate the superiority of MSDP-Net, achieving 80.75% accuracy on the simulated dataset and 94.42% on the measured dataset, highlighting its robustness and practical applicability. Full article

Background: Rickettsioses are diseases caused by obligate intracellular non-motile coccobacilli transmitted via arthropods. The most common rickettsioses are scrub typhus (ST), typhus group rickettsioses (TGR), and spotted fever group rickettsioses (SFGR). This study aims to provide information and insight into rickettsioses seropositivity among suspected patients in East and Peninsular Malaysia over a six-year period from 2016 to 2021. Methodology/Principal Findings: Data obtained from four state hospitals and one national research institute providing rickettsial serological testing were analyzed using the IBM SPSS (Statistical Package for the Social Sciences) software program. The six-year analysis revealed that ST had the highest number of seropositivity cases, followed by TGR, and SFGR, for both immunoglobulin M (IgM) and immunoglobulin G (IgG) antibodies. Of the 3228 samples, 21.6%, 16.1%, and 13.9% of suspected patients were IgM seropositive for ST, TGR, and SFGR, respectively. IgG seropositivity for ST was 21.9%, followed by TGR at 21.4%, and SFGR at 17.2% among suspected rickettsioses cases. All regions in Malaysia were significantly associated with IgM seropositivity for ST, TGR, and SFGR. IgM seropositivity for SFGR was significantly higher in females. Age group 41–65 years was highly associated with IgG seropositivity for ST, TGR, and SFGR. Conclusions/Significance: Analysis of six-year data on ST, TGR, and SFGR seropositivity in Malaysia revealed variations across regions, age groups, and genders. This seropositivity study underscores ST, TGR, and SFGR as possible causes of acute febrile illness among patients suspected of rickettsial disease in Malaysia. The findings contributed to the awareness of reemerging rickettsioses and warrant public health interventions that may reduce the incidence of rickettsioses in Malaysia. Abstract summary: Scrub typhus (ST), typhus group rickettsioses (TGR), and spotted fever group rickettsioses (SFGR) are significant global public health concerns. Our results showed that the highest number of IgM and IgG seropositivity cases was observed for ST, followed by TGR and SFGR. All regions in Malaysia were significantly associated with IgM seropositivity for ST, TGR, and SFGR. East Malaysia exhibited significantly higher seropositivity for ST, TGR, and SFGR than other regions in Malaysia. IgM seropositivity for SFGR was significantly higher in females. The age group 41–65 years was highly associated with IgG seropositivity for ST, TGR, and SFGR. This study highlights the value of serological data in uncovering the hidden burden of disease in Malaysia. In addition, the findings contributed to bridging knowledge gaps on the limited data from Malaysia spanning extended periods, despite being one of the countries in the endemic Tsutsugamushi Triangle. The findings from this study may direct future research on rickettsioses and warrant public health interventions in Malaysia. Full article

Federated learning (FL) enables multiple participants to collaboratively train models while efficiently mitigating the issue of data silos. However, large-scale heterogeneous data distributions result in inconsistent client objectives and catastrophic forgetting, leading to model bias and slow convergence. To address the challenges under non-independent and identically distributed (non-IID) data, we propose DPAO-PFL, a Dynamic Parameter-Aware Optimization framework that leverages continual learning principles to improve Personalized Federated Learning under non-IID conditions. We decomposed the parameters into two components: local personalized parameters tailored to client characteristics, and global shared parameters that capture the accumulated marginal effects of parameter updates over historical rounds. Specifically, we leverage the Fisher information matrix to estimate parameter importance online, integrate the path sensitivity scores within a time-series sliding window to construct a dynamic regularization term, and adaptively adjust the constraint strength to mitigate the conflict overall tasks. We evaluate the effectiveness of DPAO-PFL through extensive experiments on several benchmarks under IID and non-IID data distributions. Comprehensive experimental results indicate that DPAO-PFL outperforms baselines with improvements from $5.41\%$ to $30.42\%$ in average classification accuracy. By decoupling model parameters and incorporating an adaptive regularization mechanism, DPAO-PFL effectively balances generalization and personalization. Furthermore, DPAO-PFL exhibits superior performance in convergence and collaborative optimization compared to state-of-the-art FL methods. Full article

Rabies is a fatal but entirely vaccine-preventable disease, with the highest risk in areas where free-roaming domestic dogs are prevalent. Understanding dog owners’ knowledge, attitudes, and practices (KAP) is crucial for shaping effective rabies control strategies. This scoping review aimed to synthesize global evidence from studies evaluating dog owners’ KAP to identify behavioral factors relevant to rabies prevention and control. A systematic literature search was conducted using PubMed, Web of Science, and Scopus, covering the period from 2012 to 2025. Seventy full-text articles were included based on predefined criteria. The findings reveal substantial gaps in dog owners’ knowledge, beliefs, and behaviors regarding rabies prevention. While general awareness of rabies is high among dog owners, their knowledge about transmission, clinical signs, and the fatal nature of the disease is inconsistent, with significant variability across studies. The vaccination uptake also varied widely across studies, ranging from less than 1% to over 90%, with no study reporting full coverage. Furthermore, a strong positive correlation was found between vaccination practice and the awareness of vaccine benefits (r = 0.69, p = 0.004). Common barriers to vaccination include lack of information, vaccine accessibility, distance to clinics, and personal constraints. These insights underscore the importance of early and targeted communication about vaccination campaigns. Future research should focus on periodically evaluating KAP before and after interventions to better inform rabies control efforts. Full article

Single image super-resolution is the inverse problem of reconstructing a high-resolution image from its low-resolution counterpart. Although recent Transformer-based architectures leverage global context integration to improve reconstruction quality, they often overlook frequency-specific characteristics, resulting in the loss of high-frequency information. To address this limitation, we propose the Dual Frequency Adaptive Network (DFAN). DFAN first decomposes the input into low- and high-frequency components via Stationary Wavelet Transform. In the low-frequency branch, Swin Transformer layers restore global structures and color consistency. In contrast, the high-frequency branch features a dedicated module that combines Directional Convolution with Residual Dense Blocks, precisely reinforcing edges and textures. A frequency fusion module then adaptively merges these complementary features using depthwise and pointwise convolutions, achieving a balanced reconstruction. During training, we introduce a frequency-aware multi-term loss alongside the standard pixel-wise loss to explicitly encourage high-frequency preservation. Extensive experiments on the Set5, Set14, BSD100, Urban100, and Manga109 benchmarks show that DFAN achieves up to +0.64 dBpeak signal-to-noise ratio, +0.01 structural similarity index measure, and −0.01learned perceptual image patch similarity over the strongest frequency-domain baselines, while also delivering visibly sharper textures and cleaner edges. By unifying spatial and frequency-domain advantages, DFAN effectively mitigates high-frequency degradation and enhances SISR performance. Full article