151398 research outputs found
Sort by
The impact of weather variability on renewable energy consumption: insights from explainable machine learning models
No full textThe pursuit of carbon neutrality is reshaping global energy systems, making the transition to renewable energy critical for mitigating climate change. However, unstable weather conditions continue to challenge energy consumption stability and grid reliability. This study investigates the effectiveness of various machine learning (ML) models at predicting energy consumption differences and employs the SHapley Additive Explanations (SHAP) interpretability tool to quantify the influence of key weather variables, using five years of data (2017–2022) and 196,776 observations collected across Europe. The dataset consists of hourly weather and energy consumption records, and key variables such as Global Horizontal Irradiance (GHI), sunlight duration, day length, cloud cover, and humidity are identified as critical predictors. The results demonstrate that the Random Forest (RF) model achieves the highest accuracy and stability (R2 = 0.92, RMSE = 360.17, MAE = 208.84), outperforming other models in predicting energy consumption differences. Through SHAP analysis, this study demonstrates the profound influence of GHI, which exhibits a correlation coefficient of 0.88 with energy consumption variance. Incorporating advanced data preprocessing and predictor selection techniques remains the RMSE of RF but reduces the RMSE by approximately 25% for the XGBoost model, underlining the importance of selecting appropriate input variables. Hyperparameter tuning further enhances model performance, particularly for less robust algorithms prone to overfitting. The study reveals the complex seasonal and regional effects of weather conditions on energy demands. These findings underscore the effectiveness of ML models at addressing the challenges of complex energy systems and provide valuable insights for policymakers and practitioners to optimize energy management strategies, integrate renewable energy sources, and achieve sustainable development objectives.<br/
A state-of-the-art appraisal of nanomaterials in microneedles in the delivery of therapeutics and vaccines
No full textNanomaterial‐loaded microneedles are a novel development in the fields of medicine and vaccines. Researchers have created extremely effective systems for the targeted and controlled delivery of a variety of bioactive agents by fusing nanomaterials with microneedle platforms. The design and manufacturing processes of nanomaterial‐loaded microneedles are covered herein, along with applications to improve drug stability, bioavailability, and patient adherence. Important preclinical and clinical studies that demonstrate the efficiency of these systems in delivering small molecules, biologics, and vaccines are also covered in the review. In order to direct ongoing research and expedite the clinical translation of this promising technology, important challenges and future directions are identified. This review offers a thorough evaluation of the most recent developments in this quickly developing field of technology
Mapping drug-resistant tuberculosis treatment outcomes in Hunan Province, China
No full textBackground: Drug-resistant tuberculosis (DR-TB) remains a major public health challenge in China, with varying treatment outcomes across different regions. Understanding the spatial distribution of DR-TB treatment outcomes is crucial for targeted interventions to improve treatment success in high-burden areas such as Hunan Province. This study aimed to map the spatial distribution of DR-TB treatment outcomes at a local level and identify sociodemographic and environmental factors associated with poor treatment outcomes in Hunan Province, China. Methods: A spatial analysis was conducted using DR-TB data from the Tuberculosis Control Institute of Hunan Province, covering the years 2013 to 2018. The outcome variable, the proportion of poor treatment outcomes, was defined as a composite measure of treatment failure, death, and loss to follow-up. Sociodemographic, economic, healthcare, and environmental variables were obtained from various sources, including the WorldClim database, the Malaria Atlas Project, and the Hunan Bureau of Statistics. These covariates were linked to a map of Hunan Province and DR-TB notification data using R software version 4.4.0. The spatial clustering of poor treatment outcomes was analyzed using the local Moran’s I and Getis–Ord statistics. A Bayesian logistic regression model was fitted, with the posterior parameters estimated using integrated nested Laplace approximation (INLA). Results: In total, 1381 DR-TB patients were included in the analysis. An overall upward trend in poor DR-TB treatment outcomes was observed, peaking at 14.75% in 2018. Deaths and treatment failures fluctuated over the years, with a notable increase in deaths from 2016 to 2018, while the proportion of patients lost to follow-up significantly declined from 2014 to 2018. The overall proportion of poor treatment outcomes was 9.99% (95% credible interval (CI): 8.46% to 11.70%), with substantial spatial clustering, particularly in Anxiang (50%), Anren (50%), and Chaling (42.86%) counties. The proportion of city-level indicators was significantly associated with higher proportions of poor treatment outcomes (odds ratio (OR): 1.011; 95% CRI: 1.20 December 2024 001–1.035). Conclusions: This study found a concerning increase in poor DR-TB treatment outcomes in Hunan Province, particularly in certain high-risk areas. Targeted public health interventions, including enhanced surveillance, focused healthcare initiatives, and treatment programs, are essential to improve treatment success
Using approximate matching and machine learning to uncover malicious activity in logs
No full textThe rapid expansion of digital services has led to an unprecedented surge in digital data production. Logs play a critical role in this vast volume of data as digital records capture notable events within systems or processes. Large-scale systems generate an overwhelming number of logs, making manual examination by analysts infeasible during critical events or attacks. While hashes, whether cryptographic or fuzzy, are widely used in digital forensics because they serve as the foundation for software integrity and validation, authentication and identification, similarity analysis, and fragment detection, this study investigates and extends the use of approximate matching (AM) algorithms in semi-structured data, such as logs. Existing AM algorithms such as ssdeep, sdhash, TLSH, and LZJD struggle particularly with semi-structured data due to the size of the input data being comparatively small, with syntactical and structural information comprising a significant amount of the data. We present a novel approximate matching algorithm for application across a range of semi-structured data types, which requires no knowledge of the underlying data structure. The algorithm produces digests that serve as input to a machine learning classifier, classifying the behaviour of the underlying logs the hashes represent. Experimental results on a benchmark dataset of IoT network traffic show that the proposed framework can correctly discern malicious logs from benign records with a 95% accuracy, with an F1 score of 0.98. The behaviour of the records deemed malicious was then correctly identified with a 99% accuracy when evaluated using a test data set, producing an average F1 score of 0.99. Additionally, we demonstrate that this approach provides a faster and lightweight framework to perform classification with high accuracy on a list of logs, producing those indicative of an attack for review.<br/
SaaS-enabled RGB to hyperspectral imaging: a novel paradigm in image processing technology
No full textIn the rapidly evolving domain of image processing, the conversion from RGB to hyperspectral imaging represents a significant leap forward, offering unparalleled depth and accuracy in image analysis with a lower cost. This paper introduces a novel Software-as-a-Service (SaaS) framework that revolutionizes this transition, making hyperspectral imaging more accessible and efficient for various applications. We propose an advanced Deep Learning algorithm that seamlessly converts standard RGB images into hyperspectral data, leveraging cloud and edge computing to enhance processing power and scalability. This method not only democratizes high-end imaging technology for broader use but also significantly reduces the cost and complexity traditionally associated with hyperspectral imaging. Our analysis shows that our SaaS platform is much easier to use than traditional hyperspectral image acquisition techniques. Additionally, it clearly demonstrates how a software-centric approach reduces acquisition time.<br/
A comprehensive CNN model for age-related macular degeneration classification using OCT: integrating inception modules, SE Blocks, and ConvMixer
No full textBackground/Objectives: Age-related macular degeneration (AMD) is a significant cause of vision loss in older adults, often progressing without early noticeable symptoms. Deep learning (DL) models, particularly convolutional neural networks (CNNs), demonstrate potential in accurately diagnosing and classifying AMD using medical imaging technologies like optical coherence to-mography (OCT) scans. This study introduces a novel CNN-based DL method for AMD diagnosis, aiming to enhance computational efficiency and classification accuracy. Methods: The proposed method (PM) combines modified Inception modules, Depthwise Squeeze-and-Excitation Blocks, and ConvMixer architecture. Its effectiveness was evaluated on two datasets: a private dataset with 2316 images and the public Noor dataset. Key performance metrics, including accuracy, precision, recall, and F1 score, were calculated to assess the method’s diagnostic performance. Results: On the private dataset, the PM achieved outstanding performance: 97.98% accuracy, 97.95% precision, 97.77% recall, and 97.86% F1 score. When tested on the public Noor dataset, the method reached 100% across all evaluation metrics, outperforming existing DL approaches. Conclusions: These results highlight the promising role of AI-based systems in AMD diagnosis, of-fering advanced feature extraction capabilities that can potentially enable early detection and in-tervention, ultimately improving patient care and outcomes. While the proposed model demon-strates promising performance on the datasets tested, the study is limited by the size and diversity of the datasets. Future work will focus on external clinical validation to address these limita-tions
Mind the gap: detecting black-box adversarial attacks in the making through query update analysis
No full textAdversarial attacks remain a significant threat that can jeopardize the integrity of Machine Learning (ML) models. In particular, query-based black-box attacks can generate malicious noise without having access to the victim model's architecture, making them practical in real-world contexts. The community has proposed several defenses against adversarial attacks, only to be broken by more advanced and adaptive attack strategies. In this paper, we propose a framework that detects if an adversarial noise instance is being generated. Unlike existing stateful defenses that detect adversarial noise generation by monitoring the input space, our approach learns adversarial patterns in the input update similarity space. In fact, we propose to observe a new metric called Delta Similarity (DS), which we show it captures more efficiently the adversarial behavior. We evaluate our approach against 8 state-of-the-art attacks, including adaptive attacks, where the adversary is aware of the defense and tries to evade detection. We find that our approach is significantly more robust than existing defenses both in terms of specificity and sensitivity.<br/
Perspectives of patients on the role of general practice pharmacists: a systematic review and meta-synthesis of qualitative studies
No full textBackgroundThere is a scarcity of research about patients’ perspectives on the role of general practice pharmacists (GPPs). In this review, we aimed to compile qualitative evidence of patients’ perspectives regarding the role of GPPs.MethodsA systematic, qualitative meta-synthesis was undertaken. A comprehensive search was conducted on six databases. Additionally, the reference lists of included studies were searched. Findings and verbatim quotes were extracted from the included studies and were analysed using thematic synthesis. The Critical Appraisal Skills Programme (CASP) checklist was employed to evaluate the quality of the included studies. The GRADE-CERQual approach was utilised to evaluate confidence in the findings.ResultsTen qualitative studies were included. Four main themes were identified: awareness of the GPP (patients were unaware of the GPP’s role), accessibility to the GPP (some patients had difficulties arranging appointments with GPPs), benefits and challenges (medication review conducted by GPPs reaffirmed patients’ trust in taking their medicines, although some were dissatisfied with the medication review process), and GPP integration into general practice (successful integration of GPPs was attributed to their skills and teamwork). The included studies satisfied all or at least seven out of the ten criteria of the CASP checklist. GRADE-CERQual indicated high confidence for one theme, and moderate confidence for three themes.ConclusionsThis systematic review and meta-synthesis of qualitative studies provides valuable insights into patients’ perspectives on the role of GPPs. The findings highlight both positive aspects and challenges associated with GPP integration into primary care, including concerns about role awareness and accessibility. These findings suggest that while GPPs can add value to general practice teams, there is a need for improved patient education about the GPP role and enhanced accessibility to maximise the potential benefits of the GPPs.<br/
"Thriving at work" in tourism and hospitality: An integrative systematic literature review and research agenda
No full textDespite the fast-growing scholarship, Thriving at Work (TAW) investigations in tourism and hospitality remain fragmented, failing to capture the full range of factors and context-specific conditions influencing TAW experiences. This study aims to address these gaps by developing a comprehensive framework that conceptualizes TAW within the unique context of tourism and hospitality, mapping out knowledge of what TAW entails and how it can be effectively nurtured in these sectors. Through an integrative systematic literature review of 31 peer-reviewed studies, the research highlights the integration of self-determination states (autonomy, competence, and relatedness) to existing TAW conceptualizations. We map out enablers and outcomes of TAW at multiple levels—individual, team, and organizational—and propose a research agenda for multidisciplinary studies to explore personal experiences of TAW, collective thriving, the influence of customers, and the organizational impact of thriving workforces. This review significantly contributes to tourism and hospitality scholarship, organizational psychology, and behavior, providing a structured approach to studying TAW and equipping practitioners with targeted strategies for cultivating a thriving and sustainable workforce
Losing my job and family? How power shapes the boundaries between work and family life
No full textJob insecurity is often understood as the perceived powerlessness to maintain desired continuity in one’s job, and experiences of it can have significant implications for both work and family life. Despite the crucial role of power in conceptualising the effects of job insecurity, little is known regarding the role of power dependence in the relationship between job insecurity and work-family enrichment. To address this gap, we analysed three-wave data from 267 UK white-collar employees to test a model linking job insecurity to work-family enrichment. Our findings reveal that (1) job insecurity negatively impacts work-family enrichment, (2) approach and avoidance power-balancing operations mediate this relationship, and (3) the negative effect is weaker when psychological contract breach is low. This study advances theoretical understanding by demonstrating that asymmetric power dependence is a critical factor in determining when and why job insecurity diminishes work-family enrichment