19684 research outputs found
Sort by
Developing A Framework for Identifying Motivational LA Features and Predicting Motivation Types Experienced by Computer Science Students in the UK
No full textA narrative inquiry exploring how the occupational identities of individuals seeking asylum in the UK shift over time
No full textData for: Modelling Phosphate and Arsenate Adsorption on Cerium Dioxide: A Density Functional Theory Study
No full textMobile Network Traffic Prediction Using Temporal Fusion Transformer
Get PDFThe continuous development of mobile communication technologies has led to a rapid increase in cellular network traffic. Therefore, traffic prediction models have become very important for the design of mobile communication networks, as they are essential for increasing the quality of service (QoS) and ensuring a high level of quality of experience (QoE). Accurate and timely prediction of network traffic volume enables efficient planning of radio resource allocation, improves network energy efficiency, and reduces network congestion and operational costs. However, the task of mobile network traffic prediction is inherently challenging due to the dynamic, multivariate nature of traffic patterns that are influenced by diverse factors such as location, user behavior, and temporal variations. In this article, we propose a novel prediction model based on deep learning techniques. Specifically, we develop a customized temporal fusion transformer (TFT) for accurate time series prediction that effectively captures the complex dependencies in mobile network traffic and ensures resilience to unexpected variations, which is critical for efficient network management and QoE enhancement. The prediction model is evaluated and tested against state-of-the-art prediction models using real-world cellular network data as the training dataset. The experimental results validate the excellence of this customized transformer architecture in capturing the complex temporal dynamics of cellular network traffic by exploiting attention-based mechanisms.</p
Fear of intimate partner and women’s engagement in exercise:insights from a national survey in Kenya
No full textBackground: Women in abusive or controlling relationships often experience restrictions on their autonomy, mobility, and decision-making capacity. Furthermore, fear of a husband or partner, whether stemming from psychological abuse, coercive control, or physical violence, may influence a woman’s ability to engage in health-promoting activities like exercise. However, the relationship between fear in intimate relationships and excercise remains underexplored. We examined whether there was an association between relational fear and women’s engagement in exercise, as well as the direction of this association. Methods: We analyzed the data of 5,052 women (15–49 years) who participated in the 2022 Kenya Demographic and Health Survey. We derived the outcome variable from the question: “how many days per week do you exercise?” The responses were recoded as ‘0 = do not exercise’ and ‘1/7 days = exercises’. All estimates were weighted. Cross-tabulations and two sets of binary logistic regression models were computed in STATA version 18. Statistical significance was set at p < 0.05. Results: Most women exercised three or more days per week (59.6%) while 22.9% did not exercise at all. Women who were most of the time afraid of their partner had a 47% higher likelihood of engaging in exercise compared to those who were never afraid (COR = 1.47, 95%CI: 1.16–1.88). After adjusting for confounders, this association weakened but remained significant (AOR = 1.33, 95%CI: 1.03–1.71). Similarly, women who were sometimes afraid of their partner showed significantly higher odds of engaging in exercise in both crude (COR = 1.30, 95%CI: 1.11–1.53) and adjusted models (AOR = 1.23, 95%CI: 1.04–1.46). Increasing age, higher education levels, rural residency and media exposure were strongly associated with increased exercise engagement. Conclusion: This study reveals a positive association between fear in intimate relationships and women’s engagement in exercise, suggesting that exercise may serve as a coping mechanism for some women experiencing relational fear. While these results contribute to the limited literature on the intersection of intimate partner dynamics and preventive health behaviors, they remain preliminary. Further research is needed to explore the causal pathways, contextual influences, and potential long-term implications of relational fear on exercise engagement.</p
Access Repository Dashboard
Do you manage Huddersfield Research Portal? Access insider analytics, issue reports and manage access to outputs from your repository in the CORE Repository Dashboard!