Publication Management System
Not a member yet
3916 research outputs found
Sort by
Early-Stage Cardiovascular Disease Prediction Using a Sigmoidtropy-Based Decision Tree
Full text linkHeart disease (HD) is a significant health issue in the world, and its early and proper prediction is essential to minimize mortality and the development of the disease. Cardiovascular disease (CVD) is one of the diseases that need effective and stable predictive models to assist clinical decision-making. This paper gives a Sigmoidtropy-Based Decision Tree (SDT) model of cardiovascular disease prediction, which improves the traditional decision tree by adding a sigmoid-based formulation of entropy. The heart disease data are first grouped by the K-means clustering method in order to enhance the data representation. The suggested SDT model is tested on the Cleveland heart disease dataset of the UCI repository and compared to the traditional classifiers, such as Naive bayes, random forest, and the traditional Decision Tree models. Experimental findings indicate that the SDT has an accuracy of 99.67 which is better than the performance of Random Forest (76.89%), Decision Tree (76.56%), and Naive Bayes (81.84%) with a lower execution time. Despite the promising performance shown by the results, it needs further validation with more datasets and strong evaluation plans to determine the generalizability
Autoencoder-Based Nonlinear Dimension Reduction for Single-Cell RNA-Seq Data: A Comparative Study of t-SNE and UMAP
Full text linkThis paper proposes using an Autoencoder (AE) prior to t-SNE or UMAP visualization for scRNA-seq data. Direct application of t-SNE/UMAP to the raw, sparse expression matrix often yields unstable, poorly separated clusters. To address this, the framework first employs an AE to learn a denoised, compact latent representation. Subsequent t-SNE or UMAP embedding of this latent space produces more robust visualizations with enhanced cluster consistency and structural separability. A real-data-based comparison shows that, when using the same AE-derived latent space, UMAP outperforms t-SNE. It achieves better cluster cohesion, stronger global structure preservation, greater robustness to initialization and data perturbation, and lower computational cost. Statistical validation via a projection F-test confirms that clusters in the AE latent space exhibit significant between-group mean differences, quantifying the observed visual improvement. The study concludes that AE-based representation learning creates an effective input space for nonlinear embedding, with the AE-UMAP pipeline emerging as a particularly stable and efficient choice for scRNA-seq exploratory analysis.
Purpose: This study aims to investigate the effectiveness of AE based latent representations in enhancing nonlinear dimension reduction methods, namely t-SNE and UMAP, for single-cell gene expression data analysis. The performance of AE-based UMAP and AE-based t-SNE is systematically evaluated from multiple perspectives, including visualization quality, clustering consistency, structural preservation, and robustness.
Methods: This paper constructs a two-step dimension reduction framework for single-cell gene expression data analysis. First, an AE is employed to compress high-dimensional, sparse, and noisy gene expression data into a low-dimensional latent representation. Subsequently, t-SNE and UMAP are applied to the learned AE latent space for nonlinear embedding and visualization. The performance of different methods is systematically evaluated under multiple experimental conditions using clustering consistency metrics, structure preservation measures, and a projected F-test.
Results: Experimental results indicate that directly applying t-SNE or UMAP to the original expression data fails to stably recover meaningful clustering structures, whereas nonlinear dimension reduction performed on AE latent representations substantially improves visualization quality and clustering stability. Within the same latent space, t-SNE and UMAP exhibit comparable performance in terms of clustering accuracy; however, UMAP demonstrates superior performance with respect to cluster compactness, global structure preservation, stability across repeated experiments, and computational efficiency. Statistical testing further confirms the significance of between cluster differences in the AE latent space.
Contribution: This study systematically reveals the critical role of AE latent representations in stabilizing nonlinear dimension reduction for single cell data and provides a quantitative comparison between t-SNE and UMAP within a unified latent space. The results demonstrate that UMAP applied to AE latent representations achieves superior performance in terms of visualization stability and computational efficiency, offering a more robust two step dimension reduction strategy for exploratory analysis of high dimensional single cell data
Interactive Effect of Gender and Self-Efficacy on Mathematics Achievement among Students with Mild Intellectual Disability in Calabar Education in Cross River State of Nigeria: Implications for Inclusive Education
No full textBackground: Due to the poor academic achievement of identified SS1 students with mild intellectual disabilities in public secondary schools, this research investigates how gender interacts with self-efficacy regarding mathematics achievement. The goal is to improve these students' academic achievement in mathematics. Studies on the interactive effects of gender and self-efficacy on mathematics achievement in Nigeria are scarce.
Objective: This paper examines the interactive effect of gender and self-efficacy on the mathematics achievement of SS1 students with mild intellectual disabilities in the Calabar Education Zone of Cross River State, Nigeria.
Methodology: An ex-post facto design was adopted. The study population consisted of 4,031 Senior Secondary (SSI) students with mild intellectual disabilities in the Calabar Education Zone of Cross River State, Nigeria. A sample of 538 students was selected (286 males and 252 females). The instruments used for data collection were the Mathematics Achievement Test (MAT) and a Mathematics Self-Efficacy Rating Scale Questionnaire (MSERSQ). The reliability coefficients were strong (KR-20 = 0.83, Cronbach's Alpha = 0.79) for the MAT and MSERSQ, respectively, indicating good reliability. The study was guided by two research hypotheses. Descriptive statistics were used to describe the collected data, while analysis of covariance and Pearson product-moment correlation were used to test the first hypothesis, and a two-way ANOVA was used to test the second hypothesis.
Results: The analysis using Pearson product-moment correlation indicated a significant positive correlation between self-efficacy and mathematics achievement among students with mild intellectual disabilities (r = 0.656, n = 538, p < 0.05). The results of the two-way ANOVA indicated a statistically significant interaction between gender and self-efficacy on mathematics achievement (F = 13.670, n = 538, p = 0.000). This interaction suggests that the influence of self-efficacy on mathematics achievement varies by gender. Specifically, male students (mean = 31.818, SD = 8.320) tended to achieve higher mathematics scores than female students (mean = 27.389, SD = 7.736) did, given their self-efficacy levels.
Conclusion: The study found a significant positive relationship between self-efficacy and mathematics achievement, and an interaction between gender and self-efficacy among students with mild intellectual disabilities.
Unique Contribution: This paper highlights the unique influence of self-efficacy and the interactive effect of gender and self-efficacy on students with mild intellectual disabilities' mathematics achievement.
Recommendation: The government should ensure that sufficient qualified counselors are recruited to help raise students' self-efficacy and guide them accordingly
Hispanic Parent-Child Relationships and Communication on Substance Use and Sex in 4th-6th Graders
Full text linkBackground and Purpose: Parent-child communication is vital in preventing pre-adolescent health risk behaviors such as substance use and sex, yet little is known about these dynamics in Hispanic families. This study explored how Hispanic parents and their pre-adolescent children communicate about such risks.
Methods: Using a qualitative descriptive design, researchers conducted focus groups and interviews with 24 Hispanic parents and 23 children (grades 4–6) from an afterschool program in the Southeastern U.S. Data were analyzed using conventional and directed content analysis.
Results: Children expressed love and respect for their parents but were hesitant to discuss sensitive topics. Parents wanted to guide their children but struggled with timing conversations about sex, managing media use, and general parenting challenges. Mothers noted that fathers were often less involved in these discussions.
Conclusions: Culturally and developmentally tailored interventions are needed to support Hispanic parents in addressing risk behaviors with their children
Buffalo Identification in Mixed-Species Environments: A Comparative Deep Learning Approach Using ResNet50 and EfficientNetB3
Full text linkAbstract: Background: Buffaloes are integral to agricultural economies, particularly in regions that depend on them for milk production, labor, and income. However, their accurate visual identification in mixed-species environments, especially when co-existing with animals like elephants and rhinos, remains a technological challenge.
Method: This study explores deep learning-based image classification for species-specific buffalo detection using two convolutional neural network architectures: ResNet50 and EfficientNetB3. A balanced image dataset comprising four classes (buffalo, elephant, rhino, zebra) was curated, with training (80%) and validation (20%) splits. The models were fine-tuned using transfer learning, with custom dense layers added atop frozen base layers. EfficientNetB3 used higher-resolution inputs (300x300) and extensive augmentation, while ResNet50 operated on 300x300 images. Performance was evaluated using confusion matrices and key metrics, including validation accuracy, precision, recall, and F1-score, primarily focusing on buffalo classification.
Results: ResNet50 achieved a validation accuracy of 47%, and EfficientNetB3 achieved 42%. However, ResNet50 misclassified buffaloes heavily, resulting in a buffalo recall of only 0.07 and an F1-score of 0.11. In contrast, EfficientNetB3 correctly classified 72 out of 200 buffalo images, achieving a buffalo recall of 0.36 and an F1-score of 0.32. These numerical results highlight EfficientNetB3’s superior ability to identify buffaloes accurately in complex visual contexts.
Conclusion: EfficientNetB3 is more effective than ResNet50 for buffalo-focused image recognition tasks, offering higher sensitivity and precision in buffalo classification. This study supports the development of AI-powered species-specific monitoring tools, aiding in health tracking, ecological studies, and smart agricultural systems
Parental Knowledge Attitudes and Practice Towards Headaches Among Elementary School-Aged Children in Al-Baha, Saudi Arabia
Full text linkAim: To evaluate parental knowledge, attitudes, and practices regarding childhood headaches in Al-Baha, Saudi Arabia, and identify gaps that could inform targeted educational interventions.
Methods: A cross-sectional online survey was administered to 399 parents residing in Al-Baha. The survey assessed parental understanding, behavior, and perceptions concerning pediatric headaches. Data analysis was conducted using SPSS version 27.0, applying descriptive statistics, Mann–Whitney U, Kruskal–Wallis, and Spearman’s correlation tests.
Results: Among the respondents, 52.4% were female (N = 209) and 47.6% male (N = 190), with a mean age of 42.56 years. Female participants exhibited significantly higher knowledge scores than their male counterparts. The most frequently reported headache triggers were sleep disturbances (79.4%), vision problems (61.7%), and psychological factors (52.1%), whereas malnutrition was identified by only 48.9% of respondents. Symptom monitoring practices varied: 46.1% of parents reported observing symptoms before seeking medical care, while 23.0% considered headaches an emergency. Notably, 57.4% sought professional consultation when symptoms persisted, yet 32.1% administered painkillers without medical advice. Knowledge scores were positively correlated with both attitude scores (r = 0.151, p = 0.002) and practice scores (r = 0.336, p < 0.001).
Conclusion: The findings indicate that parental understanding of childhood headaches is often limited, particularly concerning nutritional triggers and evidence-based management strategies. This underscores the urgent need for targeted educational initiatives to enhance awareness, promote appropriate health-seeking behavior, and reduce the risk of mismanagement
Strengthening the Health System to Address the COVID-19 Surge: An Empirical Study in South Kalimantan Province, Indonesia
Full text linkThe COVID-19 case entered South Kalimantan Province on May 12, 2020, and spread throughout all districts/cities. This research aims to examine the ability of the South Kalimantan Provincial Health System to address the COVID-19 pandemic. This study analyses secondary data from the South Kalimantan Provincial Health Office and in-depth interviews with policymakers. This study assesses the capacity of the South Kalimantan health system in managing the COVID-19 pandemic. Findings reveal significant challenges, including hospital bed shortages, high infection rates among health workers (10.02%), and limited ventilator availability. Despite allocating 23.27% of the health budget to the pandemic response, key subsystems such as human resources, drug supply, and coordination mechanisms remained under strain. Strengthening these subsystems is essential for better preparedness in future health emergencies. In conclusion, strengthening the health system is very important in overcoming the COVID-19 pandemic, and it is hoped that the lessons of the COVID-19 pandemic will make the health system more prepared to address the disease pandemic
The Influence of Emotional Intelligence on Coping Skills
Full text linkBackground: The relevance of the study is determined by the interest in studying the influence of emotional intelligence (EI) on stress resistance, which is of great importance in view of numerous stress factors.
Objective: The aim of the study is to determine the influence of EI on coping skills and the choice of coping strategies.
Methods: The study employs a test method (Mayer-Salovey-Caruso Emotional Intelligence Test (MSCEIT), Holmes-Rahe Stress Inventory). The Coping Strategies Questionnaire (CSQ) was also used. The results were processed using statistical methods (mean, range, mode and median, the Mann-Whitney U test, Pearson correlation coefficient (PCC)). The factor analysis was carried out.
Results: More pronounced emotion regulation (weight 0.53) have been found in men, while women better recognize emotions (weight 0.45). The correlation between the level of EI and adaptive strategies is confirmed: high EI reduces the negative cumulative effect of stress (M = 55 in a group with high EI). High EI is related to active stress strategies, such as planning and seeking social support, confirming its role as a protective factor.
Conclusion: It can be argued that the high EI significantly reduces the frequency, intensity of stress and its impact, facilitating adaptive strategies for overcoming it. Further studies may focus on the influence of EI on stress resistance in different age and cultural groups, as well as on long-term effects in the context of professional stress
Effectiveness of Art-Therapy-Based Intervention Programmes for Improving Social Communication in Children with Rett Syndrome
No full textThe research into effective art-therapy-based interventions for improving the social communication skills of children with Rett syndrome is important for the adaptation of this group of children. This study aims to evaluate the effect of a 6-month art-therapy-based intervention program based on art therapy on improving social communication in children with Rett syndrome. The research employed a quasi-experimental method, direct (unstructured) observation, a standardized Social Responsiveness Scale, and mathematical and statistical data processing methods (Levene test, paired sample t-test). The results showed a significant improvement in social communication in the experimental group (EG) after the intervention, as evidenced by paired and independent sample t-tests. This indicates statistically significant differences between pre-and post-test scores in the EG (mean difference 14.525 with a standard deviation of 22.592). The standard error for this group was 3.572, and the 95% confidence interval for the mean difference ranged from 7.300 to 21.750. The Student's t-test reached 4.066 with 39 degrees of freedom, resulting in a two-tailed p-value of less than 0.001. It has been found that art therapy can significantly improve social communication and emotional regulation subscales in children with Rett syndrome. The obtained data indicate the need to include therapeutic strategies based on art therapy in intervention programs for children with Rett syndrome. Prospects for further research are based on studying the impact of art therapy and other interventions not only on social communication but also on the cognitive development of children with Rett syndrome
Research on Renewal Design of Humanistic Space under the Perspective of Chinese Poetic Space: Study on the Renovation Design of Fotuguan Park in Chongqing
Full text linkIn traditional Chinese culture, there is a concept of "poetic space", which emphasizes the atmosphere full of poetic romantic emotions in the environment. This atmosphere has rich emotional feelings and can convey a delicate personal aesthetic, which is an important feature of traditional Chinese aesthetic. In modern urban renewal, the implementation of poetic space transformation for areas with historical and humanistic aesthetic can better activate traditional humanistic and historical resources, which is conducive to the renewal and improvement of traditional parks and the maximization of social, cultural and economic benefits. Starting from the perspective of poetic space construction and public art, this paper explores the renewal design path of the unique landscape of Fotuguan Park, a traditional historical footpath park in Chongqing, and focuses on how contemporary public art intervenes in urban parks to establish effective site space and emotional connection between ancient and modern culture, so as to promote the improvement of urban humanistic quality