8333 research outputs found
Sort by
Leukemia Classification through Deep Learning Techniques and Generative AI
No full textLeukemia is a cancer originating in the bone marrow and leads to rapid proliferation of abnormal blood cells. The main objective of this study is to implement a Convolutional Neural Network (CNN) to detect and classify leukemia from microscopic cell images. The proposed framework combines a Generative Adversarial Network (GAN) that generates synthetic images of healthy cells to address class imbalance and training on a balanced leukemia dataset, with four different CNN architectures (InceptionV3, ResNet50, EfficientNetB3 and InceptionV4) - the effectiveness of this approach is validated on a Breast Cancer tumor dataset consisting of ultrasound images. Unlike prior studies that rely on standard augmentation, our approach incorporates synthetic image quality metrics (FID, IS, SSIM) to validate realism and structural fidelity.The results reveal GAN architecture achieving 16% higher performance on cell images compared to tumor images. Additionally, results obtained for each model were 76%, 80%, 75%, and 75% respectively, with RestNet50 attaining the best result. Obtained results underline potential contribution of deep learning in cancer detection and improving clinical outcomes through GAN-augmentation, addressing class imbalance effectively
Self-Organization in Metal Plasticity: An ILG Update †
No full textIn a 1987 article of the last author dedicated to the memory of a pioneer of classical plasticity Aris Philips of Yale, the last author outlined three examples of self-organization during plastic deformation in metals: persistent slip bands (PSBs), shear bands (SBs) and Portevin Le Chatelier (PLC) bands. All three have been observed and analyzed experimentally for a long time, but there was no theory to capture their spatial characteristics and evolution in the process of deformation. By introducing the Laplacian of dislocation density and strain in the standard constitutive equations used for these phenomena, corresponding mathematical models and nonlinear partial differential equations (PDEs) for the governing variable were generated, the solution of which provided for the first time estimates for the wavelengths of the ladder structure of PSBs in Cu single crystals, the thickness of stationary SBs in metals and the spacing of traveling PLC bands in Al-Mg alloys. The present article builds upon the 1987 results of the aforementioned three examples of self-organization in plasticity within a unifying internal length gradient (ILG) framework and expands them in 2 major ways by: (i) introducing the effect of stochasticity and (ii) capturing statistical characteristics when PDEs are absent for the description of experimental observations. The discussion focuses on metallic systems, but the modeling approaches can be used for interpreting experimental observations in a variety of materials
Sensitivity to Punishment and Reward, Tolerance for Ambiguity and Peer Influences on Positive Risk-Taking
No full textBackground: Taking risks is a decision we make as a part of everyday life. Most of the research perceives risks as negative but it’s important to acknowledge that risks can be positive too.
Aim: The purpose of this research is to investigate the extent to which positive risk-taking is predicted by sensitivity to reward and punishment, tolerance for ambiguity and peer influences, while also exploring associations of gender and age on positive risk-taking.
Methodology: A cross-sectional convenient sample design was utilised via survey to measure the Positive Risk-Taking Scale (PRT), Sensitivity to Punishment and Sensitivity to Reward Questionnaire (SPSRQ), Tolerance for Ambiguity Scale (TAS) and the Positive Peer Questionnaire (PPQ) among 153 adult participants across countries.
Results: The standard multiple regression analyses revealed that tolerance to ambiguity was the most significant predictor of positive risk taking. The independent t-test analysis found non-significant findings between men and women. The Spearman’s rank-order correlation analysis found non-significant findings between age and positive risk taking.
Conclusion: Broader implications include providing structured opportunities for positive risk taking in academic environments as it would allow growth of soft skills that can be applied in both academic and real-world settings
Hybrid FinBERT-LSTM Deep Learning Framework for Stock Price Prediction: A Sentiment Analysis Approach Using Earnings Call Transcripts
No full textStock market prediction remains a critical area of research due to its significant economic implications and inherent complexity. With advancements in machine learning, research interest has grown substantially in understanding the impact of textual data on financial forecasting. This study presents a hybrid FinBERT-LSTM model that combines sentiment analysis of quarterly earnings conference calls with traditional price prediction methods. We evaluate our model’s effectiveness against standalone LSTM approaches across six major US stocks from the financial and technology sectors. Experimental results demonstrate that the sentiment-enhanced hybrid model achieves superior predictive accuracy for four of the six studied stocks, as measured by Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE), and Accuracy metrics. Most notably, Citibank and Meta demonstrated substantial improvements when incorporating sentiment analysis, with MSE scores approximately 38 percent lower compared to predictions without sentiment data. Our findings contribute to the growing body of research on textual analysis in financial forecasting, offering practical implications for investment decision-making and aligning with the United Nations Sustainable Development Goal (SDG) 9—Industry, Innovation, and Infrastructure
Mate Value and Relationship Satisfaction in Dating Couples
No full textAims: Previous literature has looked at mate value and relationship satisfaction in a largely married sample. The current study examined the relationship between mate value and relationship satisfaction in, looked into any potential gender differences and sought to gain an insight on mate value as a predictor of relationship satisfaction in dating couples.
Method: A questionnaire was posted online where participants (n = 20) were able to partake. The questionnaire took roughly 6 minutes and consisted of the Røysamb Relationship Satisfaction Scale (RS10) and the Edlund and Sagarin Mate Value Scale.
Results: The results suggested that there was no correlation between mate value and relationship satisfaction amongst dating couples, there were no gender differences for relationship satisfaction and mate value and that duration of relationship in dating couples did not impact mate value or relationship satisfaction.
Conclusion: The findings of the current study provide a greater understanding into potential differences between married and unmarried couples in relation to mate value and relationship satisfaction. Findings may possess implications for how mate value could be examined in the future
The Impact of Colourism and Western Beauty Standards on the Self-Esteem of Women of Colour in Ireland
No full textThis study aimed to explore the relationship between how attitudes towards the components of colourism (self-concept, upward mobility, impression formation, and affiliation) and the endorsement of Western beauty standards affect the self-esteem of women of colour from various immigrant backgrounds in a predominately white country such as Ireland, addressing a critical gap within a global context as previous research suggests a need for intersectionality. A cross-sectional study design was employed (N=174) across diverse ethnic and immigrant backgrounds, using validated scales such as the Rosenberg Self-Esteem Scale, American Beauty Standards subscale and the In Group Colourism Scale. Multiple regression analysis revealed that the endorsement of Western beauty standards and upward mobility significantly predicted low self-esteem, explaining 54.4% of the variance. Generational and ethnic differences were analysed using two-way ANOVA’s, highlighting nuanced patterns within the descriptive statistics, as successive generations reported lower endorsement levels of Western beauty standards and attitudes towards colourism, but overall, there were no significant interactions between the variables. The findings of the results highlight the harmful effects of Western beauty standards and colourism on mental health and how prevalent this issue is, emphasising the need for culturally competent interventions, diverse media representation and educational initiatives to support self-acceptance and resilience among women of colour and their communities
Knowledge and Stigma of Alzheimer’s Disease in the General Population of Zimbabwe
No full textBackground: Previous research has shown large gaps in knowledge surrounding Alzheimer’s disease on a global level. In addition to this, there has been strong indication that lower levels of knowledge are associated with elevated levels of stigma. Aims: In order to understand the effect of this on the Zimbabwean population, overall knowledge and stigma were assessed.
Methodology: A quantitative correlational mixed within and between participant's design was used to investigate the extent in which outcomes of Alzheimer’s disease knowledge, perceived stigma and attitudes towards dementia are influenced by age, gender and educational attainment. The sample used to investigate the variables was that of 88 participants recruited form the general population of Zimbabwe.
Results: Alzheimer’s disease knowledge scale reveled low levels of knowledge within the sample. Perceived stigma scores indicated high levels of stigma, however, contradictory to this, attitudes towards dementia within the sample were shown to be more positive. Statistical analysis revealed that only knowledge of Alzheimer’s disease was predicted by age (p < .001). All other statistical analysis were non-significant.
Conclusion: The lack of knowledge shown by the sample indicates that policy needs to be put in place. Furthermore, further research needs to be conducted in order to gain a more in depth understanding on the levels of stigma within the population
The association between stress and academic performance
No full textAims: This study sought to investigate the complex relationship between stress and academic performance. Method: A questionnaire was administered to 69 participants. It included basic demographic questions and three scales. The Perceived Stress Scale (PSS-10), the Perceived Academic Performance Scale (PAPS) and the General Self-Efficacy Scale (GSE).
Results: An initial Pearson correlation analysis found a significant moderate negative between perceived stress and perceived academic performance (r = -.344, p = .004), however a multiple regression analysis that controlled for other variables did not find that perceived stress could significantly predict perceived academic performance (β = -.103, p = .522). Rather, general self-efficacy was the only variable able to significantly predict perceived academic performance (β = .445, p = .003). This model explained 24.3% of variance in academic performance.
Conclusion: Findings suggest that stress does not have a direct effect on academic performance when controlling for self-efficacy. This could mean that psychological interventions within a higher education context could be more effective at increasing academic performance by focusing on improving students’ self-efficacy rather than reducing stress. Though a combined approach is recommended. However, further research is necessary
The influence of social media on fashion marketing: an analysis of quantitative evidence from Irish consumers who are Instagram, YouTube, and Facebook users
No full textThe rapid growth of social media has significantly changed consumer behaviour and marketing strategies, especially in the fashion industry. This study examines the influence of platforms such as Instagram, YouTube and Facebook on Irish consumers' decision-making process and engagement with brands. A quantitative method including literature review, survey, and secondary data analysis is used to reveal users’ preferences and attitudes. The findings of the study revealed that both platforms and content preferences of audiences vary by age and gender. Generation Z prefers fast content and visual platforms such as TikTok and Instagram. Meanwhile, older generations favour Facebook and are cautious of new technologies, such as AI and virtual influencers. The crucial role of user-generated content in increasing brand engagement is confirmed. Moreover, sustainability and data privacy remain vital aspects in creating a trustworthy relationship between consumers and brands. The research confirms that successful social media marketing strategies require adaptation to the target audience and new technological and behavioural trends. The ethical component is also crucial for building customer loyalty. The thesis provides practical recommendations for optimising social media marketing in the context of the Irish fashion market
ConvLSTM-based tropical cyclone intensity estimation and classification using satellite imagery over the North Indian ocean
No full textTropical cyclones pose significant threats to coastal regions, and have a major negative influence on the environment and society. Precise cyclone identification and intensity estimation are crucial for effective early warning systems and disaster prevention. Traditional methods rely on manual interpretation and empirical models, often lacking efficiency and accuracy. This study proposes a deep learning framework that utilizes satellite image sequences for cyclone detection, classification, and intensity estimation. Unlike conventional models relying solely on spatial or manual features, the proposed hybrid architecture integrates Convolutional Neural Networks (CNNs) and ConvLSTM to learn spatiotemporal patterns jointly. Key innovations include the clustering-based cyclone region isolation method, sequence-level data augmentation, and the use of SMOTE to mitigate class imbalance. The proposed approach demonstrates substantial improvement in accuracy over baseline models, achieving 99.16% accuracy for binary classification using VGG16. An accuracy of 81.1 ± 4.33% across cyclone intensity levels, and an RMSE of 7.79 ± 1.27 knots in wind speed prediction using the ConvLSTM-based model. All models are evaluated using 5-fold cross-validation on CIMSS Tropical Data Archive and IMD Best-Track datasets. Overall, these results show an exciting potential for future use of deep learning for real time forecasting and early warning systems. Future work will also look to improve or increase model generalization, either through using ensemble learning, or potentially more complex architectures and larger datasets