Welcome to DBS eSource
DBS eSource is an online service hosting full content materials produced by Dublin Business School staff and students. It contains the full text of articles, theses, conference papers, book chapters and more. DBS eSource is an open access repository, with the aim of making all content as widely accessible as possible. Use the Browse functions on the right for an overview of relevant materials. For an advanced search click here
For more information on our institutional repository policy or the steps involved in submitting work to Esource click here
Recent Submissions
Item Deep Learning Study for Image Classification of Alzheimer's MRI(Dublin Business School, 2025)Alzheimer's disease is a leading cause of dementia, impacting millions worldwide. Early diagnosis is crucial for improving patient outcomes, yet traditional methods often lack the sensitivity to detect early-stage neurodegeneration. This study investigates the application of deep learning models for the classification of Alzheimer’s disease using MRI scans. The research follows the CRISP-DM framework and utilises the "Alzheimer MRI Disease Classification Dataset" from Kaggle, comprising 5,120 MRI images categorised into four classes. To enhance classification performance, the dataset was transformed into a binary classification problem—distinguishing between "No Alzheimer" and "Early Alzheimer" cases—while addressing class imbalance through oversampling techniques. Five deep learning architectures were implemented and compared: Convolutional Neural Networks (CNN), Artificial Neural Networks (ANN), Residual Networks (ResNet50), Visual Geometry Group Network (VGGNet16), and Vision Transformers (ViT). The models were trained and evaluated based on accuracy, precision, recall, and F1-score. Results indicate that CNN achieved the highest accuracy (93.46%), followed by ANN (90.10%) and ViT (86.23%), demonstrating their effectiveness in automated MRI-based Alzheimer’s detection. Future work includes refining model interpretability through explainable AI techniques and integrating larger datasets for improved generalisation. This research highlights the potential of deep learning in advancing early Alzheimer’s diagnosis and supporting clinical decision- making.Item Deep Learning Study for Image Classification of Alzheimer's MRI(Dublin Business School, 2025)Alzheimer's disease is a leading cause of dementia, impacting millions worldwide. Early diagnosis is crucial for improving patient outcomes, yet traditional methods often lack the sensitivity to detect early-stage neurodegeneration. This study investigates the application of deep learning models for the classification of Alzheimer’s disease using MRI scans. The research follows the CRISP-DM framework and utilises the "Alzheimer MRI Disease Classification Dataset" from Kaggle, comprising 5,120 MRI images categorised into four classes. To enhance classification performance, the dataset was transformed into a binary classification problem—distinguishing between "No Alzheimer" and "Early Alzheimer" cases—while addressing class imbalance through oversampling techniques. Five deep learning architectures were implemented and compared: Convolutional Neural Networks (CNN), Artificial Neural Networks (ANN), Residual Networks (ResNet50), Visual Geometry Group Network (VGGNet16), and Vision Transformers (ViT). The models were trained and evaluated based on accuracy, precision, recall, and F1-score. Results indicate that CNN achieved the highest accuracy (93.46%), followed by ANN (90.10%) and ViT (86.23%), demonstrating their effectiveness in automated MRI-based Alzheimer’s detection. Future work includes refining model interpretability through explainable AI techniques and integrating larger datasets for improved generalisation. This research highlights the potential of deep learning in advancing early Alzheimer’s diagnosis and supporting clinical decision- making.Item Gen Zs and the Future of Digital Banking: Behaviours, Preferences, and Marketing Implications for Digital Banking in Canada.(DBS Library Press, 2025)In the aftermath of the Covid-19 epidemic, like most businesses, banking moved towards cashless payments to reduce physical interactions. While this presented a challenge to older customers, Generation Z have been brought up in a digital-first environment. This research examines the unique digital banking behaviours and preferences of Generation Z in Canada, focusing on individuals born between 1997 and 2001. This research assesses how well digital banking services align with Generation Z's expectations and outlines critical areas for improvement. Recommendations emphasize enhancing mobile platforms, maintaining security trust, offering culturally responsive features, and leveraging personal recommendations. The research underscores the need for financial institutions to refine their strategies continuously to meet the evolving demands of this digitally adept generation, which is at the forefront of transforming digital finance.Item A post-pandemic critical evaluation of remote working influences on affective well-being, work-life and job satisfaction.(DBS Library Press, 2025)The advent of the Covid-19 pandemic forced many employees to work remotely from home, solidifying the use of digital processes as a normal way of working, and in this post-pandemic world, many employees continue to work from home (Silver, 2023). However, there have been few studies looking into the affective aspects of this new remote/ hybrid working normality. The Affective Events Theory (AET: Weiss and Cropanzano, 1996) has highlighted the importance of affective state in influencing employee job satisfaction and behaviour (Wegge et al, 2006), which is the focus of the current research. Participants were recruited anonymously through social media (N=128) and pseudo-anonymously through an online panel provider sample (N=112). The study implemented a correlational quantitative questionnaire design examining relationships based on the AET framework using questions pertaining to gender, age, children at home, years in job, area where home office is based, and rating of home internet connection alongside questions from pre-existing scales covering social atmosphere, personality dispositions, affective wellbeing, work-life balance, job satisfaction, and job search activities. The descriptive statistics indicate an overall mild impact from isolation and distractions from friends or other media, on average. The standard deviation indicated that some individuals experienced severe isolation and distractions while working from home. Perceptions of positive work inducements in relation to social atmosphere at work since the pandemic averaged around the same as before the pandemic but some rated social atmosphere experiences as lower. The path analysis results of the study indicate that the relationships chosen based on the AET model sufficiently cover the important relationships within the data, providing support for the utility of AET. Most notably, greater levels of isolation linked to poorer social atmosphere and affective well-being, with lower affective well-being linking to lower job satisfaction predicting more job searching behaviours in some cases. Greater emotional stability lowered work-life imbalances and enhanced affective well-being. It is important for organizational managers to consider the impact of these remote working affect related factors impacting their employees, and this current study offers guidance on how to implement changes to deal with them.Item A literature review: Exploring the influence of trust on knowledge sharing in project teams within project-based organisation(DBS Library Press, 2025)The characterisation of knowledge as the primary productive resource of organisations rather than capital, natural resources, or labour, has prompted an increase in the interest of knowledge, however, it is acknowledged that it is in the sharing of knowledge where the value is held. From this perspective it is conceded that knowledge sharing amongst team members as an intangible asset, has the power to maintain and sustain organisational growth, and survival. Therefore, the factors which enable or inhibit knowledge sharing among team members needs to be identified. Trust has been recognised as a prominent influencing factor on knowledge sharing and it is here where the focus of this literature review lies. This paper offers a review of the literature on knowledge sharing in teams, presenting enabling and inhibiting factors, giving prominence to trust. Trust is investigated to include the role of trust in teams and in knowledge sharing and factors which enables and inhibits the development of trust.
Communities in DBS eSource
Select a community to browse its collections.