SACM - United Kingdom
Permanent URI for this collectionhttps://drepo.sdl.edu.sa/handle/20.500.14154/9667
Browse
7 results
Search Results
Item Restricted Rasm: Arabic Handwritten Character Recognition: A Data Quality Approach(University of Essex, 2024) Alghamdi, Tawfeeq; Doctor, FaiyazThe problem of AHCR is a challenging one due to the complexities of the Arabic script, and the variability in handwriting (especially for children). In this context, we present ‘Rasm’, a data quality approach that can significantly improve the result of AHCR problem, through a combination of preprocessing, augmentation, and filtering techniques. We use the Hijja dataset, which consists of samples from children from age 7 to age 12, and by applying advanced preprocessing steps and label-specific targeted augmentation, we achieve a significant improvement of a CNN performance from 85% to 96%. The key contribution of this work is to shed light on the importance of data quality for handwriting recognition. Despite the recent advances in deep learning, our result reveals the critical role of data quality in this task. The data-centric approach proposed in this work can be useful for other recognition tasks, and other languages in the future. We believe that this work has an important implication on improving AHCR systems for an educational context, where the variability in handwriting is high. Future work can extend the proposed techniques to other scripts and recognition tasks, to further improve the optical character recognition field.48 0Item Restricted Integrating Digital Technologies with Customer Relationship Management (CRM) to Enhance Customer Satisfaction and Loyalty in Luxury Hotels(Manchester metropolitan university, 2024) Assiri, Tarek; Cosser, GillianThis study investigates the integration of digital technologies—namely Artificial Intelligence (AI), Internet of Things (IoT), and Big Data analytics—into Customer Relationship Management (CRM) systems in luxury hotels. The research evaluates the impact of these technologies on customer satisfaction and loyalty through a quantitative approach, utilizing data from surveys conducted with hotel front-office employees. Findings reveal a varied adoption of digital tools, with IoT significantly enhancing operational efficiency, Big Data analytics improving customer retention strategies, and AI demonstrating underutilization due to staff training challenges. The study underscores the importance of aligning technology adoption with employee proficiency and guest expectations to optimize CRM effectiveness. Strategic recommendations include enhanced staff training programs, expansion of IoT applications, and leveraging Big Data for predictive analytics to strengthen customer relationships in the luxury hospitality sector. Limitations, such as the focus on luxury hotels and the exclusion of guest perspectives, highlight areas for future research15 0Item Restricted Impact of Artificial Intelligence Integration in Emergency Department Triage on Waiting Times: A Systematic Review Compared to Conventional Practices in ED Triage.(The University of Sheffield, 2024-09) Alhazmi, Mohammed; Miles, JemieBackground: The global issue of increased patient waiting times in healthcare facilities is a pressing concern, as it can lead to significant patient harm due to delayed access to healthcare. This research proposes the integration of artificial intelligence into emergency department triage systems as a solution to mitigate this issue. Aims: To evaluate the impact of integrating Artificial Intelligence (AI) support tools on waiting times in Emergency Departments through a systematic review of existing literature. Design: A thorough systematic review of the literature was conducted by searching electronic databases and internet search engines, including ScienceDirect, Springer, and PubMed, as well as reference lists. Studies published from January 1, 2019, to May 25, 2024, were included. Articles that did not pertain to AI, interventions that were irrelevant to emergency departments (EDs) or did not provide outcomes related to reducing waiting times either directly or indirectly, or evaluation data were excluded to ensure the quality and relevance of the included studies. Results: The analysis included ten peer-reviewed journals published after January 2019 on integrated Artificial Intelligence (AI) with emergency department triage. Recent findings suggest that integrating artificial Intelligence (AI) models into the emergency department (ED) triage processes can hold significant potential for reducing overcrowding and minimising wait times. Some studies have found that AI reduces waiting times by between 20 seconds and 30 minutes. However, a study found AI to increase waiting times for categories 3 to 5 by 2.75 to 5.33 minutes. Conclusions: This review has highlighted AI's potential to bring innovative solutions to emergency department settings. Implementing these AI-driven solutions has shown promise in enhancing healthcare delivery in the emergency department. However, further research is crucial to refine these models and ensure their practical application, underscoring the importance of continued involvement in the field.75 0Item Restricted The Use of Artificial Intelligence and Machine Learning in Zero Trust Networks(Newcastle University, 2024) Alnadhari, Sultan Majid; Shepherd, CarltonThis paper focuses on the application of Artificial Intelligence (AI) and Machine Learning (ML) within the context of the Zero Trust (ZT) security model to improve Cybersecurity within the ever-evolving digital landscape. Conventional security models that focus on proactively protecting the perimeter and assuming trust within internal networks are often inadequate against these threats. Zero trust can be characterised as a modern approach resulting from the "never trust, always verify" principle; thus, it implies an unceasing process of the users' authentication and access authorisation. Regarding Zero Trust security, this research builds upon the concept by incorporating AI/ML techniques to enhance threat, anomaly, and predictive detection. The first and foremost is the implementation of deep learning models using an optimised Keras framework better suited for the unique dynamics of the Zero Trust environments. Some of these models successfully differentiate and filter network traffic into normal and malicious categories using state-of-the-art features like dropout characters and dense layers. Briefly discuss some problems and solutions, for instance, data shift and model performance decline in conditions that change with time: transfer learning and periodically, for example, perform retraining of the model. Real-world assessments clearly show that incorporating Artificial Intelligence and Machine Learning into the Zero Trust Architectures enhances the capability to identify and mitigate advanced persistent threats and zero-day attacks. Therefore, this research will form a basis for more work in the area of Artificial Intelligence and Cybersecurity by presenting the knowledge required to establish intelligent security systems that can learn to handle new threats as they emerge effectively in real-time. Specifically, the results highlight how these speeds strengthen Zero Trust security solutions against emerging threats.34 0Item Restricted The Feasibility of Implementing AI in Bid/No-Bid decision-making(University of Bath, 2024-09-02) Alowairdhi, Saleh Mohammed; Jesty, James; Liyanage, NavodThis report explores the feasibility of implementing an Artificial Intelligence (AI)-based Benchmarking Tool to enhance the bid/no-bid decision-making process at Cundall, a multi-disciplinary consultancy firm. The study addresses critical inefficiencies in the current decision-making system, including data inconsistencies, subjective judgments, and underutilization of historical data, which hinder alignment with Cundall's Blue Ocean Strategy. Through a combination of qualitative and quantitative research methods, the report identifies key decision factors, evaluates data readiness, and proposes an AI solution designed to provide data-driven insights, improve decision-making consistency, and align bid decisions with strategic objectives. The proposed AI Benchmarking Tool integrates historical data analysis, machine learning algorithms, and an interactive dashboard to deliver explainable, user-friendly recommendations. The report includes a proof-of-concept using PowerBI and Random Forest machine learning models, demonstrating the tool's potential to improve bid success rates and operational efficiency. Ethical considerations, stakeholder engagement, and implementation challenges, such as data quality and system integration, are thoroughly addressed. The findings highlight the transformative potential of AI in construction decision-making, positioning Cundall as an industry leader in innovation and strategic differentiation. Recommendations emphasize a phased implementation approach, robust governance, and continuous refinement to ensure alignment with Cundall's sustainability and innovation goals. This study contributes to the growing discourse on AI adoption in the construction industry, providing actionable insights for leveraging technology to create competitive advantages.19 0Item Restricted Integrating Industry 4.0 in Project Management: A Systematic Literature Review(De MontFort University, 2024-09-20) almehaize, Ghannam nasser; Oyinlola, AdewaleThis thesis investigates Industry 4.0 technologies with the aim of integrating them into project management methodologies to improve efficiency, decision-making, and overall project success. The study investigates the existing studies on the influence of these technologies on project management processes and evaluates the present status of their integration across a variety of sectors. This is accomplished via a comprehensive examination of the available literature and studies. Industry 4.0 technologies have the potential to revolutionise project management by enabling the sharing and analysis of real-time data, according to the results. In addition, they present challenges regarding organisational culture, communication, and skill limitations. This thesis shows that project managers need technical understanding, leadership, and flexibility. This thesis ultimately emphasises the potential of Industry 4.0 technologies to enhance project performance, while also emphasising the need for organisations to modify their project management frameworks in order to prosper in a digital environment that is swiftly evolving. In order to enable organisations to fully realise the promise of these technologies for successful and sustainable development, the study's conclusion calls for further research to develop frameworks that facilitate the effective integration of these technologies.14 0Item Restricted The Future of Indirect Marketing in a Digital World(University of Sussex, 2024-09-27) Aldowais, Raed Fahad; Ye Yang, NicoleThis dissertation explores the transformative impact of digital technologies on indirect marketing strategies, focusing on how businesses adapt to the evolving digital landscape. The study aims to assess the roles of artificial intelligence (AI), big data, and the Internet of Things (IoT) in enhancing indirect marketing, with a specific focus on consumer behaviour and brand loyalty. The research methodology is based on secondary data analysis, drawing from academic journals, industry reports, and case studies. This approach allows for a comprehensive examination of current trends and technologies affecting marketing practices across various industries. The main findings indicate that AI, big data, and IoT significantly enhance marketing effectiveness by improving customer targeting, personalization, and real-time engagement. These technologies have enabled businesses to create more meaningful consumer interactions, leading to increased customer loyalty and higher marketing ROI. The integration of these technologies provides a synergistic effect that amplifies their individual benefits. In conclusion, the dissertation underscores the critical role of digital technologies in shaping modern marketing strategies. The study highlights the importance of adopting these technologies to remain competitive in a digital-first marketplace while addressing challenges such as data privacy and the need for skilled personnel. These insights offer valuable guidance for future research and practical application in the field of digital marketing.12 0