Layan Sawalha

Layan Sawalha's PhD project revolves around the intricate realm of document classification, spanning across pivotal domains such as healthcare and civil engineering. This research illuminates existing gaps in conventional AI-driven techniques, particularly evident in scenarios where accurate categorization is paramount yet elusive.

In the healthcare sector, the pressing need for precise classification of medical documents, especially within cancer datasets, remains a formidable challenge. Traditional methods often falter in achieving the desired accuracy levels, as observed in studies like Ghany et al. (2017). Similarly, within civil engineering, the effective management and organization of extensive datasets within Building Information Modeling (BIM) frameworks present ongoing hurdles, leading to inefficiencies in decision-making processes.

Layan's research endeavors to bridge these gaps by focusing on two distinct yet interconnected domains: medical document classification and BIM data classification within civil engineering. In the medical realm, the emphasis lies on refining the categorization of medical documents, particularly within cancer datasets like the breast cancer dataset. The primary objective is to enhance the accuracy of document classification based on symptoms and patient data, thereby facilitating more accurate cancer diagnosis. This is pursued through a comparative study of quantum machine learning and traditional AI document classification techniques.

Transitioning to civil engineering, the research spotlight shifts towards the complexities surrounding classification processes within BIM frameworks. Despite the indispensable role of BIM technology in modern construction projects, challenges persist in organizing and managing extensive datasets, particularly within the cost framework. By leveraging state-of-the-art methodologies, the aim is to revolutionize decision-making processes in cost estimation, allocation, and management within the construction industry.

To address these challenges, the research explores advancements in decision-making processes across sectors. Hybrid models integrating recurrent neural networks (RNNs) and convolutional neural networks (CNNs) are proposed to streamline data organization and classification within BIM frameworks. Through these efforts, the objective is to enhance project efficiency and decision-making processes in the civil engineering domain, ultimately contributing to advancements in healthcare diagnostics and construction project management.

In essence, Layan Sawalha's research endeavors to advance both healthcare and construction sectors by fostering improved decision-making, efficiency, and accuracy in data classification processes.