Institutional-Repository, University of Moratuwa
Welcome to the University of Moratuwa Digital Repository, which houses postgraduate theses and dissertations, research articles presented at conferences by faculties and departments, university-published journal articles and research publications authored by academic staff. This online repository stores, preserves and distributes the University's scholarly work. This service allows University members to share their research with a larger audience.
 Research Publications |  Thesis & Dissertation |  E- Books |
 UoM Journal Publications |  UoM Conference Proceedings |  Articles published in Scimago's Q1 journals |  UoM Research Reports |  Other Articles authored by UoM staff |
Recent Submissions
item: Conference-Full-text
A Machine learning approach for early detection of thyroid disorders in Sri Lankan women
(IEEE, 2025) Senani, WMU; Thirukumaran, S; Arandara, RR; Ratnarajah, N
Thyroid disease is a significant global health issue, particularly affecting women’s metabolism, hormonal balance, and well-being. Detecting and treating the disease early is key to controlling its progression and avoiding complications. Traditional diagnostic methods like symptom-based assessments and blood tests are often hard to interpret due to complex and voluminous clinical data. Recently, machine learning techniques have shown promising potential in enhancing early diagnostic capabilities. This study presents a machine learning-based thyroid disease diagnosis system for Sri Lankan women, using 402 clinical samples from hospitals in the Uva and Western provinces. The system classifies individuals into three diagnostic categories: hyperthyroidism, hypothyroidism, and healthy. Feature selection using SelectKBest, refined with clinical expert input, identified eight key features from the initial 22 attributes. Four machine learning models, RF, ANN, DT, and SVM were fine-tuned and evaluated. Among them, the RF classifier achieved the highest performance, with an accuracy of 91%, and precision, recall, and F1-score of 90%. A comprehensive Sri Lankan women’s thyroid disease dataset was also compiled, offering a valuable foundation for future research and public health analysis. The proposed system shows the potential of machine learning for early and accurate thyroid disease diagnosis, especially in resource-limited settings like Sri Lanka.
item: Conference-Full-text
Multi-objective parameter optimization of fabric adhesive bonding
(IEEE, 2025) Perera, S; Gamage, JR
Bonding strength and stretchability are two key parameters that define the quality of an adhesive-bonded fabric. However, there is a lack of studies on parameter optimization focusing on achieving multiple objectives. This study examines the optimization of adhesive bonding parameters in knitted fabric applications, focusing on achieving the highest bonding strength and stretchability. Four key process factors were analyzed using Taguchi experimental design. They are adhesive weight, distance between glue dot lines, press time, and curing time. The research aimed to identify the optimal levels for these factors to maximize the performance of polyurethane-based reactive hot melt adhesives (PUR). The experimentation was conducted using an L27 orthogonal array. The bonding strength and stretchability were analyzed through the application of signal-to-noise (S/N) ratios, general Linear model, and ANOVA. The analysis discovered different optimum values for each factor when strength and stretchability were considered separately. The S/N ratios for both responses were normalized, and a composite S/N ratio was calculated. The study highlights the importance of balancing process parameters to meet the practical requirements of the textile industry, ensuring both durability and flexibility in bonded fabrics.
item: Conference-Full-text
Data sovereignty in multi regional identity systems
(IEEE, 2025) Siriwardena, M; Perera, I
As digital platforms expand globally, ensuring data sovereignty across regions has emerged as a critical concern, particularly in identity management systems. Existing identity architectures often centralize data storage and control, creating compliance risks in multi-jurisdictional deployments. This research proposes a novel architecture for multi-regional Identity and Access Management (IAM) systems to preserve data sovereignty while enabling unified customer identity experiences. The architecture ensures region-specific data storage, consentaware data sharing, and regulatory compliance.
item: Conference-Full-text
Stability analysis of expansive soil slopes stabilized with geogrids
(IEEE, 2025) Nifal, N; Nasvi, M; Kurukulasuriya, C
Expansive soil slopes are vulnerable to climatic variations due to their swell-shrinkage behaviour, ultimately resulting in slope failures. In recent decades, geogrids have gained prominence for stabilizing such slopes due to their enhanced performance. However, geogrid properties such as length and spacing should be extensively studied for the optimal application. This study investigates the effect of such parameters in expansive soil slope stabilization. Numerical models were developed with finite element method (FEM) based PLAXIS 2D software and validated with the limit equilibrium method (LEM) based SLOPE/W software. A parametric study was conducted to analyze the stability of the expansive soil slopes treated with geogrids for various slope heights (4-16 m), slope angles (30-45º), geogrid lengths (0.7-1.2 times slope height), and geogrid spacings (0.25-1.0 m). Findings indicate that the inclusion of geogrid enhances the factor of safety (FOS) by 4% to 268%, depending on the slope geometry and geogrid configuration. For effective application, shorter slopes (4-8 m) require a geogrid length equal to the slope height, while taller slopes (8-16 m) need geogrid length of 1.2 times the slope height. Similarly, milder slopes (30-45º) require geogrid spacing of 0.5–1.0 m, and steeper slopes (45-75º) require a spacing of 0.25-0.5 m.
item: Conference-Full-text
Can machine peeled cinnamon fulfil the requirements of Ceylon Cinnamon market?
(IEEE, 2025) Gunasekara, H; Amarasinghe, S; Gamage, J
Cinnamon has the highest demand in the global cinnamon market due to its superior quality and versatility across various applications. Different types as well as different forms of cinnamon are available in the market. Quills have been identified as the main form of Ceylon cinnamon in terms of production quantity. However, the scientific purpose of quillmaking is not clear. Moreover, the quill-marking process is still a manual method which is difficult to produce through mechanical means. This research focuses on rationalizing the production of handmade quills and investigating the market potential of new cinnamon forms which can be processed through mechanical means. A Cost-Volume-Profit analysis, followed by a literature review, cinnamon export statistics of the last 10 years, and a survey through online marketplaces, is carried out. To ensure realistic estimation, a sensitivity analysis was conducted to compare profitability under different production volume scenarios. Finally, the research identifies Crushed cinnamon” and “Quillings” as are most effective forms in order of importance to produce through mechanical means.