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
Exploring the suitability of fly ash and rice husk ash in one-part geopolymer: a case study for sustainable, low-carbon construction.
(IEEE, 2025) Batuwita, I; Sampath, KHSM; Ranathunga, AS
The high carbon footprint and energy-intensive production processes associated with clinker-based cement necessitate developing sustainable and environmentally friendly alternatives urgently. This study focuses on the properties of a one-part geopolymer utilizing industrial and agricultural waste materials: Fly Ash (FA)and Rice Husk Ash (RHA). Fly ash was used as the primary aluminosilicate source, and rice husk ash was used as a silicate supplementary material. Solid NaOH was utilized as the alkaline activator. The physical and chemical properties of one-part geopolymer were changed with varying water-to-solid (W/S) ratios (i.e., 0.5, 0.6, 0.7), Si/Al ratios (i.e.,2.5, 3.0, 3.5), and NaOH concentrations (i.e., 6M, 9M, 12M), and they were systematically evaluated to optimize the mix design. Furthermore, microstructural and chemical bonding also depend on W/S, Si/Al, and NaOH concentrations, and the optimised geopolymer revealed well-developed bonding mechanisms and structural integrity. Furthermore, this experiment tested that One-Part Geopolymer (OPG) has lower embedded Carbon (0.4 kg CO2e), which is more than half of the embedded Carbon (0.85 kg CO2e) of Ordinary Portland Cement (OPC). It is an excellent sign for the sustainability of OPG over OPC. Therefore, this study underscores the suitability of coal power plant fly ash and industrial waste rice husk ash for synthesizing one-part geopolymers as a transformative solution for advancing environmentally sustainable construction practices that support the UN Sustainable Development Goals 9 and 12.
item: Thesis-Full-text
Development of a risk management model in technological innovations related to the textile and apparel industry
(2025) Kumarapeli, KAUP; Ratnayake, KMVS; Jayawardena, TSS
The Textile and Apparel industry, including Sri Lanka's, has grown significantly, offering substantial employment and economic benefits globally. Over the past four decades, Sri Lanka's apparel sector has experienced exceptional growth, becoming the nation's primary foreign exchange earner and employing thousands. Despite this success, Sri Lankan apparel faces higher costs and lead times compared to competitors, alongside a limited product range, which hampers its competitiveness. To stand out, it is crucial to leverage technological innovation for faster production, improved delivery times, precise research and development processes, and modern manufacturing techniques to reduce costs. However, technological innovation is fraught with uncertainty and a broad spectrum of risks, underlining the need for a robust risk management strategy. Due to varying organizational resources and product requirements, a generic risk management model is ineffective across different products and organizations. This situation necessitates a customized risk management approach, a need that current literature often overlooks. Furthermore, organizations are often hesitant to share confidential information with third parties, adding another layer of complexity. To address these issues, a risk management model was designed as a game, to solve the root causes of risk factors in technological innovations and effectively manage the associated risks. It integrates key elements from cooperative game theory, behavioral game theory, teamwork dynamics, psychological aspects of decision- making, visual problem-solving, and the board gaming concept. This model enhances resilience and agility while preserving the confidentiality of organizational strategies.13 leading apparel manufacturers and 10 textile manufacturers were selected covering 145 factories. Data collection was conducted via questionnaires and structured/semi- structured interviews. The results present a flexible, customized risk management model that adapts to emerging risks while maintaining the strategic confidentiality of manufacturing organizations, addressing a significant gap in existing literature.
item: Thesis-Abstract
Analytic of image posts on social media for hate speech
(2025) Walawage, KSA; Ranathunga, L
Social media platforms have been developing rapidly for the last thirteen years. Billions of people communicate their ideas, information and other expressions with each other through social media. Recently most of the fake news and hate speech have spread by image posts and videos in Facebook, YouTube and Twitter platforms within Sri Lankan community. There is a vital need for obtaining the meaning of the image posts automatically. This research has been supported to the above solution and done to automatically separation and identification of Sinhala and Singlish text in image posts and video thumbnails in social media platforms. This research has three research module components. The first component is the main research component. It is the extraction of Sinhala and English text in social media images. Image posts and video thumbnails were acquired from Facebook and YouTube social media platforms which are on public. Three main algorithms and another three supporting algorithms have been derived to complete this component. They are text detection, text glow removing, text line segmentation, touching character segmentation, Sinhala English character separation and Sinhala English character recognition. The study has achieved the text line segmentation accuracy of 90% for 1,669 text lines and the overall touching character segmentation accuracy of 98% for 58,403 characters and the overall script separation accuracy of 93% for 22,383 script images. A new feature vector was formed in this study and 11,088 Sinhala script images were trained in a sequential model neural network. The accuracy of printed Unicode Sinhala character recognition is higher than the accuracy of printed non-Unicode and handwritten Sinhala character recognition. In the second component, a simple algorithm has been derived to identify the status of social issues in images which is connector module for the main research group work. In the third component, it is tested with three methods to identify key attributes of images to detect redistribution of images within social media and selected the Brute-Force Matcher with ORB descriptors as the highest accuracy obtained by this method.
item: Conference-Full-text
Transfer learning-based approach for improving cinnamon diseases and pests management
(IEEE, 2025) Senanayake, MMV
Cinnamon is a widely cultivated species in Sri Lanka and highly valued across various industries. The cultivation of cinnamon is hindered by diseases and pests, which affect the yield and quality of cinnamon production. This study suggested a computerized solution to tackle the problems of conventional human disease diagnostic processes by classifying diseases and pests affected by cinnamon leaf images. Due to the limited availability of data samples, the investigation focused on Transfer Learning. The experiments for the proposed Transfer Learning-based approach were conducted with pre-trained deep learning models as fixed feature extractors and classifiers as Softmax with cross-entropy loss and machine learning algorithms for comparative analysis. All the experimental results of this work demonstrated better performances compared to existing studies. InceptionV3 with a Softmax classifier obtained an accuracy of 98%, precision of 98%, recall of 96%, and F1-score of 97% outperforming other models. The findings of this work highlight the efficiency of pre-trained models for leaf diseases and pests’ classification in cinnamon leaves by providing effective disease and pest management and enhancing the quality of the production.
item: Conference-Full-text
A Fuzzy-adaptive sliding mode control strategy for optimizing control of underwater drone
(IEEE, 2025) Perera, KDSHM; Thushan, MDA; Ekanayake, HD; Amarasinghe, YWR; Jayathilaka, WADM
Controlling underwater robots with nonlinear dynamics is a challenging task. Sliding Mode Control (SMC), a widely used framework for underwater vehicles, suffers from chattering effects that degrade performance. Despite this drawback, SMC remains popular due to its inherent robustness against model uncertainties and external disturbances—an essential requirement in the unpredictable underwater environment. This study proposes a Type-1 fuzzy-adaptive SMC to mitigate this issue, where fuzzy logic dynamically tunes SMC parameters for smoother operation. The method significantly reduces chattering in the baseline SMC model while preserving its robustness. The proposed approach is implemented and validated in the Gazebo simulation platform. This control strategy enhances user experience and vehicle longevity by minimizing high-frequency oscillations, offering practical benefits for remotely operated systems.