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
Digital twin technology in apparel industry: potential for rebalancing of manual assembly lines
(IEEE, 2024) Bandara, DT; Senanayake, C
The efficiency of manual assembly lines in the apparel industry is often affected by the dynamic nature of operator performance, which leads to unbalanced lines and associated challenges such as bottlenecks, uneven operator utilization, unmet demand, inventory issues, and lower labor morale. Although line balancing is done at the onset to optimally allocate tasks to workers, most often, rebalancing is necessary, especially due to the uncertainty of task times and operator learning. This research looks at the potential of digital twin technology in effectively rebalancing the line using real-time production data. We employ the well-known Jackson’s 11 task case and demonstrate, through a discrete event simulation model, how real-time rebalancing can improve the performance of the system.
item: Conference-Full-text
Development of cellulose-based nanofibers by electrospinning technique
(IEEE, 2024) Madusanka,SDC; Kantha, WDY; Samarasekara, AMPB; Amarasinghe, DAS; Weragoda, VSC
Cellulose-based nanofibers exhibit biodegradability and reproducibility, as well as possessing excellent mechanical properties, a low thermal expansion coefficient, and a high surface area-to-volume ratio. This study presents the development of cellulose-based nanofibers through electrospinning techniques. Cellulose, used to produce nanofibers, was extracted from natural cotton wool and rice straw using simple, cost-effective methods. Fourier-transform infrared spectroscopy (FTIR) was used to confirm the presence and removal of hemicelluloses and lignin from the extracted cellulose. Activation, acetylation, and hydrolysis processes were carried out using acetic acid and acetic anhydride under varied reaction parameters for the extracted cellulose. The resulting cellulose acetate (CA) product was subjected to sedimentation at a defined rotational speed and duration. Subsequently, the dried CA powder was dissolved in an appropriate solvent mixture ratio of Acetone/DMF to produce the precursor solution suitable for electrospinning. The Scanning Electron Microscope (SEM) was utilized to characterize the electrospun fibers and determine their dimensions at the nanoscale. It was confirmed through SEM images that the electrospun fibers produced from both cotton and rice straw were in the nanoscale range. The production of nanofibers from rice straw proves advantageous due to the abundance and costeffectiveness of the raw material compared to cotton wool.
item: Conference-Full-text
Quality assessment of welding using regression analysis of biomechanical data
(IEEE, 2024) Pandukabhaya, M; Fonseka, T; Kulathunge, M; Godaliyadda, R; Ekanayake, P; Senanayake, C; Gamage, P; Herath, V
The widespread integration of wearable devices in various fields has paved the way for numerous novel applications in medicine, rehabilitation, sports, and industry, etc. through the data acquisition, and analysis of hand gestures and gait patterns. This study aims at a comprehensive exploration of a psychomotor skill, i.e., welding using a wearable device to capture hand movements. After the data collection, this study is focused on assessing the welding quality parameters such as symmetry and equal distribution of a welding path. For this, several machine learning and deep learning algorithms were trained in order to obtain the above welding quality parameters using biomechanical data which was captured using four IMU sensors placed on the hand of the worker when performing the welding task. From our results, it is evident that it is possible to use regression analysis to predict the welding quality parameters including equal distribution of a welding path with minimum error.
item: Conference-Full-text
Modeling streamflow sensitivity to rainfall variability in the Budhigandaki River basin in Nepal
(IEEE, 2024) Bajracharya, S; Gunuawardhana, L; Sirisena, J; Rajapakse, L
Snow-fed River Basins in Nepal are vital water sources, which are increasingly vulnerable to climate changeinduced variability in rainfall. This study focuses on the Budhigandaki River Basin to analyze streamflow sensitivity to rainfall variability and assess its impact on drought conditions, providing insights for effective water management and adaptation strategies. The Hydrologic Engineering Center's Hydrologic Modeling System (HEC-HMS) was used to simulate streamflow under rainfall scenarios varying up to ±15%. Drought conditions were categorized using specific percentile thresholds into four levels: extreme, severe, moderate, and mild. Results show that a modest annual rainfall variation of 5% can significantly alter drought conditions, highlighting the hydrological sensitivity of the basin. Increased precipitation improved moderate drought conditions, demonstrating the resilience of the basin, while decreased rainfall exacerbates drought severity. Transitions of drought categories were observed with varying rainfall amounts, suggesting that even minor changes can lead to significant shifts in drought severity. While this study uses specific percentage increments in rainfall, simplifying the complexity of annual rainfall variability, these findings highlight the critical need for adaptive water resource management strategies in response to varying rainfall and climate change.
item: Conference-Full-text
EEG based brain-computer interface for inner speech classification
(IEEE, 2024) Dhananjaya, P; Adikari, I; Lakmali, S; Devindi, I; Liyanage, S; Wickramasinghe, M; Dissanayake, T; Ragel, R; Nawinne, I
Electroencephalogram (EEG) based Brain-Computer Interfaces (BCIs) were initially designed to aid those with motor disabilities. However, recent research delves into their potential for non-clinical uses like gaming. Utilizing non-motor imagery, such as inner speech, has emerged as a promising approach for BCI control. Inner speech, a mental form of self-directed speech, serves as a basis for this study to decode control commands like left, right, up, and down for navigation in a game. This paper evaluates EEG signal processing techniques across various applications. It employs passive-time inner speech classification and introduces a successful transfer learning method using ResNet50, achieving an impressive accuracy of 45% when tested with data from entirely different subjects from training. Further fine-tuning with 50% of the data increased the model’s performance to 88%. The study also explores personalized model capabilities and assesses optimal dataset sizes. Additionally, it delves into real-time applications, experimenting with neural network architectures for instantaneous classification. Connectivity between these components is also addressed, underscoring the infrastructure’s significance in EEG-based BCI systems.