DSpace 9

This site is running DSpace 9. For more information, see the DSpace 9 Release Notes.

DSpace is the world leading open source repository platform that enables organisations to:

easily ingest documents, audio, video, datasets and their corresponding Dublin Core metadata
open up this content to local and global audiences, thanks to the OAI-PMH interface and Google Scholar optimizations
issue permanent urls and trustworthy identifiers, including optional integrations with handle.net and DataCite DOI

Join an international community of leading institutions using DSpace.

The test user accounts below have their password set to the name of this software in lowercase.

Demo Site Administrator = dspacedemo+admin@gmail.com
Demo Community Administrator = dspacedemo+commadmin@gmail.com
Demo Collection Administrator = dspacedemo+colladmin@gmail.com
Demo Submitter = dspacedemo+submit@gmail.com

Photo by @inspiredimages

Communities in DSpace

Select a community to browse its collections.

Now showing 1 - 5 of 17

Recent Submissions

Stock price prediction using ARIMA model: Evidence from Colombo Stock Exchange
(University of Kelaniya in Sri Lanka, 2026) Tharshiga, P.; Paranika, T.; Subramaniam, V.M.
Purpose: The core objective of the research is to investigate the forecasting capability of the Autoregressive Integrated Moving Average (ARIMA) model for predicting short-term stock prices in the Colombo Stock Exchange (CSE) of Sri Lanka. Design/Methodology/Approach: The data gathered on a daily basis through the CSE Price Index, ranging between July 1, 2014, and June 30, 2024, was analyzed by using the Box-Jenkins approach. The selection of the optimum models was based on the minimum of Akaike Information Criterion and Schwarz Bayesian Criterion. The Autocorrelation Function, Augmented Dickey-Fuller Test, and error test measures, such as Mean Absolute Percentage Error, were considered for validation and for assessing the goodness of fit of the forecasting results. Findings: From the Autoregressive Integrated Moving Average (ARIMA) model analysis, the ARIMA (2,1,1) model was the best, with an MAPE of 3.9%, indicating strong forecasting performance. For the Autoregressive and the Moving Regression tests, both were highly significant at the 1% level, supporting the idea that past price variations contain useful information for predicting prices. Results suggest that partial weak-form inefficiency exists in the Sri Lankan Stock Market. Research limitations/ Future research directions: The study uses a univariate linear approach and does not account for exogenous variables, nonlinearity, or structural breaks. The findings of this approach would be more relevant to short-term linear predictability. The approach would not account for non-linear phenomena that could be prevalent in an emerging economy. Originality: The current research is among the first 10-year empirical validations of the ARIMA model's predictive accuracy in the Sri Lankan market, as the study’s results provide theoretical and practical insights into predictive modelling and market efficiency
SLIF-Tomato: Inverted Residual Convolutional Block Attention Module for In- field Tomato Leaf Disease Recognition
(Springer Nature, 2026) Romiyal, G.; Thuseethan, S.; Ragel, R.G.; Pakeerathan, K.; Vaithehi, S.; Mithuran, T.
Tomato cultivation represents a critical component of nutrition, economic development, and public health, yet it is increasingly compromised by foliar diseases that diminish yield and intensify dependency on hazardous agrochemicals. Although deep learning models have demonstrated strong capabilities for automated disease recognition, existing benchmark datasets exhibit limited real-world utility, primarily due to the absence of in-field imagery and precise annotations of diseased regions. A novel attention mechanism, Inverted Residual Convolutional Block Attention Module (IR-CBAM), is proposed, combining inverted residual blocks with the CBAM Module, and is specifically tailored to address challenges posed by in-field image variability, such as complex backgrounds and inconsistent lighting. Furthermore, this study introduces SLIF-Tomato, the Sri Lankan In-Field Tomato leaf disease dataset, which is the first complete in-field dataset comprising class labels and bounding box annotations collected under diverse real-world conditions. The proposed approach achieved 99.66% and 99.91% accuracy rates on two curated versions of the SLIF-Tomato dataset. Subsequently, the YOLOv12-large model is employed to detect diseased regions, which obtained an average precision score of 88.5%. These contributions advance the development of accurate, efficient and field- adaptable diagnostic systems for tomato leaf disease management in precision agriculture.
Haar wavelet-guided dynamic Feature Pyramid Network for an efficient paddy leaf disease classification
(Elsevier, 2026) Kiriharan, T.; Thanikasalam, K.; Amirthalingam, R.; Terensan, S.; Fernando, S.
Early and accurate identification of paddy leaf diseases is crucial for timely intervention and effective crop management. Although deep learning based approaches have demonstrated strong performance in paddy leaf disease classification, they often struggle to capture the diverse multiscale symptom patterns of diseases, resulting in the misclassification of challenging samples. Moreover, the high computational cost of deep learning based models remains a significant limitation. To address these challenges, this study proposes a novel Haar wavelet-guided deep Feature Pyramid Network (FPN) model. In the proposed framework, deep features are extracted using a backbone network, and a FPN is employed to capture multiscale disease symptoms. In parallel, Haar wavelet features are extracted to provide complementary texture cues that are not explicitly modelled by deep features. Guided by these wavelet features, a gating-based dynamic feature selection module is then utilised to identify image-specific FPN features, which are subsequently used for classification. In the second phase of the study, a lightweight variant of the proposed model is developed using a knowledge distillation technique, achieving high classification accuracy while substantially reducing the number of parameters and FLOPs. In addition, a new benchmark dataset, named NP-LankaPaddy, is constructed to address the limited availability of datasets representing Sri Lankan paddy leaf disease conditions. Experimental results demonstrate that both the proposed approach and its lightweight variant outperform state-of-the-art methods across four benchmark datasets, achieving notably high accuracies of 98.04% and 97.84%, respectively, on the well known Paddy Doctor dataset. The source code and dataset supporting this study are openly available at https://doi.org/10.5281/zenodo.18334503.
Acarous calamus L. based nano-bio formulation as an alternative to synthetic fungicides against Aspergillus flavus link
(Springer Nature, 2026) Kanagasabai, V.; Pakeerathan, K.; Sashikesh, G.
Carcinogenic Aflatoxins producing Aspergillus flavus contaminate food crops and pose health risks to humans and livestock. Synthetic fungicides are commonly used to control A. flavus, but they can have negative environmental and health impacts. Acarous calamus L., also known as sweet flag, is a plant with potential antifungal properties. Nanotechnology can enhance the effectiveness of plant extracts by increasing their surface area and allowing for better penetration. Current study focused to explore nano-bio formulation of A.calamus silver nanoparticle and comparative study of its efficacy on growth inhibition and reproduction of A. flavus. All the experiments were conducted in Complete Randomized Design (CRD), and data were subjected ANOVA using SAS 9.1 and Tukey’s HSD multiple comparison test was used to determine the best treatment combination at P < 0.05. The UV spectrophotometer results confirmed that the silver nanoparticle was synthesized at the optimum condition of optimum volume was found to as 25 mL of 0.01 mol L (−1) of silver nitrate, optimum time was found as 210 min with the absorption peak range of 400 –500 nm. SEM characterization captured the AgNPs size varies from 0.11 μm to 2.23 μm. AgNPs concentration of 0.02 g inhibit the growth by 50% compared to A. calamus water extracts and > 90% reduction in spore production reduction at . Moreover, growth inhibition percentage and rate spore production of A. flavus in Ag-Nano particle inoculated treatments were perfectly corelated with the R 2 value of 0.96 at P < 0.01& 0.05. This study concludes Nano-bio formulations show enhanced the efficiency and promise of plant-based solution as a natural fungicide against A. flavus. Field research is underway to fully understand the potential of this Nano-bio formulations.
Characterization of Mexican mint (Plectranthus amboinicus) using morphological, molecular, and GC-MS analyses
(Elsevier, 2026) Mohanathas, A.C.; Terensan, S.; Kanapathy, G.
Plectranthus amboinicus (Lour.) Spreng., commonly known as Mexican mint, is an aromatic and medicinal herb extensively used in traditional medicine across tropical regions. Despite its pharmacological and economic importance, information on its morphological, genetic, and chemical diversity in Sri Lanka is scarce. This study comprehensively characterized P. amboinicus accessions collected from different regions of the Northern Province of Sri Lanka through integrated morphological, sensory, molecular, phylogenetic, and chemical analyses. Morphological assessment revealed significant variation among five identified morphotypes based on plant stature, leaf size, branching pattern, and trichome density. Among them, morphotype M004 exhibited the strongest aroma intensity, despite its shorter stature, likely due to its dense glandular trichomes and compact leaf structure. Molecular confirmation using partial Internal Transcribed Spacer (ITS) sequence identified all morphotypes as P. amboinicus. Phylogenetic analysis clustered the Sri Lankan accessions (PQ387080, PQ390379, PQ390380) within the P. amboinicus clade but as a distinct subcluster separated from Indian and Indonesian sequences, indicating a possible unique lineage shaped by local adaptation, although this has to be tested further with more samples and by analyzing more DNA markers. GC–MS analysis of hexane extract from morphotype M004 revealed 28 volatile compounds dominated by monoterpenes and sesquiterpenes; p-Cymene (12.91%), Thymol (12.01%), cyclohexanol derivative (10.84%), Germacrene D (9.10%), γ-Terpinene (7.44%), Humulene (6.00%), Caryophyllene (5.54%), and α-Copaene (4.13%). Compared to earlier reports, Thymol was lower while sesquiterpenes were higher, with a rare cyclohexanol derivative underscoring a unique chemical profile of the accession as well. The distinct genetic and chemical divergence of the Sri Lankan population highlights the emergence of a region-specific variant with potential applications in pharmacology, aromatics, and genetic improvement programs.