Scopus Index Publications
Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/2162
This collection consists of all Scopus-indexed publications produced by SLIIT researchers. Scopus is recognized worldwide as a leading and reputable academic indexing database.
Browse
273 results
Search Results
Publication Embargo Assessing the Efficacy of Machine Learning Algorithms in Predicting Critical Properties of Gold Nanoparticles for Pharmaceutical Applications(Springer Nature Link, 2025-07-08) Fernando, H; Mohottala, S; Jayanetti, M; Thambiliyagodage, CAu nanoparticles are increasingly used in pharmaceuticals, but their synthesis is costly and time-intensive. Machine Learning can help optimize this process. In this research, eight distinct Machine Learning models were implemented and optimized on a dataset comprising 3000 records of gold nanoparticles. The performance of these models was assessed using four accuracy metrics and the time required for training and inference. The results are promising, with all seven models demonstrating high accuracy and low time requirements. Notably, the XGBoost and Artificial Neural Network models exhibited exceptional performance, with Mean Squared Error values of 0.0235 and 0.0098, Mean Absolute Error values of 0.1021 and 0.0674, Mean Absolute Percentage Deviation values of 0.4945 and 0.3590, R2 scores of 0.9995 and 0.9998, and inference times of 0.0029 and 0.4299 s, respectively. The Explainable Artificial Intelligence analysis of the resulting models revealed some interesting insights into how the models make the predictions and what factors heavily contribute to the nanoparticle AVG_R, allowing chemists to optimize the synthesis for gold nanoparticles better. The key contributions of the research include the design and development of eight Machine Learning models using industry-standard frameworks, the training, tuning, and evaluation of these eight models using five different metrics, and further assessment of these trained models using Explainable Artificial Intelligence. The findings indicate a substantial potential for applying neural networks in the design phase of nanoparticle synthesis, which could lead to significant reductions in both the time and cost required for synthesizing Au nanoparticles for pharmaceutical applications.Publication Open Access Facial identity recognition using StyleGAN3 inversion and improved tiny YOLOv7 model(www.nature.com, 2025-03-17) Kumar, A; Bhattacharjee, S; Kumar, A; Jayakody, D. N. KFacial identity recognition is one of the challenging problems in the domain of computer vision. Facial identity comprises the facial attributes of a person’s face ranging from age progression, gender, hairstyle, etc. Manipulating facial attributes such as changing the gender, hairstyle, expressions, and makeup changes the entire facial identity of a person which is often used by law offenders to commit crimes. Leveraging the deep learning-based approaches, this work proposes a one-step solution for facial attribute manipulation and detection leading to facial identity recognition in few-shot and traditional scenarios. As a first step towards performing facial identity recognition, we created the Facial Attribute Manipulation Detection (FAM) Dataset which consists of twenty unique identities with thirty-eight facial attributes generated by the StyleGAN3 inversion. The Facial Attribute Detection (FAM) Dataset has 11,560 images richly annotated in YOLO format. To perform facial attribute and identity detection, we developed the Spatial Transformer Block (STB) and Squeeze-Excite Spatial Pyramid Pooling (SE-SPP)-based Tiny YOLOv7 model and proposed as FIR-Tiny YOLOv7 (Facial Identity Recognition-Tiny YOLOv7) model. The proposed model is an improvised variant of the Tiny YOLOv7 model. For facial identity recognition, the proposed model achieved 10.0% higher mAP in the one-shot scenario, 30.4% higher mAP in the three-shot scenario, 15.3% higher mAP in the five-shot scenario, and 0.1% higher mAP in the traditional 70% − 30% split scenario as compared to the Tiny YOLOv7 model. The results obtained with the proposed model are promising for general facial identity recognition under varying facial attribute manipulation.Publication Open Access Identifying the causes of adolescent malnutrition in Nuwara-Eliya District, Sri Lanka(Nature Research, 2025-05-06) Nandajeewa, S; Aluthwatta, S; Weerarathna, R; Rathnayake, N; Rajapakse, V; Wijesinghe, N; Liyanaarachchi, TMalnutrition, a persistent illness, significantly reduces fat, muscle and bone levels, harming internal organs. The economic crisis in Sri Lanka has led to widespread malnutrition among children, including adolescents experiencing growth spurts. This study identifies factors influencing malnutrition in grade 10 pupils in the Nuwara-Eliya District, with the highest rates of malnutrition and also a multicultural area with many estate sector residents. Using a cross-sectional, quantitative approach, the data was collected from 379 respondents via a Likert scale questionnaire. Structural Equation Model (SEM) analysis was conducted using Smart PLS 4.0. Key findings indicate that environmental factors, such as access to clean water and sanitation, significantly influence adolescent malnutrition. A comprehensive strategy incorporating education, healthcare, and environmental improvements is essential for this. Ongoing observation, community engagement, and cooperative tactics are crucial for sustainable solutions. Addressing environmental issues and promoting a holistic approach to health education and infrastructure improvements are vital to combat adolescent malnutrition in vulnerable populations.Publication Open Access Exploring nontoxic perovskite materials for perovskite solar cells using machine learning(Discover, 2025-07-06) Pabasara, W.G.A.; Wijerathne, H.A.H.M; Karunarathne, M.G.M.M.; Sandaru, D.M.C.; Abeygunawardhana, Pradeep K. W.erovskite solar cells are promising renewable energy technology that faces significant challenges due to the Pb induced toxicity. The current study addresses this issue by leveraging machine learning techniques to explore Pb-free perovskite materials that ensure environmental sustainability and human safety. A highly accurate machine learning model was developed to predict Goldschmidt factor and the band gap, aiming to discover lead-free perovskites. Extreme Gradient Boost (XGBoost), Random Forest (RF), Gradient Boost Regression (GBR), and Ada Boost Regression (ABR) models were employed for this purpose. The findings exhibit that XGBoost delivers the most precise and reliable results for Goldsmith tolerance factor prediction with an accuracy of 98.5%. Furthermore, GBR model, combined with K-nearest neighbors (KNN) model delivers an impressive accuracy of 98.7% for the band gap predictions. 49 Pb-free perovskite materials were screened out considering the toxicity and the abundance. Utilizing Principal Component Analysis (PCA) and K-means clustering, six optimal materials (KBiBr3, KZnBr3, RbBiBr 3, RbZnBr3, MAGeI3, and FAGeI3null) were identified as the potential environment-friendly materials for photovoltaic applications. These results show the crucial role of machine learning and statistical analysis in discovering nontoxic and environmental-friendly perovskite materials, advancing the development of sustainable energy solutions.Publication Open Access Impact of geographical variation on nutritional and antioxidant properties of Basella alba L. from Sri Lanka(BioMed Central Ltd, 2025-01-27) Dahanayaka, L.W; Mapa, M. M. S. T.; Kadigamuwa, C.C; Udayanga, DBackground Basella alba L. (Malabar spinach) is a widely consumed leafy vegetable, well known for its nutritional and therapeutic properties. These properties arise from the availability of essential nutrients, phytochemicals, and antioxidant potential, which may vary depending on environmental factors induced by the geographical location. In this study our aim is to investigate the correlation between the geographical location and proximate composition, phytochemical content, and antioxidant activity of B. alba harvested from fifteen locations in Sri Lanka. Results According to the statistical analysis by ANOVA and Tukey test, the results of proximate analysis confirmed that samples from different locations showed statistically significant variance in nutritional content. Furthermore, phytochemical content and antioxidant potential varied showing a significant difference between locations in total chlorophyll (27.53 to 6.69 µg/g dry weight), carotene (4.54 to 1.15 µg/g dry weight), total flavonoid content (10.54 to 3.94 mg/g dry weight in Quercetin equivalents), total phenolic content (8.33 to 0.46 mg/g dry weight in gallic acid equivalents), 1,1-diphenyl-2-picrylhydrazyl radical scavenging activity (38.03–11.4% inhibition), and ferric ion-reducing antioxidant power (1.23 to 3.76 mg/g dry weight in ascorbic acid equivalents) (p < 0.05). The Pearson correlation showed a strong positive correlation between total phenolic content and antioxidant activity. Principal component analysis indicates the role of antioxidant activity and chlorophyll content in location differentiation, forming distinct clusters. Cluster analysis categorized samples into four groups, linking biochemical traits to agro-climatic zones. The principal component analysis and cluster analysis showed a close relationship between some locations due to their high antioxidant and phytochemical accumulation. Conclusion This study exhibits the importance of geographical location on the phytochemical profile and antioxidant properties of B. alba. These findings can be used to refine optimal cultivation sites for B. alba to enhance the efficacy of its nutraceutical and pharmaceutical potential.Publication Open Access Unveiling the challenges: exploring start-up hurdles faced by small and medium-sized enterprise entrepreneurs in Sri Lanka(https://www.nature.com, 2025-03-30) Gankandage, A; Jayathilaka, RThis study specifically focuses on the factors contributing to start-up failures in the SME sector in Sri Lanka, with particular emphasis on the educational, socio-cultural, economic, and psychological variables that affect entrepreneurial outcomes. The primary objective is to identify and analyse the factors contributing to these failures. Data collection involved interviews, telephone surveys, and online questionnaires. Given that the dependent variable categorises outcomes as either success or failure, a Probit regression model, was deemed the most appropriate analytical method. The findings reveal significant impacts of educational and economic factors on start-up failures in the SME sector. Additionally, psychological, and socio-cultural factors were found to influence these failures. Most participants recommended integrating entrepreneurship and skill development topics into the O/Level and A/Level curricula. Based on these insights, this study proposes several policy recommendations. It suggests that policymakers improve the education system to meet the country’s educational needs more effectively. It also recommends that family members, society, and religious leaders receive education pertaining to start-up development. Furthermore, it advises policymakers and financial institutions to align more closely with entrepreneurial needs to prevent business failures. Lastly, the study emphasises the importance of educating entrepreneurs on maintaining a motivated and positive attitude, addressing the fear of loss, and understanding the psychological aspects of business management. Building upon the brief overview in the abstract, the following introduction lays the foundation for our study, elaborating on the economic concepts and contextual background.Publication Open Access Unmasking climate vulnerability in Africa: the role of CO2 and CH4 emissions on rising temperatures and sea levels(www.nature.com, 2025-05-02) Gunaratne, T.; Liyanage, S.; Punchihewa, C; Badurdeen, S; Jayathilaka, RClimate change influenced by anthropogenic emissions is a global occurrence affecting the Mean Surface Temperature (MST) and Mean Sea Level (MSL) patterns. The African continent contributes to the lowest Greenhouse Gas (GHG) emissions globally. However, GHG emissions, particularly Carbon Dioxide (CO2) and Methane (CH4) emission patterns, show a continuous increase in the African region, reflecting the importance of practising economic growth in the continent with sustainable environmental policies to meet future global climate targets. Given Africa’s increasing emissions and the continent’s vulnerability to climate change, this study contributes to the existing literature by assessing the continental and country-wise impact of CO2 and CH4 emissions on MST and the resulting impact on MSL through Fixed Effect (FE) panel estimation and Simple Linear Regression (SLR). The research employs data from 1993 to 2020 for fifty-four African countries. The study’s main findings show that CO2 and CH4 positively impact MST at a 1% significance level, and MST positively impacts MSL at a 5% significance level. This study focuses on continent-specific and country-specific emissions and their impacts and proposes policy measures to mitigate the emissions in the African continent.Publication Open Access Economic and healthcare determinants of under-five mortality in low-income countries(Springer Nature Link, 2025-06-06) Rajapakse, V; Fernando, A; Sudangama, N; Adikari, D; Sundaram, A; Jayathilaka, RBackground Under-five mortality (U5MR) remains a critical development challenge, particularly in low-income countries (LICs), where children face the highest risk of preventable deaths. This study explores the influence of three key variables, per capita Gross Domestic Product (PGDP), DTP1 immunisation coverage, and Government Healthcare Expenditure (GHE), on U5MR across 19 LICs from 2000 to 2020, providing a clearer understanding of their individual and combined effects. Methods A balanced panel dataset was analysed using both fixed-effects and random-effects panel regression models. Additionally, country-level insights were derived through multiple linear regression (MLR) to capture variations across different LIC contexts. Results The analysis revealed a strong inverse relationship between PGDP and U5MR, highlighting the role of economic growth in improving child survival. DTP1 immunisation coverage showed mixed effects, positively linked to reduced mortality in most LICs, but unexpectedly associated with higher U5MR in specific contexts like Malawi and the Central African Republic, suggesting challenges in access or implementation. Similarly, GHE showed varied impacts, with some countries benefiting significantly, while others demonstrated weaker or adverse effects, likely due to inefficiencies in spending. Conclusions The findings highlight that reducing U5MR in LICs requires more than isolated actions. It calls for combined strategies that connect economic improvements with fair healthcare investments and better immunisation delivery. Policymakers must design context-specific solutions to ensure lasting and meaningful progress in child health outcomes.Publication Open Access Surviving the first five years: the economic and healthcare determinants of child mortality in Sri Lanka(Springer Nature Link, 2025-06-21) Rajapakse, V; Jayathilaka, RBackground This study investigates the role of economic growth, healthcare investment, immunization coverage, and malnutrition in reducing under-five mortality rates (U5MR) in Sri Lanka. Understanding how these factors interact within socio-economic ecosystems is essential to formulating sustainable strategies to improve child survival outcomes. Methods This study employs multiple linear regression to analyze the statistical associations between economic growth, healthcare investment, immunization, malnutrition, and under-five mortality in Sri Lanka. Using secondary data from the World Bank and UNICEF (2000–2021), U5MR was modeled against economic growth (per capita GDP), government healthcare expenditure (GHE), immunization coverage (DTP1), and malnutrition (MLN), with significance assessed through p-values and model fit via R². Results The multiple linear regression model demonstrated strong explanatory power, accounting for 85% of the variation in under-five mortality (R² = 0.85). Economic growth and immunization coverage were negatively associated with U5MR and found to be statistically significant (p < 0.05 and p < 0.10 respectively), indicating their potential role in reducing child mortality. Malnutrition showed a strong positive association (p < 0.01), emphasizing its continued threat to child health. Although government healthcare expenditure had a negative association, it was not statistically significant, suggesting possible inefficiencies in resource utilization. Conclusion The study highlights the significant role of economic growth, healthcare expenditure, immunization coverage, and nutrition in shaping U5MR trends in Sri Lanka. The findings emphasize the need for targeted policy interventions to enhance child health outcomes and ensure sustainable progress in reducing child mortality.Publication Open Access The interplay between globalisation and economic growth: a multi-regional analysis(Springer Nature Link, 2025-06-10) Athalage, D; Wijesuriya, P; Sandanayaka, I; Rathnayake, D; Jayathilaka, RGlobalisation is recognised as a prospective dynamic that facilitates the performance and expansion of economies. This study analyses the causal progression between globalisation, its sub dimensions (economic, social and political) and economic growth spanning 97 countries and six regions (Africa, Asia, Europe, North America, Oceania, and South America) covering the period from 1971 to 2021. The Panel Granger causality test is employed as the statistical methodology to comprehend the nexus between globalisation and economic growth. The Granger results reveal bi-directional causal flows between economic growth and globalisation in Asia, North America, and Oceania, along with one-way causal flows in Africa, South America, and Europe. Bidirectional dynamics pertaining to economic globalisation were also revealed in Asia, Africa, Oceania, and Europe. This study recommends the enhancement of regional integration, addressing of structural changes, leveraging the use of technology, and the development of comprehensive globalisation strategies with respect to regions with the intention of reinforcing their globalisation-growth stance, while complementing the Sustainable Development Goals of the United Nations.