2025
Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4035
Browse
Publication Open Access Alcohol Consumption and Stroke Mortality: Global Patterns, Risks and Public Health Implications(Springer Nature 2025, 2025-05-07) Kolonne, T; Mudalige, K; Dissanayaka, G; Rathnayake, K; Jayathilaka, R; Rajamanthri, L; Wickramaarachchi, CGlobally, stroke remains a leading cause of mortality and disability, while alcohol consumption continues to vary widely across regions, prompting concern over its health impacts. This study examines the association between different alcoholic beverages and stroke mortality, using secondary data from 1990 to 2020. Alcohol consumption and stroke death rates across 189 countries were categorized into five levels, from very high to very low, and averaged over two periods (1990–1999 and 2011–2020). Multiple Correspondence Analysis (MCA) was applied to assess relationships among four categorical variables. The findings indicate a significant association between very high alcohol consumption and increased stroke mortality, with eight countries showing elevated death rates. Conversely, moderate beer consumption was linked to reduced stroke mortality, suggesting nuanced effects based on beverage type and quantity. These insights offer a foundation for targeted public health policies and emphasize the need for further investigation into the mechanisms driving alcohol-related stroke risks.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 Embargo Breaking the Glass Ceiling: The Impact of Board Gender Diversity on Firm Financial Performance in Sri Lanka(Wiley, 2025-03-05) Kaluarachchi, SThe purpose of this study is to examine the influence of board gender diversity on the financial performance of firms in SriLanka. While extensive research has been conducted in developed countries, this study addresses the gap in literature by exam-ining how cultural and economic differences influence the relationship between gender diversity and corporate performance.Understanding this relationship in developing countries is crucial for shaping inclusive corporate governance policies and pro-moting sustainable development in diverse economic contexts. This study employs secondary data from the annual reports oflisted companies over the period 2012–2022, using panel regression and multiple linear regression models to explore the rela-tionship between board gender diversity and firm financial performance. The findings reveal that, despite Sri Lanka's corporateboards being predominantly male-dominated, the inclusion of female directors is positively associated with improved financialperformance. This is evident through factors such as the presence of female directors, female chairpersons, board size, CEOduality and firm age. In contrast, independent directors and leverage are found to have a negative impact on performance. Thestudy provides valuable insights for researchers, investors and policymakers, offering a roadmap for enhancing gender diversityin Sri Lanka's corporate governance and promoting sustainable developmentPublication Open Access Carbon emissions and global R&D patterns: a wavelet coherence perspective(Springer, 2025-03-23) Senevirathna, D; Gunawardana, H; Ranthilake, T; Caldera, Y; Jayathilaka, R; Rathnayake, N; Peter, SThis study examines the causality between Research and Development (R&D) and Carbon dioxide (CO2) emissions at the global level, utilising data gathered from 2000 to 2020 across various countries categorised as developed, developing, economies in transition, and least-developed. The data collected for the study are analysed using the Wavelet coherence methodology. The findings reveal both bidirectional and unidirectional causality between the variables, which have evolved over time. Globally, a bidirectional relationship is present in the short-term, no causality in the medium-term and unidirectional causality in the long-term. Developed countries exhibit a two-way causality in the short-term, while no causality exists in the medium-term and long-term. Developing countries show a bidirectional relationship across all time frequencies. In economies in transition, a bidirectional relationship appears towards the end of the period over the short, medium, and long-term. The least developed countries show no causality in the short and long-term, but a one-way causality in the medium-term. Governments and the policymakers can implement environmental policies to mitigate carbon emissions through R&D. The findings suggest targeted and strategic strategies to enhance the impact of R&D on emissions reduction. Policymakers can use this analysis to prioritize funding for clean energy innovations, establish incentives for low-tech technologies, and promote international cooperation in green technology research. Additionally, focusing on these carbon mechanisms and aligning R&D efforts to support development goals can increase the effectiveness of climate policies, ensuring a balance between economic growth and environmental sustainability.Publication Open Access Comparative Determinants of Global Competitiveness: Governance, Social Progress, and Economic Trade-Offs(Wiley, 2025-03-31) Kalansuriya, N; Jayathilaka, RThis study analyses the determinants of global competitiveness in 2018 and 2023, focusing on governance, social progress, economic dynamics, sustainability, and human development. Using an Ordered Probit Regression model, countries are classified into low, middle, and high competitiveness tiers, enabling a structured assessment of how these factors influence rankings over time. The results indicate that reducing corruption and improving social progress are key to enhancing competitiveness across all tiers, as governance quality and human capital investment significantly impact economic advancement. Environmental performance and trade openness present trade-offs: while they support long-term growth, they impose short-term costs, particularly in highly competitive economies. Human development emerges as a consistent driver of upward mobility, emphasising the importance of sustained investment in education and healthcare. This study contributes uniquely by providing a two-year comparative analysis and employing an Ordered Probit Model to assess competitiveness, offering deeper insights into how countries transition between tiers. The findings highlight the need for tailored policy approaches: low-tier nations should prioritise institutional reforms, middle-tier economies should focus on innovation-driven growth, and advanced economies must balance environmental policies with economic sustainability. These insights provide valuable guidance for policymakers navigating global economic transitions.Publication Open Access A Comprehensive Investigation of Microplastic Contamination and Polymer Toxicity in Farmed Shrimps; L. vannamei and P. monodon(Springer Nature, 2025-02-20) Jayaweera, Y.U; Hennayaka, H.M.A.I; Herath, H.M.L.P.B; Gajanayake Mudalige, P.K; Mahagamage, M.G.Y.L; Rodrigo, U.D; Manatunga, D.CMicroplastic (MP) pollution poses a significant threat to marine ecosystems, seafood safety, and human health. This study investigates the accumulation of microplastics in two commercially important shrimp species, Litopenaeus vannamei (L. vannamei) and Penaeus monodon (P. monodon), sourced from cluster farming sites in Puttalam, Sri Lanka. Shrimp exoskeletons and edible soft tissues underwent rigorous microplastic analysis, including density separation, alkali digestion, stereo microscopy, and Raman spectroscopy. The results revealed high microplastic contamination, with L. vannamei containing an average of 4.99 ± 1.81 MP particles/g and P. monodon containing 1.87 ± 0.55 MP particles/g. Microplastic sizes varied, with L. vannamei predominantly contaminated with 100–250 µm particles and P. monodon with 500 µm—1000 µm particles. Fiber morphotypes were prevalent in L. vannamei, while blue-colored microplastics were dominant in P. monodon. These comprised polystyrene (PS), nylon 6,6, and polyethylene (PE) which were identified by Raman spectroscopy. Additionally, the study investigated the acute toxicity effects of microplastic polymer combinations using a zebrafish embryo model (FET236 assay). Zebrafish embryos exposed to polyethylene-nylon 6,6 combinations exhibited significant adverse effects on hatching, survival, and heart function at lower concentrations, while polyethylene terephthalate-polystyrene combinations showed no considerable effects. These findings underscore the urgent need for monitoring and managing microplastic contamination in shrimp farming areas. Future research should focus on elucidating the ecological impacts and human health risks associated with microplastic exposure.Publication Open Access Deciphering Online Consumer Behaviour: Uncovering Factors Affecting Purchase Intentions for Electronic Items in Sri Lanka Using Ordered Probit Model(SAGE, 2025-05-29) Rathnaweera, D; Jayathilaka, RThis study identifies key determinants of Sri Lankan consumers’ online purchase intention for electronic goods and quantifies their impact using an ordered probit regression model. The findings reveal that a 1% increase in online reviews is associated with a 0.33 percentage point increase in high purchase intention, while trust and word-of-mouth similarly exert strong positive effects (0.30 and 0.21 percentage points, respectively). Notable, delivery terms, although significant, play a lesser role compared to online reputation factors. These insights offer strategic implementation for e-commerce businesses, emphasizing the need for enhanced consumer trust mechanisms, proactive reputation management and optimized delivery strategies. Policy can leverage these findings to develop consumer protection frameworks that ensure reliability in online transactions, fostering long-term e-commerce growth in emerging markets.Publication Open Access Digitalisation dynamics: Developing a global index for digital pioneers, adapters, and followers(Science Direct, 2025-04-25) Kumara, U; Wijerathna, D; Jayathilaka, RDigitalisation has become a transformative force revamping economies, societies, and governance systems. It has fostered innovation and enhanced global competitiveness in an interconnected world. This study aims to construct a composite index for digitalisation to evaluate global digitalisation levels and categorise nations as digital pioneers, adapters, and followers. The index is developed using a Principal Component based on Factor Analysis, utilising secondary data gathered from World Development Indicators from 2010 to 2022. The study highlights that the United States, Hong Kong, Singapore, China, and Korea dominate the top tier as digital pioneers through adopting emerging fourth-industrial revolution technologies such as artificial intelligence, blockchain, etc. Moreover, nations like Japan, Switzerland, Estonia, Czechia, and Iceland are categorised as digital adapters due to less digital investments in digital technologies and building digital ecosystems. At the same time, Madagascar, Paraguay, Ecuador, Guatemala, and Egypt remain at the bottom of the index as digital followers due to existing digital gap and digital literacy and skills among the population. This evidence provides digitalisation index an effective tool for policymakers and researchers to assess each nation's digitalisation levels and technological readiness, to formulate strategies and policies to enhance digital interaction, foster innovation, and promote economic growth.Publication Embargo Durability and mechanical performance of glass and natural fiber-reinforced concrete in acidic environments(Elsevier, 2025-02-28) Justin, S.; Thushanthan, K; Tharmarajah, GThis study investigates the mechanical and durability characteristics of fiber-reinforced concrete when exposed to acidic environments. The research focuses on the effects of adding 1 % of treated coir fibers (TCF), treated rice husk fibers (TRH), and glass fibers (GF), along with 5 % silica fume (SF), to concrete. Experimental results show that the inclusion of these fibers and SF enhances both compressive and tensile strengths, with the most significant improvements observed in GF-reinforced concrete. The durability of the concrete was tested by immersing samples in acidic solutions with pH values of 3 and 5 for 28 days. Ultrasonic Pulse Velocity (UPV) tests indicated that the concrete's quality remained stable, while compressive strength tests revealed an increase in strength, particularly in samples exposed to pH 5. Sorptivity tests, which measure water absorption, indicated higher initial absorption rates due to the porous nature of fiber-reinforced concrete. However, as hydration progressed, the rate decreased. SEM images show that incorporating silica fume improves the microstructure of the specimens benefitting the strength of the structure. The study concludes that concrete reinforced with GF and SF exhibits superior mechanical properties and durability in acidic environments, making it a promising material for use in harsh conditions.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 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 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 Foreign direct investment and foreign reserves linkage: a global study based on wavelet coherence and granger causality(Springer Nature, 2025-04-02) Jayathilaka, R; Vidyapathirana, G; Fernando, C; Sandaruwan, C; Lakshani, SIn the contemporary global economy, foreign direct investment (FDI) and foreign reserves (FR) play a crucial role in economic stability, particularly amid geopolitical and financial uncertainties. This study examines the relationship between FR and FDI over a 23-year period (2002–2022), utilising panel data from 110 countries. By employing Wavelet Coherence analysis, the findings indicate that FR significantly influences FDI inflows across most regions, except in Europe, where the relationship is more complex. Additionally, the Granger causality test confirms a predominantly unidirectional linkage from FDI to FR in most countries, particularly in North America, Asia, and Oceania. These findings suggest that policies fostering economic stability, such as flexible tax regimes and strong governance, are essential for enhancing FDI attractiveness, particularly in regions where the FR-FDI relationship remains weak.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 Impact of geographical variation on nutritional and antioxidant properties of Basella alba L. from Sri Lanka(BioMed Central Ltd, 2025-01) 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 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 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.Publication Open Access A novel application with explainable machine learning (SHAP and LIME) to predict soil N, P, and K nutrient content in cabbage cultivation(Elsevier B.V., 2025-08) Abekoon, T; Sajindra, H; Rathnayake, N; Ekanayake, I.U.; Jayakody, A; Rathnayake, UCabbage (Brassica oleracea var. capitata) is commonly cultivated in high altitudes and features dense, tightly packed leaves. The Green Coronet variety is well-known for its robust growth and culinary versatility. Maximizing yield is crucial for food sustainability. It is essential to predict the soil's major nutrients (nitrogen, phosphorus, and potassium) to maximize the yield. Artificial intelligence is widely used for non-linear predictions with explainability. This research assessed the predictive capabilities of soil nitrogen, phosphorus, and potassium levels with explainable machine learning methods over an 85-day cabbage growth period. Experiments were conducted on cabbage plants grown in central hills of Sri Lanka. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were used to clarify the model's predictions. SHAP analysis showed that high feature values of the number of days and plant average leaf area negatively impacted for nutrient predictions, while high feature values of leaf count and plant height had a positive effect on the nutrient predictions. To validate the results, 15 greenhouse-grown cabbage plants at various growth stages were selected. The nitrogen, phosphorus, and potassium levels were measured and compared with the predicted values. These insights help refine predictive models and optimize agricultural practices. A user-friendly application was developed to improve the accessibility and interpretation of predictions. This tool is a user-friendly platform for end-users, enabling effective use of the model's predictive capabilities.Publication Open Access Restoring life expectancy in low-income countries: the combined impact of COVID-19, health expenditure, GDP, and child mortality(BioMed Central Ltd, 2025-03-06) Karunarathne, M.; Buddhika, P; Priyamantha, A; Mayogya, P; Jayathilaka, R; Dayapathirana, NBackground: Life expectancy is a vital indicator of a country’s health and progress. Low-income countries face uncertainty regarding the long-term impact of the COVID-19 pandemic, driven by health expenditure levels, concerns over rising child mortality rates, and decreasing per capita income. These factors challenge life expectancy and demand urgent attention. This study aims to identify patterns, challenges, and opportunities to improve life expectancy in these countries through better health policies and resource allocation. Methods: The research investigates the impact of the COVID-19 pandemic, health expenditure, per capita income, and child mortality rates on life expectancy in low-income countries. By examining 22 years of data from 20 countries, using a comprehensive dataset from the Our World in Data database, this study employs panel regression and time series analysis to explore how these factors influence life expectancy. Results: The findings indicate a significant negative effect of COVID-19 on life expectancy, while health expenditure and per capita income show a positive impact. Conversely, child mortality rates exert a negative effect on life expectancy in low-income countries. Conclusion: This research contributes to the existing body of knowledge by analysing how COVID-19, health expenditure, per capita income, and child mortality collectively affect life expectancy in low-income countries. The insights gained may inform policymakers and health consultants about the need for targeted interventions, prioritising healthcare investment and child health. By addressing these critical areas, it may be possible to improve life expectancy and overall health outcomes, thus contributing to global health equity. © The Author(s) 2025.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.