Browsing by Author "Fernando, A"

Filter results by typing the first few letters
Now showing 1 - 5 of 5
  • Thumbnail Image
    PublicationEmbargo
    Automated Diabetic Retinopathy Screening With Montage Fundus Images
    (IEEE, 2020-12-10) Kumari, S; Padmakumara, N; Palangoda, W; Balagalla, C; Samarasingha, P; Fernando, A; Pemadasa, N
    Diabetic retinopathy (DR), also known as diabetic eye disease is one of the major causes of blindness in the active population. The longer a person has diabetes, higher the chances of developing DR. This research paper is an attempt towards finding an automatic way to staging DR using montage eye images through artificial intelligence (AI). Convolutional neural networks (CNNs) play a big role in DR detection. Using transfer learning and hyper-parameter tuning DR staging is analyzed through different models. VGG16 gave the highest classification accuracies for the stages Proliferative DR (PDR) & Non-proliferative DR (NPDR). The highest level of NPDR is severe DR which achieved 94.9% classification accuracy (CA) & special features like cotton wool & laser treatment performed at 83.3% CA for each. Moreover, by using patient's history data such as age, right eye & left eye value accuracies & diabetic diagnosed year, system can predict the DR stages. That predictive model has achieved the best CA of 94 % by using Xgboost classifier. Overall, a fully functional app has been developed to detect DR stages with Montage Fundus images using AI.
  • Thumbnail Image
    PublicationEmbargo
    Cloud-based Salesman-Bot for Ontology-based Negotiation
    (IEEE, 2023-04-06) Fernando, A; Rahubedda, T; Jayasinghe, B; Mallikahewa, S; Hettiarachchi, O; Rajapaksha, S
    We have proposed a cloud-based ChatBot (Salesman-Bot) approach to handling multiple negotiation scenarios in a supermarket environment. The web application is a simple interface that can be implemented on a single standalone device or interacted with through a mobile phone. The Salesman-Bot responds both via text and speech. By introducing a Salesman-Bot, efficient negotiation, with quick preferences and suggestions can be provided. A new architecture proposed to operate the Salesman-Bot together with Google APIs and libraries such as Natural Language AI, Vision AI, Speech to Text API, Text to Speech API and Machine Learning using TensorFlow. The application also uses the Google Cloud Platform with related services such as Google App Engine. The goal is to make ChatBots more efficient in negotiating in different business scenarios. This paper presents the work carried out with ontology and machine learning in a cloud-based environment to handle multiple negotiation scenarios based on a negotiation hierarchy. It also proposes the opportunities and drawbacks of such a system.
  • Thumbnail Image
    PublicationOpen Access
    Driving down child mortality in the SAARC: the impact of GDP, healthcare, and vaccination
    (Springer Nature, 2025-09-25) Fernando, A; Sudangama, N; Adikari, D; Sundaram, A; Jayathilaka, R; Rajapakse, V
    This study investigates the determinants of under-five mortality rate (U5MR) in South Asian Association for Regional Cooperation (SAARC) countries from 2000 to 2020, focusing on the roles of per capita gross domestic product (PGDP), Diphtheria-Tetanus-Pertussis (DTP1) immunisation coverage, and government healthcare expenditure (GHE). Despite global progress in reducing child mortality, disparities persist in SAARC countries, where economic, healthcare, and immunisation factors influence child survival. The research employs a panel regression analysis using a fixed effects model to assess the impact of these variables on U5MR across seven SAARC nations (excluding Afghanistan due to insufficient and inconsistent data), as well as multiple linear regression (MLR) for a country-specific explanation. Results reveal that both PGDP and DTP1 coverage are inversely related to U5MR, highlighting the importance of economic growth and immunisation programs in reducing child mortality. However, while the associations between PGDP, GHE, and DTP1 with U5MR were not statistically significant in the panel model, the country specific MLR analysis revealed statistically significant relationships in some cases. In fact, GHE presents mixed results, indicating that healthcare expenditure alone may be insufficient without effective allocation. The study’s findings emphasise the need for region-specific policies to address healthcare inequalities and expand immunisation programs, providing practical recommendations for SAARC policymakers to achieve sustainable improvements in child health outcomes.
  • Thumbnail Image
    PublicationOpen Access
    Economic and healthcare determinants of under-five mortality in low-income countries
    (Springer Nature, 2025-06-06) Rajapakse, V; Fernando, A; Sudangama, N; Adikari, D; Sundaram, A; Jayathilaka, R
    Background 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.
  • Thumbnail Image
    PublicationOpen 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, R
    Background 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.