Publish in Scimago's Q1 and Q2 Journals

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4196

Browse

Filters

2025 - 20262

Advanced Search

Filter by

Settings

Author: search.filters.author.Hoshino, YStart date: 2025

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationOpen Access
    Explainable AI for public health surveillance: investigating the persistent crisis of intentional injury mortality (suicide and homicide) in the Americas
    (Nature Research, 2026-05-24) Kularathne, S; Rathnayake, N; Jayathilaka, R; Nakaoka, I; Hoshino, Y
    Intentional injury mortality (IIM), comprising homicide and suicide, remains a critical public health crisis in the Americas, which not only has the highest regional homicide rates globally but is also the only region where suicide rates continue to rise. This study employs explainable artificial intelligence (XAI) to examine the structural and temporal drivers of IIM across 25 countries, based on data from the previous two decades. Two complementary models were developed: a snapshot model based on contemporaneous socioeconomic indicators and a persistence-aware model incorporating lagged effects of predictors. Analyses were conducted across both income-level categories and geographic sub-regions to uncover context-specific patterns. While both models performed at acceptable levels in distinguishing immediate and enduring effects, persistence-aware models consistently outperformed snapshot models, thereby reframing IIM as a temporally sustained phenomenon. Feature importance, interpreted through SHapley Additive exPlanations (SHAP), highlighted the varying impacts of unemployment, inflation, corruption, and economic growth across income tiers and sub-regions. The results demonstrate that a combination of short-term shocks and the long-standing effects of governance and social factors drives IIM in the Americas. These findings underscore the need for dual-horizon policy approaches that address both immediate crises and structural root causes.
  • Thumbnail Image
    PublicationOpen Access
    Efficient Hotspot Detection in Solar Panels via Computer Vision and Machine Learning
    (Multidisciplinary Digital Publishing Institute (MDPI), 2025-07-15) Fernando, N; Seneviratne, L; Weerasinghe, N; Rathnayake, N; Hoshino, Y
    Solar power generation is rapidly emerging within renewable energy due to its cost-effectiveness and ease of deployment. However, improper inspection and maintenance lead to significant damage from unnoticed solar hotspots. Even with inspections, factors like shadows, dust, and shading cause localized heat, mimicking hotspot behavior. This study emphasizes interpretability and efficiency, identifying key predictive features through feature-level and What-if Analysis. It evaluates model training and inference times to assess effectiveness in resource-limited environments, aiming to balance accuracy, generalization, and efficiency. Using Unmanned Aerial Vehicle (UAV)-acquired thermal images from five datasets, the study compares five Machine Learning (ML) models and five Deep Learning (DL) models. Explainable AI (XAI) techniques guide the analysis, with a particular focus on MPEG (Moving Picture Experts Group)-7 features for hotspot discrimination, supported by statistical validation. Medium Gaussian SVM achieved the best trade-off, with 99.3% accuracy and 18 s inference time. Feature analysis revealed blue chrominance as a strong early indicator of hotspot detection. Statistical validation across datasets confirmed the discriminative strength of MPEG-7 features. This study revisits the assumption that DL models are inherently superior, presenting an interpretable alternative for hotspot detection; highlighting the potential impact of domain mismatch. Model-level insight shows that both absolute and relative temperature variations are important in solar panel inspections. The relative decrease in “blueness” provides a crucial early indication of faults, especially in low-contrast thermal images where distinguishing normal warm areas from actual hotspot is difficult. Feature-level insight highlights how subtle changes in color composition, particularly reductions in blue components, serve as early indicators of developing anomalies.