Research Publications

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4194

This main community comprises five sub-communities, each representing the academic contribution made by SLIIT-affiliated personnel.

Browse

Filters

2022 - 20267

Advanced Search

Filter by

Settings

Author: search.filters.author.Tissera, W

Search Results

Now showing 1 - 7 of 7
  • Thumbnail Image
    ItemEmbargo
    An Integrated Smart Framework for Post-Harvest Optimization and Market Intelligence
    (Institute of Electrical and Electronics Engineers Inc., 2026-08-04) Gamage U.V.A; Wimalarathna B.P.K; Dharmappriya W.A.I.U.; Rathnayaka S.J.; Tissera, W; Rupasinghe, S; De Silva, H; Priyadarshana W.H.D.
    Post-harvest losses in Sri Lanka's fruit and vegetable supply chain remain a critical challenge, attributed to the absence of integrated quality assessment tools, real-time market intelligence, and accessible decision support systems tailored to local conditions. Existing approaches address these problems in isolation, leaving smallholder farmers without a unified platform for quality grading, price forecasting, post-harvest advisory, and cultivation planning. This paper presents CropShield, a novel four-component AI framework designed to address these gaps for Sri Lankan agricultural stakeholders. The first component employs YOLOv8 for fruit detection followed by MobileNetV2 fine-tuned on a papaya dataset for defect classification across six categories and maturity classification across three stages, with Grad-CAM explainability and a Random Forest recommendation engine integrated with Department of Agriculture knowledge. The second component delivers price forecasting across eleven crop varieties using a hybrid ensemble of ARIMAX, XGBoost, and LightGBM trained on HARTI market data from 2008 to 2025. The third component provides a bilingual post-harvest risk advisory assistant supporting Sinhala and English, integrating real-time weather data with an NLP-driven prediction engine, with SHAP-based explainability for transparent advisory outputs. The fourth component implements a Random Forest-based crop suitability and yield estimation model using district-level agronomic data with SHAP explainability for interpretable crop recommendations. The defect detection model achieved 95.65% accuracy and F1-score under clean conditions and 93.48% under robust augmentation, while the price forecasting model achieved R2=0.986 and MAPE=3.16%. CropShield delivers a scalable, explainable, and farmer-accessible platform for evidence-based agricultural decision-making across Sri Lanka
  • Thumbnail Image
    ItemEmbargo
    Knowledge Graph-Based AI Framework for Predicting Nutritional and Health Impacts of Food Ingredients
    (Institute of Electrical and Electronics Engineers Inc., 2026-08-04) Dakshina P.D.S.D; Rupasighe W.A.R.K; Waduge N.P; Nimsitha M.V.T; Tissera, W; Rathnayake, S; Krishara, J
    The increasing complexity of modern food products and dietary supplements has made it challenging for both consumers and healthcare professionals to interpret nutritional information and assess the potential health risks associated with these products. Modern food labeling schemes provide static and fragmented information and cannot effectively capture the relationships between different ingredients, nutrients and their health effects. In this study, a new AI-based framework named Food Health Risk Analyzer has been proposed that utilizes KGs, GNNs, RAG and a dose-response module based on consumption quantities to perform the dynamic, explainable and evidence-based prediction of food-related health risks. The model uses heterogeneous data in order to analyze the relationships between ingredients and diseases to predict potential health risks while generating scientifically supported explanations as well. The experimental evaluation has shown high prediction accuracy with a micro-F1 score of 0.88 and AUC of 0.85 which shows that the framework surpasses conventional machine learning baseline models. In addition to that, the use of RAG has helped in improving the interpretability of predictions through evidence-based natural language explanations whereas dose-response module improves the practical relevance of risk assessment by considering the consumption quantities of ingredients.
  • Thumbnail Image
    ItemEmbargo
    CocoSense: AI-Powered Drone-Based System for Comprehensive Coconut Tree Health Monitoring and Yield Prediction
    (Institute of Electrical and Electronics Engineers Inc., 2026-05-22) Subasinghe, M; Panditharathne, R; Pasanjith, R; Nadun, T; Samarakoon, U; Tissera, W
    Coconut cultivation is vital to Sri Lanka's agricultural economy, yet farmers face significant challenges in early pest detection, disease diagnosis, and yield prediction. This research presents CocoSense, an AI-powered mobile application integrated with IoT technology for automated coconut tree health monitoring using drone-captured imagery. The system comprises four modules: (1) pest detection using EfficientNetB0 (91.44% accuracy) and MobileNetV2 (96.08% accuracy) with a trilingual AI chatbot for treatment recommendations; (2) disease detection for leaf rot, leaf spot, and leaf dieback classification (98.69% accuracy); (3) health assessment for leaf (93.70%) and branch health (99.63%); and (4) coconut yield estimation (87.86% accuracy) using YOLOv8 with dual-view acquisition strategy. Additionally, a coconut bunch detection (88.96% accuracy) module is developed to support yield estimation by identifying fruit clusters within tree canopies. The system integrates IoT-based GPS tracking with Google Maps API for real-time plantation visualization. Experimental results demonstrate that CocoSense provides a robust, accessible solution for intelligent coconut plantation management in Sri Lanka.
  • Thumbnail Image
    ItemEmbargo
    Enhancing the Performance of Supply Chain using Artificial Intelligence
    (Institute of Electrical and Electronics Engineers Inc., 2025) Wijedasa, S; Gnanathilake, K; Alahakoon, T; Warunika, R; Krishara, J; Tissera, W
    Optimizing warehouse operations is essential to meet dynamic customer demands while maintaining efficiency in the rapidly changing supply chain landscape. Using four key components, this research presents a comprehensive AI-based approach to improve supply chain management performance. The first component uses Long Short-Term Memory (LSTM) networks to predict demand and returns, allowing for accurate forecasting of product demand and returns based on historical sales data. The second component uses Q-learning, a Reinforcement Learning (RL) technique that optimizes the scheduling of product replenishments by prioritizing critical stock shortages based on inventory levels and predicted demand. The third component analyzes customer purchasing patterns using FP Growth and clustering algorithms to analyze customer buying patterns, strategically placing items in aisles to reduce selection time and improve picking efficiency. The final component involves customer churn prediction using machine learning techniques to identify at-risk customers and facilitate proactive retention strategies. To bridge the gap between complex AI models and practical warehouse operations, a web-based application named 'OptiFlow AI' has been developed. This platform provides warehouse workers with user-friendly interfaces to access demand forecasts, replenishment priorities, optimized product placements, and customer retention insights. The proposed system significantly enhances operational efficiency, reduces time delays, and improves customer satisfaction, contributing to a more resilient and intelligent supply chain ecosystem.
  • Thumbnail Image
    PublicationEmbargo
    A Smart Waste Disposal System: To Encourage Proper Waste Disposal
    (IEEE, 2022-12-09) Alwis, D; Munasinghe, P; Rajapaksha, S; Ranawaka, B; Krishara, J; Tissera, W
    Waste disposal is one of the most important industries in the world. If not maintained properly it would lead to the destruction of the environment. Improper waste disposal is becoming a critical issue in Sri Lanka and the lack of waste segregation, inadequate waste collection methods, the lack of support for waste management from the public are among the root causes of the problem. As a solution we propose an IoT-based solid waste management system that allows garbage bin monitoring, routing of garbage collector trucks, a prediction model and a point rewarding system. As the end result of this research the following prototypes was built; a prototype model of a smart bin with the capabilities of opening and closing by itself and detecting the waste level of the bin, a prototype mobile application for garbage collectors which delivers analysed data on truck position and ensures timeliness, a prototype mobile application for the public which receives the weight and type of solid waste discarded as an input and calculate reward points to encourage the public in proper waste disposal, a prototype web application which delivers statistical data for detailed reports and a prediction model which predicts the amount of waste to be collected in the coming month using machine learning. This is a low-cost IoT-based solution that uses existing resources to handle the massive amounts of garbage collected each day.
  • Thumbnail Image
    PublicationEmbargo
    An Automated System for Employee Recruitment Management
    (IEEE, 2022-12-09) Silva, G.L.L.I.; Jayasinghe, T.L; Rangalla, R.H.M; Gunarathna, W.K.L; Tissera, W
    Recruitment of employees is an important process in the human resource management of a company. Currently, most of the recruitment process is done manually in many companies. This manual process may be time-consuming and possibly may be erroneous in employing inappropriate individuals. This may result in the loss of time, money, and efficiency of a company. As a solution to the above problem, we are considering developing an automated process for recruitment. The scope of the system is to cover not only the recruitment process but also to provide job seekers a platform to identify their current skills, help them identify the current skill trends that are required by companies, and provide the ability to automatically generate their resumes through the system. On the other hand, employers will save a lot of time and money since the system will automate the processes such as skill matching of the employee and the company, shortlisting of resumes, and scheduling interviews. The platform involves features such as online mock interview hosting, automated scheduling, and a pre-interview quiz with a monitoring background. To achieve the above components, machine learning algorithms are used along with other technologies such as web scraping.
  • Thumbnail Image
    PublicationEmbargo
    Recommendation system based on Tamil-English code-mixed text analysis
    (Institute of Electrical and Electronics Engineers, 2022-10-15) Vijayakumar, S; Murugaiah, G; Sivanesan, J; Archchana, K; Tissera, W; Vidhanaarachchi, S
    The cinema industry has always been popular since its inception many years ago and is a preferred pastime of many people. It can be observed that even though online movie applications are popular in multilingual society, English is the preferred language. Naturally, people of other languages mix their native language with English during communications resulting in an abundance of multilingual data called code-mixed data, available in today's world. This research focuses on the movie recommendation system whose primary objective is to make a recommender system through Natural Language Processing (NLP) Tools for Tamil-English Code-mixed (Tanglish) Comments. Our recommendation system will be a filtering scheme whose primary objective is to predict a viewer's rating or preference towards a movie or web series.