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

2019 - 201912020 - 20254

Advanced Search

Filter by

Settings

Subject: search.filters.subject.Personalized

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    ItemOpen Access
    Model Optimization for Personalized Health Metrics Analysis
    (Institute of Electrical and Electronics Engineers Inc., 2025) Perera, M; Wijesiriwardena, A; Pathirana, A; Gamaathige, L; Wijesiri, P; Jayakody, A
    This paper investigates the development and application of four machine learning models designed to enhance personalized health management, specifically targeting young adults aged 15-30. The research addresses common health challenges, such as obesity and lifestyle-induced diseases, through data-driven methodologies that provide personalized meal plans, workout recommendations, and progress monitoring. The first model generates optimized personalized recommendations according to the user's health condition using Random Forest and Decision Tree algorithms. The second model utilizes an ensemble of Random Forest, LightGBM, and XGBoost, combined through a stacking technique with Linear Regression as the meta-model, to generate optimized personalized meal plans according to health condition. The third model generates optimized workout plans using Gradient Boosting and XGBoost classifiers, accounting for individual fitness objectives, body compositions, and medical conditions. A fourth model predicts goal achievement timelines by analyzing features such as caloric balance and hydration efficiency, providing users with actionable feedback using XGBoost. The integration of these AI-driven components into a scalable digital platform demonstrates the potential of machine learning in transforming health management. Future enhancements include improving model accuracy, enabling real-time feedback, and deploying the system as an accessible mobile application. ensemble
  • Thumbnail Image
    PublicationEmbargo
    A Machine Learning Approach to Predict the Personalized Next Payment Date of An Online Payment Platform
    (IEEE, 2022-12-09) Karunathunge, L. C. R.; Dewapura, B. N.; Perera, V. A. S.; Kavirathne, G. P. R. A.; Karunasena, A.; Pemadasa, M. G. N.
    Use of digital payments has risen exponentially in the recent past especially due to the COVID-19 pandemic. This is because online payment methods offer many benefits in performing their day-to-day transactions and paying utility bills such as electricity bills, water bills, telephone bills and etc. Knowing when a consumer will perform a specific online transaction, or bill payment is beneficial to an online payment platform to plan marketing campaigns since targeted marketing has become very prevalent nowadays. However, predicting this is not an easy task since thousands of transactions are happening in each and every minute of an online payment platform. This paper presents the results of a study that investigated predicting the customer personalized, utility bill payment type wise next payment date of a financial company in Sri Lanka by using machine learning techniques. This is accomplished by analyzing not only online transaction history but also customer characteristics and a holiday calendar which is specific to Sri Lanka. At the end of the study, it was identified that XGBoost Regressor is the most suitable machine learning algorithm, etc deal with this scenario which provided 91.02% accuracy. These predictions will be used for sending personalized reminders and discount offers to customers without sending general common notifications when they are planning to do an online payment. Such reminders and offers will be notified on the mobile devices of the customers and, ultimately both customers and the business owners will be benefited by this.
  • Thumbnail Image
    PublicationEmbargo
    A Mobile Application to Predict and Manage High Blood Pressure and Personalized Recommendations
    (IEEE, 2019-12-05) Rajapaksha, S. K; Abhayarathne, W. J. A; Kumari, S. G. K; De Silva, M. V. L. U; Wijesuriya, W. M. S. M
    The purpose of this investigation is to present a mobile application using AI expert and how to predict and manage high blood pressure and provide personalized recommendations to lower it. Basically, the system interprets the inadequate and inappropriate intake of food is known to cause various health issues and diseases. Due to the diversity of food components and a large number of dietary sources, it is challenging to perform a real-time selection of diet patterns that must fulfill one's nutrition needs and with considering your health issues and diseases. In this research, to address this issue to present an android based system, called Smart Blood Pressure Recommendation app. The purpose of this system is to allow patients to have an easy way to monitor their health and to see how their blood pressure has changed over time. This offer advice or suggestions, without having to schedule an appointment. As the system continues to gather data from a patient, it begins to offer advice its own if it finds that the patient's current conditions fit a certain condition or pattern. To generate a recommendation, it refers to an Ontology based data model. The data model gains information about its knowledge by doctors and nutritionists that can be used by AI expert. This research helps users to identify their previous record charts of blood pressure, reliable alarms for user blood pressure medication, popup notifications, build health diary and also share log data processing through the AI expert.
  • Thumbnail Image
    PublicationEmbargo
    HopOn: A Personalized Ride-Sharing System based on Socio-Economic Factors
    (IEEE, 2021-12-09) Thilakaratne, A; Pinnawala, N; Wijerathna, K; Senavirathna, K; Wellalage, S; Wijekoon, J
    Rapid urbanization and increasing income levels combined with poor and insufficient road network to accommodate vehicles is causing a major traffic problem in Sri Lanka. Additionally, in urban areas, traffic congestion is leading to an increase in air and noise pollution as well. Numerous solutions were tried by authorities, yet no promising results were yielded to address these issues successfully. Contrastingly, increasing road network capacity to solve this problem is very costly and feasible only up to a certain point. Another option is to limit the number of vehicles in the city either by law or by alternative means such as ride-sharing. The best ride-sharing method available is the public transportation, however, due to the limitations of it, upper middle-class opt not to use those hence use their own vehicle to get the expected comfortability. This study is aimed at developing a ride-sharing application by profiling the users based on user reputations, vehicle type, socioeconomic variables such as education, social status, and security concerns of the users, and user ratings. Unlike existing carpooling applications that primarily depend on cost and destination to offer ride options, the proposed application further developed to consider the model of the vehicle for fare calculation.
  • Thumbnail Image
    PublicationEmbargo
    Personalized Assistive Learning System for Primary Education
    (2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Yapa, Y.M.T.S.; Fernando, W.S.I.; Sampath, W.H.M.K.; Kodithuwakku, K.D.D.I.; Samaratunge, U.S.S.; Lunugalage, D.
    Due to the COVID 19 pandemic, almost all educational institutions, including schools, remain closed. This caused a dramatic change in the educational systems. The sudden shift away from the classroom made the profound transformation of the teacher-centered education system prevail so far; consequently, the education of primary level students has been collapsed. Therefore, the primary students from grades 1 to 3 cannot acquire the primary education given by the school. This research proposes a personalized assistive learning system for primary education from grade 1 to 3 students, aiming to improve their learning skills. The proposed system aims to increase the automation and self-learning of students. A novel method is proposed to acquire personalized course materials for students of grades 1 to 3 according to their knowledge level. The system is founded on a solid theoretical foundation and enables children to grow cognitive and psycho-therapeutic skills such as drawing, writing, recognizing numbers, enabling self-learning, and focusing on measuring the progress of the students and reporting it to parents. CNN is the primary classifier used in image recognition and classification tasks in computer vision. The components' median accuracy is 94.74%.