Smart Computing and Systems Engineering - 2025 (SCSE 2025)

Permanent URI for this collectionhttp://repository.kln.ac.lk/handle/123456789/30037

Browse

Start date: 2025

Search Results

Now showing 1 - 10 of 40
  • No Thumbnail Available
    Item
    BookStore: An Innovative Book Recommendation System Driven by Facial Expressions
    (Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Neelananda, M.; Rathnayake, R.
    In the age of digital content consumption, personalization plays a crucial role in enhancing the user experience. However, many existing recommendation systems focus primarily on past interactions or ratings, often overlooking the user's current emotions and cultural background. This is particularly relevant in literature, where readers' mood and background can significantly influence their reception of various genres or topics. The proposed study addresses this gap by proposing an emotion-based book recommendation system that utilizes Facial Emotion Recognition (FER) to suggest culturally appropriate books aligned with the user’s emotional state. A deep learning model based on Convolutional Neural Networks (CNN) was trained to classify facial expressions and identify a person’s real-time emotions. The system features a culturally diverse dataset of books, categorized by emotion-relevant themes using Natural Language Processing (NLP) techniques. The user’s emotional state is determined through the FER model, and recommendations are made based on this identified mood and the user's cultural background. The model is trained to recognize facial emotions using labeled facial emotion datasets and has been tested across multiple scenarios to ensure it provides relevant book suggestions. The prototype system accurately identified users’ emotions with an 84% success rate and successfully recommended books of interest in 90% of the attempts. Users confirmed that the system could enhance their interest in reading by aligning book suggestions with their emotional and cultural inclinations. While these preliminary results are promising, they highlight the model’s potential to create a friendly reading environment by suggesting books that resonate with users' moods and cultural contexts.
  • No Thumbnail Available
    Item
    Predictive Modeling of Rubber Plant Growth Using Environmental Data and Machine Learning Techniques
    (Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Liyanage, Y. L. S. N.; Hettiarachchi, P. L.; Dilpashan, L. T. C.; Navodya, M. L. H.; Jayasekara, B.
    Rubber plant nurseries require effective management to maximize agricultural resources and ensure good plant health. This paper presents the Rubber Plant Growth Prediction System, which uses environmental data to predict the diameter of the stem, an important index used in plant growth. In this work, initial plant growth was predicted using a vision-based technique, but due to difficulties in data acquisition and the accuracy point of view, that approach may not be feasible. The method based on stem diameter was then adopted, incorporating environmental parameters such as soil moisture, soil temperature, ambient temperature, and humidity. With a limited dataset, it was quite challenging to be accurate in the predictions, but developing a comprehensive data collection system filled those gaps, making the measurements more reliable. This forms the basis for increasing predictive accuracy in improving resource management in the nursery and therefore contributing to sustainable agricultural practices.
  • No Thumbnail Available
    Item
    Determining Factors Related to Artificial Intelligence Adoption Among Sri Lankan ICT Service Providers
    (Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Nizar, Z.; Lakshan, J.; Wijayarathne, C.; Jayasuriya, N.; Oshani, W.; Rathnapriya, S.
    This study investigates the factors influencing Artificial Intelligence (AI) adoption among ICT service providers in Sri Lanka, a developing economy where AI integration remains in its early stages. Using the Technology-Organization-Environment (TOE) framework, six key determinants were examined: relative advantage, data quality, top management commitment, employee adaptability, competitive pressure, and external support. Data was collected via a structured questionnaire distributed to 146 ICT service providers, with the sample size determined using G*Power software for statistical robustness. Ordered probit regression was employed to analyze the data, providing precise insights for ordinal variables. The findings identify data quality (DQ) and relative advantage (RA) as significant drivers of AI adoption, underscoring the critical role of high-quality data and the operational benefits of AI technologies. However, top management commitment (TMC) exhibited a negative impact, highlighting barriers in leadership awareness and alignment with AI strategies. Although competitive pressure (CP), external support (ES), and employee adaptability (EA) were not statistically significant, they showed potential as mediators or moderators in specific contexts. This study bridges a critical gap by providing localized insights into AI adoption challenges and opportunities in Sri Lanka. It emphasizes the importance of data management, leadership commitment, and strategic alignment, offering actionable recommendations for policymakers and industry leaders to enhance competitiveness and digital transformation in the global economy.
  • No Thumbnail Available
    Item
    Advanced NLP Framework for Analysing Elasticity Feedback in Apparel Design
    (Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Wimalasuriya, D. T.; Rajapakse, C.; Jayatissa, Y.
    Elasticity is critical in modern apparel design, directly affecting product performance and customer satisfaction. This study presents a scalable framework leveraging advanced Natural Language Processing (NLP) to systematically analyze elasticity-related customer feedback. Utilizing 93,860 customer reviews of leggings, pants, and crops, the framework combines manual annotation, keyword extraction, and Named Entity Recognition (NER) to identify and refine elasticity-specific reviews. A GPT-4o–based categorization model and hierarchical clustering of themes further segment reviews into aspects: attributes (e.g., flexibility, durability), components (e.g., stretch fabric, elastic waistbands), usage situations (e.g., washing, wearing), and common issues (e.g., pilling, sagging). Aspect-Based Sentiment Analysis (ABSA) and VADER scoring capture explicit and implicit sentiments, while advanced visualizations (heatmaps, scatter plots) reveal correlations among product features, consumer sentiment, and usage contexts. Comparative evaluations demonstrate the proposed framework’s superiority over lexicon-based and other machine learning methods. The results, integrated with product metadata, provide actionable insights for manufacturers, highlighting the importance of activity-specific designs and innovative fabric development. This work establishes a foundation for future integration of multimodal data, further enhancing customer feedback analytics in the apparel industry.
  • No Thumbnail Available
    Item
    Deep Learning-Based Approach for Distinguishing Between AI-Generated and Human-Drawn Paintings
    (Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Warnakulasooriya, A. I.; Rupasingha, R. A. H. M.; Kumara, B. T. G. S.
    With the increasing number of robust Artificial Intelligence (AI) art generation applications, more realistic AI-generated paintings (AIGPs) are emerging, creating a significant impact on artists. Due to the widespread acceptance of AIGPs, the cultural, historical, and monetary value of real masterpieces is becoming uncertain, raising concerns about the significance of human painters and their artistic techniques. To protect artists’ rights, it is crucial to differentiate AIGPs from human-drawn paintings (HDPs). Accordingly, the main objective of this research is to develop a Convolutional Neural Network (CNN) model that can automatically distinguish between AI-generated and human-drawn paintings without human intervention. Unlike previous studies that focused mainly on pixel-level analysis, the proposed model considers additional features such as edge patterns, object arrangements, pattern distributions, and gradient characteristics in painting classification. A diverse dataset of 3,000 paintings from the AI-ArtBench Dataset—comprising 1,500 AIGPs and 1,500 HDPs across 10 different art themes—was collected and preprocessed for this study. The AIGPs were generated in equal proportions using Latent Diffusion and Standard Diffusion Models. The implemented CNN model achieved an optimum classification accuracy of 90% with a training data size of 10%, while the ANN model exhibited 77% accuracy under the same conditions. Furthermore, models were compared using performance metrics such as precision, recall, F1-score, RMSE, and MAE. Through Gradient-weighted Class Activation Mapping (Grad-CAM), the key visual features that the CNN model used to distinguish AIGPs from HDPs were identified. These findings highlight the potential of automated systems in detecting AI-generated versus human-created artworks for authentication purposes. Future work will focus on analyzing model performance across different art styles and identifying the unique discriminative features associated with each.
  • No Thumbnail Available
    Item
    AI-Driven Solutions for Automated Fish Freshness Classification Using CNN Architectures
    (Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Peries, R. F. S.; Adeeba, S.; Ahamed, M. F. S.; Kumara, B. T. G. S.
    Ensuring fish freshness is essential for market value, consumer health, and seafood quality. In Sri Lanka, traditional sensory-based methods for assessing freshness are subjective and often inaccessible to small-scale fishermen due to high costs and limited resources. This study addresses these challenges by employing Convolutional Neural Networks (CNNs) to automate fish freshness classification using image data from the Mannar coastal region. The approach involved capturing images of whole fish, fish eyes, and fish gills, followed by preprocessing steps such as labeling, resizing, and augmentation. Separate custom CNN models were developed for each dataset, with the gill dataset achieving the highest performance at 98.26% accuracy, along with excellent precision, recall, and F1-scores. Furthermore, advanced pre-trained models—including VGG16, ResNet50, MobileNetV2, InceptionV3, Xception, and DenseNet121—were evaluated on the gill dataset. Among these, DenseNet121 emerged as the best-performing model due to its high accuracy, precision, recall, F1-score, and stable learning curve. These findings highlight the potential of CNN-based and pre-trained models to provide scalable, cost-effective solutions for fish freshness assessment, promoting sustainable seafood practices, empowering small-scale fishers, and enhancing food safety standards.
  • No Thumbnail Available
    Item
    Comparative Study on Neural Network and Transformer-based Models for Predicting Exchange Rates in Sri Lanka
    (Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Basnayake, B. R. P. M.; Chandrasekara, N. V.
    Transformer (TF) models have demonstrated exceptional performance across various domains, with a significant focus on their application to time series forecasting. Key strengths of TFs are their ability to capture long-run dependencies and complex interactions within the data. This study aims to apply time series TF models for forecasting exchange rates and focuses on exploring the strengths and limitations of TFs in the hyperparameter tuning process and compare their performance with Seasonal Autoregressive Integrated Moving Average (SARIMA), Double SARIMA (DSARIMA) and neural network (NN) models. The study utilized daily exchange rate data for eight currency pairs relative to LKR. Hyperparameter tuning was performed using a trial-and-error approach to optimize model performance. The main findings from fitted TF models can be summarized as follows: The inherent fluctuations in exchange rate movements highlighted that a larger embedding size enhances the models' performance. Better performance was observed with four encoder and decoder layers and the attention head parameter was within the range of four to six, as deviating from this configuration led to higher error values. Further, higher error values were observed across all exchange rates when the learning rate was greater than 0.5. Maintaining a batch size of 16 and reduced dropout rates also yielded the lowest error values. This parameter selection enables the TFs to effectively capture key features from the input data while maintaining a balance that minimizes the risks of overfitting or underfitting. Overall, TF models performed well compared to SARIMA/DSARIMA and NN models, achieving the lowest error metrics owing to their advanced capability to capture non-linear patterns. This research will be valuable to scholars exploring the application of TF models and professionals in sectors like finance and economics, where precise exchange rate forecasting plays a vital role in informed decision-making and effective resource allocation.
  • No Thumbnail Available
    Item
    AI Powered Integrated Code Repository Analyzer for Efficient Developer Workflow
    (Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Akalanka, I.; De Silva, S.; Ganeshalingam, M.; Abeykoon, A.; Wijendra, D.; Krishara, J.
    Transitioning between new and legacy codebases in diverse project environments poses significant challenges for developers, especially with traditional Knowledge Transfer (KT) methods, which are often resource intensive and prone to obsolescence. These limitations hinder the Software Development Life Cycle (SDLC), particularly in fast-paced industrial settings. This research introduces an AI-driven automation solution that leverages large language models (LLMs) and advanced artificial intelligence technologies to address critical gaps in technical knowledge transfer, with a focus on modern software frameworks. The proposed system reduces development costs, improves team performance, and accelerates adaptation to complex codebases. Key features include a documentation generation tool that cuts manual effort by up to 90%, with an average generation time of 6.8 minutes. Additionally, a virtual knowledge transfer assistant enhances onboarding efficiency, potentially reducing senior developer involvement by 50-60%. The system also includes an automated diagram generator that achieves 97% validation accuracy and a code smell detection tool with 71% accuracy, resulting in better code quality assessments. These findings demonstrate the effectiveness of AI-driven automation in improving developer productivity, streamlining onboarding processes, and optimizing software development workflows.
  • No Thumbnail Available
    Item
    An Integrated Deep Learning Framework for Early Detection of Vision Disorders
    (Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Jayathilaka, S.; Balaruban, D.; Kumanayake, I.; Elladeniya, A.; Wijendra, D.; Krishara, J.; De Silva, M.
    Vision impairment due to retinal diseases like Diabetic Retinopathy (DR), Age-Related Macular Degeneration (AMD), Glaucoma, and Retinal Vein Occlusion (RVO) poses a significant health challenge in Sri Lanka, where these conditions are leading causes of blindness. This research presents a novel multi-disease prediction system leveraging advanced deep learning techniques for early detection of DR, AMD, Glaucoma, and RVO. The study utilized publicly available datasets, including retinal fundus images from repositories such as RFMiD, IDRiD, APTOS validated by medical professionals to ensure diagnostic reliability. These images were preprocessed and augmented to train robust convolutional neural network (CNN) models tailored to each disease. The predictive models were developed and optimized using hybrid architectures, integrating attention mechanisms and feature fusion for enhanced performance. This approach achieved high accuracies—93% for DR, 92% for AMD, 94% for Glaucoma, and 94% for RVO—demonstrating robustness and consistency across diverse retinal conditions. To validate real-world applicability, the models underwent further testing in clinical settings using a Sri Lankan dataset, reflecting local disease prevalence and imaging conditions. By combining validated public data with clinical testing, this scalable system supports ophthalmologists in early diagnosis, reducing diagnostic delays and improving patient outcomes. This work offers a reliable, innovative solution to mitigate the burden of blindness in Sri Lanka and beyond.
  • No Thumbnail Available
    Item
    A Systematic Literature Review of Deepfake Face Image Detection with Transfer Learning Techniques
    (Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Wimalasena, W.; Herath, H.; Hewapathirana, I
    Artificial intelligence-based fake content generation, also known as deepfake media content, is spreading rapidly with the advancement of technology. This can manipulate or completely change the real media by threatening the authenticity of the data. With the availability of major amounts of data, deepfake face image generation has become an emerging issue in today’s digitalized world. Therefore, it is crucial to understand the most effective methods to detect this deepfake face image content. This paper provides a comprehensive discussion about how transfer learning can be used in this specific area to detect deepfake face images through a systematic literature review of (49) papers using the PRISMA method. The paper addresses the gap in up-to-date detailed analysis of transfer learning methods in this area which emphasizes the effectiveness of the process of deepfake image detection by studying papers in the past decade. This paper presents a comprehensive discussion of the models that have been used in this area along with the transfer learning approaches that have been used. The key findings highlight that the most common transfer learning approach for deepfake image detection is CNN combined and the most effective model for deepfake image detection in transfer learning is fine-tuned models. This paper also highlights the challenges and possible improvements in the area of deepfake face image detection with transfer learning techniques.