7th International Conference on Advancements in Computing [ICAC] 2025

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/5302

Browse

Now showing 1 - 8 of 8

Embargo
Adaptive Video Game Content Generation through Player Centered Modeling
(Institute of Electrical and Electronics Engineers Inc., 2025-12-09) Hapuarachchi H.A.R.S; Herath H.M.N.R; Kaveesha B.G.S; Deheragoda D.M.L.M; Rathnayake, S; Chamara, D
This research introduces a novel, integrated AI system for Adaptive Video Game Content Generation Through Player Centered Modeling, designed to overcome the limitations of conventional static game mechanics by dynamically modifying gameplay elements (levels, quests, music, and enemy behavior) in real-time based on player biometric and behavioral data. Key contributions include the Personalized Quest Generation System, where the CatBoost model performed well in predicting player engagement, and shifting to the YOLO11X-CLS classification model substantially reduced computational lag for real-time emotional adaptation. For Level Generation, the implementation of a bootstrapping methodology during DCGAN training enabled continued refinement, resulting in lower Symmetry Error and Block Diversity Error, while the Intelligent Enemy Agent, trained using Dueling DQN, demonstrated a clear upward trend in Mean Rewards, successfully generalizing learned pursuit strategies to a real-time environment. Despite these successes, limitations include potential mild overfitting in the emotion recognition model, evidenced by a slight increase in validation loss after 20 epochs, and the CNN used for dynamic music adjustment struggled with low-resolution webcam inputs, leading to occasional minor misclassifications and slight delays in music transitions when multiple biometric parameters changed simultaneously.
Embargo
CINNOVA: Advancing Sustainable Cinnamon Farming through AI and Collaborative Solutions
(Institute of Electrical and Electronics Engineers Inc., 2025-12-09) Bandara D.; Fernando M.K.K.L; Senadeera N.A.D.N; De Silva R.C.T; Wijendra, D; Krishara, J
Cinnamon is one of the most economically significant export crops in Sri Lanka. However, its cultivation is challenged by plant diseases, nutrient deficiencies, and inefficient harvesting practices, which reduce yield quality and productivity. Traditional methods for identifying plant health issues are time-consuming and require expert evaluation, often inaccessible to rural farmers. To address these limitations, this study introduces an AI-driven intelligent monitoring system for sustainable cinnamon cultivation, a mobile-based solution specifically designed to enhance cinnamon farming practices. The system leverages Artificial Intelligence (AI), Deep Learning (DL), and Image Processing techniques to support real-time plant health diagnostics. It integrates multiple AI-powered components for early detection of bark diseases such as Rough Bark Disease (RBD) and Canker Disease (CD) using a contrastive learning-based model, severity prediction of leaf diseases, including Leaf Gall and Leaf Blight, using the YOLO model, identification of nutrient deficiencies, particularly Magnesium and Potassium, through transfer learning and prediction of cinnamon bark maturity and quality grades utilizing spatial attention mechanisms based on diameter and color. Each model is optimized for mobile deployment to provide real-time feedback and enable efficient decision-making. This AI-driven approach enhances disease management and improves yield quality while promoting sustainable, data-driven cinnamon cultivation in Sri Lanka.
Embargo
Eye Health Monitoring and Eye Care System
(Institute of Electrical and Electronics Engineers Inc., 2025-12-09) Herath H.M.S.C; Swarnajith T.H.M.P; Senanayaka W.S.H.M; Hettiarachchi H.W.R.A; Walgampaya, N; De Zoysa, R
This study presents a multi-modal AI-powered system designed for real-time eye health monitoring and early diagnosis. The proposed system integrates computer vision, machine learning, and image processing techniques to deliver non-invasive and accessible diagnostic solutions. The system comprises four key modules. The first one is a real-time eye exercise module that utilizes webcam-based eye tracking and adaptive machine learning to provide personalized routines for reducing digital eye fatigue. The second module is an AI-driven cataract detection module that analyzes retinal images to enable early diagnosis, particularly in resource-limited settings. The third module is a glaucoma detection system that tracks pupil dynamics, such as size and light reactivity, to identify early symptoms; and the fourth and final module is a color blindness and eye fatigue detection module that employs multi-modal AI techniques to assess color vision deficiencies and monitor signs of visual fatigue in real-time Collectively, these components form a comprehensive array of tools focused on improving eye health monitoring and treatment. Through the combination of advanced AI technologies with user-friendly interfaces, the proposed systems aim to democratize access to eye care, reduce the global burden of preventable vision loss, and enhance the quality of life for individuals everywhere.
Embargo
Human-Ai Cooperative Driving Through Emotion-Aware Decision Making and Driver Personalization
(Institute of Electrical and Electronics Engineers, 2025-12-09) Wickramasuriya L.H.N.Y; Rathnayaka D.B; Walpalage J.V.; Rathnayake, S
Conventional in-vehicle safety systems often neglect real-time emotional monitoring, prediction, and passenger influence, leading to reactive rather than proactive interventions. This paper presents an emotion-aware cooperative driving system that combines facial emotion recognition, time-series emotion forecasting, and personalized music-based regulation. The system detects both driver and front-seat passenger emotions through a Vision Transformer (ViT) model, while a time-series model anticipates the driver's upcoming emotional state. A prioritization algorithm ensures driver emotions hold precedence, with passenger states considered when the driver is stable. Based on this prioritized emotional context, the system regulates the in-cabin atmosphere using music recommendations drawn from the driver's preferred artists via the Spotify API. Experimental results show robust real-time emotion classification (86.4% validation accuracy), proactive forecasting (81.6% predictive accuracy), and improved driver acceptance due to personalization. The proposed framework advances intelligent transportation by shifting from static monitoring toward predictive, human-centered, and non-intrusive emotional regulation, thereby enhancing both safety and user comfort.
Embargo
NoFake Trustworthy Reviewer Scoring System for Detecting Fake Reviews
(Institute of Electrical and Electronics Engineers Inc., 2025-12-09) Dissanayaka S.D; Jayawardhana R.A.D.G.S; Jayalath, T; De Silva, H
The proliferation of fake online reviews has severely undermined consumer trust and market fairness in digital platforms. Traditional detection systems relying on rule-based filters or shallow machine learning models often fail to identify sophisticated, artificially intelligent-generated, or behaviorally deceptive content. This research proposes an intelligent system for fake review detection that integrates advanced Natural Language Processing, behavioral anomaly analysis, and explainable artificial intelligence to enhance accuracy, transparency, and usability. The system employs a hybrid feature set of about 212 dimensions, including Term Frequency-Inverse Document Frequency scores, sentiment-rating inconsistency, readability metrics, and reviewer behavioral indicators such as review frequency and account metadata. A neural network trained on the Deceptive Opinion Spam dataset (40,000 reviews) classifies reviews as genuine or fake, achieving 81.55% accuracy and an Area Under the Receiver Operating Characteristic Curve of 0.9019. Anomaly detection models Isolation Forest generate a dynamic trust score for reviewers, improving detection of coordinated spam campaigns. To ensure transparency, SHapley Additive exPlanations are integrated into a full-stack web application, providing human-readable insights such as Sentiment-Rating Mismatch or Robotic Writing Detected. Results show the proposed system outperforms traditional methods in accuracy and interpretability, offering a scalable and trustworthy solution for digital trust ecosystems.
Embargo
Optimizing LLMs for Context-Sensitive Text Summarization: Insights from PLOS and SciSummNet
(Institute of Electrical and Electronics Engineers Inc., 2025-12-09) Nawarathne U.M.M.P.K; Subasinghe, S; Rathnayake, T; Sumathipala, P
Text summarization is an important task in natural language processing (NLP), as it allows vital information to be extracted from large amounts of textual input. This work investigates the efficacy of fine tuning large language models (LLMs) for summarization tasks by comparing their performance to that of untuned alternatives. Using the PLOS dataset consisted of biomedical papers and SciSummNet dataset consisted of computing linguistics related scientific papers, LLM models such as Falconsai-T5 text summarization, T5-small, Bart and Bart-large-CNN were tested using ROUGE, BLEU, and METEOR metrics to measure their summarization abilities. The results show that fine-tuning improves model performance significantly across the evaluation metrics. Fine tuned models performed well on the SciSummNet dataset, with Bart-tuned model getting the highest scores across multiple measures, demonstrating the efficacy of targeted adaptation where the obtained results for ROUGE-1-0.6808, ROUGE-2 0.6487, BLEU - 0.4163, and METEOR - 0.5083. The analysis underscores the importance of aligning model architectures and datasets to achieve optimal results. The structured biomedical content of the PLOS dataset highlighted the vital necessity of semantic preservation, as evidenced by specially the higher METEOR scores achieved by fine tuned models. The SciSummNet dataset, which focuses on computing and linguistic publications, demonstrated the ability of the models to navigate abstract concepts and complex technical vocabulary. This study demonstrates the transformative power of fine-tuning in customizing LLMs resulting in significant increases in summarization accuracy.
Embargo
Reducing Cancer Mortality Inequalities: The Role of Education, Socioeconomic Factors, and Digital Ecosystem Interventions
(Institute of Electrical and Electronics Engineers Inc., 2025-12-09) Liyanage R.P.B; Karunarathne B.A.P.M; Maheshika J.M.D.; Priyamantha K.V.A
Cancer remains one of the leading causes of mortality worldwide, with education and socio-economic status emerging as critical determinants of health outcomes. This review synthesizes global evidence on the impact of educational attainment and socioeconomic disparities on cancer mortality, emphasizing how structural inequalities hinder access to timely diagnosis, treatment, and preventive care. While traditional health systems often fail to address these disparities effectively, the rapid growth of digital ecosystems offers transformative opportunities. Digital marketplaces for healthcare services, telemedicine platforms, social media based awareness campaigns, and innovative health-tech startups can mitigate barriers related to low income and limited health literacy. Furthermore, the integration of information systems, digital collaboration tools, and knowledge management frameworks enables policymakers, practitioners, and communities to create inclusive, technology-driven solutions. This paper positions cancer mortality not only as a public health challenge but also as a socio-technical issue that demands sustainable digital interventions. By linking education, socio economic status, and mortality with digital entrepreneurship and organizational innovations, the study contributes to ongoing discussions on building resilient, equitable, and technology enabled socioeconomic ecosystems in global healthcare.
Embargo
Unveiling EEG Emotional Patterns during Interactive Engagement Activities: A Performance Comparison of Machine Learning Models
(Institute of Electrical and Electronics Engineers Inc., 2025-12-09) Rathnayake, T; Subasinghe, S; Nawarathne, M; Sumathipala, P
This paper presents a comparative evaluation of machine learning and deep learning models for emotion recognition from electroencephalography (EEG) signals recorded during interactive engagement activities. EEG data were collected using a Muse headband as participants performed engagement activities designed to elicit five emotions: Afraid, Happy, Calm, Neutral, and Sensitive. After preprocessing and feature extraction, eight machine learning and deep learning models were trained. Based on the experiment, Random Forest emerged as the best-performing classifier, achieving ~95.6% accuracy with balanced precision-recall, while gradient boosting and SVM also shown comparative results. The models demonstrated potential for real-time streaming despite slightly lower accuracy, highlighting scalability with larger datasets. These findings demonstrate the feasibility of consumer-grade EEG devices, enhanced with multimodal features, for robust emotion recognition in realistic engagement activities. The results underscore the effectiveness of multimodal fusion and engagement-based design, confirming that lightweight EEG systems can support practical, real-time affective computing applications in education, adaptive interfaces, and mental well-being monitoring.