Scopus Index Publications

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/2162

This collection consists of all Scopus-indexed publications produced by SLIIT researchers. Scopus is recognized worldwide as a leading and reputable academic indexing database.

Browse

Filters

2025 - 20263

Advanced Search

Filter by

Settings

Author: search.filters.author.Haddela, P.S

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    PublicationOpen Access
    EuqAud: Detecting Gender Bias in Audio Datasets Using Polynomial Regression-Based Metric
    (Institute of Electrical and Electronics Engineers Inc., 2026) Jayawardena, S; Haddela, P.S; Shyamalee, T; Ekanayake, A; Mudalige, T; Dhanawardhana, I
    With the growing adoption of audio based AI systems in high-stakes domains such as healthcare, law enforcement, and social media, ensuring fairness particularly regarding gender bias has become critically important. While prior work on fairness has predominantly focused on disparities in model performance, bias inherent in training datasets remains underexplored. To address this gap, we propose EuqAud, a novel, pre-trained and traceable fairness metric that quantifies gender bias in audio datasets using raw acoustic features such as pitch, energy, amplitude, and voice activity. Unlike methods dependent on demographic labels such as race, age or language, EuqAud is designed to be demographic and language agnostic, enhancing its applicability across diverse contexts. The score is computed using an equation derived from polynomial regression with L2 regularization (Ridge regression), yielding robust and generalizable outputs. It spans a range from −10 to 10, where 0 denotes neutral, positive scores indicate male dominant bias, and negative scores reflect female dominant bias. For clarity, bias severity is categorized into three tiers: Neutral (EuqAud < 2), Moderate Bias (2 ≤ EuqAud ≤ 6), and Strong Bias (EuqAud > 6). Evaluation across multiple datasets demonstrates high predictive performance, with R2 values between 0.95 and 0.99. By focusing on dataset level bias rather than model outcomes, EuqAud offers a scalable and rigorous solution for advancing fairness in audio-based AI systems.
  • Thumbnail Image
    ItemEmbargo
    Performance Analysis of Text Classification Algorithms for Dhivehi Language Documents
    (Institute of Electrical and Electronics Engineers Inc., 2025) Mohamed, F.R; Haddela, P.S
    This study examines the effectiveness of various machine learning algorithms in classifying text written in 'Dhivehi,' the official language of the Maldives. As a low-resource language with limited research in text analytics, 'Dhivehi' poses unique challenges due to its distinctive linguistic properties. To address these challenges, this research evaluates the performance of algorithms, including Support Vector Machines, Naive Bayes, Decision Trees, Neural Networks, XGBoost, and Random Forest, leveraging a newly curated 'Dhivehi' language dataset. The evaluation highlights that K-Neighbors achieved the highest performance, with an accuracy of 64.7% and F1 scores (macro: 0.640, weighted: 0.642), demonstrating a strong balance between precision and recall. Support Vector Machines (accuracy: 63.9%) and XGBoost (accuracy: 62.8%) also showed competitive results, with SVM slightly outperforming XGBoost in F1 metrics. Decision Tree exhibited the lowest performance across all metrics. The findings provide critical insights into improving text classification for low-resource languages and contribute to developing natural language processing tools adapted explicitly for 'Dhivehi.' Furthermore, the dataset is publicly available on Mendeley data under the name 'Dhivehi Categories data set' to foster future research and innovation in this domain.
  • Thumbnail Image
    ItemEmbargo
    Predictive Policing with Neural Networks: A Big Data Approach to Crime Forecasting in Sri Lanka
    (Institute of Electrical and Electronics Engineers Inc., 2025) Nauzad, H; Dayawansa, D; Dias, N.Y; Haddela, P.S; Ratnayake, S
    The surge in crime rates, particularly in urban regions, has underscored the importance of predictive policing within law enforcement strategies. This research introduces a neural network-based crime prediction model, specifically tailored to address the complexities of Sri Lanka's crime landscape. By combining big data analytics with advanced machine learning methods - including ensemble models such as Random Forest and Gradient Boosting, alongside Artificial Neural Networks (ANNs) - our study presents a robust framework to forecast crime incidents, locations, and time spans. While neural networks excel in predictive accuracy, their "black-box"nature can hinder practical applications in critical fields like law enforcement. To address this, our model integrates Explainable AI (XAI), making the decision-making process of the system transparent and interpretable for end-users. XAI helps break down complex neural network predictions, ensuring trust and clarity in the model's insights. With a prediction accuracy rate of 85%, this approach demonstrates substantial potential to improve crime prevention efforts and optimize resource allocation. Our research not only highlights the predictive strengths of neural networks but also showcases the essential role of interpretability for deploying these models effectively in real-world policing.