Theses

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/2429

Postgraduate students are required to submit a thesis as part of fulfilling the requirements of their respective postgraduate degree programmes. This community features merit-based graduate theses submitted by SLIIT postgraduate students. Abstracts are available for public viewing, while the full texts can be accessed on-site within the library.
CC BY-NC-ND 4.0 License
Theses and Dissertations of the Sri Lanka Institute of Information Technology (SLIIT) are licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License .

Browse

Filters

2023 - 20253

Advanced Search

Filter by

Settings

Subject: search.filters.subject.Algorithms

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    PublicationOpen Access
    The Role of Machine Learning Algorithms in Shaping Teenage Social Identity through Curated Digital Experiences.
    (Sri Lanka Institute of Information Technology, 2025-12) Sajipratha, R.
    Social media has taken its place as one of the most powerful instruments of the modern digital environment that affects the perception of young individuals towards each other and themselves. Identity formation is a significant developmental condition among teenagers, and due to the individualized algorithms that shape what they view, like, and interact with online, it is becoming more affected by the latter. The paper examines the influence of Machine Learning-based recommendation systems on the social identity of teenagers in the framework of algorithmic curation, and the connection between algorithmic exposure, diversity of content, and identity pressure. The study enables a more profound insight into how Artificial Intelligence impacts social comparison, body image, and self-perception of adolescents by studying the psychological implications of the use of algorithms in personalization. The research design was a quantitative one to analyze the data gathered based on 150 students between age 18 to 19 of an international school in Kandy, Sri Lanka. The research employed an indexed questionnaire, which measured the following: Algorithmic Exposure Index (AEI), Stereotypical Content Reinforcement (SCR), Number of Topics (NTOP), and Body/Identity Pressure (BIP). The data were analyzed using descriptive, correlation and multinomial logistic regression techniques to identify the interaction of these variables and predictive of the emotional and identity related outcomes. Findings showed that more than 60 percent of the subjects especially females indicated that they experienced a lot of social comparison and body pressure following the exposure to the algorithms. Tik Tok and Instagram users reported much more odds of being subjected to appearance and behavioral pressure than YouTube users, thereby affirming that appearance-focused and engagement-oriented platforms enhance conformity and self-assessment. Moreover, negative self-perception at the time of exposure to stereotypical material (high SCR) was strongly related to exposure, and increased diversity of the topic (high NTOP) was a protective factor, decreasing the identity stress and resulting in a more balanced sense of self. The results promote both Social Identity Theory and Algorithmic Bias Theory, showing the Machine Learning systems not only suggest content, but also act as the contributors to the formation of the identity of users by supporting specific social norms and values. Young people who are in algorithmic echo chambers are less exposed to different or anti-stereotypical stories, which results in more limited ideas of attractiveness, popularity, and success. This paper thus lays emphasis on the importance of algorithmic responsibility, ethical design and media literacy interventions. The research will offer a solution to these issues by proposing the Responsible Curation Framework, which is a complex intervention encompassing algorithmic diversity prompts, user-controlled content filters and digital literacy education. Collectively, these measures will help to regain the balance of exposure, self-awareness and encourage psychological well-being in young users. On the whole, this analysis can be discussed as part of the expanding discourse of ethical AI and digital well-being and can serve as a way of starting to change how algorithmic recommendation systems are managed so as to become instruments of conformity instead of instruments of diversity, empowerment, and positive identity formation.
  • Thumbnail Image
    PublicationOpen Access
    Analyzing the Performance of Different Text Classification Algorithms for “Dhivehi” Documents
    (SLIIT, 2024-12) Mohamed, F.R
    This research investigates the effectiveness of various machine learning classification algorithms applied to Dhivehi text-based documents. Dhivehi, the official language of the Maldives, presents unique linguistic challenges for text classification due to its limited digital resources and distinct grammatical structure. The study aims to identify the most suitable algorithm for classifying Dhivehi documents and to provide insights into optimizing text classification approaches for less- resourced languages. The research systematically evaluates the performance of several machine learning algorithms, including Support Vector Machines (SVM), Naive Bayes, Decision Trees, XGboost , Random Forest and Neural Networks. These algorithms are applied to a diverse dataset of Dhivehi text, encompassing various genres and topics. The study employs a rigorous methodology involving data preprocessing, feature extraction, and model training and testing. Performance metrics such as accuracy, precision, recall, and F1-score are used to compare the efficacy of each algorithm. Additionally, the research explores the impact of different text representation techniques, including bag-of-words, TF-IDF, and word embeddings, on classification performance. The findings offer valuable insights into optimizing text classification methods for low-resource languages and aim to advance natural language processing tools specifically tailored for “Dhivehi.” 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. By identifying the most effective classification algorithms and representation techniques, this research aims to enhance the accuracy and efficiency of Dhivehi text classification tasks. The results will have practical applications in areas such as sentiment analysis, document categorization, and information retrieval systems tailored for the Dhivehi language. 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
    PublicationOpen Access
    Development of Queue Estimation Algorithms for Urban Intersections in Mixed Traffic Conditions
    (Department of Civil Engineering Sri Lanka Institute of Information Technology, 2023-12) Jayatilleke, J.A. D.S.S
    Traffic congestion has increased globally due to rapid urbanization and expedited economic developments in many countries. Vehicle queues are a governing aspect of traffic congestion, studied over the past decades. Most of the existing queue estimation approaches are limited to homogeneous traffic conditions. However, the traffic conditions in many developing countries are heterogeneous and are heavily influenced by mixed vehicle composition, lane changing, and gapfilling behaviors. This study aims to estimate the queue length at signalized intersections having heterogeneous traffic conditions. The methodology employed in this study integrates both statistical and neural network analyses utilizing a time-series approach. A key innovation in this research lies in the incorporation of heterogeneity considerations, where Passenger Car Units (PCU) are assimilated into the measurements of traffic flow and lane-changing movements within the analyzed road section. The influential factors impacting queue length were examined, encompassing arrival flow, discharge flow, outbound lane change, inbound lane change, and signal configuration. The statistical analysis was undertaken through an econometric approach, representing another novel contribution to queue estimation studies. Vector Auto Regression (VAR) models were developed to estimate queue lengths for signalized and unsignalized intersections. The VAR estimation results demonstrated heightened accuracy in queue estimation and practical applicability for prediction, capturing the traffic characteristics of the formed vehicle queue. However, limitations were identified, particularly in terms of lower prediction times, which impeded the practical utilization of the model for traffic management. Consequently, to address this limitation, neural network analysis using the Long Short-Term Method (LSTM) was incorporated to enhance queue predictions over longer time sequences. While the neural network exhibited promise, challenges in data collection contributed to lower accuracy in predictions. Notwithstanding the challenges, the methodological development in this thesis presents a promising direction for queue estimations under heterogeneous conditions. This advancement brings the scientific and research field one step closer to improved queue estimation methods within this specific scope.