https://www.um.edu.mt/library/oar/handle/123456789/8368 Previously known as Department of Intelligent Computer Systems Sat, 14 Nov 2026 01:07:07 GMT 2026-11-14T01:07:07Z https://www.um.edu.mt/library/oar/handle/123456789/150900 Title: A comparative analysis of AI models for scenario-based learning Authors: Borg, Gabriel; Azzopardi, Keith; Montebello, Matthew; Camilleri, Vanessa; Cardona, Luke Abstract: Scenario-Based Learning (SBL) is a pedagogical approach that situates learners within realistic narratives to promote skill transfer, decision-making, and contextual understanding (Clark, 2012). With the rise of generative artificial intelligence, Large Language Models (LLMs) have become central to enhancing SBL by enabling adaptive dialogue, dynamic narrative generation, and personalized feedback (Liu, Yang, & Xu, 2023; Zhang, Wang, & Li, 2024). This paper presents a comparative analysis of LLM applications in SBL across immersive (VR/digital) and non-immersive (text-based and 2D) environments, focusing on education and safety training domains. The study incorporates a review of SBL literature and evaluation frameworks, highlighting how learning outcomes, engagement, and realism are assessed in current research (Lee, Park, & Kim, 2024; Kim & Torres, 2023). We also examine design processes underpinning SBL systems, including human-centered design, iterative prototyping, and collaborative scenario development with educators (WHO, 2022; Ahmed, Brooks, & Liu, 2023; Hu & Chan, 2025). Findings from recent studies (Liu et al., 2023; Rajputh, Seetharam, & Balasubramanian, 2019) indicate that LLM-driven systems support high levels of psychological fidelity and learner engagement, particularly in dialogue-rich contexts, though challenges such as prompt control and response reliability persist (Zhang et al., 2024). Finally, through this paper we aim to conclude that the most effective SBL implementations are built on hybrid AI architectures that combine the creativity and adaptability of LLMs with the precision and structure of rule-based or knowledge-driven components. Such hybrid designs enable educators to maintain control over content accuracy while benefiting from AI-driven flexibility. Additionally, robust evaluation frameworks that systematically assess learning outcomes, engagement, and realism are crucial to ensure both educational effectiveness and technical reliability. Together, these strategies provide a pathway toward developing realistic, adaptive, and safe learning environments powered by AI (Lee et al., 2024; Kim & Torres, 2023; Ahmed et al., 2023). Thu, 01 Jan 2026 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/150900 2026-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/150260 Title: garNER at SemEval-2023 : simplified knowledge augmentation for multilingual complex named entity recognition Authors: Hossain, Zobaer; So, Averie Ho Zoen; Silwal, Silviya; Gongora, H. Andres Gonzalez; Samin, Ahnaf Mozib; Junaed, Jahedul Alam; Mazumder, Aritra; Saha, Sourav; Soha, Sabiha Tahsin Abstract: This paper presents our solution, garNER, to the SemEval-2023 MultiConer task. We propose a knowledge augmentation approach by directly querying entities from the Wikipedia API and appending the summaries of the entities to the input sentence. These entities are either retrieved from the labeled training set (Gold Entity) or from off-the-shelf entity taggers (Entity Extractor). Ensemble methods are then applied across multiple models to get the final prediction. Our analysis shows that the added contexts are beneficial only when such contexts are relevant to the target-named entities, but detrimental when the contexts are irrelevant. Sat, 01 Jul 2023 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/150260 2023-07-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/149091 Title: Iterative hybrid discrete-continuous viewpoint planning for UAV photogrammetry Authors: Grech, Alan; Pisani, Daniel; Grima, Andre; Debono, Carl James; Formosa, Saviour; Seychell, Dylan Abstract: Unmanned aerial vehicle (UAV) photogrammetry requires camera networks that provide sufficient surface coverage, image overlap, parallax, and resolution, yet conventional flight patterns are often poorly adapted to scene geometry, resulting in local reconstruction errors. This paper proposes an iterative hybrid discrete-continuous viewpoint planning method for targeted UAV photogrammetry from a proxy reconstruction. The method scores sampled surface points using photogrammetric heuristics based on frontality, imaging distance, parallax, and multi-view observation count, while also evaluating the full viewpoint set in terms of visibility, pairwise overlap, and graph connectivity. Candidate viewpoints are generated around weakly observed regions, refined using clustered Covariance Matrix Adaptation Evolution Strategy (CMA-ES) optimisation, and removed when redundant. The final flight path combines close-range detail viewpoints with wider model-coverage viewpoints, balancing local reconstruction quality with global image-network robustness. Evaluation on three synthetic scenes shows that the proposed method improves both reconstruction accuracy and completeness compared with prior UAV path-planning methods. Thu, 01 Jan 2026 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/149091 2026-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/149083 Title: Enhancing object detection with privileged information : a model-agnostic teacher-student approach Authors: Bartolo, Matthias; Seychell, Dylan; Hili, Gabriel; Montebello, Matthew; Debono, Carl James; Formosa, Saviour; Makantasis, Konstantinos Abstract: This paper investigates the integration of the Learning Using Privileged Information (LUPI) paradigm in object detection to exploit fine-grained, descriptive information available during training but not at inference. We introduce a general, model-agnostic methodology for injecting privileged information-such as bounding box masks, saliency maps, and depth cues-into deep learning-based object detectors through a teacher-student architecture. Experiments are conducted across five state-of-the-art object detection models and multiple public benchmarks, including UAV-based litter detection datasets and Pascal VOC 2012, to assess the impact on accuracy, generalization, and computational efficiency. Our results demonstrate that LUPI-trained students consistently outperform their baseline counterparts, achieving significant boosts in detection accuracy with no increase in inference complexity or model size. Performance improvements are especially marked for medium and large objects, while ablation studies reveal that intermediate weighting of teacher guidance optimally balances learning from privileged and standard inputs. The findings affirm that the LUPI framework provides an effective and practical strategy for advancing object detection systems in both resource-constrained and real-world settings. Thu, 01 Jan 2026 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/149083 2026-01-01T00:00:00Z