SLIIT Conference and Symposium Proceedings

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/295

All SLIIT faculties annually conduct international conferences and symposiums. Publications from these events are included in this collection.

Browse

Filters

20263

Advanced Search

Filter by

Settings

Author: search.filters.author.Tan, M.L

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    publications.listelement.badgeOpen Access
    Work in Progress: Applying Model-Based Systems Engineering to Decentralised Earthquake Early Warning System Design
    (Sri Lanka Institute of Information Technology, 2026-05-21) Mirzaei, S; Prasanna, R; Tan, M.L; Herath, P
    Earthquake Early Warning (EEW) systems built on low-cost MEMS sensors and decentralised processing architectures represent a promising path toward affordable, largescale seismic warning coverage. Yet despite considerable progress at the component level, the field lacks a formal engineering infrastructure capable of binding these components into a coherent, verifiable, and maintainable system. This paper presents work in progress toward filling that gap through the systematic application of Model-Based Systems Engineering (MBSE) to the design of a decentralised EEW framework. Grounded in Design Science Research Methodology (DSRM), the approach uses Systems Modelling Language (SysML) to produce a formal, traceable representation of system architecture and behaviour. We report on three completed stages: a systematic literature review that identified the core research gaps, a component analysis that produced a conceptual framework for the decentralised architecture, and the formalisation of node-level detection and alert logic. The ongoing SysML modelling activity and the path toward simulation-based validation are also described. The central argument is that MBSE is not merely a documentation exercise for EEW research; it is the missing engineering foundation that makes these systems verifiable, scalable, and transferable.
  • Thumbnail Image
    publications.listelement.badgeOpen Access
    From Beach to Cliff: Adapting CoastSnap Citizen Science for Coastal Cliff Change Detection Using ML-Assisted Image Registration and Prompted Segmentation
    (Sri Lanka Institute of Information Technology, 2026-05-21) aramillo-Velez, A; Gamlath, S; Chandirakumar, M; Prasanna, R; de Vilder,S; McColl, S; Tan, M.L; Stewart, C; Ambegoda, T.D
    CoastSnap is a citizen science tool that uses repeat smartphone photographs from fixed stations to monitor coastal change, yet it has rarely been applied to coastal cliffs. We test a workflow for cliff change screening using a controlled pilot CoastSnap station at Ōnaero, New Zealand (iPhone 12), integrating (i) Machine Learningassisted ground control point (GCP) transfer for image registration, (ii) pinhole camera calibration and reprojection-based geo-rectification onto a curved cliff-surface model, and (iii) prompted segmentation for isolating cliff-related features. Auto-GCP benchmarking shows a tradeoff between precision and robustness: the Scale-Invariant Feature Transform (SIFT) model achieves low localisation error when successful, but is sensitive to changes in illumination. In contrast, the Local Feature ransformer (LoFTR) model provides a higher detection yield and more stable performance, but is sensitive to the threshold used. Nevertheless, it is well suited to operational use with human-inthe- loop verification. Calibration produced consistent parameters across repeat images, with focal length estimates matching device specifications. Visual segmentation based only in Regions of Interest (RoI) often merged adjacent objects, while text-guided Segment Anything Model (LangSAM) delineated cliff and debris more reliably than fracture-like features. Preliminary detection of the supply and removal of debris highlights the potential for quantifying the frequency and magnitude of mass movements at each cliff.
  • Thumbnail Image
    publications.listelement.badgeOpen Access
    Structural Gaps in Disaster Technology Systems: A Longitudinal Review of Post-Event Assessments in Aotearoa New Zealand
    (Sri Lanka Institute of Information Technology, 2026-05-21) Tan, M.L; Adikari, K.E; Prasanna, R
    Over the past decade, Aotearoa New Zealand has experienced multiple large-scale disasters that have exposed recurring challenges in information management, communication, coordination, and technology integration within the emergency management system. This paper analyses eleven major disaster-response review reports published between 2012 and 2024 to examine how technology-related issues are represented in official assessments and to identify structural gaps. Using a mixed-method approach combining keyword frequency analysis and qualitative thematic analysis, the study finds that information and communication dominate review discourse, while explicit references to technology, situational awareness, and common operating picture appear less frequently and inconsistently. Longitudinal synthesis reveals persistent reform themes, including calls for nationally integrated platforms, interoperable systems, professionalised capability, and shared intelligence frameworks. Yet implementation details regarding architectural ownership, standards, lifecycle management, and funding remain limited. The paper advances a structured research agenda organised around four domains: data governance and architecture, decision-support design, ICT resilience and interoperability, and organisational technology governance.