Research Publications

Search Results

Now showing 1 - 2 of 2

Open Access
Automated Landslide Mapping with Open-Source Satellite Data in GEE: A Sri Lankan Case Study.
(Sri Lanka Institute of Information Technology, 2026-05-21) Lasantha H S; Prasanna R; Madusanka D A G
Rainfall-induced landslides are the most frequent natural hazards in Sri Lanka. This study developed a scalable, cloudbased landslide detection method that integrates satellite data, topographic parameters, and a machine learning framework implemented on Google Earth Engine (GEE) to support rapid, reliable landslide mapping in disaster scenarios and datascarce regions. The methodology was applied to the central highlands and the south-western parts of Sri Lanka. Multitemporal Sentinel-1 and Sentinel-2 images, along with a 12.5 m digital elevation model, were used to generate four composite datasets (M1–M4) for pixel-based classification. M1 includes spectral index differences between pre-event and post-event optical images, M2 incorporates spectral distance and spectral angle data, M3 contains topographic attributes, and M4 combines all datasets with synthetic aperture radar (SAR) amplitude ratio bands. Inter-area model training and validation were conducted using RF, CART, SVM, and GTB with independent datasets from study area-1, followed by transferability testing in a second area. Model performance was evaluated using overall accuracy, Precision, Recall, F1- Score, Kappa, and AUC. SVM-M4 performed best in interarea analysis, while GBT–M4 and CART–M3 showed supe Cloud contamination and false detections remained key challenges.
Embargo
Offline Signature Verification Using a Statistical Approach
(Faculty of Humanities and Sciences,SLIIT, 2021-09-25) Dias, D.P.N.P; Sucharitharathna, K.P.G.C
There is a growing interest in signature verification with the increasing number of transactions, especially financial, that are being authorized via signatures. Hence methods of automatic signature verification are essential if authenticity is to be verified regularly. In this research, two statistical approaches are used to develop an offline signature verification system. Data collection was done from 100 individuals. Everyone was asked to provide 12 samples of his/her original signature for training and testing processes. 600 forgeries were collected from three forgers and 6 forgeries were generated for each of the original signature samples. In this study features were extracted from the signatures after the preprocessing stage. Altogether 10 features were collected and those were used to verify the signatures. It was found that when there is a multicollinearity, Generalized Linear model by estimating parameters using generalized estimating equations is not appropriate to solve the above problem. Multicollinearity problem can be minimized using factor analysis and then generalized linear model was found to be a more effective approach. However, further research needs to be carried out to solve this problem.

Research Publications

Browse

Filters

Advanced Search

Filter by

Settings

Sort By

Results per page

Search Results