Skip to content
View dewminigunasekera's full-sized avatar

Block or report dewminigunasekera

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. ForestFire-StateModel ForestFire-StateModel Public

    Reframing forest fire propagation as a stochastic state transition problem — not a regression task. Performed using UCI forestfires data set

    Jupyter Notebook 2

  2. physics-informed-fire-prediction-occurrence physics-informed-fire-prediction-occurrence Public

    Physics-informed fire occurrence prediction using structured fire indices (ISI, FFMC, DMC, DC, BUI, FWI), and latent clustering. Implements an interpretable neural model fulfilling ISI’s predictive…

    Jupyter Notebook 3

  3. Forest_Fire_Mathematical_Modelling Forest_Fire_Mathematical_Modelling Public

    Mathematical modeling of forest fire occurrence and spread using a two-stage machine learning framework. Binomial ignition and overdispersed fire area are modeled with Random Forest and Negative Bi…

    Jupyter Notebook

  4. quant-surveillance-system quant-surveillance-system Public

    A layered ML Framework for Market Surveillance

    Jupyter Notebook 1

  5. Biophysics-Informed-Quantitative-Diabetes-Screener Biophysics-Informed-Quantitative-Diabetes-Screener Public

    Interpretable diabetes risk screener using biophysics-informed signal modeling and hybrid probabilistic gating. Pima Indians Diabetes Dataset. Recall: 0.906 | Accuracy: 0.689 | F1: 0.671

    Jupyter Notebook 1

  6. cleveland-heart-disease- cleveland-heart-disease- Public

    Cleveland heart disease dataset. Predicted using correlated inputs using RF. Recall 0.97 and accuracy 0.87

    Jupyter Notebook 1