https://github.com/danielhanchen/markovian_sir_deaths_model

I noticed that traditional methods to predict a disease outbreak was by performing sentiment analysis on Twitter posts and Google Search terms. Unfortunately, these methods were inadequate, as Twitter and Google is not popular in all countries. So, I created a system to model and predict outbreaks without the need for social media. The system was able to update the probabilities of a virus from spreading from A to B in real time, and I plan to release it to the public next year. I also used Machine Learning and Deep Learning to predict larger long-term virus trends with Google Trends, and this acted as a validator for the MSIRD model.
https://github.com/danielhanchen/markovian_sir_deaths_model

machine-learning markov-chains markovian-epidemic-processes sir zika

Last synced: 11 days ago
JSON representation

I noticed that traditional methods to predict a disease outbreak was by performing sentiment analysis on Twitter posts and Google Search terms. Unfortunately, these methods were inadequate, as Twitter and Google is not popular in all countries. So, I created a system to model and predict outbreaks without the need for social media. The system was able to update the probabilities of a virus from spreading from A to B in real time, and I plan to release it to the public next year. I also used Machine Learning and Deep Learning to predict larger long-term virus trends with Google Trends, and this acted as a validator for the MSIRD model.

• Host: GitHub
• URL: https://github.com/danielhanchen/markovian_sir_deaths_model
• Owner: danielhanchen
• License: mit
• Created: 2017-11-10T01:39:23.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2017-11-11T12:08:04.000Z (almost 7 years ago)
• Last Synced: 2024-10-06T13:41:25.452Z (about 1 month ago)
• Topics: machine-learning, markov-chains, markovian-epidemic-processes, sir, zika
• Language: Jupyter Notebook
• Size: 31 MB
• Stars: 3
• Watchers: 3
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Markovian_SIR_Deaths_Model

I noticed that traditional methods to predict a disease outbreak was by performing sentiment analysis on Twitter posts and Google Search terms.  Unfortunately, these methods were inadequate, as Twitter and Google is not popular in all countries. So, I created a system to model and predict outbreaks without the need for social media.  

The system was able to update the probabilities of a virus from spreading from A to B in real time, and I plan to release it to the public next year.  I also used Machine Learning and Deep Learning to predict larger long-term virus trends with Google Trends, and this acted as a validator for the MSIRD model.

# Research Highlights

1. Mosquito Distribution Formulation

   a. Temperature, Environmental Factors

   b. Living Standards

   

2. Basic Markov Modelling

   a. Growth and Decay

   b. New Route Derivation - Encoding and Decoding graphs

   

3. MSIR Model

   a. Matrix block concentation

   b. States and average states

   c. [S->I], [S->S], [S->R], [I->R], [I->I], [R->R] blocks

   d. Markov Updating

   

4. Demonstration

   a. 9 squares

   b. 49 squares

   

5. MSIRD Model

   a. Revised Formulas

   b. Deaths incoporation

      i. [S->D], [I->D], [R->D]