Raj Abhijit Dandekar

Raj Abhijit Dandekar

Bengaluru, Karnataka, India
150K followers 500+ connections

Join to follow

About

I graduated with a PhD from Massachusetts Institute of Technology in the department of…

Articles by Raj

  • ML: Teach by Doing Project. Day 1
    Mar 27, 2024

    ML: Teach by Doing Project. Day 1

    Read time: 6 minutes I have taken the decision to start learning Machine Learning again. In 2018, I attended my first…

Activity

Join now to see all activity

Experience

  • Vizuara Graphic

    Vizuara

    Bengaluru, Karnataka, India

  • -

    Bengaluru, Karnataka, India

  • -

  • -

    Greater Boston Area

  • -

  • -

  • -

Education

Publications

  • Quantifying the effect of quarantine control in Covid-19 infectious spread using machine learning

    MedRxiv (preprint)

    See publication

  • Universal Rim Thickness in Unsteady Sheet Fragmentation

    Physical Review Letters

    See publication

  • Film spreading from a miscible drop on a deep liquid layer

    Journal of Fluid Mechanics

    See publication

  • SafeBlues: A method of estimation and control in the fight against COVID-19

    Medrxiv

    How do fine modifications to social distancing measures really affect COVID-19 spread? At the moment, we don't know! In an imaginary world, we would develop a harmless biological virus that spreads just like COVID-19 but is traceable via cheap and reliable diagnosis. Then by spreading such an imaginary virus throughout the population, the spread of COVID-19 could be estimated because the benign virus would respond to population behaviour and social distancing measures in a similar manner to…

    How do fine modifications to social distancing measures really affect COVID-19 spread? At the moment, we don't know! In an imaginary world, we would develop a harmless biological virus that spreads just like COVID-19 but is traceable via cheap and reliable diagnosis. Then by spreading such an imaginary virus throughout the population, the spread of COVID-19 could be estimated because the benign virus would respond to population behaviour and social distancing measures in a similar manner to COVID-19. However, such a benign biological virus does not exist. Instead, we developed a safe and privacy-preserving digital alternative. We call this framework Safe Blues.

    See publication

  • SciML: Automatic Discovery of droplet fragmentation Physics

    JuliaCon 2020 (Accepted)

    We consider a classical droplet fragmentation problem in fluid mechanics, and augment the system modeling with neural architectures using DiffEqFlux.jl. This augmentation speeds up experimental inquiries by training physically-interpretable neural architectures to recover the physical equations for the spatial and temporal variation of dynamic quantities. Together we showcase how Julia's unique differentiable programming ecosystem can be the basis for next-generation physical science.

    See publication

Courses

  • Design and Optimization of Energy Systems

    -

  • Fluid Mechanics

    -

  • Fluids and Diseases

    -

  • Interfacial Phenomena

    -

  • Introduction to Machine Learning

    6.036

  • Learning Machines

    2.168

  • Linear Algebra

    -

  • Multivariate Data Analysis

    -

  • Non linear dynamics and waves

    -

  • Statistical Learning Theory

    6.860

Projects

  • Safe Blues: A Method for Estimation and Control in the Fight Against COVID-19

    - Present

    How do fine modifications to social distancing measures really affect COVID-19 spread? At the moment, we don't know! In an imaginary world, we would develop a harmless biological virus that spreads just like COVID-19 but is traceable via cheap and reliable diagnosis. Then by spreading such an imaginary virus throughout the population, the spread of COVID-19 could be estimated because the benign virus would respond to population behaviour and social distancing measures in a similar manner to…

    How do fine modifications to social distancing measures really affect COVID-19 spread? At the moment, we don't know! In an imaginary world, we would develop a harmless biological virus that spreads just like COVID-19 but is traceable via cheap and reliable diagnosis. Then by spreading such an imaginary virus throughout the population, the spread of COVID-19 could be estimated because the benign virus would respond to population behaviour and social distancing measures in a similar manner to COVID-19. However, such a benign biological virus does not exist. Instead, we developed a safe and privacy-preserving digital alternative. We call this framework Safe Blues.

    See project

  • Quantifying the effect of quarantine control in Covid-19 infectious spread using machine learning

    -

    • Developed a COVID-19 epidemiological assisted by machine learning for quantifying the quarantine strength in China, Italy, South Korea and USA.

    • Model made public on April 1 2020 predicted a stagnation in the infected case count in USA by 15 - 20 April 2020 at about 600, 000 infections, which matched reasonably well with actual data seen during that period.

    See project

Languages

  • English

    Full professional proficiency

  • Hindi

    Full professional proficiency

  • Marathi

    Full professional proficiency

More activity by Raj

View Raj’s full profile

  • See who you know in common
  • Get introduced
  • Contact Raj directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Add new skills with these courses

See all courses