Skip to content

Local Chapter project

Predicting Autism in Toddlers through Machine Learning

Data VisualizationEDADeep learning / Machine Learning
Start date
January 22, 2023
Finish date
February 26, 2023
Project status
completed
Predicting Autism in Toddlers through Machine Learning

Challenge background

Nearly 1% of the population globally sufferers from Autism. Autism is a lifelong battle and early detection of autism can cure or help to manage the condition better. Therefore, a autism prediction model can help both child and parents to have better quality of life.

The problem

Current screening processes incur costs and require expertise. Therefore, this project will apply ML to screen autism in children using a simple set of parameters reducing the cost and expertise needed.

Goal of the project

  1. Exploratory Data Analysis
  2. Train ML model to predict Autism.
  3. Use explainability to identify the reason behind predictions.
  4. Write a research paper.

Project timeline

  1. 1

    Week 1

    Exploratory Data Analysis

  2. 2

    Week 2

    Train Classical ML Models

  3. 3

    Week 3

    Train Deep Learning ML Models

  4. 4

    Week 4

    Analyze results including Explainability and bias analysis

  5. 5

    Week 5

    Write a research paper based on the results

  6. 6

    Week 6

    Write a research paper based on the results

What you'll learn

EDA, Machine Learning, Deep Learning, Explainable AI, Writing Research Papers

Get involved

What to expect from a Local Chapter project

First project

  • Welcomes beginners and experienced practitioners.
  • Focuses on education and collaborative delivery.
  • Produces open-source project work.

Benefits

  • Address a significant real-world problem with your skills.
  • Build your project portfolio.
  • Demonstrate your work to organizations and project partners.

Requirements

  • Working English communication.
  • A learning mindset.
  • Commitment to collaborative project work.

This challenge is hosted by

No public hosting chapter is linked to this project.