Disaster-Response-ML-Project

Intel oneAPI Hackathon Project based on ML and AI

Introduction

This project is part of the Intel oneAPI Hackathon conducted in CHRIST(Deemed to be University) conducted on March 16,2023.

In this project, the pre-labeled disaster messages will be used to build a disaster response model that can categorize messages received in real time during a disaster event, so that messages can be sent to the right disaster response agency.

This project includes a web application where disaster response worker can input messages received and get classification results.

How I built it

1. First I Import Libraries
2. Understand the idea
3. Test different model and find best model outt of it
4. Train the model using Intel oneDAL to get better results and faster computation(Intel oneAPI Data Analytics Library (oneDAL))

What I learned

1. Building application using intel oneDAL:The Intel oneAPI Data Analytics Library (oneDAL) contributes to the acceleration of big data analysis by providing highly optimised algorithmic building blocks for all phases of data analytics (preprocessing, transformation, analysis, modelling, validation, and decision making) in batch, online, and distributed processing modes of computation.The library optimizes data ingestion along with algorithmic computation to increase throughput and scalability.

2. Collaboration: Building a project like this likely required collaboration with a team of experts in various fields, such as mediacal filed, machine learning, and data analysis, and I likely learned the importance of working together to achieve common goals.

3. Data Analysis: I likely gained experience in collecting and analyzing large amounts of data, including historical disaster data, response and evacuation activities and the status of the injured, to train our machine learning models.

4. Machine Learning: I likely learned about different machine learning algorithms and how they can be applied to analyze texts and make evacuation actions to response team.