AI-Powered disease outbreak prediction

Liew, Sze Wen (2023) AI-Powered disease outbreak prediction. Project Report. Melaka, Malaysia, Universiti Teknikal Malaysia Melaka. (Submitted)

	Text (24 Pages) AI-Powered disease outbreak prediction.pdf - Submitted Version Download (654kB)
	Text (Full Text) AI-Powered disease outbreak prediction.pdf - Submitted Version Restricted to Registered users only Download (2MB)

Abstract

The severity of disease outbreaks has increased in recent times. This project aims to use AI techniques, specifically the Long Short-Term Memory (LSTM) algorithm, to predict Monkeypox outbreaks accurately. Traditional reporting methods have limitations, such as being time-consuming, error-prone, and limited scope. Furthermore, language and cultural barriers hinder obtaining precise, detailed outbreak information through manual reporting. An AI-based platform was developed to overcome these challenges, incorporating cultural sensitivity into its computational algorithms. The platform can efficiently analyze vast amounts of data to identify early signs of outbreaks. It provides real-time insights through an analytical dashboard. The LSTM algorithm in this project outperforms other algorithms, with a Root Mean Square Error (RMSE) of less than 1, indicating high precision. The system and dashboard developed through this project are effective tools for health officials to prevent and manage outbreaks proactively. Ultimately, this project aims to enhance disease outbreak prediction and response strategies by utilizing artificial intelligence to mitigate their effects.

Actions (login required)

View Item