NOR HANIFAH BINTI ANUAR
Siti Hafizah Ab. Hamid
Associate Prof Dr Rafdzah Ahmad Zaki
This project aims to develop a self-alert system for drones and mobile apps to anticipate early dengue outbreaks and provide homeowners with personal prevention measures. The system utilizes data extracted from https://idengue.mysa.gov.my/ and historical meteorological data from 2018 to 2023, along with images of potential mosquito breeding areas around houses. By analyzing and predicting dengue outbreaks using the collected data, the system generates alerts on mobile apps to notify homeowners. The project is divided into four modules: 1) prediction of dengue outbreaks from current dengue case data using machine learning, 2) prediction of dengue outbreaks from historical meteorological data using machine learning, 3) detection of potential mosquito breeding areas using a drone and supervised machine learning, and 4) development of a self-alert system through a mobile app and drone. The students will be responsible for Raspberry Pi-based drone equipment and stakeholder requirements, while supervisors will provide historical meteorological data and filtered dengue case data. The project's challenges include developing a crawling system for data extraction, learning machine learning algorithms, Raspberry Pi-based drone development, and establishing webserver access through Raspberry Pi equipment.
Student 1 will focus on predicting dengue outbreaks using historical and current dengue case data from https://idengue.mysa.gov.my/ through machine learning. Additionally, they will provide recommendations for dengue prevention based on historical dengue cases, meteorological data, and potential mosquito breeding areas, delivered through a mobile phone alert system.
Student 2 will concentrate on predicting dengue outbreaks using historical meteorological data through machine learning. They will also work on detecting potential mosquito breeding areas around houses using a drone.