Artificial intelligence monitoring at the edge for smart nation deployment

Abstract

A key aspect of Smart Nation is the collection of data with the use of live monitoring, which is then sent for analysis using artificial intelligence algorithms to extract the desired information.

This project aims to improve the model training process using data augmentation via mixing noise into the training data, then implement the model prediction in a Raspberry Pi. This allows for sensors or microphones to be installed in various strategic locations, capturing the audio type of interest such as loud noises like crashes or screams to regular noises such as traffic or footstep noises.

With this proof-of-concept system can help to eventually automate and streamline the process of noise and audio-related monitoring.