Artificial intelligence monitoring at the edge for smart nation deployment

Abstract

Machine learning and computer vision have become closely related in the recent years. With the vast amount of data generated in this heavily digitalized century, the advancement of machine learning field is growing exponentially. The ability to utilize data to categories and predict pattern made machine learning a powerful tool to solve problems in many fields. In the field of computer vision, machine learning helps to improve recognition and tracking. In this paper, we will discuss the possibility of using machine learning technique to implement Direction of Arrival (DOA) estimation in embedded system to detect the source of audio signal. This project consists of mainly two parts, data acquisition and creating machine learning model for estimation. The performance is evaluated with the accuracy outcome of the model to estimate the angel of audio played in the environment.