Recognition of energy-based activities performed by the aged

• Main Author: Ang, Aaron Kian Kai
• Other Authors: Soh Yeng Chai
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/149414
• Institution: Nanyang Technological University

Over the years, there has been a boom in the mobile technology industry, namely the smartphone industry. With smartphone consumption on the rise, the producers in the mobile industry are compelled to innovate and produce better smartphones with more features than the previous model of smartphone. This project aims to utilize the embedded microphones in our smartphones to recognize home related activities through the unique sound signatures that these activities produced. Through some research, it is shown that while speech and music recognition have been around for some time, the area of environmental sound recognition is relatively unexplored. However, the basic idea and model composition of environmental sound recognition is similar. Through this project, Mel Frequency Cepstral Coefficients (MFCCs) will be used for feature extraction along with the Convolutional Neural Network (CNN) classification model composition. The outcome of this project was satisfactory, however there is still room for improvement in terms of the accuracy. This report includes the research and model process of the project as well as suggestions for potential future works.