Energy related activities recognition using smartphones

• Main Author: Tai, Jie Qin
• 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/10356/149321
• Institution: Nanyang Technological University

In recent years, the use of machine learning techniques in applications increased rapidly. More researchers are interested to develop machine techniques to bring comfortability and increase safety through the implementation of smart home and smart office. This report focused on Energy Related Activities Recognition using Smartphones. Machine learning techniques such as Neural Network (NN) and Convolutional Neural Network (CNN) are the main discussion topic of the report. By using different types of parameters such as the Adam and Stochastic Gradient Descent (SGD) optimizer, observations are made on how the accuracy of the model will be affected. Moreover, the learning rate is also one of the factors that can affect accuracy. Subsequently, the CNN was identified as the most suitable model. In summary, the accuracy of the model is high. However, the samples size data of this project was 1300. Future research can increase the sample data.