Improved Sensor-Based Human Activity Recognition Via Hybrid Convolutional and Recurrent Neural Networks
Date of Award
Master of Science in Computer Science
School of Computer Science and Engineering
First Reader/Committee Chair
Non-intrusive sensor-based human activity recognition is utilized in a spectrum of applications including fitness tracking devices, gaming, health care monitoring, and smartphone applications. Deep learning models such as convolutional neural networks (CNNs) and long short-term memory (LSTMs) recurrent neural networks provide a way to achieve human activity recognition accurately and effectively. This project designed and explored a variety of multi-layer hybrid deep learning architectures which aimed to improve human activity recognition performance by integrating local features and was scale invariant with dependencies of activities. We achieved a 94.7% activity recognition rate on the University of California, Irvine public domain dataset for human activity recognition containing 6 activities with a 2-layer CNN-1-layer LSTM hybrid model. Additionally, we achieved an 88.0% activity recognition rate on the University of Texas at Dallas Multimodal Human Activity dataset containing 27 activities with a 4-layer CNN-1-layer LSTM hybrid model. For both datasets, our hybrid models outperformed other deep learning models and traditional machine learning methods.
Perez-Gamboa, Sonia, "Improved Sensor-Based Human Activity Recognition Via Hybrid Convolutional and Recurrent Neural Networks" (2022). Electronic Theses, Projects, and Dissertations. 1428.