Wi-Fi CSI-based human activity recognition and anomaly detection using advanced machine learning models | |
| Author | Dit Preechakarnjanadit |
| Call Number | AIT RSPR no.TC-25-01 |
| Subject(s) | Human activity recognition Machine learning Anomaly detection (Computer security) |
| Note | A research study submitted in partial fulfillment of the requirements the degree of Master of Engineering in Telecommunications |
| Publisher | Asian Institute of Technology |
| Abstract | Falls are a major health risk, especially for the elderly, often resulting in severe injuries or fatalities. Traditional monitoring methods, such as CCTV-based systems and wearable devices, face limitations, including privacy concerns, complex installations, and user inconvenience. This research explores Wi-Fi Channel State Information (CSI) for Human Activity Recognition (HAR) to handle these issues in hospital settings. Wi Fi CSI captures signal variations caused by human movement, enabling passive, non intrusive monitoring. We evaluate multiple advanced machine learning models, including Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks, Graph Neural Networks (GNNs), and Transformers, to classify human activities and distinguish similar gestures, such as falling and lying down, even in complex environments. This work aims to build a real-time system for continuous patient monitoring in hospitals and homes. Expected outcomes include improved fall detection accuracy, enhanced patient comfort, and lower implementation costs compared to conventional systems. |
| Year | 2025 |
| Type | Research Study Project Report (RSPR) |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Telecommunications (TC) |
| Chairperson(s) | Attaphongse Taparugssanagorn |
| Examination Committee(s) | Chaklam Silpasuwanchai;Chantri Polprasert |
| Scholarship Donor(s) | Royal Thai Government Fellowship |
| Degree | Research Studies Project Report (M. Eng.) - Asian Institute of Technology, 2025 |