A Hidden Markov Model (HMM) is a probabilistic sequential model that represents a system as a series of hidden states with associated observation probabilities and state transition probabilities, used in CSI-based sensing to capture the temporal dynamics of human activities by modeling how underlying motion states evolve over time and generate observable signal features. HMMs are particularly valuable in device-free human sensing because many activities such as walking, gestures, or fall events are inherently sequential and time-dependent, making static classifiers insufficient for capturing their full structure. Key variants applied in this field include continuous HMMs, which model observations as Gaussian distributions, and hybrid approaches that combine HMMs with neural networks or other feature extractors to improve robustness against environmental variability and inter-subject differences.
Source Papers
- A Survey on Green Wireless Sensing: Energy-Efficient Sensing via WiFi CSI and Lightweight Learning ↗ — A Survey on Green Wireless Sensing: Energy-Efficient Sensing
- A Survey on Human Behavior Recognition Using Channel State Information ↗ — A Survey on Human Behavior Recognition Using Channel State I
- A Survey on Wireless Device-free Human Sensing: Application Scenarios, Current Solutions, and Open Issues ↗ — A Survey on Wireless Device-free Human Sensing: Application
- Channel State Information from Pure Communication to Sense and Track Human Motion: A Survey ↗ — Channel State Information from Pure Communication to Sense a
- Understanding and Modeling of WiFi Signal Based Human Activity Recognition ↗ — Understanding and Modeling of WiFi Signal Based Human Activi
- WiFi Sensing with Channel State Information ↗ — WiFi Sensing with Channel State Information