Wireless Signal Activity Detection via Hidden Markov Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing home automation systems face challenges in determining user activity without explicit commands, as image-based approaches are costly and invasive, and wireless signal analysis methods only detect presence rather than activity level.
Innovation Solution
A system utilizing a trained machine learning model, such as a Hidden Markov Model, processes wireless signal data to infer user activity levels, enabling automated actions based on detected transitions between static, slow, and fast movements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If image-based approaches are used to determine user activity, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces image-based detection systems with wireless signal processing systems. Instead of using cameras and computer vision algorithms to detect user activity, the system uses wireless signal data (such as Wi-Fi signals) and machine learning models to infer activity levels. This substitution reduces device complexity and cost while maintaining the ability to determine user activity states.
2Ease of operation
If wireless signal analysis is used to detect user presence, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent transforms wireless signal data into meaningful activity indicators by changing the parameters being analyzed. Instead of simply detecting presence, the system analyzes signal characteristics (such as channel state information, signal strength variations) and uses machine learning models to infer activity levels. This parameter transformation enables the system to maintain ease of operation while improving measurement precision for activity detection.
3Measurement precision
If cameras are deployed for activity detection, then measurement precision is improved, but loss of information increases due to privacy concerns
Solution Approach 1:
The patent introduces wireless signals as an intermediary medium for detecting user activity. Instead of directly capturing visual information through cameras, the system uses wireless signals that naturally pass through the environment to infer activity levels. This intermediary approach maintains measurement precision while preserving privacy, as the system processes abstract signal characteristics rather than personal visual information.
Data Source
AI summary
A system that can determine states of human activity and transitions between those states using wireless signal data. A machine learning model such as a Hidden Markov Model (HMM) may be trained to determine transitions between states of human activity (e.g., static, slow movement, fast movement) using information from wireless signal data, such as channel state information gathered from Wi-Fi signal beacons. Depending on the state of the human activity the system may then cause certain commands to be executed corresponding to the human activity such as turning on a certain configuration of lights, playing certain music, or the like.