Mobile Device Motion State Classification Using Accelerometer and HMM
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting whether a mobile device is riding in a vehicle are prone to errors, particularly when satellite positioning systems are unreliable, such as in urban areas or tunnels, and fail to distinguish between vehicular transport and other forms of movement like walking or cycling.
Innovation Solution
The use of a state machine combined with a Hidden Markov Model (HMM) that leverages accelerometer data to classify motion states, differentiating between vehicular and pedestrian movements by analyzing sequences of motion states and previous states, and potentially incorporating additional sensors like GPS or audio signatures for enhanced accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If satellite positioning systems are used to detect vehicular movement, then location information can be obtained, but detection accuracy deteriorates in urban areas or tunnels where satellite signals are unreliable
Solution Approach 1:
The patent replaces satellite positioning systems with inertial sensors (accelerometers, gyroscopes) to detect vehicular movement. Instead of relying on external satellite signals, the system uses onboard mechanical sensors to measure acceleration and orientation changes, enabling reliable detection in urban canyons and tunnels where satellite signals are blocked or degraded.
Solution Approach 2:
The patent introduces inertial measurement units as an intermediary between the mobile device and the detection goal. These sensors serve as a mediator that can operate independently of satellite infrastructure, providing alternative measurement capabilities when primary positioning systems fail.
2Device complexity
If simple motion detection methods are used, then device complexity is reduced, but the ability to distinguish between vehicular transport and other movements deteriorates
Solution Approach 1:
The patent segments the motion detection problem into distinct motion states (pedestrian, vehicular, stationary) and uses a state machine to model transitions between these states. By dividing the continuous motion space into discrete states with specific transition rules, the system achieves accurate classification without requiring overly complex algorithms.
Solution Approach 2:
The patent employs a dynamic state machine that adapts to changing motion conditions by modeling state transitions over time. The system continuously updates the current motion state based on sensor inputs and transition probabilities, enabling accurate distinction between different types of movement while maintaining computational efficiency.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach improves the accuracy of detecting vehicular movement, even in scenarios where satellite positioning is unreliable, by effectively distinguishing between different motion states and reducing false positives, enabling robust mobile device functionality.
Implementation Method 1
accelerometer data is used
Data Source
AI summary
Systems and methods herein enable a mobile device to detect that a user is traveling in association with a vehicle based at least on motion data. In some embodiments, accelerometer data is used. Motion data is leveraged in combination with various observations regarding vehicular movement to determine whether or not a mobile device is located in or on the vehicle. For instance, before entering the state of vehicular movement, it can be determined that the user is first in a walking state (e.g., walking to the car, bus, etc., and entering it). Likewise, after exiting the state of vehicular movement, the user re-enters the walking state (e.g., after stepping out of the car, bus, etc., the user again begins walking). Further, it can be determined that when the user is in the walking state, the accelerometer signals appear different to any accelerometer signals seen in the vehicular movement state.