Mobile Transport Mode Recognition Using Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing transportation mode recognition systems face challenges in achieving reliable and accurate detection, particularly with GPS-based methods due to energy consumption and signal limitations, and accelerometer-based methods struggle with precise position and orientation determination, leading to difficulties in distinguishing between similar modes like buses, cars, and trains.
Innovation Solution
A system utilizing a combination of an accelerometer and GPS sensors, along with wireless connections, employs a gradient boosting machine-learning classifier to recognize transportation modes, including public transportation and other forms, by analyzing time series data from multiple sensors and incorporating user corrections to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If GPS-based recognition is used, then transportation mode detection can be performed, but energy consumption increases and signal reception becomes unreliable
Solution Approach 1:
The patent combines GPS data with accelerometer data to create a hybrid recognition system. The GPS component provides location and movement information while the accelerometer captures motion patterns. By merging these two data sources, the system achieves reliable transportation mode detection without relying solely on GPS, thereby reducing energy consumption compared to GPS-only approaches while maintaining detection accuracy.
2Use of energy by moving object
If accelerometer-based recognition is used, then energy consumption is reduced, but position and orientation determination becomes difficult
Solution Approach 1:
The patent uses GPS data as an intermediary to complement accelerometer measurements. While the accelerometer provides continuous low-energy motion data, the GPS component serves as an intermediary reference that helps determine absolute position and orientation. This combination allows the system to maintain measurement precision without the high energy cost of using GPS alone, as the accelerometer handles continuous tracking while GPS provides periodic calibration.
3Reliability
If accelerometer data is averaged over time, then noise is reduced, but gravity component measurement accuracy decreases
Solution Approach 1:
The patent segments the accelerometer signal processing into different components: dynamic acceleration, gravity, and noise. Instead of averaging the entire signal which would blur these components, the system processes them separately. The gravity component is extracted and analyzed independently to maintain precision, while other components are averaged or filtered separately to reduce noise. This segmentation allows simultaneous achievement of signal reliability and measurement precision.
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
The system achieves enhanced accuracy in distinguishing between various transportation modes, enabling real-time and continuous tracking, supporting applications like personal navigation and risk-transfer processes.
Implementation Method 1
the GPS sensor measures the mobile device's longitude, latitude and altitude position by measuring different speed of light delays in the signals coming from two or more satellites
Implementation Method 2
the measuring parameters comprise time series of sensory parameter values of a 3-axis accelerometer as sensor
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Proposed is a method and system for automated transportation mode recognition based on sensory data measured by a plurality of sensors (102) of a cellular mobile device (10) of a user (6/61 /62), the plurality of sensors (102) at least comprising an accelerometer (1025) and a gyroscope (1026), the plurality of sensors (102) being connected to a monitoring mobile node application (101) of the mobile device (10), wherein the mobile device (10) measures time series of sensory parameter values based on measuring parameters obtained from the sensors (102), the measuring parameters comprise time series of sensory parameter values of a 3-axis accelerometer as sensor (102) and time series of sensory parameter values of GPS-based speed measurements of a GPS receiver as sensor (102), and wherein the measured time series of sensory parameter values trigger the automated transportation mode recognition as input feature values to a gradient boosting machine-learning classifier, the transportation modes at least comprising the modes public transportation and/or motorcycle and/or cycling and/or train and/or tram and/or plane and/or car and/or skiing and/or boat, and the transportation mode recognition generating a transport mode label for a transport mode movement pattern of a trip.