Accelerometer-based transportation mode detection on smartphones
read more
Citations
Smart Devices are Different: Assessing and MitigatingMobile Sensing Heterogeneities for Activity Recognition
A survey of online activity recognition using mobile phones
A Survey on Mobile Crowdsensing Systems: Challenges, Solutions, and Opportunities
Recognizing Detailed Human Context in the Wild from Smartphones and Smartwatches
Mobility Increases Localizability: A Survey on Wireless Indoor Localization using Inertial Sensors
References
A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
Understanding individual human mobility patterns
Activity recognition from user-annotated acceleration data
A Short Introduction to Boosting
Limits of Predictability in Human Mobility
Related Papers (5)
Frequently Asked Questions (13)
Q2. What are the features that the authors consider for the peak area?
The segment-based features the authors consider are the frequency of acceleration and breaking periods, the frequency and duration of the intermittent stationary periods, and the variance of individual peak-based features.
Q3. What is the method used to estimate the gravity component from accelerometer measurements?
Once the measurements have been filtered, the authors project the sensor measurements to a global reference frame by estimating the gravity component along each axis and calculating gravity eliminated projections of vertical and horizontal acceleration.
Q4. What are the common locomotion types?
Typical locomotion types include different pedestrian modalities (e.g., walking, running or moving in stairs), non-motorised transportation (e.g., bicycling, roller skating) and motorised transportation (e.g., bus, train or car).
Q5. How can the authors reduce the power consumption of the stationary classifier?
As humans tend to spend most of their time within a limited set of locations, with only occasional transitions between these places [10], significant reductions in power consumption could be achieved by minimizing the power consumption of the stationary classifier.
Q6. What are the main drawbacks of all these approaches?
The main drawbacks of all these approaches are that GPS receiver has high power consumption, requiresinconsistent time for obtaining satellite lock, and is unavailable or unreliable when view to satellites is obstructed, e.g., when the user is underground, inside a station, moving in urban canyons or is insufficiently close to a window in a transportation vehicle.
Q7. What is the key technical contribution of this work?
The key technical contributions of their work are (i) an improved algorithm for estimating the gravity component of the accelerometer measurements, (ii) a novel class of features, extracted from the horizontal accelerometer representation, that are capable of capturing characteristics of acceleration and breaking patterns for different motorised transportation modalities; and (iii) a hierarchical decomposition of the overall detection task.
Q8. How do the authors reduce the influence of orientation changes on the gravity estimate?
To reduce the influence of orientation changes on the gravity estimate, the authors reset the estimate of the gravity component when a large shift in orientation is observed.
Q9. How does the approach improve detection accuracy?
The results of their evaluation demonstrate that their approach is able to improve detection accuracy by over 20% compared to current accelerometer-based solutions, and even exceed the accuracy of the current state-of-art hybrid GPS and accelerometer system by over 10%.
Q10. What is the mean precision and recall of their approach?
The mean precision and recall of their approach is over 80%, demonstrating that it can accurately distinguish between different transportation modalities despite relying solely on accelerometer measurements.
Q11. What is the problematic task with the current design?
With their current design, the most problematic task is to distinguish between metro and commuter train as both have very similar framebased and peak features.
Q12. What is the impact of the current system on the battery life of the phone?
Their current system relies solely on the phone’s accelerometer, which means that the impact of their system on the phone’s battery lifetime is reasonable even when the sensor is polled with maximum sampling frequency.
Q13. What is the importance of the frequency of the acceleration and breaking peaks?
The frequency of the acceleration and breaking peaks are the most important features as they enable distinguishing between vehicles that move alongside other traffic (i.e., car, bus and tram) and vehicles moving independently of other traffic (i.e., train and metro).