1. Accelerometer-based Transportation Mode Detection on Smartphones
Samuli Hemminki, Petteri Nurmi, Sasu Tarkoma
Helsinki Institute for Information Technology
Proceedings of the 11th ACM Conference on Embedded Networked Sensor Systems, 2013
배문규

2. Contents Introduction Communication management Protocol description
Validation
Conclusion

3. Introduction Contributions Results
An improved algorithm for estimating the gravity component of accelerometer measurements
A novel set of accelerometer features that are able to capture key characteristics of vehicular movement patterns
A hierarchical decomposition of the detection task
Results
It is able to improve transportation mode detection by over 20% compared to current accelerometer-based systems

4. Introduction A positive impact on many research fields Challenge
Automatically monitor the transportation behavior of individuals
Unban planning
Monitoring and addressing the spread of diseases and other hazards
Providing emergency responders information of the fastest route
Localization and positioning algorithms
applications: 𝐶 𝑂 2 -footprint, level of physical activity
User profiling
Challenge
To distinguish information pertaining to movement behavior from other factors that affect the accelerometer signals

5. Transportation mode detection: overview

6. Preprocessing and gravity estimation
Three dimensional acceleration measurement
Preprocessing the raw measurements by applying a low-pass filter that retains 90% of energy
Aggregating the measurements using a sliding window with 50% overlap and a duration of 1.2 seconds
Projecting 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
우리는 센서 측정 결과를 글로벌 레퍼런스 프레임에 투영하였다. (각 축을 따라 중력 성분을 추정하고, 수평과 수직 가속도의 중력이 제거된 투영값을 계산함으로써)

7. Preprocessing and gravity estimation
Algorithm for estimating the gravity component of accelerometer measurements

8. Preprocessing and gravity estimation

9. Feature extraction Frame-based features Peak-based features
Statistical features, time-domain metrics, frequency-domain metrics
These are able to effectively capture characteristics of high-frequency motion
Peak-based features
These characterize acceleration and deceleration period to capture features from key periods of vehicular movement
Extract these features only during stationary and motorized periods
peak areas

10. Feature extraction Segment-based features
These characterize patterns of acceleration and deceleration periods

11. Feature extraction
Full list of the features

12. Classification Instance-based classifier Hidden Markov Model (HMM)
Decision tree, SVM
Hidden Markov Model (HMM)
For the kinematic motion classifier

13. Classification Adaptive boosting (AdaBoost) Decision tree
To iteratively learn weak classifiers that focus on different subsets of the training data and to combine these classifiers into one strong classifier
This paper uses decision trees with depth of one or two as the weak classifier
Boosting rounds T was determined using the scree-criterion
Decision tree

14. Classification Segment-based classification
It is performed for the stationary and the motorized classifiers
Acquiring classification results from the two information source
Aggregating classification results of frame- and peak-based features over the observed segment (simple voting scheme)
Computing the classification result of the segment-based features over the observed segment
Obtaining the final classification by combining the results of the two classifier outputs
Average of the two source

15. Classification Kinematic motion classifier (99%)
It utilizes the frame-based accelerometer features extracted from each window to distinguish between pedestrian and other modalities
It uses decision trees with depth one
It captures the repetitive nature of walking, typically with 1 – 3s interval

16. Classification Stationary classifier (90%)
It uses both the peak features and the frame-based features for distinguishing between stationary and motorized periods
15 weak learners, each comprising a decision tree of depth two

17. Classification Motorized classifier (80%)
It is responsible for distinguishing between different motorized transportation modalities
20 weak leaners, decision trees of depth two

18. Classification Motorized classifier (80%)
Car, bus, tram vs. train, metro
The frequency of acceleration and breaking peaks
car vs. other
the intensity, length of the acceleration and breaking period
tram vs. other
the intensity, volume of acceleration and breaking periods
Frame-based features to distinguish vehicles on roads and rails
it can capture characteristics of vertical movement as well as overall noisiness of the measurements

19. Evaluation

20. Conclusion
A novel accelerometer techniques for transportation mode detection on smartphones
This generalizes well across user and geographic locations
Critics
Performance evaluation (estimation delay) is nowhere
The detailed algorithms or information about classifier does not exist
It is needed to compare other accelerometer-based mode detection algorithm