Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 Oct 24;18(11):3612.
doi: 10.3390/s18113612.

On-Body Sensor Positions Hierarchical Classification

Affiliations
Free PMC article

On-Body Sensor Positions Hierarchical Classification

Vu Ngoc Thanh Sang et al. Sensors (Basel). .
Free PMC article

Abstract

Many motion sensor-based applications have been developed in recent years because they provide useful information about daily activities and current health status of users. However, most of these applications require knowledge of sensor positions. Therefore, this research focused on the problem of detecting sensor positions. We collected standing-still and walking sensor data at various body positions from ten subjects. The offset values were removed by subtracting the sensor data of standing-still phase from the walking data for each axis of each sensor unit. Our hierarchical classification technique is based on optimizing local classifiers. Many common features are computed, and informative features are selected for specific classifications. In this approach, local classifiers such as arm-side and hand-side discriminations yielded F1-scores of 0.99 and 1.00, correspondingly. Overall, the proposed method achieved an F1-score of 0.81 and 0.84 using accelerometers and gyroscopes, respectively. Furthermore, we also discuss contributive features and parameter tuning in this analysis.

Keywords: feature selection; fractal dimension; hierarchical classification; inertial measurement unit; sensor position.

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Overview of sensor position classification.
Figure 2
Figure 2
Target positions used in this study, FB: forward and backward, TA: toward and away, ML: medial and lateral.
Figure 3
Figure 3
The flows of data in preprocessing stage.
Figure 4
Figure 4
First 25 s of raw and the preprocessed data from the accelerometer at right thigh of one subject.
Figure 5
Figure 5
An overlapping sliding window creates more patterns than a non-overlapping sliding window.
Figure 6
Figure 6
The hierarchical classification body-segment approach (left) and body-side approach (right).
Figure 7
Figure 7
The comparison of final results based on different hierarchical classifiers.
Figure 8
Figure 8
The boxplot for hand sides of all subject using accelerometer and gyroscope.

Similar articles

See all similar articles

Cited by 2 articles

References

    1. Shi D., Wang R., Wu Y., Mo X., Wei J. A novel orientation- and location-independent activity recognition method. Pers. Ubiquitous Comput. 2017;21:427–441. doi: 10.1007/s00779-017-1007-3. - DOI
    1. Godfrey A. Wearables for independent living in older adults: Gait and falls. Maturitas. 2017;100:16–26. doi: 10.1016/j.maturitas.2017.03.317. - DOI - PubMed
    1. Morales J., Akopian D. Physical activity recognition by smartphones, a survey. Biocybern. Biomed. Eng. 2017;37:388–400. doi: 10.1016/j.bbe.2017.04.004. - DOI
    1. Pannurat N., Thiemjarus S., Nantajeewarawat E., Anantavrasilp I. Analysis of Optimal Sensor Positions for Activity Classification and Application on a Different Data Collection Scenario. Sensors. 2017;17:774 doi: 10.3390/s17040774. - DOI - PMC - PubMed
    1. Shoaib M., Bosch S., Incel O., Scholten H., Havinga P. A Survey of Online Activity Recognition Using Mobile Phones. Sensors. 2015;15:2059–2085. doi: 10.3390/s150102059. - DOI - PMC - PubMed
Feedback