close
Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Apr 13;20(8):2189.
doi: 10.3390/s20082189.

An Activity-Aware Sampling Scheme for Mobile Phones in Activity Recognition

Zhimin Chen  1 , Jianxin Chen  1 , Xiangjun Huang  1
Affiliations

An Activity-Aware Sampling Scheme for Mobile Phones in Activity Recognition

Zhimin Chen et al. Sensors (Basel). .

Abstract

In recent years, sensors in smartphones have been widely used in applications, e.g., human activity recognition (HAR). However, the power of smartphone constrains the applications of HAR due to the computations. To combat it, energy efficiency should be considered in the applications of HAR with smartphones. In this paper, we improve energy efficiency for smartphones by adaptively controlling the sampling rate of the sensors during HAR. We collect the sensor samples, depending on the activity changing, based on the magnitude of acceleration. Besides that, we use linear discriminant analysis (LDA) to select the feature and machine learning methods for activity classification. Our method is verified on the UCI (University of California, Irvine) dataset; and it achieves an overall 56.39% of energy saving and the recognition accuracy of 99.58% during the HAR applications with smartphone.

Keywords: activity recognition; feature selection; machine learning; power consumption.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Energy-efficient activity recognition system.
Figure 2
Figure 2
Sensor importance for classifying activities.
Figure 3
Figure 3
Energy consumption for smartphone between 2 h.
Figure 4
Figure 4
Recognition with a different sampling rate.
Figure 5
Figure 5
Curve of acceleration change (before preprocessing).
Figure 6
Figure 6
Curve of acceleration change (after preprocessing).
Figure 7
Figure 7
Box-plot of angle between the x-axis and Gravity_mean (before preprocessing).
Figure 8
Figure 8
Box-plot of angle between the x-axis and Gravity mean (after preprocessing).
Figure 9
Figure 9
Confusion matrix of a support vector machine (SVM) classifier with linear kernel.
See this image and copyright information in PMC

References

    1. Lara D., Labrador M. A Survey on Human Activity Recognition using Wearable Sensors. IEEE Commun. Surv. Tutor. 2013;15:1192–1209. doi: 10.1109/SURV.2012.110112.00192. - DOI
    1. Foerster F., Smeja M., Fahrenberg J. Detection of posture and motion by accelerometry: A validation study in ambulatory monitoring. Comput. Hum. Behav. 1999;15:571–583. doi: 10.1016/S0747-5632(99)00037-0. - DOI
    1. Anjum A., Ilyas M. Activity recognition using smartphone sensors; Proceedings of the Consumer Communications and Networking Conference; Las Vegas, NV, USA. 11–14 January 2013; pp. 914–919.
    1. Chen Y., Chen C. Performance analysis of smartphone-sensor behavior for human activity recognition. IEEE Access. 2017;5:3095–3110. doi: 10.1109/ACCESS.2017.2676168. - DOI
    1. Buenaventura C., Tiglao N. Basic human activity recognition based on sensor fusion in smartphones; Proceedings of the Integrated Network and Service Management; Lisbon, Portugal. 8–12 May 2017; pp. 1182–1185.

LinkOut - more resources