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
. 2025 Jun 13;25(12):3704.
doi: 10.3390/s25123704.

LightGBM-Based Human Action Recognition Using Sensors

Yinuo Liu  1 , Ziwei Chen  2
Affiliations

LightGBM-Based Human Action Recognition Using Sensors

Yinuo Liu et al. Sensors (Basel). .

Abstract

In recent years, research on human activity recognition (HAR) on smartphones has received extensive attention due to its portability. However, the discrimination issues between similar activities such as leaning forward and walking forward, as well as going up and down stairs, are hard to deal with. This paper conducts HAR based on the sensors of smartphones, i.e., accelerometers and gyroscopes. First, a feature extraction method for sensor data from both the time domain and frequency domain is designed to obtain more than 300 features, aiming to enhance the accuracy and stability of recognition. Then, the LightGBM (version 4.5.0) algorithm is utilized to comprehensively analyze the above-mentioned extracted features, with the goal of improving the accuracy of similar activity recognition. Through simulation experiments, it is demonstrated that the feature extraction method proposed in this paper has improved the accuracy of HAR. Compared with classical machine learning algorithms such as random forest (version 1.5.2) and XGBoost (version 2.1.3), the LightGBM algorithm shows improved performance in terms of the accuracy rate, which reaches 94.98%. Moreover, after searching for the model parameters using grid search, the prediction accuracy of LightGBM can be increased to 95.35%. Finally, using feature selection and dimensionality reduction, the efficiency of the model is further improved, achieving a 70.14% increase in time efficiency without reducing the accuracy rate.

Keywords: LightGBM; feature selection; human activity recognition.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Algorithm block diagram.
Figure 2
Figure 2
Feature contributions.
Figure 3
Figure 3
LightGBM hyperparameter optimization.
Figure 4
Figure 4
Confusion matrix.
See this image and copyright information in PMC

References

    1. Islam S.M.M., Talukder K.H. Exploratory Analysis of Smartphone Sensor Data for Human Activity Recognition. IEEE Access. 2023;11:99481–99498. doi: 10.1109/ACCESS.2023.3314651. - DOI
    1. Zuo K., Li X., Dong Y., Dezert J., Ge S.S. Combination of Different-Granularity Beliefs for Sensor-Based Human Activity Recognition. IEEE Sens. J. 2023;23:12309–12319. doi: 10.1109/JSEN.2023.3266609. - DOI
    1. Wu B., Ma C., Poslad S., Selviah D.R. An Adaptive Human Activity-Aided Hand-Held Smartphone-Based Pedestrian Dead Reckoning Positioning System. Remote Sens. 2021;13:2137. doi: 10.3390/rs13112137. - DOI
    1. Javed A.R., Sarwar M.U., ur Rehman S., Khan H.U., Al-Otaibi Y.D., Alnumay W.S. PP-SPA: Privacy Preserved Smartphone-Based Personal Assistant to Improve Routine Life Functioning of Cognitive Impaired Individuals. Neural Process. Lett. 2023;55:35–52. doi: 10.1007/s11063-020-10414-5. - DOI
    1. Khatun M.A., Yousuf M.A., Ahmed S., Uddin M.Z., Alyami S.A., Al-Ashhab S., Akhdar H.F., Khan A., Azad A., Ali Mon M. Deep CNN-LSTM With Self-Attention Model for Human Activity Recognition Using Wearable Sensor. IEEE J. Transl. Eng. Health Med. 2022;10:2700316. doi: 10.1109/JTEHM.2022.3177710. - DOI - PMC - PubMed

LinkOut - more resources