The Academic Perspective Procedia publishes Academic Platform symposiums papers as three volumes in a year. DOI number is given to all of our papers.
Publisher : Academic Perspective
Journal DOI : 10.33793/acperpro
Journal eISSN : 2667-5862
Year :2019, Volume 2, Issue 3, Pages: 1051-1057
22.11.2019
Motion Type Verification Studies Using Accelerometer Sensor Data With Local Mean Decomposition
It is a significant improvement that the physical movements directly related to human physiology can be detected with high accuracy using sensors. In our study, three-axis accelerometer data recorded using a cell phone sensor in a controlled manner were used. Validation of walking, jogging, up-stairs, down-stair movements is aimed. For this purpose, local mean decomposition (LMD) function was used. The axis (x, y, z) in which the orthogonality value obtained from LMD was high was determined. Then, it was evaluated that there is movement in the direction of high value axis. While there is a high degree of accuracy in up-stair, down-stair and jogging movements, the desired success in walking movement was not achieved.
Keywords:
accelerometer, local mean decomposition, sensor, motion
References
[1] Malekzadeh M, Clegg RG, Cavallaro A, Haddadi H. Mobile sensor data anonymization.In Proceedings of the International Conference on Internet of Things Design andImplementation (IoTDI '19) 2019. ACM, New York, NY, USA, 49-58. DOI:https://doi.org/10.1145/3302505.3310068
[2] Smith J S. The local mean decomposition and its application to EEG perception data
[J]. JRSoc Interface, 2005; 2(5): 443-454.
[3] W. Sun, B. S. Xiong, J. P. Huang, et al. Fault diagnosis of a rolling bearing using waveletpacket de-nosing and LMD
[J]. Journal of Vibration and Shock, 2012, 31(18): 153-156.
[4] L. Li, Y. X. Zhang, T. F. Ming. An improved LMD algorithm and its application in bearingfault diagnosis
[J]. Journal of Vibration and Shock, 2016, 35(8): 183-186.
[5] H. J. Song, C. J. Huang, H. C. Liu. A new power quality disturbance detection methodbased on the improved LMD
[J]. Proceedings of CSEE, 2014, 34(10): 1700-1708.
[6] Y. Xiao and Y. Dong, Local mean decomposition algorithm improved by de-correlation,(CISP-BMEI), Datong, 2016;1206-1210. doi: 10.1109/CISP-BMEI.2016.7852898
[7] Benson, L.C., Clermont, C.A., Bošnjak, E., Ferber, R., The use of wearable devices forwalking and running gait analysis outside of the lab: A systematic review, Gait & Posture,2018;63:124–138.
[8] Baerg, S., Cairney, J., Hay, J., "Rempel, L., Mahlberg, N., Faught, B.E. Evaluating physicalactivity using accelerometry in children at risk of developmental coordination disorder inthe presence of attention deficit hyperactivity disorder", Research in DevelopmentalDisabilities 2011;32,1343–1350.
[9] Sztyler, T., Stuckenschmidt, H., Petrich, W., Position-aware activity
Cite
@article{acperproISITES2019ID117, author={Esas, Mustafa Yasin and Latifoğlu, Fatma}, title={Motion Type Verification Studies Using Accelerometer Sensor Data With Local Mean Decomposition}, journal={Academic Perspective Procedia}, eissn={2667-5862}, volume={2}, year=2019, pages={1051-1057}}
Esas, M. , Latifoğlu, F.. (2019). Motion Type Verification Studies Using Accelerometer Sensor Data With Local Mean Decomposition. Academic Perspective Procedia, 2 (3), 1051-1057. DOI: 10.33793/acperpro.02.03.117
%0 Academic Perspective Procedia (ACPERPRO) Motion Type Verification Studies Using Accelerometer Sensor Data With Local Mean Decomposition% A Mustafa Yasin Esas , Fatma Latifoğlu% T Motion Type Verification Studies Using Accelerometer Sensor Data With Local Mean Decomposition% D 11/22/2019% J Academic Perspective Procedia (ACPERPRO)% P 1051-1057% V 2% N 3% R doi: 10.33793/acperpro.02.03.117% U 10.33793/acperpro.02.03.117