Comparison of Methods for Determining Activity from Physical Movements

Year 2021, , 17 - 23, 01.03.2021

Mücahit Çalışan , Muhammed Fatih Talu

https://doi.org/10.2339/politeknik.632070

Cited By: 3

Abstract

In this study, the methods which can detect the basic physical movements of a person (downward, upward, sitting, stop, walking, running) from inertial sensor (IMU) data are evaluated. The performances of classical (ANN, SVM, k-NN) and current approaches (Convolutional Neural Networks-ESA) to map IMU data to activity classes were compared. A three-stage study was carried out for this aim: 1) data acquisition; 2) creating training/test sets; 3) construction and classification of network architectures. At the stage of data acquisition, to obtain 6 different physical movements from 10 different people, the accelerometer sensor is placed on the persons. Repetitive movements of persons were recorded. At the second stage, the recorded long-term accelerometer data is divided into packages in the form of short-term windows. The training set of classical approaches was constructed by features extracting from each packet data containing one-dimensional acceleration information. The transformation of one-dimensional signals to a two-dimensional image matrix for the training set of the deep learning-based approaches was performed. In the third stage, ANN, SVM, k-NN and CNN architectures were constructed, and classification process was carried out. As a result of the experimental studies, it was found that the accuracy of IMU-activity mapping was 99% with the ANN method and 95% with the CNN method.

Keywords

Physical movement, determining activity, IMU, ANN, CNN

Comparison of Methods for Determining Activity from Physical Movements

Abstract

In this study, the
methods which can detect the basic physical movements of a person (downward,
upward, sitting, stop, walking, running) from inertial sensor data are evaluated.
The performances of classical and current approaches to map IMU data to
activity classes were compared. A three-stage study was carried out for this
aim: 1) data acquisition; 2) creating training/test sets; 3) construction and
classification of network architectures. At the stage of data acquisition, to
obtain 6 different physical movements from 10 different people, the
accelerometer sensor is placed on the persons. Repetitive movements of persons
were recorded. At the second stage, the recorded long-term accelerometer data
is divided into packages in the form of short-term windows. The training set of
classical approaches was constructed by features extracting from each packet
data containing one-dimensional acceleration information. The transformation of
one-dimensional signals to a two-dimensional image matrix for the training set
of the deep learning-based approaches was performed. In the third stage, ANN,
SVM, k-NN and CNN architectures were constructed, and classification process
was carried out. As a result of the experimental studies, it was found that the
accuracy of IMU-activity mapping was 99% with the ANN method and 95% with the
CNN method.

Keywords

Physical Movement, Determining Activity, IMU, ANN, CNN

References

• [1] N. D. Lane, E. Miluzzo, H. Lu, D. Peebles, T. Choudhury, and A. T. Campbell, “A survey of mobile phone sensing,” IEEE Commun. Mag., 2010.
• [2] W. Zijlstra and K. Aminian, “Mobility assessment in older people: New possibilities and challenges,” European Journal of Ageing. 2007.
• [3] D. Roetenberg, P. J. Slycke, and P. H. Veltink, “Ambulatory position and orientation tracking fusing magnetic and inertial sensing,” IEEE Trans. Biomed. Eng., 2007.
• [4] P. Prasertsung and T. Horanont, “A classification of accelerometer data to differentiate pedestrian state,” in 20th International Computer Science and Engineering Conference: Smart Ubiquitos Computing and Knowledge, ICSEC 2016, 2017.
• [5] X. Su, H. Tong, and P. Ji, “Activity recognition with smartphone sensors,” Tsinghua Sci. Technol., 2014.
• [6] U. Lindemann, A. Hock, M. Stuber, W. Keck, and C. Becker, “Evaluation of a fall detector based on accelerometers: A pilot study,” Med. Biol. Eng. Comput., 2005.
• [7] E. Jovanov, A. Milenkovic, C. Otto, and P. C. De Groen, “A wireless body area network of intelligent motion sensors for computer assisted physical rehabilitation,” J. Neuroeng. Rehabil., 2005.
• [8] E. A. Sağbaş and S. Balli, “Akıllı telefon algılayıcıları ve makine öğrenmesi kullanılarak ulaşım türü tespiti Transportation mode detection by using smartphone sensors and machine learning,” Pamukkale Univ Muh Bilim Derg, 2016.
• [9] J. R. Kwapisz, G. M. Weiss, and S. A. Moore, “Activity recognition using cell phone accelerometers,” ACM SIGKDD Explor. Newsl., 2011.
• [10] M. Shoaib, S. Bosch, H. Scholten, P. J. M. Havinga, and O. D. Incel, “Towards detection of bad habits by fusing smartphone and smartwatch sensors,” in 2015 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2015, 2015.
• [11] D. Natarajasivan and M. Govindarajan, “Filter Based Sensor Fusion for Activity Recognition using Smartphone,” Int. J. Comput. Sci. Telecommun. J. Homepage, 2016.
• [12] F. Dadashi et al., “A hidden Markov model of the breaststroke swimming temporal phases using wearable inertial measurement units,” in 2013 IEEE International Conference on Body Sensor Networks, BSN 2013, 2013.
• [13] B. J. Mortazavi, M. Pourhomayoun, G. Alsheikh, N. Alshurafa, S. I. Lee, and M. Sarrafzadeh, “Determining the single best axis for exercise repetition recognition and counting on smartwatches,” in Proceedings - 11th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2014, 2014.
• [14] J. J. Guiry, P. van de Ven, and J. Nelson, “Multi-sensor fusion for enhanced contextual awareness of everyday activities with ubiquitous devices,” Sensors (Switzerland), 2014.
• [15] G. M. Weiss, J. L. Timko, C. M. Gallagher, K. Yoneda, and A. J. Schreiber, “Smartwatch-based activity recognition: A machine learning approach,” in 3rd IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2016, 2016.
• [16] “MTw Avinda Software.” [Online]. Available: https://www.xsens.com/mt-software-suite-mtw-awinda/. [Accessed: 10-Dec-2018].
• [17] X. Xin, C. Wang, X. Ying, and B. Wang, “Deep community detection in topologically incomplete networks,” Phys. A Stat. Mech. its Appl., 2017.
• [18] S. E. Buttrey and C. Karo, “Using k-nearest-neighbor classification in the leaves of a tree,” Comput. Stat. Data Anal., 2002.
• [19] N. Hajibandeh, F. Faghihi, H. Ranjbar, and H. Kazari, “Classifications of disturbances using wavelet transform and support vector machine,” Turkish J. Electr. Eng. Comput. Sci., 2017.
• [20] S. M. S. Shah, S. Batool, I. Khan, M. U. Ashraf, S. H. Abbas, and S. A. Hussain, “Feature extraction through parallel Probabilistic Principal Component Analysis for heart disease diagnosis,” Phys. A Stat. Mech. its Appl., 2017.
• [21] R. Moraes, J. F. Valiati, and W. P. Gavião Neto, “Document-level sentiment classification: An empirical comparison between SVM and ANN,” Expert Syst. Appl., 2013.
• [22] D. P. Kingma and J. L. Ba, “Adam: A method for stochastic gradient descent,” ICLR Int. Conf. Learn. Represent., 2015.