Accelerometer vs. Electromyogram in Activity Recognition

Heli KOSKIMAKI, Pekka SIIRTOLA

Abstract


In this study, information from wearable sensors is used to recognize human activities. Commonly the approaches are based on accelerometer data while in this study the potential of electromyogram (EMG) signals in activity recognition is studied. The electromyogram data is used in two different scenarios: 1) recognition of completely new activities in real life and 2) to recognize the individual activities. In this study, it was shown that in gym settings electromyogram signals clearly outperforms the accelerometer data in recognition of completely new sets of gym movements from streaming data even though the sensors would not be positioned directly to the muscles trained. Nevertheless, in recognition of individual activities the EMG itself does not provide enough information to recognize activities accurately.

Keywords


Activity recognition; Wearable sensor; Acceleration; Electromyogram; Unseen activities

Full Text:

PDF

References


Banos, O., Damas, M., Pomares, H., Prieto, A., and Rojas, I., 2012. Daily living activity recognition based onstatistical feature quality group selection. Expert Systems with Applications, 39(9):8013–8021. https://doi.org/10.1016/j.eswa.2012.01.164

Bulling, A., Blanke, U., and Schiele, B., 2014. A Tutorial on Human Activity Recognition Using Body-wornInertial Sensors. ACM Comput. Surv., 46(3):33:1–33:33. ISSN 0360-0300. https://doi.org/10.1145/2499621

CCS Insight, 2016. www.ccsinsight.com/press/company-news/2516-wearables-momentum-continues.

Chang, K., Chen, M., and Canny, J., 2007. Tracking Free-Weight Exercises. UbiComp 2007: UbiquitousComputing, pages 19–37. https://doi.org/10.1007/978-3-540-74853-3_2

Cheng, H., Sun, F., Griss, M., Davis, P., and Li, D., J.and You, 2013. NuActiv: Recognizing Unseen NewActivities Using Semantic Attribute-based Learning. In Proceeding of the 11th Annual InternationalConference on Mobile Systems, Applications, and Services, MobiSys '13, pages 361–374. ACM, NewYork, NY, USA. ISBN 978-1-4503-1672-9. https://doi.org/10.1145/2462456.2464438 https://doi.org/10.1145/2462456.2464438

Devijver, P. A. and Kittler, J., 1982. Pattern recognition: A statistical approach, volume 761. Prentice-HallLondon.

Duda, R. O., Hart, P. E., and Stork, D. G., 2012. Pattern classification. John Wiley & Sons.

Holviala, J., Kraemer, W., Sillanpää, E., Karppinen, H., Avela, J., Kauhanen, A., Häkkinen, A., and Häkkinen,K., 2012. Effects of strength, endurance and combined training on muscle strength, walking speed anddynamic balance in aging men. European Journal of Applied Physiology, 112(4):1335–1347. ISSN 1439-6319. https://doi.org/10.1007/s00421-011-2089-7

Koskimäki, H., 2015. Avoiding Bias in Classification Accuracy - a Case Study for Activity Recognition. IEEESymposium on Computational Intelligence and Data Mining (accepted). https://doi.org/10.1109/ssci.2015.52

Koskimäki, H., Huikari, V., Siirtola, P., Laurinen, P., and Röning, J., 2009. Activity recognition using awrist-worn inertial measurement unit: a case study for industrial assembly lines. The 17th MediterraneanConference on Control and Automation, pages 401–405.

Koskimäki, H. and Siirtola, P., 2014. Recognizing gym exercises using acceleration data from wearable sensors. https://doi.org/10.1109/cidm.2014.7008685

Koskimäki, H. and Siirtola, P., 2016. Recognizing Unseen Gym Activities from Streaming Data-AccelerometerVs. Electromyogram. In Distributed Computing and Artificial Intelligence, 13th International Conference,pages 195–202. Springer International Publishing.

Morris, D., Saponas, T., Guillory, A., and Kelner, I., 2014. RecoFit: Using a Wearable Sensor to Find,Recognize, and Count Repetitive Exercises. Proceedings of ACM CHI. https://doi.org/10.1145/2556288.2557116

Muehlbauer, M., Bahle, G., and Lukowicz, P., 2011. What Can an Arm Holster Worn Smart Phone Do forActivity Recognition? 15th Annual International Symposium on Wearable Computers (ISWC), pages 79 –82.

Myo, 2016. https://www.myo.com/. Accessed: 2015-10-30.

Peng, H., Long, F., and Ding, C., 2005. Feature selection based on mutual information criteria of maxdependency,max-relevance, and min-redundancy. Pattern Analysis and Machine Intelligence, IEEETransactions on, 27(8):1226–1238. ISSN 0162-8828. https://doi.org/10.1109/TPAMI.2005.159

Siirtola, P., 2015. Recognizing human activities based on wearable inertial measurements: methods andapplications. Doctoral dissertation, Department of Computer Science and Engineering, University ofOulu, (Acta Univ Oul C 524).

Siirtola, P., Koskimäki, H., Huikari, V., Laurinen, P., and Röning, J., 2011. Improving the classification accuracyof streaming data using sax similarity features. Pattern Recognition Letters, 32(13):1659–1668. https://doi.org/10.1016/j.patrec.2011.06.025

Stiefmeier, T., Roggen, D., Tröster, G., Ogris, G., and Lukowicz, P., 2008. Wearable Activity Tracking in CarManufacturing. IEEE Pervasive Computing, 7(2):42–50. https://doi.org/10.1109/MPRV.2008.40

Weinswig, D., 2016. 16 global Retail Tech Trends at a glance. www.jda.com/-/media/jda/knowledge-center/white-papers/16-retail-trends-2016.ashx. Accessed: 2016-06-10.




DOI: http://dx.doi.org/10.14201/ADCAIJ2016533142





Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

Clarivate Analytics