MyoBuddy: Detecting Barbell Weight Using Electromyogram Sensors

Muscular dystrophy is a group of genetic diseases that cause the loss of muscles and hence weakening the muscle strength. A typical treatment for muscular dystrophy patients is routinely performing weight exercise to slow down the loss in muscles. Thus, we propose a system MyoBuddy to help both physical therapists and patients to keep track of the weights in workout activities based on electromyography (EMG) sensors embedded in Myo armband. In our study, we collect 102 sessions of EMG data from barbell bicep curl exercise with a range of weights from 20 to 70 lbs with a 10-pound increment. Both Support Vector Machine and Random Forest algorithms are explored to classify which weight of barbells are lifted. At the end, we achieve 77.1% classification accuracy on average.

[1]  Hae Young Noh,et al.  Burnout: A Wearable System for Unobtrusive Skeletal Muscle Fatigue Estimation , 2016, 2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN).

[2]  Qian Zhang,et al.  Secret from Muscle: Enabling Secure Pairing with Electromyography , 2016, SenSys.

[3]  Alexius E G Sandoval Electrodiagnostics for low back pain. , 2010, Physical medicine and rehabilitation clinics of North America.

[4]  Dan Morris,et al.  RecoFit: using a wearable sensor to find, recognize, and count repetitive exercises , 2014, CHI.

[5]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[6]  Peter Kokol,et al.  Exercise repetition detection for resistance training based on smartphones , 2012, Personal and Ubiquitous Computing.

[7]  Wei Xi,et al.  FEMO: A Platform for Free-weight Exercise Monitoring with RFIDs , 2015, SenSys.

[8]  Majid Sarrafzadeh,et al.  Determining the Single Best Axis for Exercise Repetition Recognition and Counting on SmartWatches , 2014, 2014 11th International Conference on Wearable and Implantable Body Sensor Networks.

[9]  Martin L. Griss,et al.  NuActiv: recognizing unseen new activities using semantic attribute-based learning , 2013, MobiSys '13.

[10]  Hae Young Noh,et al.  MyoVibe: vibration based wearable muscle activation detection in high mobility exercises , 2015, UbiComp.

[11]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[12]  Carlo J. De Luca,et al.  The Use of Surface Electromyography in Biomechanics , 1997 .

[13]  J. Schwartz,et al.  Abstract MP11: Fitbit: An Accurate and Reliable Device for Wireless Physical Activity Tracking , 2015 .

[14]  Paul Lukowicz,et al.  Never skip leg day: A novel wearable approach to monitoring gym leg exercises , 2016, 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[15]  Kristof Van Laerhoven,et al.  myHealthAssistant: a phone-based body sensor network that captures the wearer's exercises throughout the day , 2011, BODYNETS.