Gazelle: Energy-Efficient Wearable Analysis for Running

Running is one of the most popular sports with hundreds of millions of participants worldwide. Good running form is the key to fast, efficient, and injury-free running. Existing kinematic analysis technologies, such as high-speed camera systems, are expensive, difficult to operate, and exclusive to sports physiology laboratories and elite athletes. Miniature MEMS-based motion sensors enable portable high-precision kinematic analysis, but suffer from high energy consumption hence short battery lifetime, especially for continued online analysis for running. This paper presents Gazelle, a wearable online analysis system for running that is compact, lightweight, accurate, and highly energy efficient; intended for runners of all levels. To enable long-term maintenance-free mobile analysis for running, Sparse Adaptive Sensing (SAS) is proposed, which selectively identifies the best sampling points to maintain high accuracy while greatly reducing sensing and analysis energy overheads. Experimental results demonstrate 97.7 percent accuracy with 76.9 to 99 percent reduced energy consumption (83.6 percent average reduction under real-world testing)-a one-order-of-magnitude improvement over existing solutions. SAS enables $>$ 200 days of continuous high-precision operation using only a coin-cell battery. Since 2014, Gazelle has been used by over 100 elite and recreational runners during daily training and at top-level races like the Kona Ironman World Championships and New York Marathon.

[1]  E.J. Candes,et al.  An Introduction To Compressive Sampling , 2008, IEEE Signal Processing Magazine.

[2]  T. Rantalainen,et al.  Running in a minimalist and lightweight shoe is not the same as running barefoot: a biomechanical study , 2013, British Journal of Sports Medicine.

[3]  Sean T. Miller,et al.  Validating the Adidas miCoach for estimating pace, distance, and energy expenditure during outdoor over-ground exercise accelerometer , 2012 .

[4]  Vivek K. Goyal,et al.  Backward Adaptation for Power Efficient Sampling , 2014, IEEE Transactions on Signal Processing.

[5]  D. I. Miller,et al.  Ground reaction forces in running: a reexamination. , 1987, Journal of biomechanics.

[6]  Yi Wang,et al.  A framework of energy efficient mobile sensing for automatic user state recognition , 2009, MobiSys '09.

[7]  Tao Liu,et al.  Three-dimensional gait analysis system with mobile force plates and motion sensors , 2011, 2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI).

[8]  Ye Wang,et al.  Reducing the Power Consumption of an IMU-Based Gait Measurement System , 2012, PCM.

[9]  Jay Dicharry,et al.  A three-dimensional kinematic and kinetic comparison of overground and treadmill walking in healthy elderly subjects. , 2010, Clinical biomechanics.

[10]  Joonbum Bae.  Gait analysis based on a hidden Markov model , 2012, 2012 12th International Conference on Control, Automation and Systems.

[11]  Muriel Medard,et al.  Locally Adaptive Sampling , 2010, 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[12]  Gerhard Tröster,et al.  Out of the lab and into the woods: kinematic analysis in running using wearable sensors , 2011, UbiComp '11.

[13]  Shyamal Patel,et al.  Mercury: a wearable sensor network platform for high-fidelity motion analysis , 2009, SenSys '09.

[14]  Vivek K. Goyal,et al.  Time-Stampless Adaptive Nonuniform Sampling for Stochastic Signals , 2012, IEEE Transactions on Signal Processing.

[15]  Andreu Català,et al.  A Wearable Inertial Measurement Unit for Long-Term Monitoring in the Dependency Care Area , 2013, Sensors.

[16]  Majid Sarrafzadeh,et al.  Smart insole: a wearable system for gait analysis , 2012, PETRA '12.

[17]  I. Davis,et al.  Foot strike patterns and collision forces in habitually barefoot versus shod runners , 2010, Nature.

[18]  Begonya Garcia-Zapirain,et al.  Gait Analysis Methods: An Overview of Wearable and Non-Wearable Systems, Highlighting Clinical Applications , 2014, Sensors.

[19]  Tarek F. Abdelzaher,et al.  SATIRE: a software architecture for smart AtTIRE , 2006, MobiSys '06.

[20]  Stéphane Mallat,et al.  An approximation tour , 1999 .

[21]  D R Bassett,et al.  Validity of the Nike+Device During Walking and Running , 2009, International journal of sports medicine.

[22]  D. Lieberman,et al.  Foot strike and injury rates in endurance runners: a retrospective study. , 2012, Medicine and science in sports and exercise.

[23]  Wilhelm Braune,et al.  Versuche am unbelasteten und belasteten Menschen , 1895 .

[24]  Youngki Lee,et al.  SeeMon: scalable and energy-efficient context monitoring framework for sensor-rich mobile environments , 2008, MobiSys '08.

[25]  Aleksandar Milenkovic,et al.  mHealth @ UAH: computing infrastructure for mobile health and wellness monitoring , 2013, XRDS.

[26]  Momcilo Bogdanov,et al.  A Simple Adaptive Sampling Algorithm , .

[27]  Shaw Bronner,et al.  Comparison of steps and energy expenditure assessment in adults of Fitbit Tracker and Ultra to the Actical and indirect calorimetry , 2013, Journal of medical engineering & technology.

[28]  U. Croce,et al.  A kinematic and kinetic comparison of overground and treadmill walking in healthy subjects. , 2007, Gait & posture.

[29]  Vigneshwaran Subbaraju,et al.  Energy-Efficient Continuous Activity Recognition on Mobile Phones: An Activity-Adaptive Approach , 2012, 2012 16th International Symposium on Wearable Computers.

[30]  Gerhard Tröster,et al.  A Data-Driven Approach to Kinematic Analysis in Running Using Wearable Technology , 2012, 2012 Ninth International Conference on Wearable and Implantable Body Sensor Networks.

[31]  P. Weyand,et al.  Faster top running speeds are achieved with greater ground forces not more rapid leg movements. , 2000, Journal of applied physiology.

[32]  Paul Lukowicz,et al.  Human tracking and identification using a sensitive floor and wearable accelerometers , 2013, 2013 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[33]  W. A. Sparrow,et al.  Identifying Heel Contact and Toe-Off Using Forceplate Thresholds with a Range of Digital-Filter Cutoff Frequencies , 2003 .

[34]  A.Y. Benbasat,et al.  Design of a real-time adaptive power optimal system , 2004, Proceedings of IEEE Sensors, 2004..

[35]  Namita Mittal,et al.  Identification of spatio-temporal and kinematics parameters for 2-D optical gait analysis system using passive markers , 2015, 2015 International Conference on Advances in Computer Engineering and Applications.

[36]  Talle Shridevi Ashok,et al.  Kinematic study of video gait analysis , 2015, 2015 International Conference on Industrial Instrumentation and Control (ICIC).

[37]  C. Senanayake,et al.  Human assisted tools for gait analysis and intelligent gait phase detection , 2009, 2009 Innovative Technologies in Intelligent Systems and Industrial Applications.

[38]  Daibashish Gangopadhyay,et al.  Compressed Sensing System Considerations for ECG and EMG Wireless Biosensors , 2012, IEEE Transactions on Biomedical Circuits and Systems.

[39]  Inseok Hwang,et al.  E-Gesture: a collaborative architecture for energy-efficient gesture recognition with hand-worn sensor and mobile devices , 2011, SenSys.

[40]  David Atienza,et al.  A real-time compressed sensing-based personal electrocardiogram monitoring system , 2011, 2011 Design, Automation & Test in Europe.