New method for human activity recognition based on IMU sensors and digital speech processing theory
Abstract
This paper presents a new method for human activity recognition (HAR). Nowadays the biggest parts of HAR systems are relying on wearable IMU (inertial measurement unit) sensors. The common IMU sensors are accelerometer and gyroscope. These sensors are widespread in mobile devices such as smartphones and smart watches. Authors usually use real time signal features as inputs for classifiers that were calculated using only sliding windows. This paper proposes a new method based on speech-silence discrimination technique for detecting the beginning and the end of an activity. The presented method relies on short-time log energy (STLE) and cumulative sum of angle of STLE. Method was tested on two similar physical activities: squat and knee raise. This algorithm provides a 41.2% pre-classification accuracy, only by precise detection of the length of individual exercise states (start, intermediate, and finish position). Proposed method reduces complexity, classifying only activities when they were detected (not classifying pause between activities).
References
Bonnet V., Joukov V., Kulić D., Fraisse P., Ramdani N., and Venture G.: ‘Monitoring of Hip and Knee Joint Angles Using a Single Inertial Measurement Unit During Lower Limb Rehabilitation’, IEEE Sensors Journal, 2016, 16, (6), pp. 1557-1564.
Tao D., Jin L., Yuan Y., and Xue Y.: ‘Ensemble Manifold Rank Preserving for Acceleration-Based Human Activity Recognition’, IEEE Transactions on Neural Networks and Learning Systems, 2016, 27, (6), pp. 1392-1404.
Yurur O., Liu C.H., and Moreno W.: ‘Unsupervised posture detection by smartphone accelerometer’, Electronics Letters, 2013, 49, (8), pp. 562-564.
El-Shazly H., Abdelwahab M. M., Shimada A., and Taniguchi R.: ‘Early gesture recognition with adaptive window selection employing canonical correlation analysis for gaming’, Electronics Letters, 2016, 52, (16), pp. 1379-1381.
Yurur O., Liu C.H., Sheng Z., Leung V.C.M., Moreno W., and Leung K.K.: ‘Context-Awareness for Mobile Sensing: A Survey and Future Directions’, IEEE Communications Surveys & Tutorials, 2016, 18, (1), pp. 68-93.
Toth-Laufer E., and Varkonyi-Koczy A. R.: ‘A Soft ComputingBased Hierarchical Sport Activity Risk Level Calculation Model for Supporting Home Exercises’, IEEE Transactions on Instrumentation and Measurement, 2014, 63, (6), pp. 1400-1411.