Robust human intensity-varying activity recognition using Stochastic Approximation in wearable sensors Conference Paper uri icon


  • Detecting human activity independent of intensity is essential in many applications, primarily in calculating metabolic equivalent rates (MET) and extracting human context awareness from on-body inertial sensors. Many classifiers that train on an activity at a subset of intensity levels fail to classify the same activity at other intensity levels. This demonstrates weakness in the underlying activity model. Training a classifier for an activity at every intensity level is also not practical. In this paper we tackle a novel intensity-independent activity recognition application where the class labels exhibit large variability, the data is of high dimensionality, and clustering algorithms are necessary. We propose a new robust Stochastic Approximation framework for enhanced classification of such data. Experiments are reported for each dataset using two clustering techniques, K-Means and Gaussian Mixture Models. The Stochastic Approximation algorithm consistently outperforms other well-known classification schemes which validates the use of our proposed clustered data representation. 2013 IEEE.

name of conference

  • 2013 IEEE International Conference on Body Sensor Networks (BSN)

published proceedings

  • 2013 IEEE International Conference on Body Sensor Networks

author list (cited authors)

  • Alshurafa, N., Xu, W., Liu, J. J., Huang, M., Mortazavi, B., Sarrafzadeh, M., & Roberts, C.

citation count

  • 17

complete list of authors

  • Alshurafa, Nabil||Xu, Wenyao||Liu, Jason J||Huang, Ming-Chun||Mortazavi, Bobak||Sarrafzadeh, Majid||Roberts, Christian

publication date

  • May 2013