A Machine Learning Approach for Posture Recognition Based on Simplified Shock Graph


Tahir N. M. , Hussain A., Samad S. A. , Husain H.

8th WSEAS Int Conference on Signal Processing/3rd WSEAS Int Symposium on Wavelets Theory and Applicat in Appl Math, Signal Proc and Modern Sci, İstanbul, Türkiye, 30 Mayıs - 01 Haziran 2009, ss.27-28 identifier

  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.27-28

Özet

In this paper, posture classification using Simplified Shock Graph as feature vectors based on two machine learning techniques namely Artificial Neural Network along with Support Vector Machine are investigated. Initial results showed that both classifiers are able to classify the four main postures with high recognition rate. Moreover, the tremendous performance of Support Vector Machine (SVM) as classifier Is confirmed based on the Kappa Score calculated. Initial findings have proven that SSG is apt as feature vectors for posture recognition whilst ANN and SVM were apposite to perform the classification task.