A Mobile Based Activity Recog-nition Model

Abstract

In the last decade, activity recognition (AR) of humans via smart phones became important and attractive subject for scholars and developers in many areas from health care to real-time security systems. In this research, we worked on AR that based on data collected from Android-based smart phone's accelerometers held at waist region while performing different activities (i.e. walking, jogging, climbing stairs, downing stairs, sitting, and standing). To achieve this goal, six classification algorithms were performed: Naïve Bayes (NB), Multi Layer Perceptron (MLP), Bayes Network (BN), Sequential Minimal Optimization (SMO), Kstar, and Decision Tree (DT). Experimental results of the six models were illustrated and analyzed. Comparison results declare that MLP algorithm outperforms other algorithms.