Data analyzing and daily activity learning with hidden Markov model
GuoQing Yin, Dietmar Bruckner · 2010
To observe and analyze person's daily activities, and build the activities model is an important task in an intelligent environment. In an Ambient Assisted Living (AAL) project we get sensor data from a motion detector. At first we translate and reduce the raw data to state data. Secondly using hidden Markov model, forward algorithm, and Viterbi Algorithm to analyze the data and build the person's daily activity model. Comparing individual observation with the build model to find out best and worst (abnormal) activities.