Stochastic analysis of smart home user activities

This paper attempts to formulate the behavioral pattern of smart homes user activities. Smart homes depend on effective representation of residents´ activities into ubiquitous computing elements. User activities inside a home follow specific temporal patterns, which are predictable utilizing statistical analysis. This paper intended to develop a temporal learning algorithm to find out the time difference between residents´ activities in smart homes. A temporal algorithm is proposed to incrementally construct a temporal database, which is used to predict the time of next activity of the residents employing central limit theory of statistical probability. The algorithm exhibits 88.3% to 95.3% prediction accuracies for different ranges of mean and standard deviations when verified by practical smart home data. Further stochastic analyses prove that the time difference between the residents´ activities follows normal distribution, which was merely an assumption previously.