Abstract: An important application of pervasive computing is to obtain the electricity usage information for each appliance in a household using one sensor. The key problem of this application is current disaggregating, which is to estimate the currents of individual appliances from the total current waveform. Existing methods to solve this problem can be classified into two classes: steady-state estimation methods and linear disaggregating methods. Based on the steady-state load assumption, the methods in the first class estimate the current for a running appliance using its steady-state current waveform. These methods can avoid the interference between appliances. But the results of these methods cannot reflect the real-time changes of the total current. The methods in the second class reduce the dimensions of the current waveforms for a specific appliance using model constraints or data constraints, and disaggregate the total current into the linear spaces with low dimensions. The results of these methods can reflect the real-time change of the total current, but similar appliances reduce the accuracy of disaggregating results. From the perspective of the Bayesian statistics, this paper relaxes the key assumptions of the above methods as the prior of position vectors and the prior of noises, and proposes a Bayesian current disaggregating method based these two priors. Using the electricity usage data generated by actual appliances, we conduct several simulation experiments to evaluate our method. The experiment results show that the accuracy of the proposed method is higher than previous methods. Our method not only reflects the real-time change of the total current, but also reduces the effects of similar appliances on the disaggregating results.