The simulation of open one-side uncertain probability for fusion model of data uncertainty and data relation uncertainty

Uncertain big data has become increasingly important in our life, since uncertainties exist in data generation/acquisition, physical measurements and data staling. Thus, in this paper, we aim to create a unified mathematical model between data uncertainties and data relation uncertainties, which are both important aspects of uncertain big data. We first proposed the fusion model of data uncertainty and data relation uncertainty, which consists of data uncertainty model and data relation uncertainty model. Then we defined two fundamental forms for data uncertainty model and two fundamental forms for fusion model, which are open uncertainty, closed uncertainty and one-side uncertainty, coupling uncertainty respectively. After that we picked a part of the fusion model called open one-side uncertainty to discuss. We studied the open one-side uncertainty under both continuous distribution assumption and discrete distribution assumption, and obtained the expressions for reverse probability respectively. Last but not least, we simulated our model and acquired the averaged values of relative error and absolute error under two kinds of distribution assumption, which are around 0.5% and 0.1% respectively. Finally, we concluded that our model is correct and feasible while the simulation program is efficient as well.