A method of tracking a service queue using a single-point signal monitor in which at least one customer carries a wireless device may include: receiving a received signal strength from the wireless device as a trace; identify first segments of the trace containing mostly positive sloped received signal strength; identify second segments of the trace containing mostly negative sloped received signal; extract attributes from the first and second segments as child variables for two parent nodes in a Bayesian Network in which the two parent nodes respectively model a beginning of service and a leaving period for a service queue; and inputting the extracted attributes into Bayesian Network; and determining a beginning of service and leaving period using the Bayesian Network. The method may also include determining critical time points in a trace using a K-L divergence technique.