<< Chapter < Page | Chapter >> Page > |
Some signals have no waveform. Consider the measurement of when lightning strikes occur within some region; the random processis the sequence of event times, which has no intrinsic waveform. Such processes are termed point processes , and have been shown (see Snyder ) to have simple mathematical structure. Define some quantities first.Let be the number of events that have occurred up to time (observations are by convention assumed to start at ). This quantity is termed the counting process, and has the shape of a staircase function: The counting functionconsists of a series of plateaus always equal to an integer, with jumps between plateaus occuring when events occur.The increment corresponds to the number of events in the interval . Consequently, . Theevent times comprise the random vector ; the dimension of this vector is , the number of events that have occured. The occurrence of events is governed by a quantityknown as the intensity of the point process through the probability law for sufficiently small . Note that this probability is a conditional probability; it can depend on how many events occurredpreviously and when they occurred. The intensity can also vary with time to describe non-stationary point processes. Theintensity has units of events, and it can be viewed as the instantaneous rate at which events occur.
The simplest point process from a structural viewpoint, the Poisson process, has no dependence on process history. Astationary Poisson process results when the intensity equals a constant: . Thus, in a Poisson process, a coin is flipped every seconds, with a constant probability of heads (an event) occuring that equals and is independent of the occurrence of past (and future) events. When this probability varies with time, theintensity equals , a non-negative signal, and a nonstationary Poison process results.
From the Poisson process's definition, we can derive the probability laws that govern event occurrence. These fall intotwo categories: the count statistics , the probability of obtaining events in an interval , and the time of occurrence statistics , the joint distribution of the first event times in the observation interval. These times form the vector , the occurrence time vector of dimension . From these two probability distributions, we can derive the sample function density.
We derive a differentio-difference equation that , , must satisfy for event occurrence in an interval to be regular and independent of event occurrences in disjointintervals. Let be fixed and consider event occurrence in the intervals and , and how these contribute to the occurrence of events in the union of the two intervals. If events occur in , then must occur in . Furthermore, the scenarios for different values of are mutually exclusive. Consequently,
Notification Switch
Would you like to follow the 'Statistical signal processing' conversation and receive update notifications?