Temporal Bayesian Network of Events for Diagnosis and Prediction in Dynamic Domains

Abstract

In some domains like industry, medicine, communications, speech recognition, planning, tutoring systems, and forecasting; the timing of observations (symptoms, measures, test, events, as well as faults) play a major role in diagnosis and prediction. This paper introduces a new formalism to deal with uncertainty and time using Bayesian networks called Temporal Bayesian Network of Events (TBNE). In a TBNE each node represents an event or state change of a variable, and an arc corresponds to a causal-temporal relationship. A temporal node represents the time that a variable changes state, including an option of no-change. The temporal intervals can differ in number and size for each temporal node, so this allows multiple granularity. Our approach is contrasted with a Dynamic Bayesian network for a simple medical example. An empirical evaluation is presented for a subsystem of a thermal power plant, in which this approach is used for fault diagnosis and event prediction with good results. The TBNE model can be used for the diagnosis of a cascade of anomalies arising with certain delays; this situation is typical in the diagnosis of medical and industrial processes.

Discovering human immunodeficiency virus mutational pathways using temporal Bayesian networks

“…Whenever temporal changes occur infrequently, the DBN representation becomes unnecessarily over expressive. One alternative are temporal nodes Bayesian networks [25].…”

“…A TNBN [25,26] is composed by a set of TNs connected by arcs representing a probabilistic relationship between TNs. A TN, v i , is a random variable characterized by a set of states S. Each state is defined by an ordered pair S = (λ, τ ), where λ is the particular value taken by v i during its associated interval τ = [a, b], corresponding to the time interval in which the state changes, i.e.…”

“…The following is an example of a TNBN based on [25], its corresponding graphical representation is shown in Figure 1. Each node in the TNBN has a conditional probability table.…”

Automatic Scenario Recognition for Visual-Surveillance by Combining Probabilistic Graphical Approaches

“…It assumes a Markov property by considering that a single snapshot in the past is sufficient for predicting the future. A second category, represents the "event-based approach" also known as the "interval based approach", which allows the integration of specific nodes associated to temporal information like in (Figueroa, 1999) by the Temporal Nodes Bayesian Networks (TNBN), or Net of Irreversible Events in Discrete Time (NIEDT) (Galan & Diez, 2000). In these networks, nodes represent events that can take place at a certain time interval.…”

Temporal Bayesian Networks for Scenario Recognition

“…The second category, less explored, represents the "event based" approach which permits to integrate explicitly temporal nodes (Temporal Nodes Bayesian Networks (TNBN) [14] and Net of Irreversible Events in Discrete Time (NIEDT) [15]. This second category of approaches has several advantages.…”