Binary sensor systems in homeland security, military, QC, and medical applications

Abstract

Binary sensor systems are various types of analog sensors (optical, MEMS, X-ray, gamma-ray, acoustic, electronic, etc.), based on the binary decision process. Typical examples of such "binary sensors" are X-ray luggage inspection systems, product quality control systems, automatic target recognition systems, numerous medical diagnostic systems, and many others. In all these systems, the binary decision process provides only two mutually exclusive responses: "signal" and "noise." There are also two types of key parameters that characterize either system (such as false positive and false negative), or a priori external-to-system conditions (such as absolute probabilities). In this paper, by using a strong medical analogy, we analyze a third type of key parameter that combines both system-like and a priori information, in the form of so called Bayesian Figures of Merit, and we show that the latter parameter, in the best way, characterizes a binary sensor system.

Bayesian truthing and experimental validation in homeland security and defense

“…So far we have discussed only direct conditional probabilities. However, Bayes has also introduced inverse conditional probabilities, such as p(S|S'), actually denoted as the PPV [1][2][3][4]7] , based on Bayes Theorem [5] . It is easy to show that our natural questions are formulated in terms of the PPV, rather than in terms of equivalent direct probability, p(S'|S), as illustrated by the following medical diagnosis situation.…”

“…In this paper, for the sake of clarity, we comprehensively discuss only two characteristic examples: X-ray luggage inspection for explosives (Refs. [2][3]) and (night vision) active ATR, as an optical example. In addition, a number of numerical examples show the simple mathematical methodology of Bayesian Truthing and the generality of the "Target as Anomalous Event embedded in noise/clutter" concept.…”

“…In this paper, we discuss relationships among Bayesian Truthing (experimental validation), Bayesian statistics in general, and Binary Sensing [1][2][3][4] , in the context of selected Homeland Security and ISR optical and nonoptical application scenarios. Of course, any Intelligence, Surveillance, Reconnaissance (ISR) method requires some kind of experimental validation.…”

“…For all these "target recognition" methods, the Bayesian Figure of Merit (FoM) is the so-called Positive Predictive Value (PPV), originally introduced in medicine for Xray breast cancer diagnosis (mammography) [8] , including the doctor's ranking. The PPV has a simple definition of a ratio of the number of true alarms to the total number of alarms [1][2][3][4] , which, in fact, does not require knowledge of Bayesian statistics.…”

“…The concept of Bayesian Truthing is based on Binary Sensing [1][2][3][4] and "statistical quanta," to be "integrative" [9] , being applicable to a multitude of diversified areas. In this paper, for the sake of clarity, we comprehensively discuss only two characteristic examples: X-ray luggage inspection for explosives (Refs.…”