Bayesian truthing as experimental verification of C4ISR sensors

Jannson, Tomasz; Forrester, Thomas; Romanov, V. I.; Wang, Wenjian; Nielsen, Thomas A.; Kostrzewski, Andrew A.

doi:10.1117/12.2086999

Cited by 3 publications

(9 citation statements)

References 4 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Catastrophes provide a helpful new dimension in predictive analysis and decision processes. The complementary aspect of predictive analysis and decision processes, based on Bayesian cybersensors is discussed in a parallel paper [15] .…”

Section: Discussionmentioning

confidence: 99%

Anomalies, singularities, and catastrophes in C3ISR systems

et al. 2015

Self Cite

View full text Add to dashboard Cite

In this paper, we provide topological visualization of Digital Decision Support (DDS) tools, both linear and non-linear, the latter ones related to bifurcations and/or catastrophes, including such non-linear phenomena as hysteresis, or sudden jump/drop of state variable (amplitude). As a principal example, we discuss non-linear oscillator catastrophes with applications in: physics, optics, electronics, mechanics, decision process, and others. INTRODUCTIONDigital Decision Generation tools, or, rather Digital Decision Support (DDS) tools [1] are important software components of C3ISR systems and technologies. In this paper, we propose a new approach to extraction of non-linear events based on topologic visualization of essential variables and anomalous events in binary event (object) space [2] , called by us DDS tools.Any successful predictive analysis in machine/human learning [3] and/or cybersensor [4] fields should include extraction of non-linear and/or anomalous events [1][2][3] such as mathematical catastrophes [5] as precursors, for example.Catastrophes [5] are types of bifurcations [5] , or discrete singularities in topological manifold continuum, constructed from so-called essential variables, including control variables (cause) and state variables (effect). In this paper, we discuss only corank-one catastrophes [5] , such as: fold, cusp, butterfly, etc., with single state variable, z, while control variables are: x, y, etc.In general, DTS (Digital Topologic Singularities) can be categorized within three (3) major types: Threshold DTS, such as avionics of-the-expectation (OTE) incidents, a kind of flagging; Linear DTS (function's maxima, minima, inflection points, etc.); and non-linear DTS (e.g., catastrophes). In this paper, we mostly discuss the third DTS category, as well as compare them with the linear DTS, within heuristic machine learning, idealization, and abstraction. The basic flow chart of DDS includes: regression (noise extraction), smoothing, and 2D "analogization" of discrete experimental data; generation of 2D parametric curves: parametrization-to-continuum (PtC) of these curves into surface continuum (i.e., 3D "analogization"); and, discretization (or, quantization) into non-linear DTS (catastrophes), for example, in this strange discrete → analog → discrete heuristic process.In this paper, we discuss topologic visualization of singularities and anomalies, in the form of: curves, surfaces, spaces, sub-spaces, cross-sections, and projections, in 3D, 4D, and higher space. However, for the sake of clarity, we focus on Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security, Defense, and Law Enforcement XIV, edited by Edward M. Carapezza, Proc. of SPIE Vol. 9456, 94560V · © 2015 SPIE · CCC code: 0277-786X/15/$18 ·

show abstract

Section: Discussionmentioning

confidence: 99%

Anomalies, singularities, and catastrophes in C3ISR systems

et al. 2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…The BT notation above [5,7] , equivalent to Bayesian Statistics (BS) notation, is as follows: a-number of alarms, a 1 -number of true alarms, a 2 -number of false alarms (thus, a = a 1 + a 2 ); b-number of no-alarms, b 1 -number of true no-alarms, b 2 -number of false no-alarms (target misses) (thus, b = b 1 + b 2 , and: m = a + b = s + n, where s = number of targets and n = number of no targets). Among these nine (9) BT parameters, four (4) of them are free, as in Eq.…”

Section: Typical Isr Binary Sensormentioning

confidence: 99%

“…All these input Bayesian Truthing (BT) parameters (see Refs. [5][6][7]) are summarized: m = 10 9 , s = 10 3 , b 2 = 10, a 2 = 365 (2abcd)…”

Section: Typical Isr Binary Sensormentioning

confidence: 99%

“…In previous papers [1][2][3][4][5][6][7] , we presented transition of the PPV concept from well-established medical applications into less mature ISR applications. The role of PPV in medicine is well established.…”

Section: Introductionmentioning

confidence: 98%

“…The remaining software sensors, or cybersensors, are briefly discussed in Refs. [5][6][7]. Sensors are only partially a subset (crossed area) of sensors.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Target-oriented binary sensor sets in C3I systems

et al. 2016

Self Cite

View full text Add to dashboard Cite

In this paper, Single-Target-Oriented (STO) Binary Sensor Sets (BSSs) are introduced and analyzed for C3I applications. These STO BSSs are diversified multisensors (combining IR camera, LIDAR, radar, etc.) standardized into the Binary Sensor format. By increasing the k-number of Binary Sensors within the STO paradigm, we can increase target detection predictability, thus, increasing Bayesian inference strength.

show abstract

Hilbertian sine as an absolute measure of Bayesian inference in ISR, homeland security, medicine, and defense

et al. 2016

Self Cite

View full text Add to dashboard Cite

In this paper, Bayesian Binary Sensing (BBS) is discussed as an effective tool for Bayesian Inference (BI) evaluation in interdisciplinary areas such as ISR (and, C3I), Homeland Security, QC, medicine, defense, and many others. In particular, Hilbertian Sine (HS) as an absolute measure of BI, is introduced, while avoiding relativity of decision threshold identification, as in the case of traditional measures of BI, related to false positives and false negatives.

show abstract

Bayesian truthing as experimental verification of C4ISR sensors

Cited by 3 publications

References 4 publications

Anomalies, singularities, and catastrophes in C3ISR systems

Anomalies, singularities, and catastrophes in C3ISR systems

Target-oriented binary sensor sets in C3I systems

Hilbertian sine as an absolute measure of Bayesian inference in ISR, homeland security, medicine, and defense

Contact Info

Product

Resources

About