Pythagorean Neutrosophic Framework and Its Application to Correlation-Based Threat Identification
DOI:
https://doi.org/10.19139/soic-2310-5070-4383Keywords:
Pythagorean Neutrosophic Sets; Neutrosophic Correlation Measure; Behavioural Similarity; Threat Classification; Uncertain Information Modelling; Target Behaviour MappingAbstract
In intelligence analysis, surveillance systems, and threat assessments, usual models that rely on discrete mathematics often do not capture the ambiguity in the information well. Uncertainty, incompleteness, and inconsistency are common in intelligence analysis, surveillance systems, and threat assessment, where traditional mathematical models are often unable to adequately describe the ambiguity in the information. In this paper, a Pythagorean neutrosophic framework called Pythagorean Neutrosophic Framework (PNF), is developed for threat identification in uncertain environment, based on the correlation features. This proposed framework will integrate the expressive power of Pythagorean neutrosophic sets with a new correlation measure that will consider all three degrees of membership: the truth-membership, indeterminacy-membership and falsity-membership degree and will satisfy the Pythagorean constraint. Complement, union and intersection are introduced on Pythagorean neutrosophic sets and a normalized correlation coefficient is introduced that is bounded, symmetric, and identity. The suggested correlation value is then used to correlate observed behavioural indicators to threat categories that have been pre-defined. A case study of a real threat identification scenario shows that the framework is applicable in practice through the use of behavioural characteristics like thermal signature, pattern of movement, weapon handling and communication activity. The values of correlation obtained give a good separation of the various behavioural profiles and are close to the correct classification of the most likely threat category for each target for uncertain information. A series of visualization and analytical methods such as heatmaps, normalized heatmaps, two-dimensional and three-dimensional bar graphs, surface plots, spline interpolation, principal component analysis (PCA), t-distributed stochastic neighbour embedding (t-SNE) and parallel coordinate plots are used to further validate the proposed methodology. The stability, interpretability and discriminatory power of the proposed correlation measure is confirmed by the graphical analysis. The proposed Pythagorean neutrosophic framework is an interpretable mathematical model that manages uncertainty-aware threat identification, and is a potential alternative to the classical similarity measures in the field of security intelligence, decision support systems and other applications using incomplete and conflicting information.Downloads
Published
2026-08-31
How to Cite
J. Hamja, J., Abdelfattah, W., Hussain, A., Mehmood, A., U. Kamdon, S., N. Ulal, N.-H., … L. Armada, C. (2026). Pythagorean Neutrosophic Framework and Its Application to Correlation-Based Threat Identification. Statistics, Optimization & Information Computing. https://doi.org/10.19139/soic-2310-5070-4383
License
Copyright (c) 2026 Jamil J. Hamja, Walid Abdelfattah, Aqeedat Hussain, Arif Mehmood, Sisteta U. Kamdon, Noor-Han N. Ulal, Al-jayson U. Abubakar, Cris L. Armada

This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).