[Paper Review] Predicting Suicide Attacks: A Fuzzy Soft Set Approach

Athar Kharal|arXiv (Cornell University)|Jul 28, 2010

Fuzzy and Soft Set Theory13 references3 citations

TL;DR

This paper proposes a fuzzy soft set-based decision support system (FSP) to predict suicide attacks in cities by modeling incomplete, imprecise expert assessments using linguistic variables. The algorithm evaluates risk factors across cities, producing a possibility profile with O(2^n) complexity, and simulation shows decision measure Γ₁ exhibits significantly less bias than alternatives.

ABSTRACT

This paper models a decision support system to predict the occurance of suicide attack in a given collection of cities. The system comprises two parts. First part analyzes and identifies the factors which affect the prediction. Admitting incomplete information and use of linguistic terms by experts, as two characteristic features of this peculiar prediction problem we exploit the Theory of Fuzzy Soft Sets. Hence the Part 2 of the model is an algorithm vz. FSP which takes the assessment of factors given in Part 1 as its input and produces a possibility profile of cities likely to receive the accident. The algorithm is of O(2^n) complexity. It has been illustrated by an example solved in detail. Simulation results for the algorithm have been presented which give insight into the strengths and weaknesses of FSP. Three different decision making measures have been simulated and compared in our discussion.

Motivation & Objective

• To develop a decision support system for predicting suicide attacks in urban centers amid incomplete and imprecise data.
• To address the inherent uncertainty in counter-terrorism forecasting by integrating linguistic expert judgments and fuzzy soft set theory.
• To create a computationally structured model that transforms qualitative risk factors into a quantifiable possibility profile of high-risk cities.
• To evaluate and compare multiple decision-making measures for risk assessment under uncertainty.
• To provide a dynamic, knowledge-based framework for security planning and threat visualization in high-consequence environments.

Proposed method

• The model uses fuzzy soft sets to represent uncertain, imprecise, and linguistically expressed risk factors from expert assessments.
• A two-part approach is employed: (1) identification of key predictive factors influencing suicide attack likelihood; (2) application of the FSP algorithm to compute risk possibility profiles.
• The FSP algorithm performs pairwise comparisons of cities based on fuzzy soft set evaluations, aggregating scores via defined functions ρ(ψi, ψj) and χ(ψi, ψj).
• The algorithm’s computational complexity is O(2^n), arising from the need to evaluate all subsets of n cities during risk comparison.
• Three decision-making measures (Γ₁, Γ₂, Γ₃) are simulated and compared to assess bias and consistency in risk ranking.
• The model leverages the structure of a discernibility matrix to support future extensions in rough set theory-based optimization.

Experimental results

Research questions

• RQ1 How can linguistic and imprecise expert judgments about suicide attack risk be systematically modeled in a decision support framework?
• RQ2 What is the most effective way to rank cities for suicide attack risk when data is incomplete and subjective?
• RQ3 How does the FSP algorithm’s performance vary across different decision-making measures in terms of bias and consistency?
• RQ4 What are the computational and scalability limitations of using fuzzy soft sets for large-scale urban threat prediction?
• RQ5 In what ways can the model be enhanced to support dynamic, real-time threat assessment using data mining and continuous re-evaluation?

Key findings

• The FSP algorithm successfully transforms qualitative, linguistically expressed risk assessments into a structured possibility profile for cities.
• Simulation results show that decision measure Γ₁ exhibits significantly less bias (246 ties) compared to Γ₂ (440 ties) and Γ₃ (2129 ties), indicating superior consistency.
• The model’s performance is highly dependent on the quality of expert input, with risk assessments propagating uncertainty due to subjective judgments.
• The O(2^n) complexity of the FSP algorithm limits scalability, highlighting the need for future optimization to improve efficiency.
• The resemblance between the model’s comparison functions and discernibility matrices suggests potential for integration with rough set theory to extract core risk factors and reducts.
• Despite limitations, the model serves as a valuable template for organizing fragmented intelligence and visualizing threat patterns in complex urban security contexts.