In this paper we introduce definitions of generalized neutrosophic sets. After given the fundamental definitions of generalized neutrosophic set operations, we obtain several properties, and discussed the relationship between generalized neutrosophic sets and others. Finally, we extend the concepts of neutrosophic topological space [9], intuitionistic fuzzy topological space [5, 6], and fuzzy topological space [4] to the case of generalized neutrosophic sets. Possible application to GIS topology rules are touched upon.
23 September 2018 in Security and Communication Networks
Recently designing an effective intrusion detection systems (IDS) within Mobile Ad Hoc Networks Security (MANETs) becomes a requirement because of the amount of indeterminacy and doubt exist in that environment. Neutrosophic system is a discipline that makes a mathematical formulation for the indeterminacy found in such complex situations. Neutrosophic rules compute with symbols instead of numeric values making a good base for symbolic reasoning. These symbols should be carefully designed as they form the propositions base for the neutrosophic rules (NR) in the IDS. Each attack is determined by membership, nonmembership, and indeterminacy degrees in neutrosophic system. This research proposes a MANETs attack inference by a hybrid framework of Self-Organized Features Maps (SOFM) and the genetic algorithms (GA). The hybrid utilizes the unsupervised learning capabilities of the SOFM to define the MANETs neutrosophic conditional variables. The neutrosophic variables along with the training data set are fed into the genetic algorithm to find the most fit neutrosophic rule set from a number of initial subattacks according to the fitness function. This method is designed to detect unknown attacks in MANETs. The simulation and experimental results are conducted on the KDD-99 network attacks data available in the UCI machine-learning repository for further processing in knowledge discovery. The experiments cleared the feasibility of the proposed hybrid by an average accuracy of 99.3608 % which is more accurate than other IDS found in literature.
8 June 2014 in International Journal of Information Engineering and Electronic Business
This study presents an innovative multi-modal biometric authentication framework that integrates Deep Learning (DL) techniques with zero-trust architecture principles for enhanced network access control. The framework employs a three-tier fusion strategy (feature-level, score-level, and decision-level) incorporating facial, fingerprint, and iris recognition modalities. The system architecture implements a sophisticated multi-layered approach utilizing the ResNet-50 based Convolutional Neural Network (CNN) architecture for facial recognition, CNN-based minutiae extraction for fingerprint processing, and 2D Gabor wavelets with DL-based feature extraction for iris analysis. The experimental validation using established datasets, namely Labeled Faces in the Wild (LFW), CelebA, FVC2004, NIST SD14, CASIA Iris V4, and UBIRIS v2, demonstrates exceptional performance with 99.47% authentication accuracy, 0.02% False Acceptance Rate (FAR), and 0.15% False Rejection Rate (FRR). The framework resulted in a 68% reduction in fraudulent access attempts. It achieved a mean authentication time of 235 ms (SD=28 ms), representing a 45% improvement over traditional systems. The resource efficiency analysis showed significant reductions in system overhead: 32% in CPU utilization, 28% in memory consumption, and 45% in network bandwidth requirements. The scalability testing confirmed a linear performance scaling up to 100,000 concurrent authentication requests. The statistical test of significance through t-test confirmed the framework's significant improvements over existing solutions (p-value<0.001). This study establishes an effective framework to address network access control challenges across various sectors, particularly in high-security environments requiring robust authentication mechanisms.
In this paper we introduce definitions of generalized neutrosophic sets. After given the fundamental definitions of generalized neutrosophic set operations, we obtain several properties, and discussed the relationship between generalized neutrosophic sets and others. Finally, we extend the concepts of neutrosophic topological space, intuitionistic fuzzy topological space, and fuzzy topological space to the case of generalized neutrosophic sets. Possible application to GIS topology rules are touched upon.