Neutrosophic set (NS) and logic are powerful mathematical approaches for managing different uncertainties. Amongst different approaches for examining NS statistics, rough set theory (RST) offers a valuable instrument in the domain of NS statistics, and masses of researchers have been motivated by NS combination of RST. Recently, there have been no wide-ranging statistics and literature reviews of the universal RST and its applications. The Financial Crisis Prediction mechanism leverages cutting-edge computation methods to predict possible disruptions or economic downturns. By investigating past fiscal information, marketplace gauges, and macroeconomic features, the typical recognizes primary caution indications of imminent disasters. This practical method helps financial institutions, policymakers, and investors in applying pre-emptive procedures to alleviate fiscal marketplaces and threats. In this paper, we develop a Financial Crisis Prediction Model using Neutrosophic Fusion of Rough Set Theory (FCPM-NFRST) methodology. The suggested FCPM-NFRST method for financial crises incorporates numerous forward-thinking systems to improve predictive performance. It is initiated by the Firefly Algorithm (FFA) based feature selection to detect the fittest fiscal gauges. Consequently, the Neutrosophic Fusion of RST (NFRST) is exploited for strong cataloguing and successful management of vagueness and roughness in economic information. Lastly, the Whale Optimization Algorithm (WOA) is exploited for parameter fine-tuning, enhancing the system's accuracy. Investigational study displays that the FCPM-NFRST ensemble mechanism is more robust and superior than its complements. Accordingly, this study powerfully suggests that the suggested FCPM-NFRST method is very competitive than conventional and other existing algorithms.
Read MoreDoi: https://doi.org/10.54216/IJNS.250211
Vol. 25 Issue. 2 PP. 129-140, (2025)
Neutrosophic set (NS) and Neutrosophic logic (NL) play a major part in approximation theory. They are generalizations of intuitionistic fuzzy sets and logic correspondingly. Rough NS (RNS) combines the concepts of RS and NL to deal with vagueness, uncertainty, and imprecision in information. By integrating truth, indeterminacy, and false degrees, RNS provides a more solid basis for analyzing and classifying complicated data. Particularly, this makes it powerful in applications where incompleteness and ambiguity of data are ubiquitous. Smart cities are a current trend to contain information and communication technologies (ICTs) in the progression of great urban cities. It would be beneficial in defining the city's movement by monitoring the regular flow of traffic jams and visitors. One important characteristic of smart cities is Crowd management, which assists in safety and enjoyable experiences for the residents and visitors. Since the crowd density (CD) classification method encounters tasks including inter-scene, non-uniform density, and intra-scene deviations, occlusion and convolutional neural networks (CNNs) approaches were beneficial. This work focuses on the design of Automated Crowd Density Recognition using the Rough Neutrosophic Set for Smart Cities (ACDR-RNSSC) method in urban management. The presented ACDR-RNSSC method focuses on identifying various types of crowd densities in smart cities. Firstly, the ACDR-RNSSC method utilizes the ResNet50 method for feature extraction. Second, the classification is done using RNS. RNS is utilized for its ability to manage the vagueness and uncertainty in crowd density statistics. Lastly, the parameter is fine-tuned using the Fruit Fly Optimization Algorithm (FOA). This ensures that the model attains high robustness and accuracy in forecasting crowd density. The empirical analysis of the ACDR-RNSSC method is examined under benchmark crowd dataset and the outcomes are tested using various metrics. This study states the improvement of the ACDR-RNSSC method over existing techniques.
Read MoreDoi: https://doi.org/10.54216/IJNS.250210
Vol. 25 Issue. 2 PP. 117-128, (2025)
The objective of this paper is to build the Split-Complex version of Diffie-Hellman key Exchange Algorithm, where we use the mathematical foundations of Split-Complex Number Theory and Integers, such as congruencies, raising a split-complex integer to a power of split-complex integer to build novel algorithms for key Exchange depending of famous Diffie-Hellman algorithm. Additionally, we present the proposed version of the Diffie-Hellman algorithm based on neutrosophic number theory. Also, we analyze the complexity of the novel algorithms with many examples that explain their applied validity.
Read MoreDoi: https://doi.org/10.54216/IJNS.250201
Vol. 25 Issue. 2 PP. 01-10, (2025)
Indian agriculture aims at achieving sustainable development, which increases crop production per square unit without damaging the ecosystem and natural resources. Timely and prompt diagnosis and analysis of plant diseases are very beneficial in increasing food crop productivity and plant health and decreasing plant diseases. Plant disease specialists are not accessible in distant regions therefore there is an urgent need for reliable, automatic low-cost, and approachable solutions to detect plant disease without the expert’s opinion and laboratory inspection. Classical machine learning (ML)-based image classification techniques and Deep learning (DL)-based computer vision (CV) approaches such as Convolutional Neural Networks (CNN) was employed to detect plant disease. Neutrosophic set (NS), a generality of fuzzy set (FS) and intuitionistic FS (IFS), presented to characterize inconsistent, uncertain, imprecise, and incomplete data in realistic conditions. Besides, interval NS (INSs) was exactly proposed to resolve the problems with a collection of numbers in the actual entity. On the other hand, there are high levels of operational reliability for INSs, along with the decision-making method and INS aggregation operators. This study presents an Efficient Plant Disease Detection using the Possibility Neutrosophic Hypersoft Set Approach (EPDD-pNSHSS) method. The suggested EPDD-pNSHSS method uses the DL method for the recognition and classification of plant diseases. Initially, the EPDD-pNSHSS method takes place the Median filtering (MF) through the preprocessing to progress image superiority and eliminate noise. In the meantime, the possibility neutrosophic hypersoft set (pNSHSS) classifier is utilized for the detection of diseased and healthy leaf images. To optimize the detection accuracy of the pNSHSS mechanism, the whale optimization algorithm (WOA) is employed for adjusting the hyperparameter value of the DSAE technique. Wide-ranging experiments are implemented to exhibit the supremacy of the EPDD-pNSHSS method. The empirical findings showcased the development of the EPDD-pNSHSS method over other existing techniques.
Read MoreDoi: https://doi.org/10.54216/IJNS.250202
Vol. 25 Issue. 2 PP. 11-21, (2025)
A neutrosophic set (NS) is an advanced computational technique that accesses uncertain information via three membership functions. A soft expert set (SES) is derived from the hypothesis of a “soft set” with computer technology. Currently, this method is utilized in various domains such as intelligent systems, measurement theory, probability theory, cybernetics, game theory, and so on. Internet user faces a myriad of risks with the development of malware worldwide. The most prominent type of malware, Ransomware, encrypts confidential data without releasing the files until the user makes a ransom payment. Internet of Things (IoT) framework is a wide region of Internet-related devices with further computation capacities with storage capabilities that can be damaged by malware creators. Ransomware is a cruel and new malware on Internet with increasing attack levels. Ransomware encrypts the whole information to make users incapable of accessing important information and their files. In this article, we propose a Complex Proportional Assessment Based Neutrosophic Approach for Ransomware Detection in Cybersecurity (CPABNA-RDCS) methodology in IoT environment. The objective of the CPABNA-RDCS approach is to identify and categorize the ransomware to accomplish cybersecurity in the IoT network. Primarily, the CPABNA-RDCS method exploits min-max normalization for scaling the input dataset into relevant format. Meanwhile, the ransomware classification takes place via Complex Proportional Assessment Based Neutrosophic (CPABN) method. Finally, grey wolf optimizer (GWO) is employed for optimum hyperparameter choice of the CPABN system. The experimental results of the CPABNA-RDCS method are inspected on benchmark data. The simulation analysis emphasized the developments of the CPABNA-RDCS method over other existing techniques.
Read MoreDoi: https://doi.org/10.54216/IJNS.250203
Vol. 25 Issue. 2 PP. 22-32, (2025)