Intelligent Bankruptcy Prediction using Cutting-Edge N-Valued Interval Neutrosophic Sets for Classification

Vishwanadham; Rajiv; Pradeep; Rajesh Kumar; Manoj Kumar; Venkata Nagesh

doi:https://doi.org/10.54216/IJNS.250226

Journal of Cybersecurity and Information Management | 2025

Comprehensive Analysis of Internet Security Protocols and Standards for Enhanced Network Safety

This research examines all internet security protocols. To develop and test a novel network protection method. The research's comprehensive methodology includes a detailed review of existing security measures, a critical investigation of the recommended method's components, and a vital analysis of its effectiveness. AES is critical to the recommended code efficiency technique. The ablation investigation highlights AES's importance for fast encryption. Multi-factor authentication (MFA) protects and boosts authentication scores, making login simpler. The article defines "fast intrusion reaction time" and provides examples of how quickly the proposed technique may handle security incidents. The ablation research highlights the impact on this swift response, underscoring the importance of proactive intrusion detection and response. The study's findings will help firms secure their websites. The recommended solution is superior to others and protects against emerging internet dangers. The report recommends quick response systems, multi-layered identities, and security upgrades. This research teaches us online safety principles. It also provides a standard for network protection firms. Many studies have proved that the recommended strategy works, making it a significant aspect of current defensive efforts to address global concerns.

groups

Sunil Kr Pandey mail -

Prashant Kumar Shukla mail -

Piyush Kumar Pareek mail -

Cosmena Mahapatra mail -

Puneet Kumar Aggarwal mail -

Udit Mamodiya mail

link https://doi.org/10.54216/JCIM.150126

Volume & Issue

Vol. Volume 15 / Iss. Issue 1

Details open_in_new

Galoitica: Journal of Mathematical Structures and Applications | 2024

On the Perfect Italian Domination Numbers of Some Graph Classes

A function f:V(G)→{0,1,2} is called a Perfect Italian dominating function (PIDF) of a graph G=(V,E) if ∑_(v∈N(u)) f(v)=2 for every vertex u∈V(G) with f(u)=0. The weight of an PIDF is w(f)=∑_(v∈V) f(v) . The minimum weight of all Perfect Italian dominating functions that can be conducted on a graph G is called the perfect Italian domination number of G and is denoted by γ_I^p (G). In this paper, we study the problem on different graph classes. We determine the perfect Italian domination numbers of the circulant graphs C_n {1,2} for n≥5 and give upper bounds for γ_I^p (C_n {1,3})  when n≥7. We also find this parameter for generalized Petersen graph P(n,2) when n≥5. We determine γ_I^p (G) of strong grids P_2⊠P_n  and P_3⊠P_n for arbitrary n≥2, then we introduce an upper bound for γ_I^p (P_m⊠P_n ) when m,n≥2 are arbitraries. Finally, we determine the perfect Italian domination number of Jahangir graph J_(s,m) for arbitrary s≥2 and m≥3.

groups

Khadija Ben Othman mail

link https://doi.org/10.54216/GJMSA.0110104

Volume & Issue

Vol. Volume 11 / Iss. Issue 1

Details open_in_new

Galoitica: Journal of Mathematical Structures and Applications | 2024

On The Markov-Bernstein Inequalities with Weight Functions in Lp Spaces

In this paper, we study of the Markov- Bernstein inequality of a complex polynomial with exponential weight functions  e^(-r^2  z/2)   on the domain ├]-∞,+∞┤[,    we also study the Integral Markov-Bernstein inequality for the algebraic polynomials of degree 2m and degree m with algebraic weight functions on the domain [1,+∞┤[of type (1/x^2 )^(-n), and on the domain ├]0,+∞┤[of type (1/t)^(-n).

groups

Sergey Drominko mail -

Erina Kovachiskaya mail

link https://doi.org/10.54216/GJMSA.0110105

Volume & Issue

Vol. Volume 11 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2025

Integrating Internet of Things Sensors with Machine Learning for Urinary Tract Infection Prediction in Male Felines

Urinary Tract Infections (UTIs) are a prevalent medical condition affecting male felines that can lead to severe discomfort, behavioural changes, and even fatality if not promptly diagnosed and treated. This paper aims to address the limitations of traditional diagnostic methods by integrating Internet of Things (IoT) sensors with machine learning algorithms to predict UTIs in male felines. The study utilizes a multi-modal sensor array to continuously monitor various physiological and behavioural parameters, such as acidity of urine pH levels, heart rate, territorial marking, and eating habits. Observations were categorized into several states, ranging from normal conditions to severe abnormalities, including death. A machine learning model was trained on the collected data to identify early signs of UTIs. The model demonstrated a high predictive accuracy in identifying urinary tract infections before the manifestation of severe symptoms, thus providing a promising avenue for early intervention. The integrated system offers a non-invasive, real-time monitoring solution that could significantly improve the management and the treatment outcomes of UTIs in male feline.

groups

Danish Ather mail -

Tanveer Baig .Z mail -

Ambuj Kumar Agarwal mail -

Suhail Javed Quraishi mail -

Malikhan singh mail -

Rajeesh Kher mail

link https://doi.org/10.54216/JISIoT.140121

Volume & Issue

Vol. Volume 14 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2025

Transfer Learning Models for E-mail Classification

Phishing and spam are examples of unsolicited emails, result in significant financial losses for businesses and individuals every year. Numerous methodologies and strategies have been devised for the automated identification of spam, yet they have not demonstrated complete predictive precision. Within the spectrum of suggested methodologies, ML and DL algorithms have shown the most promising results. This article scrutinizes the outcomes of assessing the efficacy of three transformation-based models - BERT, AlBERT, and RoBERTa - in scrutinizing both textual and numerical data. The proposed models achieved higher accuracy and efficiency in classification tasks, which was a notable improvement above traditional models such as KNN, NB, BiLSTM, and LSTM. Interestingly, in several criteria the Roberta model achieved almost perfect accuracy, suggesting that it is very flexible on a variety of datasets.

groups

Muatamed Abed Hajer mail -

Mustafa K. Alasadi mail -

Ali Obied mail

link https://doi.org/10.54216/JCIM.150127

Volume & Issue

Vol. Volume 15 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

Kernel Neutrosophic Crisp Sets

Our study focusses on the concept of the kernel with in neutrosophic crisp sets (NCS_s) and its relationship with the separation axioms of NCTS, coinciding, and shedding light on the properties that characterize them.

groups

Reyadh D. Ali mail -

L. A. A. Jabar mail -

Ghassan A. Qahtan mail -

Ali Younis Shakir mail

link https://doi.org/10.54216/IJNS.250222

Volume & Issue

Vol. Volume 25 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2025

Interval-Valued Neutrosophic Set with Optimization Algorithm for Cyberthreat Detection and Classification in IoT Infrastructure

Neutrosophic Logic is an offspring study region in which every intention is projected to hold the proportion of indeterminacy in a subset I, the percentage of truth in a subset T, and the percentage of falsity in subset F. Neutrosophic set (NS) has been effectively used for indeterminate data processing, and establishes benefits to handle with the indeterminacy information of data and is quite a method stimulated for classification application and data analysis. NS delivers an effective and precise method to describe imbalanced data as per the features of the data. Recently, the usage of the Internet of Things (IoT) has enlarged rapidly, and cyber security effects have enlarged beside it. On the state-of-the-art of cyber security is Artificial Intelligence (AI), which employed for the progress of intricate techniques to defense systems and networks, containing IoT systems. Though, cyber-attackers have determined how to develop AI and have started to utilize adversarial AI for accomplishing cybersecurity threats. Therefore, this study designs a new Interval-Valued Neutrosophic Set using Optimization Algorithm-Based Intrusion Detection System (IVNSOA-IDS) technique in IoT cybersecurity. The key objective of the IVNSOA-IDS method rests in the automatic identification of intrusion detection in IoT cybersecurity. In the IVNSOA-IDS technique, data pre-processing is executed to convert the raw data into a compatible format. Besides, the interval-valued neutrosophic set (IVNS) model has been utilized for the automated identification of intrusion detection. Finally, an improved whale optimization algorithm (IWOA) is employed for the better hyperparameter tuning of the IVNS classifier. To demonstrate the enhanced performance of the IVNSOA-IDS technique, an extensive of simulations take place and the performances are inspected under distinct aspects. The experimental outcome reported the advancement of the IVNSOA-IDS methodology under various metrics.

groups

Thangam .S mail -

Jana .S mail

link https://doi.org/10.54216/IJNS.250223

Volume & Issue

Vol. Volume 25 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2025

Pythagorean Neutrosophic Normal Interval-Valued Weighted Averaging Approach for Sustainable Financial Risk Prediction

Neutrosophic set (NS) is a prevailing logic aimed at facilitating the understanding of inconsistent and indeterminate data; several kinds of complete or incomplete data can be described as interval-valued NS (IVNS). This study presents aggregation operator for IVNSs and prolongs the generalized weighted aggregation (GWA) operations to congruently work with IVNS information. Also, these results are formulated as IVNSs that are represented by indeterminate, truth, and false degrees. The tremendous growth of financial innovation offers a several convenience to people’s lives and production and brings many security risks to financial technology. To avoid financial risk, an improved way is to construct an accurate warning mechanism before the financial risk takes place, not to solve this matter after the risk outbreak. Recently, deep learning (DL) has delivered outstanding results in the natural language processing and image recognition areas. Thus, researcher used DL techniques for the financial risk prediction and obtained satisfactory results. This study develops a new Pythagorean Neutrosophic Normal Interval-Valued Weighted Averaging for Financial Risk Prediction (PNNIVWA-FRP) method using sustainable development. The objective of the PNNIVWA-FRP method is to have two dissimilar stages of processes. Initially, financial data are classified by the PNSNIVWA technique. This method is used for its highest proficiency in managing imprecision and uncertainty in financial data, containing incomplete and ambiguous data. Second, the classified parameter is fine-tuned by means of Glowworm Swarm Optimization (GSO) technique. Based on the luminescent communication of glowworms, GSO is proficient at navigating multidimensional, complex search spaces for identifying better solutions. The empirical findings on benchmark dataset demonstrate the effectiveness of the PNNIVWA-FRP method, showcasing significant development in prediction results than classical approaches.

groups

Halla Elziber Elsiddeg Elemam mail -

Abdelgalal O. I. Abaker mail -

Elavarasi Gunasekaran mail -

Hago E. M. Ali mail -

Abdullah S. Alharbi mail -

Amer Alsulami mail -

Azhari A Elhag mail

link https://doi.org/10.54216/IJNS.250224

Volume & Issue

Vol. Volume 25 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2025

Significant Features with M-Polar Neutrosophic Topological Spaces and Grey Wolf Optimization Algorithm for Bankruptcy Prediction Model

An interval neutrosophic set (INS) is an example of a NS, which is simplified from the theory of fuzzy set (FS), classical set, paradoxist set, intuitionistic FS, paraconsistent set, interval-valued FS, interval-valued intuitionistic FS, and tautological set. The association of an element to an INS is stated by 3 values such as t, i, and f. These values signify memberships of truth, indeterminacy, and false, correspondingly. Bankruptcy prediction is also called a corporate failure or bankruptcy prediction, which is a major focus in the area of finance and accounting, as the condition of a business is extremely substantial to its partners, shareholders, investors, creditors, even its suppliers, and buyers. Practitioners and researchers were reserved for emerging models and approaches to forecast the bankruptcy of companies more rapidly and precisely. With the excessive growth of contemporary information technology, it has developed to use machine learning (ML) or deep learning (DL) techniques to perform the prediction, from the preliminary study of economic statements. This study introduces an Optimized Bankruptcy Prediction using Feature Selection with m-Polar Neutrosophic Topological Spaces (OBPFS-MPNTS) method. The projected OBPFS-MPNTS system uses the parameter tuning and DL method to forecast the presence of bankruptcy. To achieve this, the OBPFS-MPNTS approach uses min-max normalization to convert input data into a uniform format. The OBPFS-MPNTS method begins with a grey wolf optimization (GWO) for selecting feature subsets. In addition, the OBPFS-MPNTS algorithm applies the m-polar neutrosophic topological space (MPNTS) system for bankruptcy prediction. To upsurge the performance of the MPNTS system, the whale optimizer algorithm (WOA) is employed. The experimentation outcome study of the OBPFS-MPNTS system is verified on a benchmark database and the outcomes pointed out the developments of the OBPFS-MPNTS algorithm over other current methodologies.

groups

Sergey Bakhvalov mail -

Rustem Shichiyakh mail -

Irina Gladysheva mail -

M. Ilayaraja mail -

K. Shankar mail

link https://doi.org/10.54216/IJNS.250225

Volume & Issue

Vol. Volume 25 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2025

Intelligent Bankruptcy Prediction using Cutting-Edge N-Valued Interval Neutrosophic Sets for Classification

As a generalization of fuzzy set (FS) and intuitionistic FS (IFS), neutrosophic sets (NS) were proposed to signify imprecise, uncertain, inconsistent and imperfect data present in real-time. Moreover, the interval NS (INSs) were developed just to find out the problems with an array of statistics in the actual unit interval. Then, there are least consistent processes for INSs, along with the decision-making process and INS aggregation operator. The vital operations are presented on n-valued interval NSs like intersection, union, multiplication, addition, scalar division, scalar multiplication, false-favorite and truth favorite. Bankruptcy prediction was a major concern in the areas of finance and management science that appealed to the attention of practitioners and researchers. With the great progress of up-to-date information technology, it has been developed to utilize machine learning (ML) or deep learning (DL) techniques to perform the prediction, from the primary analysis of financial statements. If ML methods have adequate interpretability, they might be employed as effectual analytical methods in bankruptcy calculation. This manuscript presents a Bankruptcy Prediction using Cutting-Edge N-Valued Interval Neutrosophic Sets (BP-CENVINS) mechanism. The projected BP-CENVINS method is a complicated approach to bankruptcy forecast that affects radical data preprocessing, classification, and hyper parameter optimization approaches. Initially, the Z-score normalization regularizes the fiscal details to increase the comparability and stability throughout the information. Next, it employs the CENVINS for the classification, skillfully detecting the subtle communication amongst variables to differentiate between creditworthy and bankrupt organizations. Finally, the Grasshopper Optimization Algorithm (GOA) is applied for parameter tuning to improve the predictive outcomes of the CENVINS classifiers, systematically purifying design parameters to achieve finest efficiency. An extensive experiments is made to illustrate the betterment of the BP-CENVINS technique. The simulation outcomes of the BP-CENVINS method have exhibited better performances than other existing methodologies.

groups

Vishwanadham Mandala mail -

Rajiv Avacharmal mail -

Pradeep Chintale mail -

Rajesh Kumar Malviya mail -

Manoj Kumar Vandanapu mail -

Venkata Nagesh Boddapati mail

link https://doi.org/10.54216/IJNS.250226

Volume & Issue

Vol. Volume 25 / Iss. Issue 2

Details open_in_new