A Multi-Server Queuing-Inventory System with Attraction-Retention Mechanisms for Impatient Customers and Catastrophes in Warehouse

Berhanu Mekonen; Natesan; Getinet Alemayehu

doi:https://doi.org/10.54216/AJBOR.120203

International Journal of Neutrosophic Science | 2025

An Intelligent Decision Support Systems for Financial Fraud Detection Using Pythagorean Neutrosophic Bonferroni Mean Approach with Machine Learning Models

Neutrosophy has developed as a generalization to fuzzy logic and is being employed in the research field in many areas such as set theory, logic, and others. Neutrosophic Logic is one of the neonate study regions and its intention is assessed to have the percentage of truth in a subset T, the percentage of falsity in a subset F, and the percentage of indeterminacy in a subset I. Recently, financial fraud has become a highly major issue, which results in severe consequences across firm sectors and affects people’s everyday lives. Therefore, financial fraud recognition is critical for the prevention of the regularly overwhelming effects of financial fraud. It includes differentiating fraudulent financial data from accurate data and permitting decision-makers to progress suitable plans to reduce the effect of fraud. Over the past few years, Artificial intelligence (AI), mainly machine learning (ML) systems, turned out to be the highest thriving model in fraud detection. This study presents a novel Intelligent Decision Support System for Financial Fraud Detection Using Pythagorean Neutrosophic Bonferroni Mean (IDSSFFD-PNBM) model. The main intention of the IDSSFFD-PNBM algorithm is to enrich the detection model for financial fraud using advanced optimization models. Initially, the z-score normalization is applied in the data normalization stage for converting input data into a beneficial format. Besides, the proposed IDSSFFD-PNBM designs a grasshopper optimization algorithm (GOA) for the selection of feature processes to enhance the efficiency and performance of the model. For the detection and classification procedure, the pythagorean neutrosophic bonferroni mean (PNBM) model has been employed. Additionally, the firefly optimization algorithm (FFOA)-based hyperparameter range method has been done to heighten the recognition outcomes of the PNBM system. The experimental evaluation of the IDSSFFD-PNBM technique takes place using a benchmark dataset. The experimental results indicated an enhanced performance of the IDSSFFD-PNBM technique compared to recent approaches

groups

Umidjon Matyakubov mail -

Ranokhon Sharofutdinova mail -

Aleksey Ilyin mail -

Rustem Shichiyakh mail -

K. Shankar mail -

E. Laxmi Lydia mail

link https://doi.org/10.54216/IJNS.250418

Volume & Issue

Vol. Volume 25 / Iss. Issue 4

Details open_in_new

International Journal of Neutrosophic Science | 2025

Geometric Properties of Neutrosophic 𝓆 -Poisson distribution Series through 𝕻𝕞ℵ Operator

This paper investigates the 𝔓𝕞&alefsym; operator, constructed from the Neutrosophic 𝓆-Poisson distribution series. The study examines this operator within the realm of geometric function theory, focusing on key characteristics such as coefficient bounds, growth and distortion behavior, and the determination of convexity and star likeness radii. Additionally, the paper explores the weighted and arithmetic means of functions associated with this operator and analyzes its closure properties under the Hadamard product.

groups

Layla Esmet Jalil mail -

Mohammad El-Ityan mail -

Rafid Habib Buti mail

link https://doi.org/10.54216/IJNS.250419

Volume & Issue

Vol. Volume 25 / Iss. Issue 4

Details open_in_new

International Journal of Neutrosophic Science | 2025

Applying Block Method for the Numerical Solutions of the Second Order n-Refined Neutrosophic ODE for n=2, 3

In this paper, we study the applications of block method to find the numerical solutions of some neutrosophic differential problems, where we discuss the approximated n-refined neutrosophic solutions and absolute n-refined neutrosophic errors in two special cases for n=2, and n=3. In addition, we list the numerical tables of our results.

groups

Ahmad A. Abubaker mail -

wael mahmoud mohammad salameh mail -

Sara A. Khalil mail -

Ibraheem Abu Falahah mail -

Ahmed Atallah Alsaraireh mail -

Abdallah Al-Husban mail

link https://doi.org/10.54216/IJNS.250420

Volume & Issue

Vol. Volume 25 / Iss. Issue 4

Details open_in_new

International Journal of Neutrosophic Science | 2025

Analyzing and Interpretation of Kernel Neutrosophic Set Based Machine Learning Model for Cost Estimation of Multi Product Supply Chain Management Systems

Neutrosophic set (NS) is a novel devise to handle uncertainty considering the memberships of truth T, indeterminacy I, and falsity F satisfying. It is employed to illustrate the indefinite data more appropriately and precisely than an intuitionistic fuzzy set. The search for cost information over the supply chain is very significant for controlling costs that aid in enhancing and beginning activities in organizations in the value chain. In today’s intricate supply networks, sharing data among suppliers and buyers is important for sustainable competitive benefit. Particularly, for both business partners, cost information is extremely appropriate in buying conditions. As per experimental analyses in literature, artificial neural networks (ANNs) are probable to have a great latent to expose cost structures by machine learning (ML). This study presents a novel Interpretation of Kernel Regression Neutrosophic Set using Enhanced Coati Optimization for Cost Estimation Model (KRNSECO-CEM). The main goal of the presented KRNSECO-CEM technique is to analyze and interpret the multi-product of Supply Chain Management Systems. At first, the KRNSECO-CEM approach applies Z-score normalization to pre-process the input data. For the regression process, the kernel regression based neutrosophic set (KRNS) model can be used. Eventually, the enhanced coati optimization algorithm (ECOA) has been applied for the fine-tuning of the best hyperparameter of the KRNS model. The experimental evaluation of the KRNSECO-CEM algorithm can be tested on a benchmark dataset. The extensive outcomes highlighted the significant solution of the KRNSECO-CEM approach over other recent approaches

groups

Olga Loseva mail -

Bakhtiyar Ruzmetov mail -

Ildar Begishev mail -

Denis Shakhov mail -

Elena Klochko mail -

Elvir Akhmetshin mail

link https://doi.org/10.54216/IJNS.250421

Volume & Issue

Vol. Volume 25 / Iss. Issue 4

Details open_in_new

Fusion: Practice and Applications | 2025

Integrating Deep Learning Architecture with Pufferfish Optimization Algorithm for Real-Time Deepfake Video Detection and Classification Model

Deepfake is a technology employed in making definite videos, which are operated utilizing an artificial intelligence (AI) model named deep learning (DL). Deepfake videos were normally videos that cover activities grabbed by definite people but with another individual's face. Substitute of people appearances in videos utilizing the DL model. The technology of Deepfake permits humans to operate videos and images utilizing DL. The outcomes from deepfakes are challenging to differentiate utilizing normal vision. It is a combination of the words DL and fake, and it mostly denotes material shaped by deep neural networks (DNNs), which is a subclass of machine learning (ML). Deepfake denotes numerous modifications of face models, and integrates innovative technologies, with computer vision and DL. The detection of a deepfake model can be assumed as a dual classification procedure that can be categorized as the original or deepfake class. It works by removing features from the videos or images that is employed to distinguish between original and deepfake content. Therefore, this study proposes Leveraging Pufferfish Optimization and Deep Belief Network for an Enhanced Deepfake Video Detection (LPODBN-EDVD) technique. The LPODBN-EDVD technique intends to detect fake videos utilizing the DL model. In the presented LPODBN-EDVD technique, the data preprocessing stages include splitting the video into frames, face detection, and face cropping. For the process of feature extraction, the EfficientNet model is exploited. Besides, the deep belief network (DBN) classifier can be executed for deepfake video detection. Finally, the pufferfish optimization algorithm (POA) is employed for the optimal hyperparameter selection of the DBN classifier. A wide range of simulations was involved in exhibiting the promising results of the LPODBN-EDVD method. The experimental analysis pointed out the enhanced performance of the LPODBN-EDVD technique compared to recent approaches

groups

Sameer Nooh mail

link https://doi.org/10.54216/FPA.180120

Volume & Issue

Vol. Volume 18 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

Practical Applications of Neutrosophic Logic in Enhancing the Accuracy of Economic Forecasting Models and Supporting Decision-Making in Banks

Using three machine knowledge models that utilise Neutrosophic Logic (NL)—Linear Regression, Random Forest, and Gradient Increasing—this study studies the possibilities of refining financial result forecast. The cognitive behind this is that NL recovers the prediction power of these models across dissimilar organisations by accounting for the inherent uncertainty, unpredictability, and lack of sureness in financial numbers. In this study, the models' presentation is evaluated using a variety of financial factors, including interest rates and stock prices. F1 score, recall, correctness, and exactness are some of the metrics used by this drive. When likened to other models, NL with Gradient Cumulative consistently outperforms them in terms of correctness and robustness. You might think of Abu Dhabi Islamic Bank and the National Bank of Bahrain as two such examples. Companies like Emirates Islamic Bank reap some benefits from Chance Forest's combination of cheap computation with precision, but only to a lower degree. Complex datasets used by businesses like Al Rajhi Bank are beyond the capabilities of Linear Reversion, even when combined with NL. By proving that cooperative techniques combined with NL positively reduce financial data volatility, our results lay the groundwork for improved financial forecasting and decision-making. The exercise has demonstrated that NL has great potential to enhance financial prediction models, which could have future applications in investment planning and risk organization.

groups

Khaled A. Hassan Mohmmed mail -

Hiba Awad Alla Ali Hussin mail -

Nadia Bushra Mohammed Ali mail -

Abdelsamie Eltayeb Tayfor mail

link https://doi.org/10.54216/IJNS.250424

Volume & Issue

Vol. Volume 25 / Iss. Issue 4

Details open_in_new

International Journal of Neutrosophic Science | 2025

Modeling Extreme Healthcare Costs Using the Neutrosophic Cauchy Distribution

Real data modelling of extreme events, such as rainfall, temperature, financial costs is very important in neutrosophic statistical methods. The Cauchy distribution is one of statistical models used for modelling such extreme events in natural processes. In cases of imprecise data which most often involve vague, incomplete and ambiguous information, standard statistical methods cannot fully describe the spectrum of uncertainty. In this study, we have considered a new Cauchy distribution under neutrosophic context to deal with uncertain data. The proposed neutrosophic Cauchy distribution (NCD) may analysis extreme events data involving incomplete observations. We provide basic mathematical characteristics and important statistical functions of the Cauchy model under neutrosophic framework. A complete procedure of random numbers generation using neutrosophic quantile function is discussed. The unknown parameters of the proposed are estimated using the maximum likelihood approach. Numerical results show that the proposed model adequately fits the data involving extreme and imprecise values. The performance and flexibility of the model are also supported by an application to a real data set.

groups

Afrah Al Bossly mail -

Adnan Amin mail

link https://doi.org/10.54216/IJNS.250422

Volume & Issue

Vol. Volume 25 / Iss. Issue 4

Details open_in_new

International Journal of Neutrosophic Science | 2025

Neutrosophic Burr Distribution for Modeling Health Risk Factors

The Burr distribution is one of the most important and commonly used probability distribution in statistical analysis. In this study, a new class of univariate distribution based on the Burr random variable is proposed. Characteristics of the proposed neutrosophic Burr distribution (NBD) are discussed. The neutrosophic form of the proposed distribution is particularly advantageous for handling the imprecise and uncertain information commonly present in real-world problems. The statistical properties and the shapes of corresponding probability density and cumulative density functions are illustrated. Some important functions commonly utilized in survival studies are formulated within neutrosophic structures. General expressions for other distributional properties of the proposed NBD are developed under neutrosophic framework. The inverse cumulative method is used to find random numbers from the suggested model. Maximum likelihood method for estimating the model parameters is described, and the performance of estimated parameters are assessed using a Monte Carlo simulation experiment. Finally, the paper demonstrates the practical use of the proposed model through a real-world application of malaria cases per thousand population at risk.

groups

Fuad S. Alduais mail -

Zahid Khan mail

link https://doi.org/10.54216/IJNS.250423

Volume & Issue

Vol. Volume 25 / Iss. Issue 4

Details open_in_new

Fusion: Practice and Applications | 2025

Compiler Sequence Optimization Using Machine Learning Prediction Method

Compiler optimization is crucial in improving program performance by improving execution speed, reducing memory usage, and minimizing energy consumption. Nevertheless, modern compilers, such as LLVM, with their numerous optimization passes, present a significant challenge in identifying the most effective sequence for optimizing a program. This study addresses the complex problem of determining optimal compiler optimization sequences within the LLVM framework, which encompasses 64 optimization passes, causing in an immense search space of 264264. Identifying the ideal sequence for even simple code can be an arduous task, as the interactions between passes are intricate and unpredictable. The primary objective of this research is to utilize machine-learning techniques to predict effective optimization sequences that outperform the default -O2 and -O3 optimization flags. The methodology involves generating 2,000 sequences per program and picking the one that achieves the shortest execution time. Three machine learning models—K-Nearest Neighbor (KNN), Decision Tree (DT), and Feedforward Neural Network (FFNN)—were employed to predict the optimization sequences based on features extracted from programs during execution. The study used benchmarks from Polybench, Shootout, and Stanford suites, each with varying problem sizes, to validate the proposed technique. The results demonstrate that the KNN model produced optimization sequences with superior performance compared to DT and FFNN. On average, KNN achieved execution times that were 2.5 times faster than those achieved using the O3 optimization flag. This research contributes to the field by programming the process of selecting optimal compiler sequences, which significantly reduces execution time and eliminates the need for manual tuning. It highlights the potential of machine learning in compiler optimization, offering a robust and scalable approach to improving program performance and setting the foundation for future advancements in the domain.

groups

Diyar Mohammed mail -

Esraa Hadi Alwan mail -

Ahmed Fanfakh mail

link https://doi.org/10.54216/FPA.180121

Volume & Issue

Vol. Volume 18 / Iss. Issue 1

Details open_in_new

American Journal of Business and Operations Research | 2025

A Multi-Server Queuing-Inventory System with Attraction-Retention Mechanisms for Impatient Customers and Catastrophes in Warehouse

This paper presents a multi-server Markovian queuing-inventory system (MQIS) that incorporates attractionretention (AR) mechanisms for impatient customers and models catastrophic inventory losses within a warehouse setting. The system consists of C identical servers, a limited waiting area, and a storage capacity of Q items. Periodic disruptions may destroy all inventory in the system, compelling waiting customers either to remain until stock is replenished or to exit the system. A subset of servers may take joint vacations when no customers are waiting. To analyze this queuing-inventory system (QIS), we derive balance equations using a three-dimensional continuous-time Markov chain framework, solving for steady-state solutions through a recursive method. We then derive performance metrics and identify special-case queuing-inventory models within the broader system. A cost-loss model is formulated to optimize the service rate and server vacation strategies, minimizing overall costs. A genetic algorithm is employed to conduct a cost analysis. We collected primary data from the Ethio Telecom district head office in Arba Minch, Ethiopia to validate our theoretical findings. The empirical analysis serves a dual purpose: to investigate performance measure sensitivity to parameter variations and to discuss an optimization problem aimed at minimizing expected total cost (ETC) while assessing the impacts of AR mechanisms and catastrophic events on ETC.

groups

Berhanu Mekonen Alemu mail -

Natesan Thillaigovindan mail -

Getinet Alemayehu Wole mail

link https://doi.org/10.54216/AJBOR.120203

Volume & Issue

Vol. Volume 12 / Iss. Issue 2

Details open_in_new