Neutrosophic Fusion Based Rough Set Theory for Intelligent Decision Support System on Business-to-Business (B2B) Sales Estimation

Elvir; Ilyos; Irina; Emil; Elena

doi:https://doi.org/10.54216/IJNS.260307

International Journal of Neutrosophic Science | 2025

Using Neutrosophic Soft Set to predict Higher Education Academic Performance

Neutrosophic Logic is a neonate research field in which every proposition is assessed to have the proportion (percentage) of truth in a sub-set T, the proportion of indeterminacy in a sub-set I, and the proportion of falsity in a sub-set F. Neutrosophic set (NS) is effectively implemented for undetermined data processing and establishes benefits for handling the indeterminacy data. In the academic industries, early performance prediction of students is significant to the academic community so strategic interference might be planned before students attain the final semester. Forecasting the performance of students has turned into a challenging task owing to the rising number of data in educational procedures. The educational data mining (EDM) models are involved in extracting a pattern to explore hidden data from educational information. Currently, Machine learning (ML) and Artificial intelligence (AI) are implemented in numerous domains generally in the field of education to evaluate and analyze several features of educational datasets gathered from many educational institutions. This study develops a Leveraging Generalized Possibility Neutrosophic Soft Set with Feature Selection for Accurate Students’ Academic Performance Prediction Model (GPNSSFS-SAPPM). The intention of the proposed GPNSSFS-SAPPM system relies on improving the prediction model of students’ higher education performance using metaheuristic optimization algorithms.  The data pre-processing model is employed at first by applying mean normalization for converting input data into a suitable format. In addition, the golf optimization algorithm (GOA) is exploited for the feature selection process. Followed by, the classification process is done by generalized possibility neutrosophic soft set (GPNSS). At last, the parameter tuning process is performed through henry gas solubility optimization (HGSO) algorithm to improve the classification performance of the GPNSS classifier. A wide-ranging experimentation was performed to prove the performance of the GPNSSFS-SAPPM method. The experimental results specified that the GPNSSFS-SAPPM model underlined advancement over other recent techniques.

groups

Sally Afchal mail -

Muhammad Eid Balbaa mail

link https://doi.org/10.54216/IJNS.260302

Volume & Issue

Vol. Volume 26 / Iss. Issue 3

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2025

AI and Machine Learning for Breast Cancer Diagnosis Using Histopathology and Clinical Decision Systems

The diagnosis of breast cancer depends on histopathology for precise and trusted evaluation between malignant tumor cells and benign cells. The analysis demands significant time and creates additional room for human errors. A deep learning approach for computer-aided diagnosis (CAD) establishes techniques to enhance the classification performance in this study. The proposed methods utilize One-hot encoding with VGG-16 for feature extraction to achieve 98% accuracy with BreakHis data while DBN for feature learning reaches 98% accuracy on BreakHis and 96% on Kaggle. SSGAN addresses unannotated images effectively with up to 89% accuracy. Through its application, deep learning technology proves to enhance breast cancer identification while decreasing the workload on medical pathologists. One-hot encoding remains efficient for computations yet the DBN extraction method produces superior features. The SSGAN model increases labeling accuracy when it uses available labeled data and unlabeled data to lower annotation expenses. Deep learning technologies validate their ability to transform breast cancer histopathological diagnosis through precision-enhanced efficient examination methods especially with semi-supervised GAN systems.

groups

Swati R. Nitnaware mail -

Bindu Madhavi Tummala mail -

Naga Siva Jyothi Kompalli mail -

Lakshmi Ramani Burra mail -

Nelli Sreevidya mail -

Gunavardini V. mail

link https://doi.org/10.54216/JISIoT.160222

Volume & Issue

Vol. Volume 16 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2025

A Novel Blockchain-Assisted Deep Learning Model for Enhancing Healthcare Data Security with Advanced Metaheuristic Optimization Techniques in Internet of Things

The Internet of Things (IoT) devices and technologies are more effective in the medical sector. It includes the combination of numerous interrelated sensor, systems, and devices for gathering, examining, and conveying health-related information for medicinal uses. In the healthcare field, Blockchain (BC) technology embraces huge latent for increasing the security and confidentiality of data. BC-aided intrusion detection on IoT healthcare methods is a new technique for increasing the privacy and security of complex health data. Patients have superior control throughout their information’s growth, granting or revoking access as needed, but healthcare employees will modernize data sharing and certify the reliability of significant data. On the other hand, deep learning (DL) is excellent for transforming healthcare analytics, presenting rapid and tremendously precise estimations of medicinal circumstances. This paper presents a Blockchain-Assisted Deep Learning Model for Enhancing Healthcare Data Security with Metaheuristic Optimization Techniques (BCDL-HDSMOT) model. The main intention of the BCDL-HDSMOT technique is to develop an effective method for enhancing data security in the medical sector. At first, the blockchain technique is applied in healthcare to enhance data security, interoperability, and transparency while ensuring patient privacy and efficient record management. Next, the data pre-processing stage employs min-max normalization to clean, transform, and organize input data into a suitable quality for analysis. Besides, the black widow optimization algorithm (BWOA) has been deployed for the feature selection process to select the relevant features from input data. For the classification process, the proposed BCDL-HDSMOT technique designs a versatile long-short-term memory (VLSTM) method. At last, the improved seagull optimization algorithm (ISOA)--based hyperparameter selection process is performed to optimize the classification results of the VLSTM method. The experimental evaluation of the BCDL-HDSMOT algorithm can be tested on a benchmark dataset. The wide-ranging outcomes highlight the significant solution of the BCDL-HDSMOT approach to the cyberattack detection process.

groups

R. Sugantha Lakshmi mail -

N. Suguna mail

link https://doi.org/10.54216/FPA.190229

Volume & Issue

Vol. Volume 19 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2025

Automated Kidney Cancer Classification using White Shark Optimizer with Ensemble Majority Voting Model on Pathology Images

Kidney cancer is a lethal cancerous and very dangerous disease caused by genetic renal disease or by kidney tumors, and some patients might survive since there is no technique for earlier diagnosis of kidney tumor. Earlier diagnosis of kidney tumor assists physicians to begin proper treatment and therapy for the patient, which prevent kidney cancers and renal transplantation. Accurate classification of kidney tumor is vital for prediction and treatment planning. However, manual classification by pathologists could be subjective and time-consuming, and there can be considerable inter-observer variability. With the development of artificial intelligence (AI), automated tools enabled by machine learning (ML) and deep learning (DL) methods could predict cancers. This study designs a new white shark optimizer with an ensemble majority voting based kidney cancer classification (WSO-EMVKCC) technique on pathology images. The presented WSO-EMVKCC technique intends to identify the different grades of kidney cancer using DL and ensemble voting concepts. To accomplish this, the presented WSO-EMVKCC technique employs a deep convolutional neural network based Xception technique for the feature extraction process. Moreover, the WSO model has been used for the optimal hyperparameter tuning of the Xception approach. Furthermore, an ensemble majority voting classifier including three ML techniques like long short-term memory (LSTM), sparse autoencoder (SAE), and gated recurrent unit (GRU) models are employed for kidney cancer classification. The stimulation validation of the WSO-EMVKCC model is performed on the open access histology image database from Kaggle repository. The stimulated values illustrate the promising performance of the WSO-EMVKCC algorithm over other DL techniques.

groups

Ashrf Althbiti mail

link https://doi.org/10.54216/FPA.190230

Volume & Issue

Vol. Volume 19 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2025

Quadripartitioned Neutrosophic Pythagorean Soft Set for Financial Cost Estimation in E-Commerce Supply Chain Management

The idea of neutrosophic set (NS) from a philosophical viewpoint is a generality of the theory of indeterminacy FS (IFS) and fuzzy set (FS). A NS is considered by a falsity, a truth and indeterminacy membership functions and all membership amount is an actual standard or a non-standard sub-set of the non-standard unit interval ]−0, 1+[. E-commerce is successful for the growth of novel business methods and should be constantly improved in the numerous decades. According to the growing E-commerce, supply chain management (SCM) has been strongly affected as we are now previously overcome by achievement in either developed or developing economies. Nowadays, E-commerce in advanced economy characterizes the newest lead of possibility in physical distribution systems and SCM, even if it emerging economy, e-commerce market is even in its infancy however, it is increasing and become integral part of commercial life. This paper presents a Quadripartitioned Neutrosophic Pythagorean Soft Set-Based Prediction Model for Supply Chain Management (QNPSSPM-SCM) model Using Hybrid Optimization Algorithms. The proposed QNPSSPM-SCM technique is for presenting an advanced E-commerce in SCM using advanced optimization techniques. At first, the min-max normalization method has been applied in the data pre-processing stage to convert input data into a beneficial pattern. In addition, the presented QNPSSPM-SCM system executes quadripartitioned neutrosophic Pythagorean soft set (QNPSS) technique for the prediction process. At last, the hybrid grey wolf optimization and teaching-learning-based optimization (GWO‐TLBO) algorithm fine-tunes the hyperparameter values of the QNPSS model optimally and results in better performance of prediction. The experimental validation of the QNPSSPM-SCM method is verified on a benchmark database and the outcomes are determined regarding different measures. The experimental outcome underlined the development of the QNPSSPM-SCM method in prediction process.

groups

N. Metawa mail -

Sait Revda Dinibutun mail -

Maha Saad Metawea mail

link https://doi.org/10.54216/IJNS.260301

Volume & Issue

Vol. Volume 26 / Iss. Issue 3

Details open_in_new

International Journal of Neutrosophic Science | 2025

An Investigation of Complex Linear Diophantine Fuzzy Ideals in BCK-Algebras

A complex linear Diophantine fuzzy (CLDF) set extends a linear Diophantine fuzzy set (LDFS) by handling uncertainty with complex-valued membership degrees within a unit disc. In this paper, we combine the notions of LDFS, BCK-algebra, and complex fuzzy set (CFS) to preface and elaborate the innovative concepts of CLDF subalgebras (CLDF − Subs), CLDF ideals (CLDF − Ids), CLDF implicative ideals (CLDF − IIds), and CLDF positive implicative ideals (CLDF − PIIds) in BCK-algebras, and probe their fundamental characteristics. These new notations of certain kinds of algebraic substructures in BCK-algebras serve as a bridge among CLDFS, crisp set, and BCK-algebra and also demonstrate the influence of the CLDFS on a BCK-algebra. Moreover, we examine some illustrative examples and prevalent features of these innovative notions in detail. Finally, characterizations of these intricate fuzzy structures are given, and related results for ideals, implicative ideals, and positive implicative ideals in the view of CLDFSs are obtained.

groups

Anas Al-Masarwah mail -

Manivannan Balamurugan mail -

Thukkaraman Ramesh mail -

Majdoleen Abuqamar mail -

Maryam Abdullah Alshayea mail

link https://doi.org/10.54216/IJNS.260303

Volume & Issue

Vol. Volume 26 / Iss. Issue 3

Details open_in_new

International Journal of Neutrosophic Science | 2025

Fuzzy Bounded Linear Operators on Fuzzy Anti-Normed Spaces

The primary goal of this paper is to study and introduce fuzzy anti-normed linear spaces, as well as, some additional properties concerning these spaces. From this point of view, some theoretical results are obtained; for example, it was proved that the space of all linear and fuzzy bounded operators over fuzzy anti-normed linear spaces is fuzzy complete. Moreover, some additional theoretical results are stated and proved.

groups

Jaafer Hmood Eidi mail -

Aamena Al-Qabani mail -

Fadhel S. Fadhel mail -

Jehad R. Kider mail

link https://doi.org/10.54216/IJNS.260304

Volume & Issue

Vol. Volume 26 / Iss. Issue 3

Details open_in_new

International Journal of Neutrosophic Science | 2025

Bipolar Fuzzy Hypersoft Set with Heuristic Search Based Customer Retention Prediction Model in Financial Sectors

From a philosophical viewpoint, the theory of neutrosophic set (NS) is a simplification of the concept of Fuzzy Set (FS) and intuitionistic FS (IFS). An NS is illustrated by a truth, an indeterminacy, and a falsity membership functions and every membership degree is an actual standard or a non-standard sub-set of the non-standard unit range of] −0, 1+ [.  Customer churn is when clients stop utilizing a company’s service or product. Moreover, it is also named customer retention, which is vastly significant metric as it is much less costly to keep the existing customers than to obtain novel customers. The prediction of churn plays an essential part in customer retention because it forecasts clients who are in danger of leaving the organization. In the banking sector, the customer attrition arises when clients quit utilizing the services and goods provided by the bank for some time. So, customer churn is vital in today’s economic banking industry. This study proposes a Leveraging Bipolar Fuzzy Hypersoft Set with Heuristic Optimization Algorithms-based Customer Retention Prediction (BFHSS-HOACRP) technique in financial sectors. The BFHSS-HOACRP technique applies optimized techniques to predict the customer retention behavior in the industry of bank.  Initially, the mean normalization technique is utilized in the data pre-processing stage to prepare raw data into a suitable format for analysis and modeling. For the selection of feature process, the grasshopper optimization algorithm (GOA) method is employed to identify and select the most relevant features from an input data. In addition, the proposed BFHSS-HOACRP technique implements bipolar fuzzy hypersoft set (BFHSS) method for the classification process. Additionally, the spider monkey optimization (SMO)-based hyperparameter selection process is performed to optimize the classification results of BFHSS model. The efficacy of the BFHSS-HOACRP approach is examined under the bank customer churn prediction dataset. The comparison analysis of the BFHSS-HOACRP approach portrayed a superior accuracy value of 95.41% over existing techniques.

groups

Alexander Kalinin mail -

Inomjon Yusubov mail -

Tatiana Yakubova mail -

Victoria Kruglyakova mail -

Tatyana Khorolskaya mail

link https://doi.org/10.54216/IJNS.260305

Volume & Issue

Vol. Volume 26 / Iss. Issue 3

Details open_in_new

International Journal of Neutrosophic Science | 2025

Pentapartitioned Neutrosophic Vague Soft Set with Optimization Algorithm Based Business Intelligence Framework for Data-Driven Demand Forecasting Model

Neutrosophic logic is a neonate research field in which all propositions are anticipated to have the percentage (proportion) of truth in a sub-set T, the proportion of falsity in a sub-set F, and the proportion of indeterminacy in a sub-set I. Neutrosophic set (NS) is efficiently applied for indeterminate information processing and provides assistance to address the indeterminacy information of data. Demand Forecasting, undoubtedly, is the only most significant element of some organization's Supply Chain. It defines the predictable demand for the future and sets the preparedness level that is needed on the supply side to match the demand. Business intelligence (BI) plays a significant part in helping the decision maker obtain the understanding for increasing productivity or improved and faster decisions. Furthermore, it improves and helps the efficacy of functional rules and its influence on corporate-level decision-making that provides improved strategic options in dynamic business environments. Within the period of data-driven demand forecasting, the integration of artificial intelligence (AI) technologies in BI models has transformed the system groups that utilize and analyze data. In the manuscript, a Business Intelligence Framework for a Data-Driven Demand Forecasting Model Using a Pentapartitioned Neutrosophic Vague Soft Set (BIFDDF-PNVSS) technique is proposed. The main goal of the BIFDDF-PNVSS technique is to progress the accurate BI structure for the demand forecasting method. The data pre-processing stage is initially applied for converting input data into a beneficial format by the Z-score normalization method. Moreover, the PNVSS technique is utilized for the data-driven demand prediction model. Finally, to improve the prediction performance of the PNVSS model, the parameter tuning process is performed by implementing the cheetah optimization algorithm (COA) model. A comprehensive experimentation is performed to verify the performance of the BIFDDF-PNVSS methodology under the demand forecasting dataset. The BIFDDF-PNVSS methodology outperforms existing techniques with a superior MSE of 0.0008, demonstrating its exceptional accuracy in demand forecasting compared to other models.

groups

Sanat Chuponov mail -

Tukhtabek Rakhimov mail -

Natalya Shcherbakova mail -

Vladimir Kurikov mail -

Olga Berezhnykh mail -

K. Shankar mail

link https://doi.org/10.54216/IJNS.260306

Volume & Issue

Vol. Volume 26 / Iss. Issue 3

Details open_in_new

International Journal of Neutrosophic Science | 2025

Neutrosophic Fusion Based Rough Set Theory for Intelligent Decision Support System on Business-to-Business (B2B) Sales Estimation

One of the most effective devices to model uncertainty in decision-making difficulties is the Neutrosophic set (NS) and its extensions, like interval NS (INS), interval complex NS (ICNS), and complex NS (CNS). Predicting the result of sales benefits is the essential element of effective business management. Traditionally, undertaking this prediction has depended generally on individual human analyses in the sales decision-making process. A model of business-to-business (B2B) sales predicting is a difficult decision-making procedure. There are several methods for supporting this procedure; however, generally it is even established on the individual judgments of the decision-maker. The B2B sales predicting problem is represented as the prediction problem. Presently, intelligible predictive methods were analyzed and studied utilizing the technique of machine learning (ML) to increase the upcoming sales prediction. This paper presents an Adaptive Intelligent Business to Business Sales Estimation using Neutrosophic Fusion of Rough Set Theory (AIB2BSE-NFRST) model. The main intention of AIB2BSE-NFRST technique is to enhance prediction analysis for B2B sales estimation using advanced techniques. Initially, the data pre-processing performs min-max normalization to prepare raw input data for analysis by transforming it into a structured format. Furthermore, the proposed AIB2BSE-NFRST technique utilizes NFRST method for the prediction process. To further optimize model performance, the seagull optimization algorithm (SOA) is utilized for hyperparameter tuning to ensure that the best hyperparameter is selected. To exhibit the enhanced performance of the presented AIB2BSE-NFRST model, a comprehensive experimental analysis is made under the E-commerce sales dataset. The AIB2BSE-NFRST model outperforms existing techniques with a superior MSE of 0.0033, highlighting its exceptional accuracy in B2B sales estimation.

groups

Elvir Akhmetshin mail -

Ilyos Abdullayev mail -

Irina Gladysheva mail -

Emil Hajiyev mail -

Elena Klochko mail

link https://doi.org/10.54216/IJNS.260307

Volume & Issue

Vol. Volume 26 / Iss. Issue 3

Details open_in_new