A Robust Disease Prediction System Using Hybrid Deep Neural Networks

K.; N. Mohana; R.

doi:https://doi.org/10.54216/JCIM.160109

International Journal of Neutrosophic Science | 2025

Neutrosophic Methodological Foundations of Marketing Research in the Rural Labor Market

This article introduces a neutrosophic methodological framework for conducting personnel marketing research in the rural labor market of Uzbekistan. Given the inherent uncertainty and indeterminacy in labor market dynamics, the study applies neutrosophic logic to enhance the reliability of marketing data regarding labor demand and supply. The research outlines the interrelated stages of personnel marketing analysis, incorporating neutrosophic sets to better identify discrepancies between labor demand and supply, the scale and causes of rural unemployment, and the structural needs for new professions. Key areas of focus include problem identification, goal formulation, data collection and analysis, forecasting labor market trends, and developing targeted interventions to mitigate unemployment and improve workforce qualifications. Additionally, the study proposes strategic marketing initiatives for rural employment assistance centers, integrating neutrosophic decision-making models to optimize labor market strategies. By adopting neutrosophic approaches, the study provides a robust, uncertainty-aware methodology for balancing labor market proportions and formulating evidence-based policies to enhance rural employment opportunities.

groups

Kholmuminov Shayzak Rakhmatovich mail

link https://doi.org/10.54216/IJNS.260129

Volume & Issue

Vol. Volume 26 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2025

Enhancement of Underwater Images using Color Correction and Weight Maps

Physical characteristics of underwater environments, such as absorption, scattering, and progressive color loss, are only a few of the many factors that cause underwater images to degrade. Additionally, the turbid water and marine plankton influence the degradation of these images. All of these play a major role in the difficulty of extracting features from underwater images. This study aims to develop a new system that combines color correction techniques and weight maps to address the challenges caused by underwater environments. First step: the color correction, which consists of both color compensation and white balance, are used to improve the colors of images. In the second step:  a comprehensive enhancement solution has been adopted on the two images that resulted from the first step by performing two different ways, the first image is improved by an image sharpening algorithm, and the gamma correction is used to process the second one. Four weights maps are applied for feature extraction and finally multi-scale fusion process is used to find the final enhanced image. Three types of underwater scenes are used (Bluish, Greenish and Foggy) to assess the suggested work. In addition to evaluating the results visually, a number of statistical metrics (IE, PCQI, AG, UIQM and UCIQE) are used to evaluate the results and compare them with previous works. The results indicate a marked improvement in all types of image.

groups

Safa Burha mail -

Asmaa Sadiq mail

link https://doi.org/10.54216/FPA.190118

Volume & Issue

Vol. Volume 19 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

Enhancing educational environments with Social Media Feedback Evaluation Employing Hybrid Neutrosophic Decision Optimization (HNDO) and Neutrosophic Sentiment Fusion (NSF)

This research work examines the critical challenge of enhancing educational environments through social media feedback, often impeded by the very uncertainties and complexities offered by textual data. Existing approaches either may indulge in sentiment analysis or may take the approach of basic data mining; nevertheless, they seldom consider ambiguity, contextual subtlety, and dynamic interventions. We propose an entirely new framework using Hybrid Neutrosophic Decision Optimization (HNDO) and Neutrosophic Sentiment Fusion (NSF) with deep learning-for advanced feature extraction-and reinforcement learning-for adaptive intervention strategies, with Explainable AI (XAI) for transparency. Presenting a new Neutrosophic Quantum Squirrel-Whale Decision Optimization (NQSWDO) framework to optimize educational enhancements based on feedback surveys and social media sentiment analysis, where it can collect, preprocess, extract features, fuse sentiments, optimize decisions, and detect concerns through reinforcement learning before interpreting feedbacks. A Neutrosophic Sentiment Fusion (NSF) model is applied to bring improvement into the accuracy of sentiment classification. Further refinement of educational improvements will come through the new application of hybrid neutrosophic decision optimization (HNDO), which incorporates multi-criteria decision analysis (MCDA) and fuzzy logic. For identification of key concerns, the VGG-Darknet detection model will be used, as well as a deep Q-network (DQN)-based reinforcement-learning system that dynamically intervenes in topic analysis. The last phase will comprehensively interpret feedback and adopt decision-making strategies to avoid wasting time in properly formulating useful educational policies. The results from the experiments indicate the practicality of the proposed framework for improving education decision-making through advanced methodologies on sentiment analysis, optimization, and reinforcement learning.

groups

Walaa Fouda mail -

Asmaa Hegazy mail -

Najla M. Alnaqbi mail -

Ebru Ozbilge mail -

Emre Ozbilge mail

link https://doi.org/10.54216/IJNS.260130

Volume & Issue

Vol. Volume 26 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

Student Academic Performance Classification Using N-Valued Interval Neutrosophic Sets with Optimization Algorithms for Significant Feature Selection

The most effectual tools for demonstrating uncertainty in decision-making issues are the neutrosophic set (NS) and its additions, like interval NS (INS), complex NS (CNS), and interval complex NS (ICNS). NS delivers an effectual and precise method for defining an imbalance of information as per the data features. In present times, students’ academic performances have been evaluated on the base of regular examinations or memory-related tests and by equating their performances to recognize the features for forecasting their academic excellence. The prediction of student academic performance is involved in Educational data mining (EDM), which mainly focuses on using data mining methods in the educational side. EDM progress models for finding data, which is a result of educational surroundings. This paper presents a Student Academic Performance Prediction Using N-Valued Interval Neutrosophic Sets and Optimization Algorithms (SAPP-NINSOA). The main intention of the SAPP-NINSOA technique is to provide a prevalent technology for predicting students’ academic performance using an advanced optimization algorithm. At first, the data pre-processing stage applies Z-score normalization to convert input data into a beneficial format. Besides, the secretary bird optimization algorithm (SBOA) to select the relevant features from input data has executed the feature selection process. Next, the proposed SAPP-NINSOA model designs the N‐Valued Interval Neutrosophic Sets (NVINS) method for the classification process. Finally, the arithmetic optimization algorithm (AOA) fine-tunes the parameter values of the NVINS model. An extensive range of experimentation was led to certify the performance of the SAPP-NINSOA technique. The simulation outcomes stated that the SAPP-NINSOA algorithm emphasized furtherance when compared to other existing systems.

groups

Nahla Moussa mail -

Cuauhtemoc Samaniego mail -

Moustafa Mohamed Abouelnour mail -

Wael F. Ali mail

link https://doi.org/10.54216/IJNS.260131

Volume & Issue

Vol. Volume 26 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

Finite time Stability and Synchronization of the Glycolysis Reaction-Diffusion model

Finite-time stability is a critical property for systems where rapid stabilization is required, as it ensures that the system reaches and maintains equilibrium within a specified time frame, regardless of initial conditions. This contrasts with asymptotic stability, which only guarantees eventual convergence over an indefinite period. This research focuses on demonstrating the finite-time stability of the glycolysis reaction-diffusion system at its equilibrium point. The equilibrium points of the system are derived, and finite-time stability conditions are established. Definitions and lemmas are provided to support the theoretical framework, including conditions for finite-time convergence and Lyapunov stability. A key result shows that the system possesses a unique equilibrium point that can achieve finite-time stability under certain conditions. Additionally, the finite-time synchronization scheme is discussed, highlighting the process of rapidly achieving synchronized behavior in reaction-diffusion systems. The proposed method involves associating the main system with a response system and addressing synchronization discrepancies through the introduction of an error vector. This research provides a robust framework for understanding and achieving finite-time stability and synchronization in complex reaction-diffusion systems.

groups

Raed Hatamleh mail -

Issam Bendib mail -

Ahmad Qazza mail -

Rania Saadeh mail -

Adel Ouannas mail -

Mohamed Dalah mail

link https://doi.org/10.54216/IJNS.250431

Volume & Issue

Vol. Volume 25 / Iss. Issue 4

Details open_in_new

International Journal of Neutrosophic Science | 2025

The Topology T (PR⋆) ^⊛ in the Frame of Primal Topological Spaces

In this paper, we will use the family of regular⁺-open subsets to present and examine two new operators (.){PR⁺}⊛ and Cl{PR⁺}⊛. We demonstrate that, in contrast to the operator (.){PR⁺}⊛, the operator Cl{PR⁺}⊛ is a Kuratowski closure operator. We show that each of these operators lies between two previously defined operators where for each subset H&sube;S, H_Pᶲ&sube;H_{PR⁺}⊛&sube;H_PRᶲ and H&sube;Cl_Pᶲ(H)&sube;Cl_{PR⁺}⊛(H)&sube;Cl_{PR}ᶲ(H). Furthermore, we show that the topology, denoted by T_{PR⁺}⊛, which is obtained by Cl_{PR⁺}⊛ is independent from T and it is finer than T_η⁺, where T_η⁺ is the family of all unions of regular⁺-open subsets of (S, T). Then we demonstrate several fundamental results concerning this new structure and present many illustrative examples that relate to our conclusions. Finally, by using the operator Cl_{PR⁺}⊛ we introduce a new notion namely, P-generalized closed sets, and study some of their basic properties.

groups

Amani Rawshdeh mail -

Ahmad Al-Omari mail

link https://doi.org/10.54216/IJNS.260127

Volume & Issue

Vol. Volume 26 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

Logarithmic neutrosophic logical communicated to basic interaction aggregating operators using various finite weighted with extension

 In this paper, we present novel techniques for the logarithmic neutrosophic interaction (LogNI) aggregating operator. The new averaging and geometric operations of LogNI numbers are studied using the universal aggregation function. The LogNI are satisfied some algebraic properties. Four novel aggregating operators are presented: LogNI weighted averaging, LogNI weighted geometric, generalized LogNI weighted averaging, and generalized LogNI weighted geometric.

groups

Nasreen kausar mail -

Swarnakar Dornala mail -

M. S. Malchijah Raj mail -

Ebru Ozbilge mail -

Emre Ozbilge mail

link https://doi.org/10.54216/IJNS.260132

Volume & Issue

Vol. Volume 26 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

ƝҪͳ- Confused Neutrosophic Crisp Sets

The importance of Neutrosophic crisp triple sets and their important effects on our daily lives was and still is aturing point in the history of science, especially mathematical sciences. From here, we began a ƝҪͳ–confused, concept that is based on both ƝҪͳ–interior, and ƝҪͳ– exterior, and important characteristic emerged because of mixing the characteristic of ƝҪͳ– interior and ƝҪͳ– exterior sets. We supported this with various examples.

groups

Asra Mohammed Jasem mail -

L. A. A. Al-Swidi mail -

Ali H. M. Al-Obaidi mail

link https://doi.org/10.54216/IJNS.260133

Volume & Issue

Vol. Volume 26 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science |

Beta Special Function of Symbolic 2-Plithogenic and 3-Plithogenic Real Numbers

The main goal of this paper is to define and study the concept of beta special function defined over the ring of symbolic 2-plithogenic numbers and symbolic 3-plithogenic numbers. Besides, we prove some of the elementary properties of these two versions of beta function by using the isomorphism that connect plithogenic numbers with the classical real numbers. In addition, we represent the relationships between plithogenic beta functions and classical beta functions using the same proposed technique.

groups

Nabil Khuder Salman mail

link https://doi.org/10.54216/IJNS.260134

Volume & Issue

Vol. Volume 26 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2025

A Robust Disease Prediction System Using Hybrid Deep Neural Networks

One of the most intriguing study subjects in the scientific world is medical data visualization. Researchers focus more on creating a medical that is reliable and efficient. Over the past ten years, varieties of methods have been developed, and investigation is still ongoing to improve healthcare systems' efficiency. To forecast or identify illnesses from medical information, the first stage in medical evaluation of information systems uses statistical techniques. However, statistical techniques yield unreliable findings due to the high amount and variety of the data, which affects the performance of the healthcare system. Numerous methods and solutions for conventional problems were made possible by the advancement of technology and the implementation of AI in the clinical field. To improve patient results and save medical expenses, acute illness prediction is essential. With an emphasis on diabetes, CVD, and specific cancers, this study investigates the effectiveness of many hybrid DL approaches in forecasting the beginning of chronic illnesses. Using a varied dataset of 100 thousand patient records, we evaluated the performance of a few hybrid methods, such as Autoencoder-Support Vector Machine (AE-SVM), Gradient Boosting-Neural Network (GB-NN), and Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM). Our findings show that when it came to forecasting the development of disease within a period of five years the CNN-LSTM model offered the greatest accuracy of 95.3%, closely followed by GB-NN with 94.1% and AE-SVM with 92.8%. Along with discussing the possible incorporation of these hybrid models into healthcare DSS, the study also found important predictive criteria. Our results indicate that hybrid DL techniques, as opposed to conventional single-algorithm approaches, can greatly improve early disease identification and treatment procedures in healthcare settings.

groups

K. Tharageswari mail -

N. Mohana Sundaram mail -

R. Santhosh mail

link https://doi.org/10.54216/JCIM.160109

Volume & Issue

Vol. Volume 16 / Iss. Issue 1

Details open_in_new