ASPG Menu
search

American Scientific Publishing Group

Research Feed

Found 3836 matches for "All Articles"
International Journal of Neutrosophic Science | 2025

Integrating Machine Learning with Two-Person Intuitionistic Neutrosophic Soft Games for Cyberthreat Detection in Blockchain Environment

Cyber-attacks involve a large number of malicious events including phishing, malware attacks, ransomware, social engineering, etc. Automatic cyber-attack recognition and classification are obtained by different technologies and techniques, including artificial intelligence (AI), data analytics, machine learning (ML), deep learning (DL), and other forward-thinking approaches. As a generality of the fuzzy set (FS) and intuitionistic FS (IFS), the Neutrosophic set (NS) can handle incongruous, uncertain, and indeterminacy data where the indeterminate is explicitly measured, and the degree of truth, indeterminacy, and false functions are liberated. It may successfully define inconsistent, uncertain, and incomplete data and overcome certain limitations of the present techniques in representing uncertain decision data. The indeterministic portion of uncertain information, presented in the NS concept, has been instrumented in proper decision-making that is impossible by the IFS concept. Cyber threat detection and classification is a crucial research area that develops intelligent systems that can identify and categorize a variety of cyber-attacks in real time. This article develops an Integrating Machine Learning with Two-Person Intuitionistic Neutrosophic Soft Games for Cyber threat Detection in Blockchain Environment (IMLTPIN-CDBE) system. The main aim of the IMLTPIN-CDBE methodology lies in the automatic recognition of the cyber-threat BC platform.  The initial phase of data normalization using a min-max scalar is conducted in the IMLTPIN-CDBE method. Moreover, the two-person intuitionistic neutrosophic soft games (TPINSSG) technique is applied for cyberattack recognition. Finally, the grasshopper optimization algorithm (GOA) technique is applied for fine-tuning the hyperparameter included in the TPINSSG classifiers. A sequence of experiments has been conducted on the ransomware database to exhibit the great performance of the IMLTPIN-CDBE method. The empirical findings show the supremacy of the IMLTPIN-CDBE method over other current approaches.

groups
Abdalla Ibrahim Abdalla Musa mail -
Mohammed Abdullah Al-Hagery mail
link https://doi.org/10.54216/IJNS.250204

Volume & Issue

Vol. Volume 25 / Iss. Issue 2

Details open_in_new
International Journal of Neutrosophic Science | 2025

Neutrosophic Net-RBF Neural Networks with Bayesian Optimization Based Sentiment Analysis on Low Resource Language

Sentiment Analysis (SA) is a crucial task for analyzing online content over languages for processes such as content moderation and opinion mining. However advanced NLP modeling approaches frequently need an abundance of training datasets to accomplish their outcomes. SA is a classification task where the polarity of text dataset is detected, viz., to analyze a document or sentence expressing a positive, negative, or neutral sentiment. Deep learning (DL) becomes predominant in resolving Natural Language Processing (NLP) tasks. On the other hand, this technique requires a significantly enormous quantity of annotated corpus, which is not easier to attain, particularly under these lower resource settings. Neutrosophic Net-RBF Neural Network (NNRBFNN) combines the principle of neutrosophic logic (NL) with RBF-NNs for handling data indeterminacy and uncertainty. This combined strategy optimizes conventional NNs by incorporating the possibility of addressing incomplete and imprecise data, augmenting decision-making in challenging circumstances. This paper introduces a Neutrosophic Net-RBF Neural Network with Sentiment Analysis on a Low Resource Language (NNRBFNN-SALRL) model. To accomplish this, the NNRBFNN-SALRL method undertakes data pre-processing to transform the input dataset into a helpful format, and Term Frequency Inverse Document Frequency (TF-IDF) technique is utilized for the process of word embedding. For the classification method, the NNRBFNN model is used. To optimize the recognition outcomes of the NNRBFNN method, the hyperparameter tuning technique can be done using the Bayesian Optimization Algorithm (BOA). Wide-ranging experiments were conducted to validate the superior outcomes of the NNRBFNN-SALRL method. The empirical findings indicated that the NNRBFNN-SALRL method emphasized betterment over other approaches.

groups
Abdalla Ibrahim Abdalla Musa mail -
Mohammed Abdullah Al-Hagery mail
link https://doi.org/10.54216/IJNS.250205

Volume & Issue

Vol. Volume 25 / Iss. Issue 2

Details open_in_new
International Journal of Neutrosophic Science | 2025

Direct and converse approximation theorems in neutrosophic L_(δ,p) (U) space

A neutrosophic is a strong framework to characterize novel mathematical structures. This framework is more suitable and flexible set side by side to fuzzy sets and intuitionistic fuzzy sets. In this work, we focus on some famous mathematical spaces like Ls,p (u)when we work on displaying a feature the immediate and contrary theorems of unrestrained functions in the spaceLs,p (u)are considered. Also, some characteristics of modification symmetric and modulus of neutrosophic smoothness have been discussed. Moreover, the identical among approximate tools such as the neutrosophic K-functional and neutrosophic modulus of softness.

groups
Alaa Adnan Auad mail -
Mohammed A. Hilal mail
link https://doi.org/10.54216/IJNS.250206

Volume & Issue

Vol. Volume 25 / Iss. Issue 2

Details open_in_new
International Journal of Neutrosophic Science | 2025

Pentapartitioned Neutrosophic Vague Soft Sets and its Applications

The objective of this paper is to extend the concept of standard soft sets to pentapartitioned neutrosophic vague soft sets (PNVSSs) by applying soft set theory to pentapartitioned neutrosophic vague sets (PNVSs)to make them stronger and more usable. We additionally describe its null, absolute, and fundamental operations, such as complement, subset, equality, union, and intersection, using examples. In addition, we defined the Pentaprtitioned Neutrosophic Vague multiset and the Possibility Pentaprtitioned Neutrosophic Vague sets (PPNVSs). We also look at several related properties and the proofs for them. Finally, this concept is applied to a decision-making problem, and its viability is demonstrated using an example. Related properties and the proofs for them. Finally, this concept is applied to a decision-making problem, and its viability is demonstrated using an example.

groups
Manal Al-labadi mail -
Shuker Khalil mail -
Radhika V. R. mail -
Mohana K. mail
link https://doi.org/10.54216/IJNS.250207

Volume & Issue

Vol. Volume 25 / Iss. Issue 2

Details open_in_new
International Journal of Neutrosophic Science | 2025

Integrating Neutrosophic Logic with Bi-directional LSTM Model for Predicting Stock Market Movements

In this paper, we present sentiment analysis on Twitter data by employing Neutrosophic Sentiment Analysis (NSA). NSA captures sentiments by considering three aspects: truth, falsehood, and indeterminacy, offering a more nuanced understanding of sentiment in tweets. To enhance this analysis, we integrate the results from Neutrosophic logic (NL) sentiment analysis into a Bi-directional Long Short-Term Memory (LSTM) model. This integration takes use of NL's capacity to manage uncertainty and indeterminacy in social media material, as well as the Bi-directional LSTM's capability to capture temporal relationships in sequential data. Our combined NL-Bidirectional LSTM technique attempts to increase the precision of forecasting, particularly when it comes to predicting stock market patterns based on Twitter sentiment. Through comprehensive evaluation, we demonstrate the effectiveness of this approach, highlighting its potential to address the inherent uncertainties and indeterminacies in social media data and thereby provide more reliable predictions for stock market movements.

groups
S.S. Saravanaraj mail -
Vediyappan Govindan mail -
Mana Donganont mail -
Broumi Said mail
link https://doi.org/10.54216/IJNS.250208

Volume & Issue

Vol. Volume 25 / Iss. Issue 2

Details open_in_new
International Journal of Neutrosophic Science | 2025

New approach for subbisemiring of bisemiring is applied to complex cubic anti neutrosophic set and its extension

We construct and analyze the concept of complex cubic anti neutrosophic subbisemiring (ComCANSBS). We analyze the important properties and homomorphic aspects of ComCANSBS. For bisemirings, we propose the ComCANSBS level sets. A complex neutrosophic subset of bisemiring Ⓢ is represented by the symbol Γ if and only if each non-empty level set R(℘,κ), where R) = |ℜ⊤Γ ·eiθ z}|{ℑ⊤Γ ,z}|{ℜ גΓ ·eiθz}|{ℑ גΓ ,z}|{ℜΓ ·eiθz}|{ℑΓ ,ℜ⊤Γ ·eiθℑ⊤Γ ,ℜ גΓ · eiθℑ גΓ,ℜΓ · eiθℑΓ ) is a ComCANSBS of Ⓢ. Let Υ be a ComCANSBS of bisemiring Ⓢ. If and only if Υ is a ComCANSBS of Ⓢ × Ⓢ, then Γ is a ComCANSBS of bisemiring Ⓢ. Let Γ be the strongest complex anti neutrosophic relation of bisemiring Ⓢ. We show that homomorphic images of all ComCANSBSs are ComCANSBSs, and homomorphic pre-images of all ComCANSBSs are ComCANSBSs. There are examples given to illustrate our results.

groups
Aiyared Iampan mail -
Murugan Palanikumar mail
link https://doi.org/10.54216/IJNS.250209

Volume & Issue

Vol. Volume 25 / Iss. Issue 2

Details open_in_new
Journal of Cybersecurity and Information Management | 2025

Modelling a Dense Convolutional Model for Crop Yield Prediction Using Kernel Computation

Crop yield prediction is performed based on crop, water, soil and environmental parameters, which is now a potential research field. Machine-learning approaches are extensively utilized for extracting significant crop features. ML approaches help in handling the issues over the crop prediction process. Some essential issues like linear and non-linear data mapping among the crop yielding values and input data need to be analyzed. However, the performance relies on the quality of extracted features. Here, a novel dense convolutional Network model with a kernel is designed to resolve the challenges identified. Based on feature learning, the anticipated model predicts the crop yielding value and linearly maps the crop yielding output with a nominal threshold value. Here, MATLAB 2020a simulator is used and various metrics like precision, accuracy, recall, F1-score, MAPE, RMSE and value are evaluated with various approaches. The model shows a superior trade-off than other approaches and intends to give better prediction accuracy. The model preserves the original data without disturbing the overall incoming values.

groups
Bhavani Vasantha mail -
G. Pradeepini mail
link https://doi.org/10.54216/JCIM.150108

Volume & Issue

Vol. Volume 15 / Iss. Issue 1

Details open_in_new
Journal of Cybersecurity and Information Management | 2025

HEART SAVIOUR: A Dense Network Four Way Transformer Network for Remote Heart Disease Monitoring using Medical Sensors for Blockchain Cloud Assisted Healthcare

Internet of Things (IoT) with Cloud Computing (CC) offers seamless connectivity in the healthcare environment which provide remote monitoring and diagnosis to the patients based on their health status. However, remote healthcare environment faced with security, privacy, bandwidth, and latency constraints which can be addressed by adopting blockchain, CC, and Edge Computing (EC) with medical IoT applications. In this research, HEART SAVIOUR model is developed which ensures real time remote heart disease analysis using Deep Learning (DL) and Transformer based method. The propounded research was tested and trained on the Hungarian and Cleveland dataset from the UCI repository. Initially, the patient data are passed to the edge gateway which are pre-processed in three folds which includes missing value replacement, noise reduction, and data normalization respectively. Within the edge gateway, the pre-processed data are subjected to encryption for guaranteeing secure communication using Binary Search Encryption Algorithm (BSEA). The encrypted sensitive data is then passed to the cloud server for automated remote heart disease analysis using Dense Nested Four Way Transformer Network (DNFW-Net). The analyzed results are securely stored in the block chain and based on the request raised by the healthcare specialists the automated and reliable reports are generated and securely provided to the remote patients. We have validated the proposed research on five performance metrics with 10% to 100% data distribution in which the proposed work achieves achievable performance than the existing works. The inclusion of edge computing, encryption, and block chain technologies with advanced AI algorithms, we ensure superior remote heart disease detection performance than the prior works.

groups
S. Geetha mail -
M. Vigenesh mail -
R. Santhosh mail
link https://doi.org/10.54216/JCIM.150109

Volume & Issue

Vol. Volume 15 / Iss. Issue 1

Details open_in_new
Journal of Cybersecurity and Information Management | 2025

Optimizing Task Offloading in Vehicular Network (OTO): A Game Theory Approach Integrating Hybrid Edge and Cloud Computing

In VANETs, user equipment (UE) schedules tasks by prioritizing them based on urgency and resource availability to ensure timely and efficient communication and processing. Effective task scheduling and resource allocation in VANET are crucial for maintaining low latency, high reliability, and optimal resource utilization for real-time vehicular communications. However, existing works often face limitations such as inadequate handling of dynamic network conditions, leading to increased latency and suboptimal resource usage. In this paper, we introduced a precise model by proposing Optimizing Task Offloading in Vehicular Network named as OTO framework. Initially, UEs are clustered using an Improved Fuzzy Algorithm (IFA) to reduce latency and energy consumption, with optimal clusters determined by a cluster validity index. Clustering considers distance, location, RSSI, link stability, and trust values, and cluster heads (CH) chosen based on distance, trust, and link stability. Following this, tasks from UE are classified using a Hybrid Deep Learning (HDL) algorithm, with LiteCNN for classification into emergency and non-emergency tasks and LiteLSTM for scheduling to reduce the weight matrix and overfitting. Dual scheduling based on task length, delay sensitivity, QoS, priority, resource consumption, and queue length reduces execution time and latency. Finally, the scheduled tasks are allocated to the optimal edge server based on task load, resource availability, waiting time, and distance using the RL-based Multi-agent Deep Reinforcement Learning (MA-DRL) algorithm, where edge servers act as sellers and users as buyers, reducing latency due to high convergence. In order to, evaluate and prove the efficacy of proposed OTO framework, we performed comparative analysis in terms of several performance metrics where our proposed OTO model outperforms other existing approaches.

groups
Mohanapriya .M mail -
V. Anusuya mail -
K. Aravindhan mail -
N. Krishnaveni mail -
R. Santhosh mail -
D. Gowthami mail
link https://doi.org/10.54216/JCIM.150110

Volume & Issue

Vol. Volume 15 / Iss. Issue 1

Details open_in_new
Journal of Cybersecurity and Information Management | 2025

TBBS-TO: Trustable Blockchain and Bandwidth Sensible-based Task Offloading and Resource Allocation in Cloud-IoT Network

The ability to facilitate high-performance task offloading while maintaining participant confidence is crucial, but not essential, to Cloud-Edge-Network (CEN) computing due to the geographic distribution and operation by various parties. Additionally, conflicts of interest may arise among the highly dynamic and diverse CEN members who provide resources. This study proposes a collaborative task offloading framework for CEN computing, called Trustable Block Chain and Bandwidth Sensible-based Task Offloading (TBBS-TO) and resource allocation empowered CEN. The E-PEFT consensus algorithm for block chain in task offloading optimizes resource allocation and task execution by dynamically adjusting consensus parameters based on environmental factors and performance feedback. Moreover, in our work for alleviating heterogeneous issues IoT users are mobility aware clustering is performed using Bi-directional Clustering Algorithm based on Local Density (BCALoD). In this work, block chain is essential to BC-CED's core functions, such as task delegation, resource utilization brokerage, and bandwidth sensible resource allocation. By modifying the block chain consensus procedure, TBBS-TO distinguish itself from other solutions by enabling participants to reach a consensus on task offloading. To achieve this, we formulate the offloading problem by considering both network performance and the computational capabilities of potential nodes. Using Multi-agent Double Deep Q-Network (MA-DDQN) based technique, TBBS-TO allow participants to compete for the right to produce a block by evaluating offloading policies and selecting the most effective one for the next period. Additionally, dynamically bandwidth sensible resource allocation is performed by considering significant parameters. Comprehensive testing on a commercial block chain platform has shown that TBBS-TO outperforms existing solutions in task offloading and blockchain maintenance.

groups
K. Saravanan mail -
R. Santhosh mail
link https://doi.org/10.54216/JCIM.150111

Volume & Issue

Vol. Volume 15 / Iss. Issue 1

Details open_in_new