The Effect of Changing Convolutional Neural Nets Parameters on EEG Signals Recognition Ratio

Khaled

doi:https://doi.org/10.54216/NIF.030205

Journal of Cybersecurity and Information Management | 2024

Systematic Analysis of threats, Machine Learning solutions and Challenges for Securing IoT environment

The Internet of Things (IoT) has revolutionized our daily lives, impacting everything from healthcare to transportation and even home automation and industrial control systems. However, as the number of connected devices continues to rise, so do the security risks. In this review, we explore the different types of attacks that target various layers of IoT infrastructure. To counter these threats, researchers have proposed using machine learning (ML) and deep learning (DL) techniques for detecting different types of attacks. However, our examination of existing literature reveals that the effectiveness of these techniques can vary greatly depending on factors like the dataset used, the features considered, and the evaluation methods employed. Finally, we delve into the current challenges facing Intrusion Detection Systems (IDS) in their mission to protect IoT environments from evolving threats.

groups

Bharti Yadav mail -

Deepak Dasaratha Rao mail -

Yasaswini Mandiga mail -

Nasib Singh Gill mail -

Preeti Gulia mail -

Piyush Kumar Pareek mail

link https://doi.org/10.54216/JCIM.140227

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new

Neutrosophic and Information Fusion | 2024

Finding the complete List of Different K-Brackets for the Projective Plane PG (2, 8)

A k-arc in a plane PG (2, q) is a set of k point such that every line in the plane intersect it in at most two points and there is a line intersect it in exactly two points. A k-arc is complete if there is no k+1-arc containing it. This thesis is concerned with studies a k-arcs, k=4, 5,…., 10 and classification of protectively distinct k-arcs and distinct arcs under collineation. We prove by using computer program that the only complete k-arcs is for, k= 6, 10.

groups

Khaled Moaz mail

link https://doi.org/10.54216/NIF.030201

Volume & Issue

Vol. Volume 3 / Iss. Issue 2

Details open_in_new

Neutrosophic and Information Fusion | 2024

On the Effect of the Layers' Number of Deep Neural Network for Improving the Reward of a Reinforcement Learning Robot

The Q learning algorithm in reinforcement learning is one of the algorithms that allows the robot to learn the surrounding environment without the need for prior training samples with the principle of reward and punishment for the robot through interaction with the environment. Increasing the number of hidden layers of the deep neural network used and adjusting some of the higher parameters in it can increase the reward of the robot and thus obtain the best path to achieve the goal.

groups

Talal Markabi mail -

Bahaa Mansoura mail

link https://doi.org/10.54216/NIF.030202

Volume & Issue

Vol. Volume 3 / Iss. Issue 2

Details open_in_new

Neutrosophic and Information Fusion | 2024

On the Stability Analysis of the Fisher Equation Based on Some Numerical Galerkin Techniques

We studied the stability of the steady state solutions for Fisher Equation in two cases, the First one with constant amplitude and we show that the steady state solution u1=1 is always stable under any condition, but the other two solutions u1=0 and u1 (x)=A cos (nπX)are conditionally stable. In the Second case, we studied the steady state solutions for various amplitude by using two Methods. The First is analytically by direct Method and the second is numerical method using Galerkin technique which shows the same results, that is the steady state solution u1=1 is always stable under any conditions, but the other two solutions u1=0 and u1 (x)=A cos (nπX) are conditionally stable.

groups

Murat Ozcek mail

link https://doi.org/10.54216/NIF.030203

Volume & Issue

Vol. Volume 3 / Iss. Issue 2

Details open_in_new

Neutrosophic and Information Fusion | 2024

On a Novel Simulation of a Control Technique for Power Oscillation Damping and Applications

This research presents a novel simulation model of adaptive control to make a control process by using MIT rule adjustment mechanism, to power oscillation damping in the SMIB system and to measure its possible effects on the response of the damper by changing its parameters according to an external disturbance using Simulink. The results showed that the use of MRAC technique maintains the response of the damper when changing the transfer function due to external disturbance.

groups

Talal Markabi mail

link https://doi.org/10.54216/NIF.030204

Volume & Issue

Vol. Volume 3 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2025

Neutrosophic Analytical Hierarchy Process (NAHP) for Addressing Cyber violence

To address the complex challenges of cyberviolence and gender-based violence among young students, it is crucial to employ analytical approaches that consider the multifaceted nature of these phenomena. The Neutrosophic Analytical Hierarchy (NAHP) method is presented as an innovative tool that allows us to unravel the different layers of influences and factors involved in these behaviors. This approach not only recognizes the diversity of perspectives and experiences that contribute to online and gender-based violence, but also offers a structured framework to assess and prioritize these factors holistically. By applying the NAHP, not only the visible and direct aspects of cyberviolence and gender violence are explored, but also the more subtle and underlying aspects that may go unnoticed in conventional analyses. This method allows us to capture the dynamic complexity of how individual perceptions, social norms, and power dynamics interact to perpetuate these problems in student environments. Thus, a deeper and more nuanced understanding of the triggering and contributing factors is fostered, facilitating the formulation of more effective interventions and policies that are sensitive to the specific needs of affected young people.

groups

Patricia Estefanía Rodríguez Palomo mail -

Sandra Giuliana Suárez Peña mail -

Paola Estefanía Salinas Aguilar mail -

Sanjar Mirzaliev mail

link https://doi.org/10.54216/IJNS.250139

Volume & Issue

Vol. Volume 25 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

Application of Multi-Criteria Methods and Neutrosophic Logic for the Analysis of Productive Factors

This article explores the innovative application of multi-criteria methods and neutrosophic logic in the analysis of productive factors, highlighting how these approaches can offer a more nuanced and comprehensive view of industrial and business dynamics  ̣ Multicriteria methods allow different aspects to be evaluated simultaneously, considering complex variables that affect productivity and efficiency in various sectors  ̣ On the other hand, neutrosophic logic introduces a theoretical framework that manages the uncertainty and imprecision inherent in many business decisions, offering tools to better interpret and manage the variabilities and ambiguities that influence productive results  ̣ This integrative approach not only seeks to improve accuracy in the evaluation of critical factors such as cost, quality and time, but also to promote more informed and strategic decision making in competitive and changing environments  ̣ By combining rigorous analysis with interpretive flexibility, the door is opened to new methodologies that can effectively adapt to the complexities of the globalized market and the dynamic demands of consumers  ̣ This article examines case studies and practical examples to illustrate how these methods can be successfully applied in the optimization of production processes and in the formulation of business strategies that seek not only to remain competitive, but also to anticipate and proactively respond to emerging challenges  ̣

groups

Franklin A. Molina-Borja mail -

Wendy Maribel-Molina mail -

Wilmer L. Toul Ayala mail -

Freddy X. Guamangate-Chiguano mail -

Sanjar Mirzaliev mail

link https://doi.org/10.54216/IJNS.250140

Volume & Issue

Vol. Volume 25 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

ANOVA and the 2-Tuple Neutrosophic linguistic method: A case study to analyze the interaction between elements

In this article, an innovative approach is presented that combines analysis of variance (ANOVA) with the Neutrosophic 2-Tuple linguistic method to explore and analyze the complex interactions between elements in various contexts. ANOVA, known for its ability to decompose variance and detect significant differences between groups, is here merged with the Neutrosophic method, which provides tools to handle the uncertainty and linguistic ambiguity present in many real data sets. This methodological synergy not only expands analytical possibilities, but also allows for a more nuanced and profound interpretation of the relationships between variables, overcoming the limitations of traditional approaches that assume absolute certainty in the data. Through detailed case studies and practical examples, it is demonstrated how this hybrid model can be effectively applied in fields as diverse as scientific research, business management, and public policy evaluation. The results obtained illustrate how the combination of ANOVA and 2-Tuple Neutrosophic not only improves the precision of statistical analysis, but also enriches the understanding of complex phenomena by considering and modeling uncertainty in a more realistic and adaptable way to different contexts and scenarios.

groups

Luis Alonso Chicaiza Sánchez mail -

Patricia Marcela Andrade Aulestia mail -

Dildora Abduturapova mail

link https://doi.org/10.54216/IJNS.250141

Volume & Issue

Vol. Volume 25 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

A proposed SWOT analysis method for integrating indeterminate Likert scale with the neutrosophic AHP

In the fast-paced world of business decision-making, where clarity and precision are vital, an integrated approach that combines the indeterminate Likert scale with the neutrosophic Analytical Hierarchy Process (AHP) offers a fresh and enriching perspective for SWOT analysis. This innovative methodology not only allows us to capture the ambiguity inherent in human evaluations, but also enhances analytical depth by incorporating neutrosophic thinking, which considers elements of truth, falsehood and indeterminacy. Instead of traditional methods that often oversimplify complexities, this integrated approach facilitates a more nuanced and holistic assessment of strengths, weaknesses, opportunities and threats, thus providing a more robust and reliable basis for formulating business strategies. Additionally, the adoption of the indeterminate Likert scale, fused with the neutrosophic AHP, introduces conceptual flexibility that is particularly useful in contexts of uncertainty and changing market dynamics. This approach not only allows decision makers to better capture the subjective and often contradictory perceptions of experts, but also facilitates the weighing of multiple criteria in a coherent and logical manner. Doing so ensures that the strategies developed are not only thoughtful and detailed, but also adaptable to the fluctuating realities of the modern business environment. In short, this integrated approach is presented as a powerful and versatile tool for strategic planning, capable of transforming complex challenges into tangible opportunities through a deep and balanced understanding of organizational reality.

groups

Edilberto Chacón Marcheco mail -

Yánez Pinto Washington Eduardo mail -

Nancy Margoth Cueva Salazar mail -

Blanca Mercedes Toro Molina mail -

Lucia Monserrath Silva Déley mail -

Burkhon Dekhkonov mail

link https://doi.org/10.54216/IJNS.250142

Volume & Issue

Vol. Volume 25 / Iss. Issue 1

Details open_in_new

Neutrosophic and Information Fusion | 2024

The Effect of Changing Convolutional Neural Nets Parameters on EEG Signals Recognition Ratio

Brain Computer Interface (BCI), especially systems for recognizing brain signals using EEG (Electroencephalography), is one of the important research topics that arouse the interest of many researchers currently. Convolutional Neural Nets (CNN) is one of the most important deep learning classifiers used in this recognition process, but the parameters of this classifier have not yet been precisely defined so that it gives the highest recognition rate and the lowest possible training and recognition time. This research proposes a system for recognizing EEG signals using the CNN network, while studying the effect of changing the parameters of this network on the recognition rate, training time, and recognition time of brain signals, as a result the proposed recognition system was achieved 76.38 % recognition rate, And the reduction of classifier training time (3 seconds) by using Common Spatial Pattern (CSP) in the preprocessing of IV2b dataset, and a recognition rate of 76.533% was reached by adding a layer to the proposed classifier.

groups

Khaled Moaz mail

link https://doi.org/10.54216/NIF.030205

Volume & Issue

Vol. Volume 3 / Iss. Issue 2

Details open_in_new