Innovations in Machine Learning Models for Hepatitis Diagnosis and Disease Progression Prediction

Marwa M.; Wei Hong

doi:https://doi.org/10.54216/MOR.010104

Journal of Cybersecurity and Information Management | 2025

Smart Grid intrusion detection system based on AI techniques

Smart grids (SGs) are integral to modern utility systems, managing power generation, energy consumption, and communication networks. However, as these systems become increasingly interconnected, they are exposed to sophisticated cyber threats that can compromise their functionality and security. To address these challenges, this paper presents an AI-driven detection framework designed to significantly enhance cybersecurity in smart grids. The proposed system combining Recurrent Neural Networks (RNNs) with Support vector classifier to improve detection accuracy, recognition capabilities, and system robustness. The methodology comprises four main stages: (1) data preprocessing to ensure high-quality input for analysis, (2) traffic detection using RNNs to capture temporal patterns, (3) classification of traffic as normal or abnormal via support vector classifier (SVC), and (4) identification of specific attack types through another SVC for refined threat categorization. This integrated approach enables real-time detection of both known and emerging threats, focusing on minimizing false positives and maximizing detection precision. The system was evaluated on three comprehensive benchmark datasets: UNSW_NB15 and BoT-IoT, achieving an average accuracy of 100%. These results underscore the superiority of this AI-based solution over traditional intrusion detection systems, providing a robust and scalable framework for securing smart grids and other critical infrastructures.

groups

Mounir Mohammad Abou-Elasaad mail -

Samir G. Sayed mail -

Mohamed M. El-Dakroury mail

link https://doi.org/10.54216/JCIM.150215

Volume & Issue

Vol. Volume 15 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2024

Enhancing Decision-Making in Uncertain Environments: The Role of Neutrosophic Cognitive Maps in Analyzing Complex Systems

Using Neutrosophic Cognitive Maps (NCM), this research tackles the very core of one of the main problems that exist in the analysis of complex structures and systems: how to represent and model decision making in situations of uncertainty, or where there is contradiction and ambiguity. This problem gets even worse in the areas of knowledge management, strategic evaluation, or design of public policies since orthodox methods do not always possess required versatility for combining partially available or contradicting information. To address this challenge, the researchers recommend Neutrosophic Cognitive Maps (NCM) as a more appropriate technique considering that the neutrosophic logic can depict and study more intricate relationships in the presence of indeterminacy. There is an iterative learning of cognitive maps which is coupled with neutrosophic analysis techniques enabling the construction of a comprehensive model capturing both certainties and the undefined and disputed areas of the evaluated systems. The findings obtained in this research demonstrate how effective NCMs are in the spatial and analytic representation of complex and multifactorial situations providing features that go beyond the conventional structure models. Apart from broadening theorization on decision-making processes in an uncertain situation, this research provides practical tools applicable in sectors such as strategic planning, complex problem solving and organizational management. In short, the study shows that neutrosophic, used as a methodological catalyst, not only expands the possibilities of analysis but also transforms how complex systems are conceptualized and managed in the academic and practical fields.

groups

Jose Luis Robalino Villafuerte mail -

Sheila Belen Esparza Pijal mail -

Mónica Isabel Mora Verdezoto mail -

Lorenzo Cevallos-Torres mail -

Sanjar Mirzaliev mail

link https://doi.org/10.54216/JISIoT.130121

Volume & Issue

Vol. Volume 13 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2025

Securing the Future: Real-Time intrusion Detection in IIoT Smart Grids through Innovative AI Solutions

The world is witnessing an unprecedented boom in the development of information technology, which has come to encompass all aspects of life, Smart networks based on the Industrial Internet of Things (IIoT) are among the latest technologies used in various industries, contributing to improved production efficiency, reduced costs, and enhanced security, With the increasing reliance on this technology, the challenge of complex cyberattacks are also on the rise, These attacks are considered one of the major challenges facing smart networks, as attackers can exploit vulnerabilities in systems to access sensitive data or disrupt industrial operations, To counteract these threats, advanced intrusion detection systems should be developed, leveraging artificial intelligence and big data analytics to effectively detect and respond to attacks in real-time. Therefore, it is imperative to strive towards developing advanced and intelligent security systems to combat cyberattacks, ensuring the safety of industrial operations and data protection. This paper provides two IDS based on AI that are developed to negate the raising sophisticated cyberattacks. IN the first technique, Group of ML techniques such as Decision tree, Random Forrest classifiers, support vector classifier, and K_Nearest Neigbor are used with Feature reduction algorithms classifying network traffic subspecies to enhancing the accuracy and efficiency of detection systems. The second proposed technique for specifying the type of intrusion advantage various methodologies, particularly in the context of IoT networks and deep learning, the two algorithms are trained and tested using three well-known datasets to investigate wide domain of cyberattacks targeting the IIoT infrastructure. Results of the simulation show that the algorithm proposed in this work provides high improvement in detection of cyberattacks. The first algorithm achieved an accuracy of 99.9% and a very low false positive rate of just 0.1%. In addition, the second proposed algorithm identifies type of attack with a detection ratio of 99.76%. These results demonstrate how the proposed IDS based on AI algorithms can effectively detect network intrusion, and significantly enhance the security of IIoT system

groups

Mounir Mohammad Abou-Elasaad mail -

Samir G. Sayed mail -

Mohamed M. El-Dakroury mail

link https://doi.org/10.54216/JCIM.150216

Volume & Issue

Vol. Volume 15 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2024

A Neutrosophic Multicriteria Analysis of Economic Recovery Systems

The article investigates the neutrosophic multicriteria analysis of the post-pandemic economic recovery, an intricate and multi-dimensional problem, which persistently affects several nations in a globalized setting with high levels of uncertainty. This study delves into how recovery measures including policies and strategies should be developed and implemented considering the newly emerging complexities that characterize the mod-ern world and its politics. The main concern is the absence of any tools that may seek to correlate the various factors that are necessarily involved in any recovery process, all of which have variable post- pandemic eco-nomic, social, and political conditions. In addition, there is clearly an importance of this issue since it has been so timely for governments and/or organizations to look for strategies and policies that would ensure a just and environmentally sound reconstruction phase. By providing a neutrosophic multicriteria analysis that has not been applied before in this context, the paper contributes to the existing literature by outlining various factors involved in economic recovery such as fiscal policy and health and social measures. This study takes the neu-trosophic perspective and forms of analysis to explore the various uncertainties and heterogeneous views con-cerning economic strategies, thus enabling an intricate analysis of the strategic options put forth. The findings emphasize the necessity for a creative and cross-cutting strategy towards the reconstruction of the economy, emphasizing the fact that the solutions must be dynamic to the changing circumstances. Making an academic contribution, this research not only proposes a new theoretically based framework for the understanding of recovery, but also has practical recommendations that may help in formulating policies that are more robust and effective in times of crises.

groups

Carlos Wilman Maldonado Gudiño mail -

Maria Fernanda Jara Campoverde mail -

Maria Belen Carlosama Ponce mail -

Marina Abdurashidova mail

link https://doi.org/10.54216/JISIoT.120112

Volume & Issue

Vol. Volume 12 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2024

Neutrosophic decision making using Saaty's AHP method and VIKOR

This study analyzes the difficulties that arise in multicriteria decision making in condition that bear uncertainty, ambiguity, and contradictions at the very core. The key issue is the shortage of instruments allowing for not only ranking of alternatives but also efficiently combining qualitative and quantitative information in management decision making. The relevance of this research is due to the growing number of critical situations in a variety of disciplines, including organizational management and public policies, which have a limited number of traditional methodologies and thus need more effective evaluation processes. Still, concerning such aspects as the integration of approaches that tend to discuss a lot of the quite fuzzy context in a structured and dynamic way, there are significant gaps in the existing literature. A methodological framework for managing uncertainties inherent in expert judgments and for prioritizing alternatives was developed through the integration of Saaty’s AHP method and the VIKOR approach from the perspective of neutrosophic logic. The results demonstrate that this integration not only improves the efficiency of ranking and selection of alternatives under complex environment but also enhances sensitivity to differences among evaluations. This progress is of central importance regarding practical implications of this advance, particularly in strategies design.

groups

Sheila B. Esparza P mail -

Luis A. Crespo-Berti mail -

Haro Teran Lilian Fabiola mail -

Dinara Turaeva mail

link https://doi.org/10.54216/JISIoT.120113

Volume & Issue

Vol. Volume 12 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2024

Neutrosophic Sentiment Analysis Method Using Orange Data Analysis

The present work tackles an urgent problem in the area of data analytics that is the shifting of sentiment against language in regards to human cognition. Although the science of data mining and machine learning has done much to address the problem of these tools, their scope is still limited regarding the management of human language which has inherent uncertainty and ambiguity. This research seeks to address this gap by illustrating how to apply a machine learning tool in a way that embraces the so-called uncertainty neutrality using the orange data analysis tool for analysis of visualized data. It is also important to note in the research that the combination of neutral and intelligent analysis with using applications such as orange increases the efficiency of sentiment classification and expands the theoretical scope of sentiment data analysis. Their findings underscore that this perspective seeks to illuminate details which other methods tend to ignore and hence offer a much more nuanced understanding of human cognition. Practically, this research presents an efficient paradigm as the new framework can be employed in market intelligence, evaluation of public policy and intelligent interface design, among others. As a result, this research does not only contribute to the body of knowledge within the profession of data science but also explores new dimensions in understanding human cognition.

groups

Janneth Ximena Iglesias Quintana mail -

Monica Alexandra Salame Ortiz mail -

Alipio Absalon Cadena Posso mail -

Joffre R. Paladines Rodriguez mail -

Bekbayeva Feruza Baxtiyerovna mail

link https://doi.org/10.54216/JISIoT.120114

Volume & Issue

Vol. Volume 12 / Iss. Issue 1

Details open_in_new

Metaheuristic Optimization Review | 2024

Leveraging Advanced Machine Learning for Pioneering Monkeypox Diagnosis: A New Paradigm in Infectious Disease Detection

Artificial intelligence (AI) is revolutionizing the problem solving of medical diagnosis, which has enduring issues, including early-stage disease, insufficient voluminous data, and diagnosis process ineffectiveness. This review demonstrates considerable progress in developing ML technologies, including monkeypox detection, Tuberculosis, and cancer diagnosis. CNNs have shown high efficiency in diagnostics; even InceptionV3, a transfer-learning model for clinicians, can reach 99.87% diagnostics. As privacy-preserving solutions, federated learning models work to improve diagnostic accuracy without increasing the exposure of individual data, and synthetic datasets derived from high-resolution techniques such as HiP-CT help deal with data scarcity by improving model construction and assessment. The hybrids of genome and metabolome integration helped enhance diagnostic accuracy measures, particularly for complex diseases like COVID-19, due to increased prognostic performance metrics using multiple biological information. However, few issues crop up even in modern society: Generalization of the model is an issue due to a lack of data, especially for rare conditions, and increased computational power requirements for most ML models pose a problem for implementation in low-resource environments. Prominent ethical issues incorporating algorithm prejudices and the ‘black box’ concept spotlight the requisite of an explainable AI (XAI) framework to provide visibility and credence in the medical facility. Possible directions in development, such as the standardization of frameworks, enhancing computational support, and integration of different fields, provide ways to address these challenges. When tackled, these challenges create the possibility of revamping global healthcare through suitable and scalable approaches informed by ML technologies that align with the patient’s needs, leading to better practices and, consequently, better health.

groups

El-Sayed M. El-kenawy mail

link https://doi.org/10.54216/MOR.010101

Volume & Issue

Vol. Volume 1 / Iss. Issue 1

Details open_in_new

Metaheuristic Optimization Review | 2024

Stem Cells and Regenerative Medicine: A Review of Artificial Intelligence Techniques for Stem Cell Differentiation

Following this background, this review discusses the advanced technologies such as AI, micro-fluids, and automated platforms that this differentiation protocol could help achieve in regenerative medicine. Stem cell research, essential in tissue engineering, disease modeling, and drug development, is challenging through heterogeneity, scalability, and reproducibility, as observed in differentiation procedures. Machine learning and deep learning patterns have become more effective in predicting cellular behavior, tracking cellular stations, and optimizing differentiation methods for current stem cell technology. These methods also reduce observer bias, increase the throughput of high-throughput screening, and advance modeling to precise therapeutic applications. At the same time, microfluidic and automated systems provide nearly perfect control over differentiation stimuli, recreating the in vivo conditions with the ability to control spatial and temporal gradients. This integration between AI and microengineering has promoted 3D culture systems, lab-on-a-chip technologies, and biosensors, enabling reproducible and efficient differentiation results. There is still much to accomplish, such as the problem of obtaining uniform stem cell populations or decoding the tissue context. This field incorporates several interdisciplinary advancements such as stimuli-responsive systems and computational modeling; it envisages new horizons in regenerative medicine, transforming stem cell-based therapeutic technologies to their optimum level for personalized medicine and other advanced tissue engineering applications.

groups

Nima Khodadadi mail -

Benyamin Abdollahzadeh mail

link https://doi.org/10.54216/MOR.010102

Volume & Issue

Vol. Volume 1 / Iss. Issue 1

Details open_in_new

Metaheuristic Optimization Review | 2024

Improving Tuberculosis Diagnosis and Forecasting Through Machine Learning Techniques: A Systematic Review

Tuberculosis (TB) is ranked as one of the leading causes of death from infectious diseases in the present world, causing important health and economic consequences in the different developing countries. The practices of traditional diagnostic approaches, although still expected, are associated with relativity, slowness, and organs, besides being confined to visual observations and touch. The new and increased capacity in advanced machine learning is a promising area that has shown potential in improving the diagnosis of TB, as well as identifying drug resistance and disease management. This review presents various aspects of using ML in diagnosing and managing TB disease based on its various categories of models, including deep learning, hybrid approach, and the metabolomics approach. Some of these methods have been very effective, with high diagnostic performance improvements in sensitivity, specificity and accuracy; Furthermore, ML has been used to analyze the molecular picture of TB and to find drug targets of the disease toward future targeted therapies. As seen with the integration of ML, substantial benefits are provided by the solutions proposed. However, questions concerning the quality of data, interpretations of ML models and ethical problems hinder further application. This review concludes with the idea that ML can transform the diagnosis and management of TB and calls for more investment in developing this field to overcome these barriers to global health.

groups

Abdelaziz Rabehi mail -

Pushan Kumar Dutta mail

link https://doi.org/10.54216/MOR.010103

Volume & Issue

Vol. Volume 1 / Iss. Issue 1

Details open_in_new

Metaheuristic Optimization Review | 2024

Innovations in Machine Learning Models for Hepatitis Diagnosis and Disease Progression Prediction

Chronic liver disease (CLD) is a group of conditions for which up to half of the global population remains at risk and causes serious complications: liver cirrhosis and liver cancer. Therefore, early diagnosis and proper treatment of these diseases enhance the prognosis of patients suffering from CLD. This review paper explores how machine learning (ML) techniques are used in practice to diagnose, prognosis, and treat chronic liver diseases. Continuing with more specific examples of collected data from the results of several studies, their more comprehensive implementation is expected to improve the respective management processes and the detection of liver disease in patients more accurately. The review further discusses the various ML methods, including supervised and unsupervised learning, neural network, and ensemble learning, also applied to the estimation of risk felt by the patients, suggesting a course of treatment or how far the disease has progressed. While the inclusion of ML technology in the field of Hepatology is progressing well, some issues like model diversity, applicability of models, and concerns about ethics still pose challenges. This paper points out the importance of working in teams from various fields to develop appropriate mechanisms for dealing with these issues and adequately use ML for clinics. In conclusion, the results indicate that there is a possibility that ML will change the management of chronic liver diseases, which in turn will lead to the development of innovative treatment methods and better patient management.

groups

Marwa M. Eid mail -

Wei Hong Lim mail

link https://doi.org/10.54216/MOR.010104

Volume & Issue

Vol. Volume 1 / Iss. Issue 1

Details open_in_new