An Algorithm for Solving Nonlinear Third-Order Differential Equations Using Exponential Spline Functions

Ahmed R.

doi:https://doi.org/10.54216/GJMSA.0100205

International Journal of Wireless and Ad Hoc Communication | 2024

Hybrid Metaheuristics with Deep Learning Assisted Intrusion Detection on Cyber-Physical Smart Grid Environment

Smart grids (SGs) offer can ensure that users with a continuous power supply, decreased line losses, improved renewable output and storing, user participation in current electricity, and demand-side responsiveness. The development of cyberphysical SG (CPSG) systems has transformed the standard power grid by allowing bi-directional energy flow among utilities and users. But, because of increased data change among consumers, it is presented a major problem to the firewall systems for the transmission networks at either cyber or physical planes. Intrusion Detection Systems (IDSs) can role an essential play in maintaining SGs systems against cyber threats by generating a second wall of defense, complementing conventional preventive security procedures (for instance, authorization, encryption, and authentication). Therefore, this article concentrates on the design and development of Hybrid Metaheuristics with Deep Learning Assisted Intrusion Detection in a Cyber-Physical Smart Grid (HMDL-IDCPSG) infrastructure. The major objective of the HMDL-IDCPSG system provides the effectual recognition of the intrusions using feature selection and classification processes in the CPSG infrastructure. In the presented HMDL-IDCPSG method, a binary dragonfly algorithm with the hybrid directed differential operator (BDA‐DDO) algorithm could be implemented for the feature selection (FS) method. Besides, attention-based bi-directional long short-term memory (ABiLSTM) algorithm could be carried out for the recognition and classification of the intrusions. At last, the sparrow search algorithm (SSA) can be exploited for highest chosen the hyperparameter values of the ABiLSTM algorithm which supports in achieving a better solution. For demonstrating the greater outcome of the HMDL-IDCPSG technique, a comprehensive simulation value can be executed. The obtained results reported the supremacy of the HMDL-IDCPSG methodology with other existing approaches

groups

Manal M. Nasir mail -

Salim M. Hebrisha mail

link https://doi.org/10.54216/IJWAC.080206

Volume & Issue

Vol. Volume 8 / Iss. Issue 2

Details open_in_new

International Journal of Wireless and Ad Hoc Communication | 2024

Improving Network Security using Tunicate Swarm Algorithm with Stacked Deep Learning Model on IoT Environment

The Internet of Things (IoT) represents important security vulnerabilities, increasing difficulties in cyberattacks. Attackers employ these vulnerabilities to establish distributed denial-of-service (DDoS) attacks, compromising availability and causing financial losses to digital platforms. Newly, numerous Machine Learning (ML) and Deep Learning (DL) approaches have been presented for the identification of botnet attacks in IoT networks. By analyzing the patterns of communication and behavior of IoT devices, DL algorithms will be differentiated between malicious and normal activity, therefore supporting the earlier detection and avoidance of botnet attacks. This is essential to protect the integrity and security of IoT systems that can be increasingly vulnerable to botnet-driven attacks because of their limited security measures and often large-scale applications. In this aspect, this study designs an innovative tunicate swarm algorithm with stacked deep learning for botnet detection (TSASDL-BD) technique for IoT platforms. The purpose of the TSASDL-BD technique is to recognize the botnets and achieve maximum network security. In the TSASDL-BD technique, the TSA is applied for the effectual feature selection process, which aids in reducing the dimensionality problem. For botnet detection, the TSASDL-BD technique makes use of the stacked long short-term memory gated recurrent unit (SLSTM-GRU) model. Finally, the artificial humming algorithm (AHA) can be used for the optimal selection of the hyperparameter values of the SLSTM+GRU system. The outcome analysis of the TSASDL-BD method on the benchmark database takes place. The extensive outcomes stated that the TSASDL-BD approach gains maximum detection results over other algorithms with respect of different measures

groups

Abedallah Z. Abualkishik mail -

Rasha Almajed mail

link https://doi.org/10.54216/IJWAC.080207

Volume & Issue

Vol. Volume 8 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2024

On Neutrosophic Truncation

Neutrosophic have found their place in neutrosophic studies due to the prevalence of indeterminacy in the world. We present the novel notion of neutrosophic truncated distribution, which is highly significant in analyzing events that involve the exclusion of certain data from the original dataset, particularly where there is a presence of indeterminacy in data. Unsure or ambiguous information, which is disregarded in classical logic, is incorporated within neutrosophic logic due to its focus on both certain and uncertain data. In this paper, the approach of neutrosophic truncation, and truncated distribution of neutrosophic random variable have been introduced, in addition to deriving some of its properties. And other cases discussed neutrosophic truncation depends on the neutrosophic probability function, a classical probability function, and studies neutrosophic probability and neutrosophic interval together. It studies the neutrosophic left truncated and neutrosophic right truncated. Some illustrative examples and statistical properties such as the cumulative function, the moment generating function, the order statistic, and the rth moment are presented.             

groups

Kawther F. Alhasan mail

link https://doi.org/10.54216/IJNS.240414

Volume & Issue

Vol. Volume 24 / Iss. Issue 4

Details open_in_new

Journal of Cybersecurity and Information Management | 2024

Investigating the Efficacy of Deep Reinforcement Learning Models in Detecting and Mitigating Cyber-attacks: a Novel Approach

Ordinary defence components like rule-based firewalls and mark based detection are not staying aware of the always expanding intricacy and frequency of cyber security dangers. The reason for this work is to explore the way that deep reinforcement learning (DRL), a subfield of artificial intelligence famous for its viability in handling testing decision-production situations, may be utilized to improve cyber security conventions. To mimic and balance threatening cyber-attacks, we present a system that utilizes deep reinforcement learning (DRL). We propose a specialist based model that can learn and adjust ceaselessly in powerful network security situations. In light of the present status of the network and the rewards it gets for its decisions, the specialist concludes what the best game-plans are. Specifically, we utilize the policy gradient (PG)- based double deep Q-network (DDQN) model and trial on three different datasets: NSL-KDD, CIC-IDS, and AWID. Our review demonstrates the way that DRL can really further develop the detection after-effects of cyber-attacks. Utilizing the policy gradient DDQN model on different datasets, we find prominent upgrades in cyber security conventions. Specific boundary modifications upgrade the viability of our philosophy much more, displaying empowering results on different datasets. This exploration features the potential of deep reinforcement learning (DRL) as a successful instrument in the field of cyber security. Our examination progresses detection techniques and gives a versatile arrangement that can be applied to an assortment of cyber security worries by giving areas of strength for a to demonstrating and relieving cyber dangers.

groups

S. Phani Praveen mail -

Anuradha Chokka mail -

Pappula Sarala mail -

Rajeswari Nakka mail -

Suresh Babu Chandolu mail -

V. Esther Jyothi mail

link https://doi.org/10.54216/JCIM.140107

Volume & Issue

Vol. Volume 14 / Iss. Issue 1

Details open_in_new

Journal of Cognitive Human-Computer Interaction | 2024

Synergistic Fusion of ECG Signals for Advanced Heartbeat Classification in Health Monitoring

This project focuses on healthcare diagnostics where it examines the problem of accurate heartbeat classification by merging Electrocardiogram (ECG) signals. ECG signals have such variability and complexity that it is hard to accurately detect various cardiac rhythms. That is why this research came up with an ensemble framework that combined recurrent neural networks (RNNs), and convolutional neural networks (CNNs) reinforced by group normalization (GN). By incorporating these techniques, the authors aimed to improve the stability and efficiency of RNNs with respect to temporal dependencies as well as CNN for spatial features. The ensemble model exhibited a greater accuracy in classifying different heartbeats after careful experimentation and analysis. During training, the inclusion of GN in the CNN part ensured its stability thereby promoting generalization of the model. This study shows that combining ECG signals is efficient and also highlights the necessity of specific normalization methods used to refine medical diagnostics.

groups

Mahmoud M. Ibrahim mail

link https://doi.org/10.54216/JCHCI.080105

Volume & Issue

Vol. Volume 8 / Iss. Issue 1

Details open_in_new

Journal of Cognitive Human-Computer Interaction | 2024

Intelligent Fusion Framework for Predicting Defect Type and Localization in Steel Manufacturing Processes

The defect prediction in the manufacturing of steel is a critical challenge because it affects the quality and safety of the products. For this reason, intelligent image fusion approach is introduced in this research to enhance accurate prediction of defect types and locations in steel materials. By utilizing U-Net architecture and pretrained ResNet18 encoder layers, our method performs fusion of data from several imaging modalities thus supporting precise localization as well as classification of defects. In our model’s learning curves as well as comparing predicted segmentation masks with ground truth images, extensive experimentation and visualization show that our model captures subtle defects very well. By so doing, it exhibits robust performance that mitigates risks associated with overfitting since it can accurately identify any flaw while still having the ability to accept unseen data from other sources. These results suggest that our approach can highly contribute to improving quality control and safety standards for steel production.

groups

Mahmoud M. Ismail mail -

Mahmoud M.Ibrahim mail -

Heba R. Abdelhady mail

link https://doi.org/10.54216/JCHCI.080201

Volume & Issue

Vol. Volume 8 / Iss. Issue 2

Details open_in_new

Pure Mathematics for Theoretical Computer Science | 2024

Incidence Topological Spaces Generated from The Simple Undirected Graphs

In this paper, we investigate topologies produced by simple connected graphs. In particular, we associate a topology with G, called the incidence topology of G. A sub-base family to generate a incidence topology is implemented on the Vertices V set. Then we analyze some of the properties and discuss the impact topology of a few essential types of graphs. Our motivation in this section is to take a fundamental step towards the investigation of some of the characteristics of simple graphs by their corresponding incidence topology.

groups

Noor Nouman mail -

Faik J. Mayah mail

link https://doi.org/10.54216/PMTCS.040101

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Journal of Neutrosophic and Fuzzy Systems | 2024

Classification of States for Literal Neutrosophic and Plithogenic Markov Chains

In this paper we represent many classifications of neutrosophic and plithogenic Markov Chains states including absorbent states, inessential and essential states, recurrent states and communicated states. We prove that if a state (i) according to a neutrosophic Markov Chain with neutrosophic transition matrix  is classified as any of the previous classifications then it is also classified as the same classification in classical scene to two Markov Chains defined with transition matrices  respectively. Also, we prove that if a state (i) according to a plithogenic Markov Chain with plithogenic transition matrix  is classified as any of the previous classifications then it is also classified as the same classification in classical scene to three Markov Chains defined with transition matrices  respectively. Many theorems and solved examples are presented and solved successfully.

groups

Suhar Massassati mail -

Mohamed Bisher Zeina mail -

Yasin Karmouta mail

link https://doi.org/10.54216/JNFS.080206

Volume & Issue

Vol. Volume 8 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2024

Extended Fuzzy Neutrosophic Classifier for Accurate Intrusion Detection and Classification

Intrusion Detection is crucial in contemporary cybersecurity landscapes to proactively thwart and identify possible threats. The risk of data breaches, malicious activities, and unauthorized access escalates as organizations increasingly rely on interconnected systems. Intrusion Detection Systems (IDS) are imperative for the continuous monitoring of system and network activities, quickly identifying patterns or anomalies indicative of cyber threats. IDS acts as a frontline defense mechanism with the ability to identify abnormal behaviors and known attack signatures. Prompt recognition allows for safeguarding sensitive data, timely response, fortifying the overall resilience of IT infrastructures, and reducing the effect of security incidents. The implementation of robust IDS is vital in an era marked by evolving cyber threats to ensure the confidentiality, availability, and integrity of digital assets. This study develops an improved Arithmetic Optimization Algorithm with an Extended Fuzzy Neutrosophic Classifier technique (AOA-EFNSC) for Accurate Intrusion Detection and Classification. The main goal of proposing this model is to recognize the presence of intrusions effectually. A min-max scalar is applied to normalize the input data before using the improved AOA as a feature selection method. For intrusion detection, the proposed model uses the FNSC technique for the recognition and classification of the intrusions. A sequence of experimentations was involved to validate the superior performance of the proposed model. The experimental value pointed out that our proposed approach outperforms the previous models and enhances the intrusion detection results.

groups

Mohamed Elhoseny mail -

Mahmoud Abdel-salam mail -

Ibrahim M. Elhasnony mail

link https://doi.org/10.54216/IJNS.240415

Volume & Issue

Vol. Volume 24 / Iss. Issue 4

Details open_in_new

Galoitica: Journal of Mathematical Structures and Applications | 2024