Counteracting Selfish Nodes Using Reputation Based System in Mobile Ad Hoc Networks

Fayaz, Muhammad; Mehmood, Gulzar; Khan, Ajab; Abbas, Sohail; Gwak, Jeonghwan

doi:10.3390/electronics11020185

Cited by 25 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tis also overcomes the overftting problem and results in higher accuracy. In order to improve accuracy and to come up with a novel approach as compared to the existing work, we have implemented the proposed hybrid model with the best combination of GB, GNB, and decision tree, along with the random forest classifers [24][25][26][27]. Te results described in Table 6 show that diagnosis of chronic kidney disease is efective using the random forest with combination as a stacking technique in the hybrid model.…”

Section: Resultsmentioning

confidence: 99%

Machine Learning Hybrid Model for the Prediction of Chronic Kidney Disease

Khalid

Khan

et al. 2023

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

To diagnose an illness in healthcare, doctors typically conduct physical exams and review the patient’s medical history, followed by diagnostic tests and procedures to determine the underlying cause of symptoms. Chronic kidney disease (CKD) is currently the leading cause of death, with a rapidly increasing number of patients, resulting in 1.7 million deaths annually. While various diagnostic methods are available, this study utilizes machine learning due to its high accuracy. In this study, we have used the hybrid technique to build our proposed model. In our proposed model, we have used the Pearson correlation for feature selection. In the first step, the best models were selected on the basis of critical literature analysis. In the second step, the combination of these models is used in our proposed hybrid model. Gaussian Naïve Bayes, gradient boosting, and decision tree classifier are used as a base classifier, and the random forest classifier is used as a meta-classifier in the proposed hybrid model. The objective of this study is to evaluate the best machine learning classification techniques and identify the best-used machine learning classifier in terms of accuracy. This provides a solution for overfitting and achieves the highest accuracy. It also highlights some of the challenges that affect the result of better performance. In this study, we critically review the existing available machine learning classification techniques. We evaluate in terms of accuracy, and a comprehensive analytical evaluation of the related work is presented with a tabular system. In implementation, we have used the top four models and built a hybrid model using UCI chronic kidney disease dataset for prediction. Gradient boosting achieves around 99% accuracy, random forest achieves 98%, decision tree classifier achieves 96% accuracy, and our proposed hybrid model performs best getting 100% accuracy on the same dataset. Some of the main machine learning algorithms used to predict the occurrence of CKD are Naïve Bayes, decision tree, K-nearest neighbor, random forest, support vector machine, LDA, GB, and neural network. In this study, we apply GB (gradient boosting), Gaussian Naïve Bayes, and decision tree along with random forest on the same set of features and compare the accuracy score.

show abstract

Section: Resultsmentioning

confidence: 99%

Machine Learning Hybrid Model for the Prediction of Chronic Kidney Disease

Khalid

Khan

et al. 2023

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

show abstract

“…Among these, some recent studies are given below. Fayaz et al 29 suggested a reputation-based model for predicting selfish nodes and enforcing cooperation through the analysis of contribution and consumption data. To safeguard resources with a positive reputation, non-cooperative nodes are excluded from the network.…”

Section: State-of-the-art Workmentioning

confidence: 99%

“…At the end of the simulation, the hop count for the proposed RHCC-DAODV protocol decreased by nearly 94 depending on the varying number of selfish nodes. Table 3 presents performance metrics for different routing protocols, including Reputation-based scheme, 29 AISBA, 30 Chimp-CoCoWa-AODV, 31 BTRP, 32 ANFIS-EESC, 33 and RHCC-DAODV (proposed). PDR is the percentage of packets sent that successfully reached their intended destinations.…”

Section: F I G U R E 12 Analysis Of Packet Drop Ratiomentioning

confidence: 99%

An artificial immune system‐based algorithm for selfish node detection in Mobile Ad Hoc Networks (MANETs)

Gowtham,

Vigenesh,

Ramkumar

2024

Trans Emerging Tel Tech

View full text Add to dashboard Cite

The Mobile Ad Hoc Network (MANET) depending on dynamic distributed topology presents several challenges such as decentralized infrastructure. In MANET, each node act as a host as well as a router to exchange packet. From Source to destination, the MANET nodes offer the ability of transmission to send, receive, and route traffic. Moreover, the presence of selfish nodes or malicious nodes in MANETs significantly degrades network performance. Identifying and isolating such nodes poses a formidable challenge. Consequently, this research introduces a security model founded on the principles of an Artificial Immune System (AIS) to detect and defend against Selfish Node (SN) attacks. This research work employs the principles of AIS to categorize a node's behavioral state based on the Mature Context Immune Antigen Rate (MCIAR). Subsequently, a hybrid protocol named Reliable History‐dependent Resource Conscious Clustered and Defensive AODV (RRCC‐DAODV) is introduced to detect Selfish Nodes (SNs) and counteract their attacks. Within the RRCC algorithm, the identification of selfish nodes relies on both Trust Value (TV) and Residual Energy (RE). Additionally, the proposed DAODV protocol incorporates the V‐detector algorithm to enhance defense mechanisms against potential attacks. The simulation of the proposed model is carried out in NS3. The proposed mechanism achieves a detection ratio of 94.05%. The simulation outcomes demonstrate the excellence of the implemented system. This superiority is observed when compared to other standard protocols, as indicated by the parameters of throughput, residual energy, packet delivery ratio, and delay.

show abstract

“…Fayaz et al 22 have proposed a reputation‐based mechanism that uses consumption to contribution (C2C) information for identifying selfish nodes and enforcing cooperation. Nodes that do not cooperate are removed from network to conserve resources of nodes with better standing.…”

Section: Related Workmentioning

confidence: 99%

Z number improved reference ideal method‐based decision‐making process for enforcing cooperation during data dissemination in mobile ad hoc networks

Mylsamy¹,

Jayaprakash²

2023

Int J Communication

View full text Add to dashboard Cite

Summary In mobile ad hoc networks (MANETs), cooperative communication and resource constraint are the two important core characteristics essential to guarantee trusted data dissemination. The cooperative communication between mobile nodes depends on the trust rendered by them towards the process of reliable data routing. However, stringent resource constraints of mobile nodes such as energy, memory, communications, and computations result in the introduction of selfish and malicious node that completely degrades the network performance in different dimensions. In this paper, Z number improved reference ideal method (RIM)‐based decision‐making process (NIRIMDMP) is proposed with the merits of maximizing deviation method (MDM) and best–worst method (BWM) to ensure reliable data routing by modeling the cooperation degree in terms of Z number. This NIRIMDMP adopted Z number to represent the information reliability and handle the problem of inherent uncertainty during the process of evaluating each mobile node in the routing process. In specific, MDM and BWM are included into the proposed NIRIMDMP to determine comprehensive attribute weights based on the calculated objective and subjective weights that could be possible derived in routing. It extended the merits of classical RIM using Z numbers to confirm reliable ranking of mobile nodes, even when the optimal solution exists amid extreme values taken into consideration for assessing the mobile nodes during decision making. Simulation investigations of the proposed NIRIMDMP confirmed improved throughput and network lifetime with reduced control overhead, energy consumptions, and delay independent of the amount of malicious and non‐cooperative nodes.

show abstract

Counteracting Selfish Nodes Using Reputation Based System in Mobile Ad Hoc Networks

Cited by 25 publications

References 37 publications

Machine Learning Hybrid Model for the Prediction of Chronic Kidney Disease

Machine Learning Hybrid Model for the Prediction of Chronic Kidney Disease

An artificial immune system‐based algorithm for selfish node detection in Mobile Ad Hoc Networks (MANETs)

Z number improved reference ideal method‐based decision‐making process for enforcing cooperation during data dissemination in mobile ad hoc networks

Contact Info

Product

Resources

About