TQOR: Trust-based QoS-oriented routing in cognitive MANETs

Asaadi, Shima; Alikhademi, Kiana; Eshghi, Farshad; Gilbert, Juan E.

doi:10.1109/nca.2017.8171332

Cited by 3 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Path learning and trust learning procedures using machine learning. This approach minimized the delay and routing overhead [16]. The perspective of learning and non-learning approaches cooperating reliability and improving the QoS [17].…”

Section: Related Workmentioning

confidence: 99%

Artificial Intelligence Machine Learning in Healthcare System for improving Quality of Service

Reddy¹,

Mungara²

2023

View full text Add to dashboard Cite

A vital element of widespread patient monitoring is consistency in transmission between the patients and the healthcare professionals not including time and position dependencies. Artificial intelligence (AI) and machine learning (ML) techniques have a vast possibility to proficiently handle the automated function of the mobile nodes distributed in the Mobile ad-hoc network (MANET). ML is a part of AI in that the computer algorithms learn themselves by improving from historical experiences. The main issues in MANET are autonomous operation, maximization of a lifetime, coverage of the network, energy utilization, connectivity issues, quality of service, high bandwidth necessity, communication protocol design, etc. ML is valuable for data aggregation, and it saves the energy of mobile nodes and enhances the network lifetime. In this paper, we propose an Artificial Intelligence Machine Learning Algorithm for improving the Quality of Service in MANET (AIMQ). ML techniques based on artificial neural networks (ANN) algorithm is helpful for data aggregation tasks. This approach formed the clusters by node mobility and connectivity. Glowworm Swarm Optimization (GSO) algorithm is applied in every cluster to choose a proficient Cluster Head (CH). Here, we choose the CH by GSO fitness function based on mobile node degree, node distance, node reliability, and energy. ANN algorithm recognizes and chooses the data aggregator with great energy and more extended stability. It updates the weight of input parameters such as node energy, node degree, packet loss ratio, and node delay to reduce the errors. It minimizes the repetitive CHs selection and member nodes’ re-affiliation in a cluster.

show abstract

Section: Related Workmentioning

confidence: 99%

Artificial Intelligence Machine Learning in Healthcare System for improving Quality of Service

Reddy¹,

Mungara²

2023

View full text Add to dashboard Cite

show abstract

“…Asaadi et al 57 developed a cognition layer that works in tandem with the network layer and contains two cognitive processes: path learning (routing) and trust learning. The first employs machine learning techniques, while the second employs trust management.…”

Section: Literature Surveymentioning

confidence: 99%

Certificate revocation schemes for providing secure QoS in MANETs

Sahana

Krishnan

2022

Concurrency and Computation

View full text Add to dashboard Cite

Due to crucial exchange issues, security in mobile ad hoc networks (MANETs) is more complicated. It is vital to secure MANET exchanges to ensure the network's services development. In this research, the proposed model focuses on providing trust and certificate-based Malicious Node detection for mobile adhoc networks and improving certificate revocation based on cluster head. The cluster head is crucial in eliminating falsely accused nodes. The malicious node may be easily discovered and isolated from the network using the trusted value. If the trust value falls below the trust threshold value in a trust management, the node is identified as malicious, the certificate is canceled, and the node is isolated from the network. The TSQRS protocol's integration with the CRS scheme was the main emphasis of the suggested model. The proposed model also creates more stable clusters with the help of Trust manager. When compared to other current protocols and methodologies, the findings produced by the suggested approach for the TSQRS-CRS scheme improve performance and stability in the QoS of MANETs. Finally, certain parameters were used to run the simulation, which resulted in an improved Packet Delivery Ratio, Routing Overhead, and reduced Delay. K E Y W O R D Scertificate revocation scheme, cluster head, mobile adhoc networks, trust-based secure QoS routing scheme INTRODUCTIONMANETs are wirelessly connected networks of mobile nodes. MANET has no stable topology because the nodes are always shifting from one site to another. Ad hoc networks' Nodes can send packets, forward packets, respond to routing messages, and send suggestions, among other things.The behavior of the nodes is defined by the collection of activities that are executed. As a result, the learning plan keeps track of the neighbors' actions to assess their behavior. 1,2 To route the packets, all of the nodes must work together. Cooperating nodes must have faith in one another.According to the relative distance between the nodes and the link's maintenance time, the link's quality and dependable communication are assessed. 3 The wireless sensor network (WSN) presently is one of the chosen study field in recent years as a critical aspect of industrial application. 4 Because of sensor nodes' restricted energy and communication capabilities, designing a routing protocol for WSNs is crucial to convey sensing data to the receiver 5 properly. The Internet of Vehicles may obtain traffic information through a vast amount of data acquired by sensors. 6 There is a particular need to be focused on energy consumption and the amount of delay on resource constraints of MANETs. [7][8][9] To identify the shortest path algorithm in the programme, a new approach of the best path selection with length priority based on past information needs to be taken into consideration. Different forms of intelligent driving vehicles can use this best path planning algorithm to efficiently choose the best way in a traffic network with limited height, width, and weight, accidents, and traffic co...

show abstract

“…-Trust: The concept of trust has prevalently been used to differentiate between the goodwill of nodes. Trust is defined as a node's degree of subjective belief about the future behavior of other entities in the network in a given context [245], [246], [247]. In the context of OR, trust can be considered to be the level of reliance on (cooperation of) a node to forward a packet if it is required to do so as a member of a CFS.…”

Section: A Parameters Developmentmentioning

confidence: 99%

Opportunistic routing metrics: A timely one-stop tutorial survey

Abdollahi

Eshghi

Kelarestaghi

et al. 2020

Journal of Network and Computer Applications

Self Cite

View full text Add to dashboard Cite

High-speed, low latency, and heterogeneity features of 5G, as the common denominator of many emerging and classic wireless applications, have put wireless technology back in the spotlight. Continuous connectivity requirement in low-power and wide-reach networks underlines the need for more efficient routing over scarce wireless resources, in multi-hp scenarios. In this regard, Opportunistic Routing (OR), which utilizes the broadcast nature of wireless media to provide transmission cooperation amongst a selected number of overhearing nodes, has become more promising than ever. Crucial to the overall network performance, which nodes to participate and where they stand on the transmission-priority hierarchy, are decided by userdefined OR metrics embedded in OR protocols. Therefore, the task of choosing or designing an appropriate OR metric is a critical one. The numerousness, proprietary notations, and the objective variousness of OR metrics can cause the interested researcher to lose insight and become overwhelmed, making the metric selection or design effort-intensive. While there are not any comprehensive OR metrics surveys in the literature, those who partially address the subject are non-exhaustive and lacking in detail. Furthermore, they offer limited insight regarding related taxonomy and future research recommendations. In this paper, starting with a custom tutorial with a new look to OR and OR metrics, we devise a new framework for OR metric design. Introducing a new taxonomy enables us to take a structured, investigative, and comparative approach to OR metrics, supported by extensive simulations. Exhaustive coverage of OR metrics, formulated in a unified notation, is presented with sufficient details. Self-explanatory, easy-to-grasp, and visual-friendly quick references are provided, which can be used independently from the rest of the paper. Finally, a new insightful framework for future research directions is developed. This tutorial-survey has been organized to benefit both generalists and OR specialists equally, and to be used not only in its entirety but selectively as well.

show abstract

TQOR: Trust-based QoS-oriented routing in cognitive MANETs

Cited by 3 publications

References 23 publications

Artificial Intelligence Machine Learning in Healthcare System for improving Quality of Service

Artificial Intelligence Machine Learning in Healthcare System for improving Quality of Service

Certificate revocation schemes for providing secure QoS in MANETs

Opportunistic routing metrics: A timely one-stop tutorial survey

Contact Info

Product

Resources

About