Centrality-aware gossiping for distributed learning in wireless sensor networks

Mertens, J.S.; Galluccio, Laura; Morabito, Giacomo

doi:10.23919/ifipnetworking55013.2022.9829795

Cited by 5 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A dual-tier clustering-based method for WSN to focus on several performance parameter aspects like network lifetime, scalability and energy consumption was designed in [11]. In [12],…”

Section: Critical Review Of Literature and Identification Of Research...mentioning

confidence: 99%

“…A dualtier clustering-based method for WSN to focus on several performance parameters aspects like network lifetime, scalability, and energy consumption was designed in [11]. In [12], the distributed learning mechanism was implemented based on the game theory principles. Nevertheless, these techniques do not take into consideration the sensor node trustworthiness that is indispensable for keeping in existence both the network reliability and security.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence-based Cayley Menger Securex-means Clustering and Hyper Gradient Reliable Data Transmission in Wsn

Srinivasamur,

Tabassum

2024

Preprint

View full text Add to dashboard Cite

WSN is a self-configured wireless network with no infrastructure which is made up of a huge number of dispersed sensors that are installed randomly. In a WSN, the sensor nodes connect wirelessly and are utilized for directing and observing the system and physical elements in a specified region. Wireless sensor nodes are interrelated to the base station which operates as WSN System's processing unit. The sensed data is shared by the WSN base station via the internet.WSN is utilized in the area of examination, processing, storage, and mining industries. Moreover, direct sensed data delivery to the sink node is a requirement in WSNs as far as large-scale networks are concerned. The utilization of clustering can permit the direct broadcast of information to the corresponding sink node, bringing about substantial energy reductions. In addition, the selection of a significant cluster head would also result in the saving of energy considerably. This proposed method develops an Artificial Intelligence-based CayleyMenger secure X-means cluster formation and Hyper Gradient DescentTrusted Neighbor Establishment (CMX- HGDTNE) for reliable data transmission. Secure cluster formation and chosen of cluster head performed by employing the Cayley–MengerSecure X-means Cluster Formation algorithm. Second Hyper Gradient Descent and Determinist Trusted Neighbor Establishment for reliable data transmission is applied to the clusters being formed via trusted neighbor identification within the clusters based on data traffic via Pearson Correlation between sensor nodes in the cluster. Experimental evaluation is carried out by several performance parameters, like, energy consumption, cluster formation time, PDR and packet drop rate. CMX-HGDTNE technique for secure cluster formation and reliable data transmission improves performances of PDR by 15%, and minimizes energy consumption by 40%, clustered time by 17% as than the conventional methods.

show abstract

“…A dual-tier clustering-based method for WSN to focus on several performance parameter aspects like network lifetime, scalability and energy consumption was designed in [11]. In [12],…”

Section: Critical Review Of Literature and Identification Of Research...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence-based Cayley Menger Securex-means Clustering and Hyper Gradient Reliable Data Transmission in Wsn

Srinivasamur,

Tabassum

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The proposed approach enables the nodes to perform model aggregation locally instead of transmitting the model parameters to the central aggregation point for aggregation. Similarly, the authors in [18] develop a centrality aware gossiping protocol distributed learning in WSNs. The nodes exploit the centrality information to enhance the collaborative learning of the model.…”

Section: Related Workmentioning

confidence: 99%

“…Advantages related to the use of gossiping in WSNs have been analyzed in [12,13], with a particular focus on distributed inference and detection. Additionally, in [14][15][16][17][18], the use of gossiping combined with FL for the purpose of solving a consensus problem in the framework of ML model weights has been proposed. The use of gossiping under has been analyzed theoretically in [19], where the control of the communication time is achieved by tuning the nodes transmission rates and modifying the network topology, consequently.…”

Section: Introductionmentioning

confidence: 99%

Clustered Distributed Learning Exploiting Node Centrality and Residual Energy (CINE) in WSNs

Galluccio

Mertens

Morabito

2023

Network

View full text Add to dashboard Cite

With the explosion of big data, the implementation of distributed machine learning mechanisms in wireless sensor networks (WSNs) is becoming required for reducing the number of data traveling throughout the network and for identifying anomalies promptly and reliably. In WSNs, the above need has to be considered along with the limited energy and processing resources available at the nodes. In this paper, we tackle the resulting complex problem by designing a multi-criteria protocol CINE that stands for “Clustered distributed learnIng exploiting Node centrality and residual Energy” for distributed learning in WSNs. More specifically, considering the energy and processing capabilities of nodes, we design a scheme that assumes that nodes are partitioned in clusters and selects a central node in each cluster, called cluster head (CH), that executes the training of the machine learning (ML) model for all the other nodes in the cluster, called cluster members (CMs). In fact, CMs are responsible for executing the inference only. Since the CH role requires the consumption of more resources, the proposed scheme rotates the CH role among all nodes in the cluster. The protocol has been simulated and tested using real environmental data sets.

show abstract

Cooperative learning by knowledge transfer in vehicular networks for applications with user-environment interactions

Mertens,

Cafiso,

Galluccio

et al. 2024

2024 7th International Balkan Conference on Communications and Networking (BalkanCom)

View full text Add to dashboard Cite

Centrality-aware gossiping for distributed learning in wireless sensor networks

Cited by 5 publications

References 18 publications

Artificial Intelligence-based Cayley Menger Securex-means Clustering and Hyper Gradient Reliable Data Transmission in Wsn

Artificial Intelligence-based Cayley Menger Securex-means Clustering and Hyper Gradient Reliable Data Transmission in Wsn

Clustered Distributed Learning Exploiting Node Centrality and Residual Energy (CINE) in WSNs

Cooperative learning by knowledge transfer in vehicular networks for applications with user-environment interactions

Contact Info

Product

Resources

About