Epidemic K-Means Clustering

Fatta, Giuseppe Di; Blasa, Francesco; Cafiero, Simone; Fortino, Giancarlo

doi:10.1109/icdmw.2011.76

Cited by 20 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Network tools such as virtualization [32] and clustering [33], [34], [35], [36] have also been used to address the redundancy reduction task [37]. Two main types of virtualization have been proposed in the context of WSN: (1) virtualization of sensors (i.e., virtual sensors) and (2) virtualization of sensor networks (i.e., virtual sensor networks or sensor cloud).…”

Section: Redundancy Reduction In Wsnsmentioning

confidence: 99%

Redundancy Reduction in Wireless Sensor Networks via Centrality Metrics

Mocanu

Vega

Liotta

2015

2015 IEEE International Conference on Data Mining Workshop (ICDMW)

View full text Add to dashboard Cite

Abstract-The advances in wireless communications, together with the need of sensing and controlling various nature or human made systems in a large number of points (e.g. smart traffic control, environmental monitoring), lead to the emergence of Wireless Sensor Networks (WSN) as a powerful tool to fulfill the above requirements. Due to the large amount of wireless devices needed and cost constraints, such networks are usually made by low-cost devices with limited energy and computational capabilities, these further on being subject to easy communication or hardware fails. At the same time, the deployment of such devices in harsh environments (e.g. in the ocean) may lead to uncontrollable redundant topologies which have to be often refined during the exploitation phase of these networks in an automated manner. In the scope of these arguments, in this paper, we take advantage of the latest theoretical advances in complex networks and we propose an automated solution to refine the topology of WSNs by using centrality metrics to detect the redundant nodes and links in a network, and further on to shut down them safely. Our solution may work in both ways, centralized or decentralized, by choosing a centralized or a decentralized centrality metric, this choice being driven by the application goal. The experiments performed on a wide variety of network topologies with different sizes (e.g. number of nodes and links), using different centrality metrics, validate our approach and recommend it as a solution for the automatic control of WSNs topologies during the exploitation phase of such networks to optimize, for instance, their life time.

show abstract

Section: Redundancy Reduction In Wsnsmentioning

confidence: 99%

Redundancy Reduction in Wireless Sensor Networks via Centrality Metrics

Mocanu

Vega

Liotta

2015

2015 IEEE International Conference on Data Mining Workshop (ICDMW)

View full text Add to dashboard Cite

show abstract

“…The available approaches of distributed partition-based clustering typically assume identical initial K-means centroids in all nodes [4], [5], [6]. This is, however, not required in our algorithm as each node can use an arbitrary parameter k with an arbitrary set of initial centroids.…”

Section: Partition-based Clustering K-meansmentioning

confidence: 99%

GDCluster: A General Decentralized Clustering Algorithm

Mashayekhi

Habibi

Khalafbeigi

et al. 2015

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Abstract-In many popular applications like peer-to-peer systems, large amounts of data are distributed among multiple sources. Analysis of this data and identifying clusters is challenging due to processing, storage, and transmission costs. In this paper, we propose GDCluster, a general fully decentralized clustering method, which is capable of clustering dynamic and distributed data sets. Nodes continuously cooperate through decentralized gossip-based communication to maintain summarized views of the data set. We customize GDCluster for execution of the partition-based and density-based clustering methods on the summarized views, and also offer enhancements to the basic algorithm. Coping with dynamic data is made possible by gradually adapting the clustering model. Our experimental evaluations show that GDCluster can discover the clusters efficiently with scalable transmission cost, and also expose its supremacy in comparison to the popular method LSP2P.

show abstract

“…Some distributed approaches use a centralized architecture with a master node that controls and synchronizes multiple slave nodes, such as MapReduce [6]. Other approaches employ a decentralized method, where peers can communicate with each other, acting as independent agents in the system [7], [13].…”

Section: Gossip Protocol For Distributed Environmentsmentioning

confidence: 99%

“…This approach is very fault tolerant due to its randomized nature and scales well due to its peer-to-peer design. In many cases, a gossip-based protocol can spread information throughout the system faster than traditional deterministic approaches [7]. There are several approaches for implementing gossip protocol in a networked system.…”

Section: Gossip Protocol For Distributed Environmentsmentioning

confidence: 99%

Gossip-based spectral clustering of distributed data streams

Talistu

Moh

2015

2015 International Conference on High Performance Computing &Amp; Simulation (HPCS)

View full text Add to dashboard Cite

With the growth of the Internet, social networks, and other distributed systems, there is an abundance of data about user transactions, network traffic, social interactions, and other areas that is available for analysis. Extracting knowledge from this data has become a growing field of research recently, especially as the size of the data makes traditional data mining methods ineffective. Some approaches assume the data is at a central location or a complete set of data is available for analysis. However, many modern-day applications consume distributed data streams. The dataset is spread across multiple locations and each location only has access to a portion of the data stream. We propose a distributed data stream analysis method, which uses hierarchical clustering for local online summary, a gossip protocol for distributing these summaries, and spectral clustering for offline analysis. The resulting solution successfully avoids the heavy computation and communication capability requirements of a centralized approach. Through experiments, we have demonstrated that the proposed solution is able to accurately cluster the data streams and is highly scalable. Its quality significantly increases as the number of microcluster increases, yet it is fault-tolerant when this number is small. Finally, it has achieved a similar level of accuracy when compared with a centralized approach.

show abstract

Epidemic K-Means Clustering

Cited by 20 publications

References 18 publications

Redundancy Reduction in Wireless Sensor Networks via Centrality Metrics

Redundancy Reduction in Wireless Sensor Networks via Centrality Metrics

GDCluster: A General Decentralized Clustering Algorithm

Gossip-based spectral clustering of distributed data streams

Contact Info

Product

Resources

About