NEMICO: Mining Network Data through Cloud-Based Data Mining Techniques

Abstract

Thanks to the rapid advances in Internet-based applications, data acquisition and storage technologies, petabytesized network data collections are becoming more and more common, thus prompting the need for scalable data analysis solutions. By leveraging today's ubiquitous many-core computer architectures and the increasingly popular cloud computing paradigm, the applicability of data mining algorithms to these large volumes of network data can be scaled up to gain interesting insights. This paper proposes NEMICO, a comprehensive Big Data mining system targeted to network traffic flow analyses (e.g., traffic flow characterization, anomaly detection, multiplelevel pattern mining). NEMICO comprises new approaches that contribute to a paradigm-shift in distributed data mining by addressing most challenging issues related to Big Data, such as data sparsity, horizontal scaling, and parallel computation.

An Efficient Bit-Based Approach for Mining Skyline Periodic Itemset Patterns

“…Data mining plays a significant role in data analysis and knowledge extraction [1]; it has become an efficient tool for pattern discovery due to its applicability in a variety of circumstances such as association rule mining (ARM) [2], clustering analysis [3], and classification [4]. Mining frequent patterns (FPs) [2] are fundamental in ARM.…”

SaFe-NeC: A scalable and flexible system for network data characterization

“…When dealing with Big Data collections, such as the network datasets, the computational cost of the data mining process (and in some cases the feasibility of the process itself) can potentially become a critical bottleneck in data analysis. To date, parallel and distributed approaches have been adopted to increase efficiency and scalability of network traffic mining algoritms [1], [2], [3], [4].…”