Data Mining (DM) is an important arena in the field of data and knowledge based systems, which has been prompted by an interesting field called Knowledge Discovery in Databases (KDD). Discovered knowledge can come in many forms such as association rules, correlations, sequences, episodes, classifiers, clusters, and many more. Mining for association rules has recently received great attention. The original motivation for searching association rules came from the need to analyze the so-called supermarket transaction data, that is, to examine customer behavior in terms of the purchased products. Many algorithms exist for association rule mining. The algorithm APRIORI is one of the earliest and most well-known algorithms for association rule mining. Some improvements on the APRIORI algorithm are now in place. During my master degree, I investigated some of the APRIORI algorithm improvements, and combine two of them namely; Sampling and Partitioning into one algorithm that I call APRIORI-SP. Additionally, I implemented the APRIORI-SP and conducted a number of experiments to measure the relative performance of the APRIORI-SP algorithm compared with the Sampling and Partitioning algorithms separately. The paper titled "Combining Some of The Improvements of Apriori Algorithm" describes the APRIORI-SP algorithm and more in detail.
As a PhD student at Kent State University, I am studying Routing, Forwarding, and Queuing in Online Social Networks using large-scale data sets from Google Plus and other platforms. My PhD research includes three consecutive phases of social priority estimation in Online Social Networks utilizing matrix factorization technique, designing a protocol for requests dissemination in Online Social Networks, and designing and implementing a simulator for Online Social Networks.
Besides my research interests in modeling large complex networks, and the diffusion of information within these networks, I am interested and I am doing research in my free time on Big Data, Internet of Things, Software-Defined Networking, and Graph Databases.