Knowledge Discovery in Data Mining and Massive Data Mining

Knowledge discovery is a process of non trivial extraction of previously unknown and presently useful information. The rapid advancement of the technology resulted in the increasing rate of data distributions. The data generated from mobile applications, sensor applications, network monitoring, traffic management, weblogs etc. can be referred as a data stream. The data streams are massive in nature. The present work mainly aims at knowledge discovery using data mining and massive data mining techniques. The knowledge discovery process in both the techniques is compared by developing a classification model using Naive bayes classifier. The former case uses Edu-data, a data collected from technical education system and the latter case uses massive online analysis frame work to generate the data streams. Mining data stream is referred as Massive Data Mining. The data streams must be processed under very strict constraints of space and time using sophisticated techniques. The traditional data mining techniques are not advised on this massive data. Therefore the massive online analysis framework is used to mine the data streams. The present work happens to be unique in the literature.