Article On Data Mining With Big Data

1734 Words7 Pages
Critique-1 Submission by Jyothikiran Nandanamudi (Class ID: 25) Ashok Yaganti (Class ID: 46) Article: Data Mining with Big Data (Paper-1) This paper addresses the complications being faced by Big Data because of increase in the volume, complexity of data and due to multiple sources, which produces large number of data sets. With the increase of big data in different fields like medicine, media, social networking etc., there is a need for better processing model which can access the data at the rate at which the data increases. This paper proposed a processing model, HACE theorem which can address the characteristics of the elements of Big Data revolution. Overview and procedures: The author started with few examples, stating how…show more content…
Here in the paper the authors mentioned about the privacy issues and then some dependency issues from social networking sites which shows a need for understanding both semantics and knowledge from applications for processing of Big Data with the use of Big Data mining algorithms in the form of three tiers. In the later part of the paper the author discussed about the challenges faced by Big Data in the three tiers as difficulty in accessing the data in terms of storage and computing, gaining knowledge by understanding semantics and how privacy can be achieved and how the overall optimization can be obtained. These challenges made the authors to develop many data mining methods which explains the convoluted relationships of evolving data. Strengths and Limitations: The introduction part is very clearly explained showing how Big Data can be used and what are the main challenges being faced today due to volume, autonomous, complexity and heterogeneity of data, but drawing the conclusion from the examples mentioned is incomprehensible. The processing framework is conveniently illustrated in three tiers but pipelining of these tiers with a comprehensible example would make the paper more satisfactory. The authors tried to drag the explanation of three tier system rather than being concise. The article lags in exhibiting scientific facts about the functionality of this HACE theorem based Big Data Processing framework. The initiative took by authors in terms of
Open Document